system

Abstract

Provide a system. 【Solution means】 Means for receiving a fashion-related request in natural language from a user, Means for analyzing the request using natural language processing technology and extracting features related to the user's wishes and preferences, Means for filtering appropriate products based on the user profile, Means for generating proposals from the selected products, Means for providing the generated proposals to the user, Means for receiving feedback from the user and performing learning to improve proposal accuracy, Means for enabling the user to purchase the proposed products in cooperation with an e-commerce platform, Means for allowing the user to input using a smart device and smoothly confirm the proposed style and complete the purchase procedure, A system including means for referring to purchase history and past profile data and improving individualized fashion proposals.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In personal fashion selection, there is a problem that it is difficult to select specific products based on ambiguous hopes and preferences of users. Also, there is a need to quickly provide personalized proposals according to the user's profile and continuously improve the quality of proposals by reflecting feedback. Furthermore, it is necessary to realize a seamless system construction such that proposals lead to product purchases.

Means for Solving the Problems

[0005] This invention receives fashion-related requests from users in natural language and analyzes them using natural language processing technology to identify the user's wishes and preferences. Then, based on the user's profile information, it filters appropriate products and generates suggestions based on the selected products. The generated suggestions are provided to the user, and feedback is received to continuously improve the accuracy of the suggestions. Furthermore, by linking with e-commerce sites, it provides an environment where users can smoothly purchase the suggested products.

[0006] A "user" is an individual who uses this system to receive fashion-related suggestions.

[0007] "Requests in natural language" refer to information that users input to communicate their fashion preferences and desires using everyday language.

[0008] "Natural language processing technology" is a technology that analyzes natural language text input by users and understands its meaning and intent.

[0009] A "user profile" is a collection of data that includes personal information about the user, such as body type, past purchase history, style preferences, and budget.

[0010] "Filtering" refers to a function that selects suitable products from a vast product database based on the user's requirements and profile.

[0011] "Means for generating suggestions" refers to the process of creating specific fashion coordinates and item suggestions for the user based on selected products.

[0012] "Feedback" refers to information provided by users, such as comments and evaluations regarding suggestions they have received, which contributes to improving the system.

[0013] An "e-commerce site" is an online platform where goods can be sold or purchased via the internet. [Brief explanation of the drawing]

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

Embodiments for Carrying out the Invention

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

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

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

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

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

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

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

[0022] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0035] This invention is implemented as an AI styling service that assists individuals in making fashion choices. This system consists of three elements: a server, a terminal, and a user, and aims to improve the user's personalized fashion experience.

[0036] First, the user uses their device to input their fashion preferences and desires in natural language. For example, they might express a specific wish such as, "I want a spring-colored skirt that would go well with office casual attire." This input information is then sent from the device to the server.

[0037] The server utilizes natural language processing technology to analyze the received natural language information and accurately understand the user's requests. During this process, keywords are extracted to clarify the user's wishes and preferences. Next, the server consults a database to retrieve user profile information. This profile information includes the user's body type, past purchase history, and style preferences, which are used as the basis for generating suggestions.

[0038] Based on the acquired information, the server filters suitable product candidates from a vast product database. This selects products that meet the user's requirements. Based on the selected products, the server suggests the optimal outfit for the user. This suggestion is sent to the terminal and provided to the user.

[0039] The user reviews the suggested outfit and enters feedback into their device. This feedback is sent to the server and used to improve the accuracy of future suggestions. The server analyzes this feedback and trains an AI model, enabling it to provide more user-friendly suggestions.

[0040] Furthermore, if a user wishes to purchase a suggested product, the system integrates with e-commerce sites to provide a seamless purchase process. This integration allows users to purchase products smoothly and enables efficient inventory management.

[0041] For example, if a user receives a suggestion such as "an elegant dress suitable for a weekend party," the server considers the user's profile, including their preferred colors and budget, and selects the most suitable dress from its database. The results are then sent to the user's device, displaying product images and detailed descriptions. The user can then purchase the suggested item directly from the e-commerce site and enjoy their next party outfit. In this way, the entire system works together to provide users with a personalized and comfortable shopping experience.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] Users use their devices to input their fashion preferences and desires in natural language into an app or website. For example, they might enter a request such as, "I want a casual jacket that's perfect for autumn."

[0045] Step 2:

[0046] The terminal sends the user's input request to the server. At the same time, necessary metadata such as the user ID and device information is also sent.

[0047] Step 3:

[0048] The server analyzes the received request using natural language processing techniques. Specifically, it breaks down the text and extracts keywords that indicate the user's wishes and preferences (e.g., "autumn," "casual," "jacket").

[0049] Step 4:

[0050] The server retrieves user profiles from the database. These profiles include the user's body type, past purchase history, style preferences, and budget.

[0051] Step 5:

[0052] The server searches the product database based on the user profile and extracted keywords, filtering products to match the request. For example, it can narrow down the search for jackets based on criteria such as color, material, and price range.

[0053] Step 6:

[0054] The server generates outfit suggestions for the user based on a filtered list of products. These suggestions include combinations of selected items and a style guide.

[0055] Step 7:

[0056] The server sends the generated proposal to the terminal. The terminal visually presents the proposal details to the user, including images, pricing information, and a purchase button.

[0057] Step 8:

[0058] Users review the proposals and provide feedback as needed. This feedback includes satisfaction levels and desired changes.

[0059] Step 9:

[0060] The device sends user feedback to the server. The server uses this information to train its AI model and improve the accuracy of future suggestions.

[0061] Step 10:

[0062] When a user purchases a suggested product, the system connects with the e-commerce site via the device. The server facilitates the purchase process and inventory check.

[0063] (Example 1)

[0064] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0065] In personal fashion choices, there is a need to efficiently and accurately generate personalized suggestions based on the user's style preferences and past purchase history. Furthermore, providing a seamless process that allows users to easily purchase suggested items is a challenge. Additionally, effectively utilizing user feedback is necessary to continuously improve the quality of suggestions.

[0066] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0067] In this invention, the server includes means for receiving fashion-related requests in natural language from a user via a communication terminal; information processing means using generative AI technology to analyze the requests and extract characteristics related to the user's wishes and preferences; and information processing means for selecting appropriate products from a product information database by referring to the user profile. As a result, the user can receive suggestions optimized for their own style and purchase products quickly and easily. Furthermore, the accuracy of suggestions can be improved based on feedback.

[0068] A "communication terminal" is an electronic device that allows users to input fashion-related requests in natural language and receive suggested information.

[0069] "Generative AI technology" is a type of artificial intelligence technology used to analyze users' requests in natural language and extract features related to their wishes and preferences.

[0070] "Information processing means" refers to the computer process by which a server analyzes user requests and profile information to select appropriate products.

[0071] A "user profile" is a dataset containing information about a user, such as their physical characteristics, past purchase history, preferred style, and budget.

[0072] A "product information database" is a database containing information about a large number of fashion products, and it is the data source referenced when generating suggestions.

[0073] A "prompt message" is a text-based explanation that provides a concrete and easy-to-understand summary of the generated fashion suggestions to the user.

[0074] An "e-commerce system" is an integrated system used when users purchase suggested products online, covering everything from product selection and payment to delivery.

[0075] This invention is embodied as an AI styling system that supports individual fashion choices. This system consists of three elements: a server, a terminal, and a user, and each component works together to provide the user with the most suitable fashion suggestions.

[0076] First, the user uses their device to input their fashion preferences and desires in natural language. Typically, a mobile device such as a smartphone or tablet is used. This information is then sent from the device to the server.

[0077] The server analyzes received requests using a generative AI model (e.g., a natural language processing model based on BERT or GPT) to break down the user's wishes into specific keywords. These keywords become important indicators used when selecting products.

[0078] Next, the server accesses an internal database to retrieve user profile information. This profile includes data such as the user's body type, past purchase history, and style preferences, and this information is used to narrow down the product selection.

[0079] The server filters products from its product information database, matching the extracted keywords and user profile. This process identifies the most suitable products for the user. The server then generates prompt messages containing detailed information about the selected products and suggested outfit combinations.

[0080] The generated prompt message is sent to the terminal and provided to the user. For example, the prompt message might say, "This spring's recommended outfit is a blue skirt paired with a white blouse, making it suitable for the office."

[0081] If a user likes a suggested product, the system integrates with the e-commerce system to facilitate a smooth purchase process. This allows users to buy products without any hassle.

[0082] Furthermore, based on user feedback, the server continues to train its AI model, improving the accuracy of its suggestions. This feedback-based learning allows the system to continuously provide suggestions tailored to each user.

[0083] This allows the system to provide users with a personalized fashion experience, thereby improving user satisfaction.

[0084] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0085] Step 1:

[0086] Users use their devices to input their fashion preferences and desires in natural language. For example, they might input something like, "I want a casual dress in a bright color that's suitable for spring." This input information is sent to the server as string data.

[0087] Step 2:

[0088] The server uses a generative AI model to process incoming natural language requests. This model is composed of natural language processing techniques such as BERT and GPT, which analyze the user's request and extract keywords such as "spring," "bright colors," "casual," and "dress." This systematizes the user's wishes and preferences into specific characteristics.

[0089] Step 3:

[0090] The server retrieves user profile information from the database. This profile includes data such as the user's body type, past purchase history, and style preferences, which can be quickly retrieved using queries. This retrieved data is then used to refine product selection later.

[0091] Step 4:

[0092] The server queries and filters the product information database based on the extracted keywords and user profile information. This data processing involves matching the product metadata, identifying only products that match the criteria of "spring," "bright colors," "casual," and "dress." This process generates a list of potential products.

[0093] Step 5:

[0094] The server selects the most suitable outfit from the generated product list and generates it as a prompt message. This prompt message includes specific product names, styling suggestions, and information about related accessories and color coordination. This prompt message is then sent to the terminal.

[0095] Step 6:

[0096] Users review the suggested outfits on their devices and provide feedback. This feedback includes specific suggestions for improvement and information about their satisfaction level, such as "I prefer this color" or "The size doesn't fit." This information is then sent to the server.

[0097] Step 7:

[0098] The server analyzes the feedback received from the user and uses it to retrain the generated AI model. Specifically, the feedback is used to update the model's weights and correct biases, improving the accuracy of future suggestions. Through this learning process, the system can continuously provide more suitable suggestions to the user.

[0099] (Application Example 1)

[0100] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0101] Conventional fashion selection support systems fail to adequately provide suggestions that match the user's desired style and preferences, making it difficult to offer optimal suggestions tailored to individual needs. Furthermore, there are challenges in ensuring a smooth purchasing process for the suggested items. Users need a way to efficiently select and purchase fashion that suits them without stress.

[0102] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0103] In this invention, the server includes means for receiving fashion-related requests from a user in natural language, means for analyzing the requests using natural language processing technology to extract characteristics related to the user's wishes and preferences, means for filtering appropriate products based on the user profile, and means for generating suggestions from the selected products. This enables the provision of appropriate fashion suggestions tailored to the user's individual needs and facilitates a smooth purchasing process.

[0104] A "user" is an individual consumer who uses the system to receive fashion suggestions.

[0105] "Natural language processing technology" is a computer-based technology that analyzes and understands the content of user requests expressed in natural language.

[0106] A "user profile" is a collection of individual data that includes a user's body type, past purchase history, preferred style, and consumption trends.

[0107] A "product" is a fashion item or merchandise suggested by the system based on the user's preferences.

[0108] An "e-commerce platform" is an online commercial system that allows users to purchase goods via the internet.

[0109] "Feedback" refers to the opinions and reactions that users offer regarding the fashion suggestions they receive.

[0110] To implement this invention, it is necessary to build a system in which a user, a terminal, and a server work together. This system begins with the user entering fashion-related requests into the terminal using natural language. The terminal has an app installed as a front-end application, using a mobile framework such as React Native. Once the user has finished entering the data, it is sent to the server.

[0111] The server is built using Python and utilizes the Google Cloud Natural Language API to analyze user requests. The received requests are analyzed using natural language processing techniques to understand their intent and extract characteristics related to the user's preferences and desires. At this stage, user profile information is retrieved from a PostgreSQL database, taking into account body type, past purchase history, style preferences, and consumption trends.

[0112] Based on this information, the server uses a generative AI model to select the most suitable fashion items for the user and build visual suggestions. This involves sending a prompt message that reads, "Please suggest items that match the user's desired fashion style. Please consider the user's past purchase history and profile, paying particular attention to color and style. Also, please ensure that the purchase process is smooth when linked to the e-commerce site."

[0113] Selected items are suggested to the user on a smartphone application and displayed along with detailed product information. If the user reviews the suggestions and wishes to purchase, the device connects to the e-commerce platform, allowing for a seamless purchase process. For example, if a user enters "I want an outfit suitable for a summer beach resort," the server can analyze the user's past data and suggest a light, coral-colored dress and hat as the most suitable beach attire. This system allows users to enjoy a simple and personalized fashion experience.

[0114] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0115] Step 1:

[0116] The user enters fashion-related requests in natural language using their device. These requests are received by an application on the device and sent to the server. The input data consists of the user's wishes and preferences in text format.

[0117] Step 2:

[0118] The server analyzes the received request data using the Google Cloud Natural Language API and extracts keywords and features contained in the user's request. The input data is a dictionary in natural language format, and the output data is a set of analyzed features.

[0119] Step 3:

[0120] The server retrieves user profiles from a PostgreSQL database, collecting data such as body type, past purchase history, style preferences, and consumption trends. Input data consists of analyzed keywords and characteristics of the user, while output data is a set of profile information.

[0121] Step 4:

[0122] The server uses a generative AI model to filter products based on collected user profile information and analyzed features. Here, a prompt is generated: "Please suggest items that match the user's desired fashion style. Consider the user's past purchase history and profile, paying particular attention to color and style. Also, ensure a smooth purchase process when linked to the e-commerce site." The input data consists of profile information and analyzed features, while the output data is a list of suitable products.

[0123] Step 5:

[0124] The server sends the suggested product list to the terminal for the user to review. The input data is a filtered list of products, and the output data is the product information displayed on the user's terminal. The user makes a purchase decision based on this information.

[0125] Step 6:

[0126] The user selects the product they wish to purchase from the suggested items and initiates the process through the terminal. The terminal connects with the e-commerce platform to facilitate the purchase process. The input data is the product selected by the user, and the output data is confirmation information for the purchase process.

[0127] This system allows users to receive fashion suggestions based on their individual preferences and complete product purchases smoothly online.

[0128] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0129] This invention is implemented as an AI styling service incorporating emotion recognition. This system consists of a server containing an emotion engine, a terminal that accepts user input, and the user themselves, in order to enhance the user's personalized fashion experience.

[0130] Users use their devices to input their fashion preferences and desires in natural language via an application or web interface. The device transmits the user's input to the server in real time. For example, a request might read, "I'm in a good mood today, so I'd like a brightly colored dress."

[0131] The server first analyzes the received input using natural language processing technology. This analysis clarifies the user's request and extracts keywords. Simultaneously, the emotion engine on the server analyzes the user's text to recognize emotional states such as joy, sadness, and excitement. This enables the system to suggest fashion items that match the user's emotional state.

[0132] Next, the server retrieves the user profile from the database. The profile includes information about body type, past purchase history, style preferences, and budget, which forms the basis of the suggestions. Based on the profile information and extracted sentiment keywords, the server searches the product database and filters for relevant products.

[0133] Referencing the selected product list, the server generates the optimal outfit. This outfit is customized to reflect the user's emotional state based on the results of an analysis by the emotion engine. It is then sent to the user's device and the suggestion is displayed visually.

[0134] Users who receive a proposal can enter feedback on their device. This feedback includes their satisfaction with the proposed coordination and any desired modifications. The device can then send this feedback to the server.

[0135] The server collects and analyzes feedback information, and uses it to train AI models, including an emotion engine, thereby improving the accuracy of suggestions for future users. In this way, the suggestion process linked to emotion recognition makes the user's fashion experience more personalized.

[0136] For example, if a user requests, "Today is a special day, so I want to wear something glamorous," the server associates the user's emotional state with "a special day" and selects items that are glamorous and in the user's preferred style. Based on this, suggestions are displayed, and the user can then make the most appropriate fashion choice.

[0137] The following describes the processing flow.

[0138] Step 1:

[0139] The user uses their device to input their fashion requests and preferences in natural language. For example, they might input, "I'm in a cheerful mood today, so I'd like a colorful outfit."

[0140] Step 2:

[0141] The terminal sends the user's natural language request to the server. Supplementary information such as a timestamp and user ID is also sent along with the request.

[0142] Step 3:

[0143] The server analyzes the received request using natural language processing technology. Specifically, it tokenizes the text and extracts keywords to clarify the user's wishes.

[0144] Step 4:

[0145] The emotion engine on the server recognizes emotions from the user's text. For example, a positive emotion is extracted from the text "feeling happy."

[0146] Step 5:

[0147] The server retrieves user profiles from the database. These profiles include body type, past purchase history, preferred style, and budget.

[0148] Step 6:

[0149] The server uses profile information and analyzed emotion data to search the product database. It narrows down the products that match the emotional state and the user's preferences, selecting a few candidates.

[0150] Step 7:

[0151] The server generates outfit suggestions that match the user's emotional state based on a list of selected items. These suggestions include specific items, color combinations, and styling examples.

[0152] Step 8:

[0153] The server sends the generated suggestions to the terminal, which then displays the suggestions to the user. The user can review the suggestions and refer to images and detailed explanations.

[0154] Step 9:

[0155] Users enter feedback on the proposal into their device. This feedback includes their satisfaction with the proposal and whether they would like to see other proposals.

[0156] Step 10:

[0157] The device sends user feedback to the server, which then uses that feedback to train the AI ​​model. This continuously improves the accuracy of the system's suggestions.

[0158] (Example 2)

[0159] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0160] In today's world, it is difficult to provide online clothing selections that cater to individual user preferences and emotions. Traditional systems have been unable to accurately understand user needs and automatically provide optimal fashion suggestions. Furthermore, there have been insufficient means to efficiently utilize user feedback to improve the accuracy of suggestions.

[0161] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0162] In this invention, the server includes means for receiving requests for clothing from a user in natural language, means for analyzing the requests using information processing technology to extract characteristics related to the user's wishes and preferences, and means for analyzing the emotional state based on the extracted characteristics to generate a design based on the emotional state. This makes it possible to quickly and accurately provide optimal fashion suggestions based on the user's individual preferences and emotions.

[0163] A "user" is an entity that utilizes a system and inputs its own requests and preferences in natural language.

[0164] "Natural language" refers to the linguistic forms that humans use on a daily basis, and not to specific programming languages.

[0165] "Clothing" refers to items such as clothes and accessories that a user chooses to wear.

[0166] "Information processing technology" refers to a series of methods and techniques for analyzing data and extracting and utilizing information with a specific intent.

[0167] "Preferences" refer to the individual preferences and tendencies that users have regarding specific styles or characteristics.

[0168] "Emotional state" refers to the feelings and psychological state a user is experiencing at a particular point in time.

[0169] "Design" refers to product and coordination suggestions generated based on the user's requirements and emotions.

[0170] "Evaluation" refers to feedback, such as opinions and impressions, that users give regarding the presented design.

[0171] A "virtual marketplace" refers to an e-commerce platform used by users to purchase goods online.

[0172] A "storage device" is a device for storing information that can store data and retrieve it as needed.

[0173] This invention is a system that provides fashion suggestions based on the user's preferences and emotional state. To implement the invention, the following specific hardware and software are used.

[0174] The user inputs their fashion-related requests in natural language using a device. This device includes computers and smartphones with internet connectivity, and preferably has a web interface or mobile application installed. An example of a user request might be, "I'm in a good mood today, so I'd like a brightly colored dress."

[0175] The terminal sends the input natural language request to the server in real time. The server then analyzes the request using information processing technology, specifically utilizing Google's Natural Language API. This analysis process extracts keywords from the request to clearly identify the user's wishes and preferences. The server also analyzes the user's emotional state using sentiment analysis engines such as OpenAI's GPT model. Based on these results, it generates a fashion design that matches the emotional state.

[0176] Next, the server retrieves the user's profile from the database. This profile includes the user's body type, past purchase history, preferences, and budget information. Based on this information, the server searches the product database and filters for suitable items. From this list of items, it generates optimal design proposals and sends them to the user's terminal.

[0177] Users review the proposed designs and send feedback, such as their satisfaction level and any desired modifications, via their devices. The server collects this feedback and uses it as training data for the generated AI model. This improves the accuracy of future fashion suggestions.

[0178] A concrete example of a prompt message would be: "Based on the user's request, 'Today is a special day, so I want to wear something flashy,' please suggest fashion items that suit their special emotional state."

[0179] Thus, the system of the present invention implements detailed processing to provide users with personalized fashion suggestions in real time.

[0180] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0181] Step 1:

[0182] Users input fashion-related requests in natural language using their devices. Specifically, they launch an application or web interface and input a request such as, "I'm in a good mood today, so I'd like a brightly colored dress." The input data is then sent directly from the device to the server.

[0183] Step 2:

[0184] The server parses the user's natural language request that it receives. The request, as input data, is parsed using Google's Natural Language API, and keywords are extracted. For example, words like "mood," "cheerful," and "dress" are extracted. These analysis results are used in the next step.

[0185] Step 3:

[0186] The server performs sentiment analysis. Based on previously analyzed keywords, it uses OpenAI's GPT model to analyze the user's emotional state. For example, if the information indicates that the user is "in a good mood," it determines that the user's emotional state is "positive." This information is then used in subsequent design generation.

[0187] Step 4:

[0188] The server retrieves the user's profile from the database. The profile includes body type, past purchase history, preferences, and budget information. This data is retrieved as input to the server and used in the next filtering step.

[0189] Step 5:

[0190] The server searches and filters the product database. It searches the product list considering the extracted keywords and user profile. For example, it filters items that match a condition such as "bright-colored dress" and outputs the appropriate items.

[0191] Step 6:

[0192] The server generates optimal design proposals from the filtered products. This process utilizes a generative AI model, customized to suit the user's emotional state. The generated design proposals are then sent to the user's device as visual information.

[0193] Step 7:

[0194] Users review the design proposal generated on their device and provide feedback. This feedback includes their satisfaction level and any desired changes, which then becomes input data for the next server.

[0195] Step 8:

[0196] The server analyzes user feedback and uses it to train the AI ​​model. Based on the feedback data, it generates new training data as prompts for the generated AI model. This process improves the accuracy of suggestions in subsequent attempts.

[0197] (Application Example 2)

[0198] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0199] Conventional fashion recommendation systems are limited to suggestions based on the user's basic preferences, body type, and past purchase history, and have the drawback of not being able to flexibly respond to specific situations and needs that change depending on the user's emotions. Therefore, there is a need to understand the user's real-time emotional state and reflect that information to provide more personalized fashion recommendations.

[0200] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0201] In this invention, the server includes means for analyzing the user's emotional state, means for filtering appropriate products based on the analyzed emotional information and user profile, and means for generating suggestions from the selected products based on the user's current emotional state. This enables personalized fashion suggestions that match the user's real-time emotions.

[0202] "A means of receiving fashion-related requests from users in natural language" refers to an interface that acquires text data directly entered by the user and registers it as information for analysis.

[0203] "A means of analyzing data using natural language processing technology to extract features related to user wishes and preferences" refers to the process of analyzing text data received from users using machine learning algorithms to extract specific keywords and phrases.

[0204] "Methods for analyzing a user's emotional state" refer to algorithms that detect emotions from a user's facial expressions, voice, and entered text, and classify that information into specific emotional categories.

[0205] "Means for filtering appropriate products based on analyzed emotional information and user profiles" refers to a process that selects appropriate products based on emotional data and the user's past behavioral data, and creates a product list that meets the user's needs.

[0206] "A means of generating suggestions based on the user's current emotional state from selected products" refers to a process of selecting items that best match the user's emotions from a filtered product list and then providing specific coordination and purchase suggestions.

[0207] "Means of receiving user feedback on proposals and learning to improve proposal accuracy" refers to a mechanism that collects evaluations and opinions from users, analyzes that information using a machine learning model, and improves the accuracy of future proposals.

[0208] This invention realizes a fashion recommendation system that incorporates sentiment analysis to improve the user experience. Users can input their fashion requests in natural language using their smartphone or other device. The device sends this natural language data to a server, which analyzes the received data using natural language processing technology. The analysis utilizes machine learning frameworks such as TENSORFLOW® and PyTorch.

[0209] The server extracts keywords from the user's request while simultaneously analyzing the user's emotional state. Emotional analysis utilizes algorithms that analyze facial expressions and tone of voice from images and audio, often leveraging libraries such as OpenCV.

[0210] The server then filters out appropriate products based on the user's emotional information and profile data. Profile data includes past purchase history, body type, style preferences, and budget. From the products retrieved through the database search, suggestions are generated that match the user's emotional state.

[0211] The generated suggestions are visually displayed on the device, allowing the user to review them. Users can submit feedback on the suggestions, which is collected on the server and used to train the generating AI model. This continuously improves the accuracy of the suggestions.

[0212] For example, if a user enters into the application, "I'm in a good mood today, so I want some brightly colored clothes," the server will analyze the emotion as "joy" and suggest brightly colored clothing that fits the happy theme. It is also possible to create more specific suggestions by inputting prompts such as, "Analyze the user's facial expression and suggest casual wear that indicates a 'relaxed' state," into the AI ​​model.

[0213] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0214] Step 1:

[0215] The terminal receives fashion-related requests entered by the user in natural language. This input is sent to the server in text data format. The received text is prepared as data for the next parsing process.

[0216] Step 2:

[0217] The server analyzes the received text data using natural language processing techniques. The input is raw data, and the output extracts specific features related to the user's wishes and preferences. In this process, a generative AI model is used to extract keywords from the text and identify the user's intent.

[0218] Step 3:

[0219] The server analyzes the user's emotional state. Input is the user's facial expressions, voice, or text data, and the server identifies the user's emotions through an emotion analysis algorithm. Output is an emotion category such as "joy" or "sadness." This process involves video analysis using tools like OpenCV.

[0220] Step 4:

[0221] The server filters appropriate products based on analyzed sentiment data and a user profile database. The input is sentiment data and profile information, and the output is a filtered product list. Filtering includes algorithmic searching.

[0222] Step 5:

[0223] The server generates optimal suggestions from the selected products based on the user's current emotional state. The input is a filtered product list and emotional data, while the output is specific fashion suggestions. The suggestion generation utilizes a generative AI model to provide coordinated outfit suggestions.

[0224] Step 6:

[0225] Users who receive a suggestion send feedback from their device to the server. The input is the user's evaluation and suggestions for improvement, and the output is training data for future suggestions. The data obtained as feedback is reflected in the AI ​​model, contributing to the improvement of suggestion accuracy.

[0226] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0227] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0228] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0229] [Second Embodiment]

[0230] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0231] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0232] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0233] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0234] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0235] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0236] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0237] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0238] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0239] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0240] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0241] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0242] This invention is implemented as an AI styling service that assists individuals in making fashion choices. This system consists of three elements: a server, a terminal, and a user, and aims to improve the user's personalized fashion experience.

[0243] First, the user uses their device to input their fashion preferences and desires in natural language. For example, they might express a specific wish such as, "I want a spring-colored skirt that would go well with office casual attire." This input information is then sent from the device to the server.

[0244] The server utilizes natural language processing technology to analyze the received natural language information and accurately understand the user's requests. During this process, keywords are extracted to clarify the user's wishes and preferences. Next, the server consults a database to retrieve user profile information. This profile information includes the user's body type, past purchase history, and style preferences, which are used as the basis for generating suggestions.

[0245] Based on the acquired information, the server filters suitable product candidates from a vast product database. This selects products that meet the user's requirements. Based on the selected products, the server suggests the optimal outfit for the user. This suggestion is sent to the terminal and provided to the user.

[0246] The user reviews the suggested outfit and enters feedback into their device. This feedback is sent to the server and used to improve the accuracy of future suggestions. The server analyzes this feedback and trains an AI model, enabling it to provide more user-friendly suggestions.

[0247] Furthermore, if a user wishes to purchase a suggested product, the system integrates with e-commerce sites to provide a seamless purchase process. This integration allows users to purchase products smoothly and enables efficient inventory management.

[0248] For example, if a user receives a suggestion such as "an elegant dress suitable for a weekend party," the server considers the user's profile, including their preferred colors and budget, and selects the most suitable dress from its database. The results are then sent to the user's device, displaying product images and detailed descriptions. The user can then purchase the suggested item directly from the e-commerce site and enjoy their next party outfit. In this way, the entire system works together to provide users with a personalized and comfortable shopping experience.

[0249] The following describes the processing flow.

[0250] Step 1:

[0251] Users use their devices to input their fashion preferences and desires in natural language into an app or website. For example, they might enter a request such as, "I want a casual jacket that's perfect for autumn."

[0252] Step 2:

[0253] The terminal sends the user's input request to the server. At the same time, necessary metadata such as the user ID and device information is also sent.

[0254] Step 3:

[0255] The server analyzes the received request using natural language processing techniques. Specifically, it breaks down the text and extracts keywords that indicate the user's wishes and preferences (e.g., "autumn," "casual," "jacket").

[0256] Step 4:

[0257] The server retrieves user profiles from the database. These profiles include the user's body type, past purchase history, style preferences, and budget.

[0258] Step 5:

[0259] The server searches the product database based on the user profile and extracted keywords, filtering products to match the request. For example, it can narrow down the search for jackets based on criteria such as color, material, and price range.

[0260] Step 6:

[0261] The server generates outfit suggestions for the user based on a filtered list of products. These suggestions include combinations of selected items and a style guide.

[0262] Step 7:

[0263] The server sends the generated proposal to the terminal. The terminal visually presents the proposal details to the user, including images, pricing information, and a purchase button.

[0264] Step 8:

[0265] Users review the proposals and provide feedback as needed. This feedback includes satisfaction levels and desired changes.

[0266] Step 9:

[0267] The device sends user feedback to the server. The server uses this information to train its AI model and improve the accuracy of future suggestions.

[0268] Step 10:

[0269] When a user purchases a suggested product, the system connects with the e-commerce site via the device. The server facilitates the purchase process and inventory check.

[0270] (Example 1)

[0271] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0272] In personal fashion choices, there is a need to efficiently and accurately generate personalized suggestions based on the user's style preferences and past purchase history. Furthermore, providing a seamless process that allows users to easily purchase suggested items is a challenge. Additionally, effectively utilizing user feedback is necessary to continuously improve the quality of suggestions.

[0273] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0274] In this invention, the server includes means for receiving fashion-related requests in natural language from a user via a communication terminal; information processing means using generative AI technology to analyze the requests and extract characteristics related to the user's wishes and preferences; and information processing means for selecting appropriate products from a product information database by referring to the user profile. As a result, the user can receive suggestions optimized for their own style and purchase products quickly and easily. Furthermore, the accuracy of suggestions can be improved based on feedback.

[0275] A "communication terminal" is an electronic device that allows users to input fashion-related requests in natural language and receive suggested information.

[0276] "Generative AI technology" is a type of artificial intelligence technology used to analyze users' requests in natural language and extract features related to their wishes and preferences.

[0277] "Information processing means" refers to the computer process by which a server analyzes user requests and profile information to select appropriate products.

[0278] A "user profile" is a dataset containing information about a user, such as their physical characteristics, past purchase history, preferred style, and budget.

[0279] A "product information database" is a database containing information about a large number of fashion products, and it is the data source referenced when generating suggestions.

[0280] A "prompt message" is a text-based explanation that provides a concrete and easy-to-understand summary of the generated fashion suggestions to the user.

[0281] The "e-commerce trading system" is an integrated system that covers the selection, payment, and delivery of products and is used when users purchase proposed products online.

[0282] The present invention is embodied as an AI styling system that supports personal fashion choices. This system is composed of three elements: a server, a terminal, and a user. By the cooperation of each component, an optimal fashion proposal is made to the user.

[0283] First, the user uses the terminal to input their hopes and preferences regarding fashion in natural language. Usually, mobile devices such as smartphones and tablets are used as the terminal. This information is sent from the terminal to the server.

[0284] The server analyzes the received request using a generated AI model (e.g., a natural language processing model based on BERT or GPT) and decomposes the user's hopes into specific keywords. The keywords obtained through this analysis become important indicators used when selecting products.

[0285] Next, the server accesses the internal database to obtain user profile information. The profile includes data such as the user's body shape, past purchase history, and style preferences, and products are narrowed down based on this information.

[0286] The server filters products from the product information database that match the extracted keywords and the user profile. Through this process, the optimal product for the user is identified. Then, the server generates detailed information about the selected product and a coordination proposal as a prompt sentence.

[0287] The generated prompt sentence is sent to the terminal and provided to the user. For example, the prompt sentence may state, "Pair this recommended blue skirt for this spring with a white blouse for a coordination suitable for the office."

[0288] If a user likes a suggested product, the system integrates with the e-commerce system to facilitate a smooth purchase process. This allows users to buy products without any hassle.

[0289] Furthermore, based on user feedback, the server continues to train its AI model, improving the accuracy of its suggestions. This feedback-based learning allows the system to continuously provide suggestions tailored to each user.

[0290] This allows the system to provide users with a personalized fashion experience, thereby improving user satisfaction.

[0291] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0292] Step 1:

[0293] Users use their devices to input their fashion preferences and desires in natural language. For example, they might input something like, "I want a casual dress in a bright color that's suitable for spring." This input information is sent to the server as string data.

[0294] Step 2:

[0295] The server uses a generative AI model to process incoming natural language requests. This model is composed of natural language processing techniques such as BERT and GPT, which analyze the user's request and extract keywords such as "spring," "bright colors," "casual," and "dress." This systematizes the user's wishes and preferences into specific characteristics.

[0296] Step 3:

[0297] The server retrieves user profile information from the database. This profile includes data such as the user's body type, past purchase history, and style preferences, which can be quickly retrieved using queries. This retrieved data is then used to refine product selection later.

[0298] Step 4:

[0299] The server queries and filters the product information database based on the extracted keywords and user profile information. This data processing involves matching the product metadata, identifying only products that match the criteria of "spring," "bright colors," "casual," and "dress." This process generates a list of potential products.

[0300] Step 5:

[0301] The server selects the most suitable outfit from the generated product list and generates it as a prompt message. This prompt message includes specific product names, styling suggestions, and information about related accessories and color coordination. This prompt message is then sent to the terminal.

[0302] Step 6:

[0303] Users review the suggested outfits on their devices and provide feedback. This feedback includes specific suggestions for improvement and information about their satisfaction level, such as "I prefer this color" or "The size doesn't fit." This information is then sent to the server.

[0304] Step 7:

[0305] The server analyzes the feedback received from the user and uses it to retrain the generated AI model. Specifically, the feedback is used to update the model's weights and correct biases, improving the accuracy of future suggestions. Through this learning process, the system can continuously provide more suitable suggestions to the user.

[0306] (Application Example 1)

[0307] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0308] Conventional fashion selection support systems cannot sufficiently make proposals corresponding to the styles and preferences desired by users, and it is difficult to provide optimal proposals according to individual requirements. In addition, there is a problem that a smooth procedure cannot be realized when purchasing the proposed products. Users need means to efficiently select fashions suitable for themselves and purchase them without stress.

[0309] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0310] In this invention, the server includes means for receiving a request regarding fashion in natural language from a user, means for analyzing the request using natural language processing technology and extracting features regarding the user's desires and preferences, means for filtering appropriate products based on a user profile, and means for generating proposals from the selected products. Thereby, it becomes possible to provide appropriate fashion proposals according to individual needs of users and a smooth purchasing procedure.

[0311] A "user" is an individual consumer who receives fashion proposals using the system.

[0312] "Natural language processing technology" is a computer-based technology for analyzing a user's request in natural language and understanding its content.

[0313] A "user profile" is aggregated data of individual information including a user's body shape, past purchase history, preferred style, and consumption tendency.

[0314] A "product" is a fashion item or merchandise suggested by the system based on the user's preferences.

[0315] An "e-commerce platform" is an online commercial system that allows users to purchase goods via the internet.

[0316] "Feedback" refers to the opinions and reactions that users offer regarding the fashion suggestions they receive.

[0317] To implement this invention, it is necessary to build a system in which a user, a terminal, and a server work together. This system begins with the user entering fashion-related requests into the terminal using natural language. The terminal has an app installed as a front-end application, using a mobile framework such as React Native. Once the user has finished entering the data, it is sent to the server.

[0318] The server is built using Python and utilizes the Google Cloud Natural Language API to analyze user requests. The received requests are analyzed using natural language processing techniques to understand their intent and extract characteristics related to the user's preferences and desires. At this stage, user profile information is retrieved from a PostgreSQL database, taking into account body type, past purchase history, style preferences, and consumption trends.

[0319] Based on this information, the server uses a generative AI model to select the most suitable fashion items for the user and build visual suggestions. This involves sending a prompt message that reads, "Please suggest items that match the user's desired fashion style. Please consider the user's past purchase history and profile, paying particular attention to color and style. Also, please ensure that the purchase process is smooth when linked to the e-commerce site."

[0320] Selected items are suggested to the user on a smartphone application and displayed along with detailed product information. If the user reviews the suggestions and wishes to purchase, the device connects to the e-commerce platform, allowing for a seamless purchase process. For example, if a user enters "I want an outfit suitable for a summer beach resort," the server can analyze the user's past data and suggest a light, coral-colored dress and hat as the most suitable beach attire. This system allows users to enjoy a simple and personalized fashion experience.

[0321] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0322] Step 1:

[0323] The user enters fashion-related requests in natural language using their device. These requests are received by an application on the device and sent to the server. The input data consists of the user's wishes and preferences in text format.

[0324] Step 2:

[0325] The server analyzes the received request data using the Google Cloud Natural Language API and extracts keywords and features contained in the user's request. The input data is a dictionary in natural language format, and the output data is a set of analyzed features.

[0326] Step 3:

[0327] The server retrieves user profiles from a PostgreSQL database, collecting data such as body type, past purchase history, style preferences, and consumption trends. Input data consists of analyzed keywords and characteristics of the user, while output data is a set of profile information.

[0328] Step 4:

[0329] The server uses a generative AI model to filter products based on collected user profile information and analyzed features. Here, a prompt is generated: "Please suggest items that match the user's desired fashion style. Consider the user's past purchase history and profile, paying particular attention to color and style. Also, ensure a smooth purchase process when linked to the e-commerce site." The input data consists of profile information and analyzed features, while the output data is a list of suitable products.

[0330] Step 5:

[0331] The server sends the suggested product list to the terminal for the user to review. The input data is a filtered list of products, and the output data is the product information displayed on the user's terminal. The user makes a purchase decision based on this information.

[0332] Step 6:

[0333] The user selects the product they wish to purchase from the suggested items and initiates the process through the terminal. The terminal connects with the e-commerce platform to facilitate the purchase process. The input data is the product selected by the user, and the output data is confirmation information for the purchase process.

[0334] This system allows users to receive fashion suggestions based on their individual preferences and complete product purchases smoothly online.

[0335] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0336] This invention is implemented as an AI styling service incorporating emotion recognition. This system consists of a server containing an emotion engine, a terminal that accepts user input, and the user themselves, in order to enhance the user's personalized fashion experience.

[0337] Users use their devices to input their fashion preferences and desires in natural language via an application or web interface. The device transmits the user's input to the server in real time. For example, a request might read, "I'm in a good mood today, so I'd like a brightly colored dress."

[0338] The server first analyzes the received input using natural language processing technology. This analysis clarifies the user's request and extracts keywords. Simultaneously, the emotion engine on the server analyzes the user's text to recognize emotional states such as joy, sadness, and excitement. This enables the system to suggest fashion items that match the user's emotional state.

[0339] Next, the server retrieves the user profile from the database. The profile includes information about body type, past purchase history, style preferences, and budget, which forms the basis of the suggestions. Based on the profile information and extracted sentiment keywords, the server searches the product database and filters for relevant products.

[0340] Referencing the selected product list, the server generates the optimal outfit. This outfit is customized to reflect the user's emotional state based on the results of an analysis by the emotion engine. It is then sent to the user's device and the suggestion is displayed visually.

[0341] Users who receive a proposal can enter feedback on their device. This feedback includes their satisfaction with the proposed coordination and any desired modifications. The device can then send this feedback to the server.

[0342] The server collects and analyzes feedback information, and uses it to train AI models, including an emotion engine, thereby improving the accuracy of suggestions for future users. In this way, the suggestion process linked to emotion recognition makes the user's fashion experience more personalized.

[0343] For example, if a user requests, "Today is a special day, so I want to wear something glamorous," the server associates the user's emotional state with "a special day" and selects items that are glamorous and in the user's preferred style. Based on this, suggestions are displayed, and the user can then make the most appropriate fashion choice.

[0344] The following describes the processing flow.

[0345] Step 1:

[0346] The user uses their device to input their fashion requests and preferences in natural language. For example, they might input, "I'm in a cheerful mood today, so I'd like a colorful outfit."

[0347] Step 2:

[0348] The terminal sends the user's natural language request to the server. Supplementary information such as a timestamp and user ID is also sent along with the request.

[0349] Step 3:

[0350] The server analyzes the received request using natural language processing technology. Specifically, it tokenizes the text and extracts keywords to clarify the user's wishes.

[0351] Step 4:

[0352] The emotion engine on the server recognizes emotions from the user's text. For example, a positive emotion is extracted from the text "feeling happy."

[0353] Step 5:

[0354] The server retrieves user profiles from the database. These profiles include body type, past purchase history, preferred style, and budget.

[0355] Step 6:

[0356] The server uses profile information and analyzed emotion data to search the product database. It narrows down the products that match the emotional state and the user's preferences, selecting a few candidates.

[0357] Step 7:

[0358] The server generates outfit suggestions that match the user's emotional state based on a list of selected items. These suggestions include specific items, color combinations, and styling examples.

[0359] Step 8:

[0360] The server sends the generated suggestions to the terminal, which then displays the suggestions to the user. The user can review the suggestions and refer to images and detailed explanations.

[0361] Step 9:

[0362] Users enter feedback on the proposal into their device. This feedback includes their satisfaction with the proposal and whether they would like to see other proposals.

[0363] Step 10:

[0364] The device sends user feedback to the server, which then uses that feedback to train the AI ​​model. This continuously improves the accuracy of the system's suggestions.

[0365] (Example 2)

[0366] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0367] In today's world, it is difficult to provide online clothing selections that cater to individual user preferences and emotions. Traditional systems have been unable to accurately understand user needs and automatically provide optimal fashion suggestions. Furthermore, there have been insufficient means to efficiently utilize user feedback to improve the accuracy of suggestions.

[0368] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0369] In this invention, the server includes means for receiving requests for clothing from a user in natural language, means for analyzing the requests using information processing technology to extract characteristics related to the user's wishes and preferences, and means for analyzing the emotional state based on the extracted characteristics to generate a design based on the emotional state. This makes it possible to quickly and accurately provide optimal fashion suggestions based on the user's individual preferences and emotions.

[0370] A "user" is an entity that utilizes a system and inputs its own requests and preferences in natural language.

[0371] "Natural language" refers to the linguistic forms that humans use on a daily basis, and not to specific programming languages.

[0372] "Clothing" refers to items such as clothes and accessories that a user chooses to wear.

[0373] "Information processing technology" refers to a series of methods and techniques for analyzing data and extracting and utilizing information with a specific intent.

[0374] "Preferences" refer to the individual preferences and tendencies that users have regarding specific styles or characteristics.

[0375] "Emotional state" refers to the feelings and psychological state a user is experiencing at a particular point in time.

[0376] "Design" refers to product and coordination suggestions generated based on the user's requirements and emotions.

[0377] "Evaluation" refers to feedback, such as opinions and impressions, that users give regarding the presented design.

[0378] A "virtual marketplace" refers to an e-commerce platform used by users to purchase goods online.

[0379] A "storage device" is a device for storing information that can store data and retrieve it as needed.

[0380] This invention is a system that provides fashion suggestions based on the user's preferences and emotional state. To implement the invention, the following specific hardware and software are used.

[0381] The user inputs their fashion-related requests in natural language using a device. This device includes computers and smartphones with internet connectivity, and preferably has a web interface or mobile application installed. An example of a user request might be, "I'm in a good mood today, so I'd like a brightly colored dress."

[0382] The device sends the input natural language request to the server in real time. The server then uses information processing technology, specifically Google's Natural Language API, to analyze the request. This analysis process extracts keywords from the request, clearly identifying the user's wishes and preferences. The server also uses sentiment analysis engines, such as OpenAI's GPT model, to analyze the user's emotional state. Based on these results, it generates a fashion design that matches the emotional state.

[0383] Next, the server retrieves the user's profile from the database. This profile includes the user's body type, past purchase history, preferences, and budget information. Based on this information, the server searches the product database and filters for suitable items. From this list of items, it generates optimal design proposals and sends them to the user's terminal.

[0384] Users review the proposed designs and send feedback, such as their satisfaction level and any desired modifications, via their devices. The server collects this feedback and uses it as training data for the generated AI model. This improves the accuracy of future fashion suggestions.

[0385] A concrete example of a prompt message would be: "Based on the user's request, 'Today is a special day, so I want to wear something flashy,' please suggest fashion items that suit their special emotional state."

[0386] Thus, the system of the present invention implements detailed processing to provide users with personalized fashion suggestions in real time.

[0387] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0388] Step 1:

[0389] Users input fashion-related requests in natural language using their devices. Specifically, they launch an application or web interface and input a request such as, "I'm in a good mood today, so I'd like a brightly colored dress." The input data is then sent directly from the device to the server.

[0390] Step 2:

[0391] The server parses the user's natural language request that it receives. The request, as input data, is parsed using Google's Natural Language API, and keywords are extracted. For example, words like "mood," "cheerful," and "dress" are extracted. These analysis results are used in the next step.

[0392] Step 3:

[0393] The server performs sentiment analysis. Based on previously analyzed keywords, it uses OpenAI's GPT model to analyze the user's emotional state. For example, if the information indicates that the user is "in a good mood," it determines that the user's emotional state is "positive." This information is then used in subsequent design generation.

[0394] Step 4:

[0395] The server retrieves the user's profile from the database. The profile includes body type, past purchase history, preferences, and budget information. This data is retrieved as input to the server and used in the next filtering step.

[0396] Step 5:

[0397] The server searches and filters the product database. It searches the product list considering the extracted keywords and user profile. For example, it filters items that match a condition such as "bright-colored dress" and outputs the appropriate items.

[0398] Step 6:

[0399] The server generates optimal design proposals from the filtered products. This process utilizes a generative AI model, customized to suit the user's emotional state. The generated design proposals are then sent to the user's device as visual information.

[0400] Step 7:

[0401] Users review the design proposal generated on their device and provide feedback. This feedback includes their satisfaction level and any desired changes, which then becomes input data for the next server.

[0402] Step 8:

[0403] The server analyzes user feedback and uses it to train the AI ​​model. Based on the feedback data, it generates new training data as prompts for the generated AI model. This process improves the accuracy of suggestions in subsequent attempts.

[0404] (Application Example 2)

[0405] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0406] Conventional fashion recommendation systems are limited to suggestions based on the user's basic preferences, body type, and past purchase history, and have the drawback of not being able to flexibly respond to specific situations and needs that change depending on the user's emotions. Therefore, there is a need to understand the user's real-time emotional state and reflect that information to provide more personalized fashion recommendations.

[0407] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0408] In this invention, the server includes means for analyzing the user's emotional state, means for filtering appropriate products based on the analyzed emotional information and user profile, and means for generating suggestions from the selected products based on the user's current emotional state. This enables personalized fashion suggestions that match the user's real-time emotions.

[0409] "A means of receiving fashion-related requests from users in natural language" refers to an interface that acquires text data directly entered by the user and registers it as information for analysis.

[0410] "A means of analyzing data using natural language processing technology to extract features related to user wishes and preferences" refers to the process of analyzing text data received from users using machine learning algorithms to extract specific keywords and phrases.

[0411] "Methods for analyzing a user's emotional state" refer to algorithms that detect emotions from a user's facial expressions, voice, and entered text, and classify that information into specific emotional categories.

[0412] "Means for filtering appropriate products based on analyzed emotional information and user profiles" refers to a process that selects appropriate products based on emotional data and the user's past behavioral data, and creates a product list that meets the user's needs.

[0413] "A means of generating suggestions based on the user's current emotional state from selected products" refers to a process of selecting items that best match the user's emotions from a filtered product list and then providing specific coordination and purchase suggestions.

[0414] "Means of receiving user feedback on proposals and learning to improve proposal accuracy" refers to a mechanism that collects evaluations and opinions from users, analyzes that information using a machine learning model, and improves the accuracy of future proposals.

[0415] This invention realizes a fashion recommendation system that incorporates sentiment analysis to improve the user experience. Users can input their fashion requests in natural language using their smartphone or other device. The device sends this natural language data to a server, which analyzes the received data using natural language processing technology. Machine learning frameworks such as TensorFlow and PyTorch are used for the analysis.

[0416] The server extracts keywords from the user's request while simultaneously analyzing the user's emotional state. Emotional analysis utilizes algorithms that analyze facial expressions and tone of voice from images and audio, often leveraging libraries such as OpenCV.

[0417] The server then filters out appropriate products based on the user's emotional information and profile data. Profile data includes past purchase history, body type, style preferences, and budget. From the products retrieved through the database search, suggestions are generated that match the user's emotional state.

[0418] The generated suggestions are visually displayed on the device, allowing the user to review them. Users can submit feedback on the suggestions, which is collected on the server and used to train the generating AI model. This continuously improves the accuracy of the suggestions.

[0419] For example, if a user enters into the application, "I'm in a good mood today, so I want some brightly colored clothes," the server will analyze the emotion as "joy" and suggest brightly colored clothing that fits the happy theme. It is also possible to create more specific suggestions by inputting prompts such as, "Analyze the user's facial expression and suggest casual wear that indicates a 'relaxed' state," into the AI ​​model.

[0420] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0421] Step 1:

[0422] The terminal receives fashion-related requests entered by the user in natural language. This input is sent to the server in text data format. The received text is prepared as data for the next parsing process.

[0423] Step 2:

[0424] The server analyzes the received text data using natural language processing techniques. The input is raw data, and the output extracts specific features related to the user's wishes and preferences. In this process, a generative AI model is used to extract keywords from the text and identify the user's intent.

[0425] Step 3:

[0426] The server analyzes the user's emotional state. Input is the user's facial expressions, voice, or text data, and the server identifies the user's emotions through an emotion analysis algorithm. Output is an emotion category such as "joy" or "sadness." This process involves video analysis using tools like OpenCV.

[0427] Step 4:

[0428] The server filters appropriate products based on analyzed sentiment data and a user profile database. The input is sentiment data and profile information, and the output is a filtered product list. Filtering includes algorithmic searching.

[0429] Step 5:

[0430] The server generates optimal suggestions from the selected products based on the user's current emotional state. The input is a filtered product list and emotional data, while the output is specific fashion suggestions. The suggestion generation utilizes a generative AI model to provide coordinated outfit suggestions.

[0431] Step 6:

[0432] Users who receive a suggestion send feedback from their device to the server. The input is the user's evaluation and suggestions for improvement, and the output is training data for future suggestions. The data obtained as feedback is reflected in the AI ​​model, contributing to the improvement of suggestion accuracy.

[0433] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0434] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0435] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0436] [Third Embodiment]

[0437] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0438] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0439] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0440] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0441] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0442] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0443] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0444] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0445] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0446] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0447] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0448] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0449] This invention is implemented as an AI styling service that assists individuals in making fashion choices. This system consists of three elements: a server, a terminal, and a user, and aims to improve the user's personalized fashion experience.

[0450] First, the user uses their device to input their fashion preferences and desires in natural language. For example, they might express a specific wish such as, "I want a spring-colored skirt that would go well with office casual attire." This input information is then sent from the device to the server.

[0451] The server utilizes natural language processing technology to analyze the received natural language information and accurately understand the user's requests. During this process, keywords are extracted to clarify the user's wishes and preferences. Next, the server consults a database to retrieve user profile information. This profile information includes the user's body type, past purchase history, and style preferences, which are used as the basis for generating suggestions.

[0452] Based on the acquired information, the server filters suitable product candidates from a vast product database. This selects products that meet the user's requirements. Based on the selected products, the server suggests the optimal outfit for the user. This suggestion is sent to the terminal and provided to the user.

[0453] The user reviews the suggested outfit and enters feedback into their device. This feedback is sent to the server and used to improve the accuracy of future suggestions. The server analyzes this feedback and trains an AI model, enabling it to provide more user-friendly suggestions.

[0454] Furthermore, if a user wishes to purchase a suggested product, the system integrates with e-commerce sites to provide a seamless purchase process. This integration allows users to purchase products smoothly and enables efficient inventory management.

[0455] For example, if a user receives a suggestion such as "an elegant dress suitable for a weekend party," the server considers the user's profile, including their preferred colors and budget, and selects the most suitable dress from its database. The results are then sent to the user's device, displaying product images and detailed descriptions. The user can then purchase the suggested item directly from the e-commerce site and enjoy their next party outfit. In this way, the entire system works together to provide users with a personalized and comfortable shopping experience.

[0456] The following describes the processing flow.

[0457] Step 1:

[0458] Users use their devices to input their fashion preferences and desires in natural language into an app or website. For example, they might enter a request such as, "I want a casual jacket that's perfect for autumn."

[0459] Step 2:

[0460] The terminal sends the user's input request to the server. At the same time, necessary metadata such as the user ID and device information is also sent.

[0461] Step 3:

[0462] The server analyzes the received request using natural language processing techniques. Specifically, it breaks down the text and extracts keywords that indicate the user's wishes and preferences (e.g., "autumn," "casual," "jacket").

[0463] Step 4:

[0464] The server retrieves user profiles from the database. These profiles include the user's body type, past purchase history, style preferences, and budget.

[0465] Step 5:

[0466] The server searches the product database based on the user profile and extracted keywords, filtering products to match the request. For example, it can narrow down the search for jackets based on criteria such as color, material, and price range.

[0467] Step 6:

[0468] The server generates outfit suggestions for the user based on a filtered list of products. These suggestions include combinations of selected items and a style guide.

[0469] Step 7:

[0470] The server sends the generated proposal to the terminal. The terminal visually presents the proposal details to the user, including images, pricing information, and a purchase button.

[0471] Step 8:

[0472] Users review the proposals and provide feedback as needed. This feedback includes satisfaction levels and desired changes.

[0473] Step 9:

[0474] The device sends user feedback to the server. The server uses this information to train its AI model and improve the accuracy of future suggestions.

[0475] Step 10:

[0476] When a user purchases a suggested product, the system connects with the e-commerce site via the device. The server facilitates the purchase process and inventory check.

[0477] (Example 1)

[0478] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0479] In personal fashion choices, there is a need to efficiently and accurately generate personalized suggestions based on the user's style preferences and past purchase history. Furthermore, providing a seamless process that allows users to easily purchase suggested items is a challenge. Additionally, effectively utilizing user feedback is necessary to continuously improve the quality of suggestions.

[0480] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0481] In this invention, the server includes means for receiving fashion-related requests in natural language from a user via a communication terminal; information processing means using generative AI technology to analyze the requests and extract characteristics related to the user's wishes and preferences; and information processing means for selecting appropriate products from a product information database by referring to the user profile. As a result, the user can receive suggestions optimized for their own style and purchase products quickly and easily. Furthermore, the accuracy of suggestions can be improved based on feedback.

[0482] A "communication terminal" is an electronic device that allows users to input fashion-related requests in natural language and receive suggested information.

[0483] "Generative AI technology" is a type of artificial intelligence technology used to analyze users' requests in natural language and extract features related to their wishes and preferences.

[0484] "Information processing means" refers to the computer process by which a server analyzes user requests and profile information to select appropriate products.

[0485] A "user profile" is a dataset containing information about a user, such as their physical characteristics, past purchase history, preferred style, and budget.

[0486] A "product information database" is a database containing information about a large number of fashion products, and it is the data source referenced when generating suggestions.

[0487] A "prompt message" is a text-based explanation that provides a concrete and easy-to-understand summary of the generated fashion suggestions to the user.

[0488] An "e-commerce system" is an integrated system used when users purchase suggested products online, covering everything from product selection and payment to delivery.

[0489] This invention is embodied as an AI styling system that supports individual fashion choices. This system consists of three elements: a server, a terminal, and a user, and each component works together to provide the user with the most suitable fashion suggestions.

[0490] First, the user uses their device to input their fashion preferences and desires in natural language. Typically, a mobile device such as a smartphone or tablet is used. This information is then sent from the device to the server.

[0491] The server analyzes received requests using a generative AI model (e.g., a natural language processing model based on BERT or GPT) to break down the user's wishes into specific keywords. These keywords become important indicators used when selecting products.

[0492] Next, the server accesses an internal database to retrieve user profile information. This profile includes data such as the user's body type, past purchase history, and style preferences, and this information is used to narrow down the product selection.

[0493] The server filters products from its product information database, matching the extracted keywords and user profile. This process identifies the most suitable products for the user. The server then generates prompt messages containing detailed information about the selected products and suggested outfit combinations.

[0494] The generated prompt message is sent to the terminal and provided to the user. For example, the prompt message might say, "This spring's recommended outfit is a blue skirt paired with a white blouse, making it suitable for the office."

[0495] If a user likes a suggested product, the system integrates with the e-commerce system to facilitate a smooth purchase process. This allows users to buy products without any hassle.

[0496] Furthermore, based on user feedback, the server continues to train its AI model, improving the accuracy of its suggestions. This feedback-based learning allows the system to continuously provide suggestions tailored to each user.

[0497] This allows the system to provide users with a personalized fashion experience, thereby improving user satisfaction.

[0498] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0499] Step 1:

[0500] Users use their devices to input their fashion preferences and desires in natural language. For example, they might input something like, "I want a casual dress in a bright color that's suitable for spring." This input information is sent to the server as string data.

[0501] Step 2:

[0502] The server uses a generative AI model to process incoming natural language requests. This model is composed of natural language processing techniques such as BERT and GPT, which analyze the user's request and extract keywords such as "spring," "bright colors," "casual," and "dress." This systematizes the user's wishes and preferences into specific characteristics.

[0503] Step 3:

[0504] The server retrieves user profile information from the database. This profile includes data such as the user's body type, past purchase history, and style preferences, which can be quickly retrieved using queries. This retrieved data is then used to refine product selection later.

[0505] Step 4:

[0506] The server queries and filters the product information database based on the extracted keywords and user profile information. This data processing involves matching the product metadata, identifying only products that match the criteria of "spring," "bright colors," "casual," and "dress." This process generates a list of potential products.

[0507] Step 5:

[0508] The server selects the most suitable outfit from the generated product list and generates it as a prompt message. This prompt message includes specific product names, styling suggestions, and information about related accessories and color coordination. This prompt message is then sent to the terminal.

[0509] Step 6:

[0510] Users review the suggested outfits on their devices and provide feedback. This feedback includes specific suggestions for improvement and information about their satisfaction level, such as "I prefer this color" or "The size doesn't fit." This information is then sent to the server.

[0511] Step 7:

[0512] The server analyzes the feedback received from the user and uses it to retrain the generated AI model. Specifically, the feedback is used to update the model's weights and correct biases, improving the accuracy of future suggestions. Through this learning process, the system can continuously provide more suitable suggestions to the user.

[0513] (Application Example 1)

[0514] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0515] Conventional fashion selection support systems fail to adequately provide suggestions that match the user's desired style and preferences, making it difficult to offer optimal suggestions tailored to individual needs. Furthermore, there are challenges in ensuring a smooth purchasing process for the suggested items. Users need a way to efficiently select and purchase fashion that suits them without stress.

[0516] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0517] In this invention, the server includes means for receiving fashion-related requests from a user in natural language, means for analyzing the requests using natural language processing technology to extract characteristics related to the user's wishes and preferences, means for filtering appropriate products based on the user profile, and means for generating suggestions from the selected products. This enables the provision of appropriate fashion suggestions tailored to the user's individual needs and facilitates a smooth purchasing process.

[0518] A "user" is an individual consumer who uses the system to receive fashion suggestions.

[0519] "Natural language processing technology" is a computer-based technology that analyzes and understands the content of user requests expressed in natural language.

[0520] A "user profile" is a collection of individual data that includes a user's body type, past purchase history, preferred style, and consumption trends.

[0521] A "product" is a fashion item or merchandise suggested by the system based on the user's preferences.

[0522] An "e-commerce platform" is an online commercial system that allows users to purchase goods via the internet.

[0523] "Feedback" refers to the opinions and reactions that users offer regarding the fashion suggestions they receive.

[0524] To implement this invention, it is necessary to build a system in which a user, a terminal, and a server work together. This system begins with the user entering fashion-related requests into the terminal using natural language. The terminal has an app installed as a front-end application, using a mobile framework such as React Native. Once the user has finished entering the data, it is sent to the server.

[0525] The server is built using Python and utilizes the Google Cloud Natural Language API to analyze user requests. The received requests are analyzed using natural language processing techniques to understand their intent and extract characteristics related to the user's preferences and desires. At this stage, user profile information is retrieved from a PostgreSQL database, taking into account body type, past purchase history, style preferences, and consumption trends.

[0526] Based on this information, the server uses a generative AI model to select the most suitable fashion items for the user and build visual suggestions. This involves sending a prompt message that reads, "Please suggest items that match the user's desired fashion style. Please consider the user's past purchase history and profile, paying particular attention to color and style. Also, please ensure that the purchase process is smooth when linked to the e-commerce site."

[0527] Selected items are suggested to the user on a smartphone application and displayed along with detailed product information. If the user reviews the suggestions and wishes to purchase, the device connects to the e-commerce platform, allowing for a seamless purchase process. For example, if a user enters "I want an outfit suitable for a summer beach resort," the server can analyze the user's past data and suggest a light, coral-colored dress and hat as the most suitable beach attire. This system allows users to enjoy a simple and personalized fashion experience.

[0528] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0529] Step 1:

[0530] The user enters fashion-related requests in natural language using their device. These requests are received by an application on the device and sent to the server. The input data consists of the user's wishes and preferences in text format.

[0531] Step 2:

[0532] The server analyzes the received request data using the Google Cloud Natural Language API and extracts keywords and features contained in the user's request. The input data is a dictionary in natural language format, and the output data is a set of analyzed features.

[0533] Step 3:

[0534] The server retrieves user profiles from a PostgreSQL database, collecting data such as body type, past purchase history, style preferences, and consumption trends. Input data consists of analyzed keywords and characteristics of the user, while output data is a set of profile information.

[0535] Step 4:

[0536] The server uses a generative AI model to filter products based on collected user profile information and analyzed features. Here, a prompt is generated: "Please suggest items that match the user's desired fashion style. Consider the user's past purchase history and profile, paying particular attention to color and style. Also, ensure a smooth purchase process when linked to the e-commerce site." The input data consists of profile information and analyzed features, while the output data is a list of suitable products.

[0537] Step 5:

[0538] The server sends the suggested product list to the terminal for the user to review. The input data is a filtered list of products, and the output data is the product information displayed on the user's terminal. The user makes a purchase decision based on this information.

[0539] Step 6:

[0540] The user selects the product they wish to purchase from the suggested items and initiates the process through the terminal. The terminal connects with the e-commerce platform to facilitate the purchase process. The input data is the product selected by the user, and the output data is confirmation information for the purchase process.

[0541] This system allows users to receive fashion suggestions based on their individual preferences and complete product purchases smoothly online.

[0542] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0543] This invention is implemented as an AI styling service incorporating emotion recognition. This system consists of a server containing an emotion engine, a terminal that accepts user input, and the user themselves, in order to enhance the user's personalized fashion experience.

[0544] Users use their devices to input their fashion preferences and desires in natural language via an application or web interface. The device transmits the user's input to the server in real time. For example, a request might read, "I'm in a good mood today, so I'd like a brightly colored dress."

[0545] The server first analyzes the received input using natural language processing technology. This analysis clarifies the user's request and extracts keywords. Simultaneously, the emotion engine on the server analyzes the user's text to recognize emotional states such as joy, sadness, and excitement. This enables the system to suggest fashion items that match the user's emotional state.

[0546] Next, the server retrieves the user profile from the database. The profile includes information about body type, past purchase history, style preferences, and budget, which forms the basis of the suggestions. Based on the profile information and extracted sentiment keywords, the server searches the product database and filters for relevant products.

[0547] Referencing the selected product list, the server generates the optimal outfit. This outfit is customized to reflect the user's emotional state based on the results of an analysis by the emotion engine. It is then sent to the user's device and the suggestion is displayed visually.

[0548] Users who receive a proposal can enter feedback on their device. This feedback includes their satisfaction with the proposed coordination and any desired modifications. The device can then send this feedback to the server.

[0549] The server collects and analyzes feedback information, and uses it to train AI models, including an emotion engine, thereby improving the accuracy of suggestions for future users. In this way, the suggestion process linked to emotion recognition makes the user's fashion experience more personalized.

[0550] For example, if a user requests, "Today is a special day, so I want to wear something glamorous," the server associates the user's emotional state with "a special day" and selects items that are glamorous and in the user's preferred style. Based on this, suggestions are displayed, and the user can then make the most appropriate fashion choice.

[0551] The following describes the processing flow.

[0552] Step 1:

[0553] The user uses their device to input their fashion requests and preferences in natural language. For example, they might input, "I'm in a cheerful mood today, so I'd like a colorful outfit."

[0554] Step 2:

[0555] The terminal sends the user's natural language request to the server. Supplementary information such as a timestamp and user ID is also sent along with the request.

[0556] Step 3:

[0557] The server analyzes the received request using natural language processing technology. Specifically, it tokenizes the text and extracts keywords to clarify the user's wishes.

[0558] Step 4:

[0559] The emotion engine on the server recognizes emotions from the user's text. For example, a positive emotion is extracted from the text "feeling happy."

[0560] Step 5:

[0561] The server retrieves user profiles from the database. These profiles include body type, past purchase history, preferred style, and budget.

[0562] Step 6:

[0563] The server uses profile information and analyzed emotion data to search the product database. It narrows down the products that match the emotional state and the user's preferences, selecting a few candidates.

[0564] Step 7:

[0565] The server generates outfit suggestions that match the user's emotional state based on a list of selected items. These suggestions include specific items, color combinations, and styling examples.

[0566] Step 8:

[0567] The server sends the generated suggestions to the terminal, which then displays the suggestions to the user. The user can review the suggestions and refer to images and detailed explanations.

[0568] Step 9:

[0569] Users enter feedback on the proposal into their device. This feedback includes their satisfaction with the proposal and whether they would like to see other proposals.

[0570] Step 10:

[0571] The device sends user feedback to the server, which then uses that feedback to train the AI ​​model. This continuously improves the accuracy of the system's suggestions.

[0572] (Example 2)

[0573] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0574] In today's world, it is difficult to provide online clothing selections that cater to individual user preferences and emotions. Traditional systems have been unable to accurately understand user needs and automatically provide optimal fashion suggestions. Furthermore, there have been insufficient means to efficiently utilize user feedback to improve the accuracy of suggestions.

[0575] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0576] In this invention, the server includes means for receiving requests for clothing from a user in natural language, means for analyzing the requests using information processing technology to extract characteristics related to the user's wishes and preferences, and means for analyzing the emotional state based on the extracted characteristics to generate a design based on the emotional state. This makes it possible to quickly and accurately provide optimal fashion suggestions based on the user's individual preferences and emotions.

[0577] A "user" is an entity that utilizes a system and inputs its own requests and preferences in natural language.

[0578] "Natural language" refers to the linguistic forms that humans use on a daily basis, and not to specific programming languages.

[0579] "Clothing" refers to items such as clothes and accessories that a user chooses to wear.

[0580] "Information processing technology" refers to a series of methods and techniques for analyzing data and extracting and utilizing information with a specific intent.

[0581] "Preferences" refer to the individual preferences and tendencies that users have regarding specific styles or characteristics.

[0582] "Emotional state" refers to the feelings and psychological state a user is experiencing at a particular point in time.

[0583] "Design" refers to product and coordination suggestions generated based on the user's requirements and emotions.

[0584] "Evaluation" refers to feedback, such as opinions and impressions, that users give regarding the presented design.

[0585] A "virtual marketplace" refers to an e-commerce platform used by users to purchase goods online.

[0586] A "storage device" is a device for storing information that can store data and retrieve it as needed.

[0587] This invention is a system that provides fashion suggestions based on the user's preferences and emotional state. To implement the invention, the following specific hardware and software are used.

[0588] The user inputs their fashion-related requests in natural language using a device. This device includes computers and smartphones with internet connectivity, and preferably has a web interface or mobile application installed. An example of a user request might be, "I'm in a good mood today, so I'd like a brightly colored dress."

[0589] The device sends the input natural language request to the server in real time. The server then uses information processing technology, specifically Google's Natural Language API, to analyze the request. This analysis process extracts keywords from the request, clearly identifying the user's wishes and preferences. The server also uses sentiment analysis engines, such as OpenAI's GPT model, to analyze the user's emotional state. Based on these results, it generates a fashion design that matches the emotional state.

[0590] Next, the server retrieves the user's profile from the database. This profile includes the user's body type, past purchase history, preferences, and budget information. Based on this information, the server searches the product database and filters for suitable items. From this list of items, it generates optimal design proposals and sends them to the user's terminal.

[0591] Users review the proposed designs and send feedback, such as their satisfaction level and any desired modifications, via their devices. The server collects this feedback and uses it as training data for the generated AI model. This improves the accuracy of future fashion suggestions.

[0592] A concrete example of a prompt message would be: "Based on the user's request, 'Today is a special day, so I want to wear something flashy,' please suggest fashion items that suit their special emotional state."

[0593] Thus, the system of the present invention implements detailed processing to provide users with personalized fashion suggestions in real time.

[0594] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0595] Step 1:

[0596] Users input fashion-related requests in natural language using their devices. Specifically, they launch an application or web interface and input a request such as, "I'm in a good mood today, so I'd like a brightly colored dress." The input data is then sent directly from the device to the server.

[0597] Step 2:

[0598] The server parses the user's natural language request that it receives. The request, as input data, is parsed using Google's Natural Language API, and keywords are extracted. For example, words like "mood," "cheerful," and "dress" are extracted. These analysis results are used in the next step.

[0599] Step 3:

[0600] The server performs sentiment analysis. Based on previously analyzed keywords, it uses OpenAI's GPT model to analyze the user's emotional state. For example, if the information indicates that the user is "in a good mood," it determines that the user's emotional state is "positive." This information is then used in subsequent design generation.

[0601] Step 4:

[0602] The server retrieves the user's profile from the database. The profile includes body type, past purchase history, preferences, and budget information. This data is retrieved as input to the server and used in the next filtering step.

[0603] Step 5:

[0604] The server searches and filters the product database. It searches the product list considering the extracted keywords and user profile. For example, it filters items that match a condition such as "bright-colored dress" and outputs the appropriate items.

[0605] Step 6:

[0606] The server generates optimal design proposals from the filtered products. This process utilizes a generative AI model, customized to suit the user's emotional state. The generated design proposals are then sent to the user's device as visual information.

[0607] Step 7:

[0608] Users review the design proposal generated on their device and provide feedback. This feedback includes their satisfaction level and any desired changes, which then becomes input data for the next server.

[0609] Step 8:

[0610] The server analyzes user feedback and uses it to train the AI ​​model. Based on the feedback data, it generates new training data as prompts for the generated AI model. This process improves the accuracy of suggestions in subsequent attempts.

[0611] (Application Example 2)

[0612] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0613] Conventional fashion recommendation systems are limited to suggestions based on the user's basic preferences, body type, and past purchase history, and have the drawback of not being able to flexibly respond to specific situations and needs that change depending on the user's emotions. Therefore, there is a need to understand the user's real-time emotional state and reflect that information to provide more personalized fashion recommendations.

[0614] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0615] In this invention, the server includes means for analyzing the user's emotional state, means for filtering appropriate products based on the analyzed emotional information and user profile, and means for generating suggestions from the selected products based on the user's current emotional state. This enables personalized fashion suggestions that match the user's real-time emotions.

[0616] "A means of receiving fashion-related requests from users in natural language" refers to an interface that acquires text data directly entered by the user and registers it as information for analysis.

[0617] "A means of analyzing data using natural language processing technology to extract features related to user wishes and preferences" refers to the process of analyzing text data received from users using machine learning algorithms to extract specific keywords and phrases.

[0618] "Methods for analyzing a user's emotional state" refer to algorithms that detect emotions from a user's facial expressions, voice, and entered text, and classify that information into specific emotional categories.

[0619] "Means for filtering appropriate products based on analyzed emotional information and user profiles" refers to a process that selects appropriate products based on emotional data and the user's past behavioral data, and creates a product list that meets the user's needs.

[0620] "A means of generating suggestions based on the user's current emotional state from selected products" refers to a process of selecting items that best match the user's emotions from a filtered product list and then providing specific coordination and purchase suggestions.

[0621] "Means of receiving user feedback on proposals and learning to improve proposal accuracy" refers to a mechanism that collects evaluations and opinions from users, analyzes that information using a machine learning model, and improves the accuracy of future proposals.

[0622] This invention realizes a fashion recommendation system that incorporates sentiment analysis to improve the user experience. Users can input their fashion requests in natural language using their smartphone or other device. The device sends this natural language data to a server, which analyzes the received data using natural language processing technology. Machine learning frameworks such as TensorFlow and PyTorch are used for the analysis.

[0623] The server extracts keywords from the user's request while simultaneously analyzing the user's emotional state. Emotional analysis utilizes algorithms that analyze facial expressions and tone of voice from images and audio, often leveraging libraries such as OpenCV.

[0624] The server then filters out appropriate products based on the user's emotional information and profile data. Profile data includes past purchase history, body type, style preferences, and budget. From the products retrieved through the database search, suggestions are generated that match the user's emotional state.

[0625] The generated suggestions are visually displayed on the device, allowing the user to review them. Users can submit feedback on the suggestions, which is collected on the server and used to train the generating AI model. This continuously improves the accuracy of the suggestions.

[0626] For example, if a user enters into the application, "I'm in a good mood today, so I want some brightly colored clothes," the server will analyze the emotion as "joy" and suggest brightly colored clothing that fits the happy theme. It is also possible to create more specific suggestions by inputting prompts such as, "Analyze the user's facial expression and suggest casual wear that indicates a 'relaxed' state," into the AI ​​model.

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

[0628] Step 1:

[0629] The terminal receives fashion-related requests entered by the user in natural language. This input is sent to the server in text data format. The received text is prepared as data for the next parsing process.

[0630] Step 2:

[0631] The server analyzes the received text data using natural language processing techniques. The input is raw data, and the output extracts specific features related to the user's wishes and preferences. In this process, a generative AI model is used to extract keywords from the text and identify the user's intent.

[0632] Step 3:

[0633] The server analyzes the user's emotional state. Input is the user's facial expressions, voice, or text data, and the server identifies the user's emotions through an emotion analysis algorithm. Output is an emotion category such as "joy" or "sadness." This process involves video analysis using tools like OpenCV.

[0634] Step 4:

[0635] The server filters appropriate products based on analyzed sentiment data and a user profile database. The input is sentiment data and profile information, and the output is a filtered product list. Filtering includes algorithmic searching.

[0636] Step 5:

[0637] The server generates optimal suggestions from the selected products based on the user's current emotional state. The input is a filtered product list and emotional data, while the output is specific fashion suggestions. The suggestion generation utilizes a generative AI model to provide coordinated outfit suggestions.

[0638] Step 6:

[0639] Users who receive a suggestion send feedback from their device to the server. The input is the user's evaluation and suggestions for improvement, and the output is training data for future suggestions. The data obtained as feedback is reflected in the AI ​​model, contributing to the improvement of suggestion accuracy.

[0640] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0641] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0642] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0643] [Fourth Embodiment]

[0644] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0645] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0646] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0647] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0648] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0649] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0650] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0651] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0652] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0653] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0654] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0655] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0656] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0657] This invention is implemented as an AI styling service that assists individuals in making fashion choices. This system consists of three elements: a server, a terminal, and a user, and aims to improve the user's personalized fashion experience.

[0658] First, the user uses their device to input their fashion preferences and desires in natural language. For example, they might express a specific wish such as, "I want a spring-colored skirt that would go well with office casual attire." This input information is then sent from the device to the server.

[0659] The server utilizes natural language processing technology to analyze the received natural language information and accurately understand the user's requests. During this process, keywords are extracted to clarify the user's wishes and preferences. Next, the server consults a database to retrieve user profile information. This profile information includes the user's body type, past purchase history, and style preferences, which are used as the basis for generating suggestions.

[0660] Based on the acquired information, the server filters suitable product candidates from a vast product database. This selects products that meet the user's requirements. Based on the selected products, the server suggests the optimal outfit for the user. This suggestion is sent to the terminal and provided to the user.

[0661] The user reviews the suggested outfit and enters feedback into their device. This feedback is sent to the server and used to improve the accuracy of future suggestions. The server analyzes this feedback and trains an AI model, enabling it to provide more user-friendly suggestions.

[0662] Furthermore, if a user wishes to purchase a suggested product, the system integrates with e-commerce sites to provide a seamless purchase process. This integration allows users to purchase products smoothly and enables efficient inventory management.

[0663] For example, if a user receives a suggestion such as "an elegant dress suitable for a weekend party," the server considers the user's profile, including their preferred colors and budget, and selects the most suitable dress from its database. The results are then sent to the user's device, displaying product images and detailed descriptions. The user can then purchase the suggested item directly from the e-commerce site and enjoy their next party outfit. In this way, the entire system works together to provide users with a personalized and comfortable shopping experience.

[0664] The following describes the processing flow.

[0665] Step 1:

[0666] Users use their devices to input their fashion preferences and desires in natural language into an app or website. For example, they might enter a request such as, "I want a casual jacket that's perfect for autumn."

[0667] Step 2:

[0668] The terminal sends the user's input request to the server. At the same time, necessary metadata such as the user ID and device information is also sent.

[0669] Step 3:

[0670] The server analyzes the received request using natural language processing techniques. Specifically, it breaks down the text and extracts keywords that indicate the user's wishes and preferences (e.g., "autumn," "casual," "jacket").

[0671] Step 4:

[0672] The server retrieves user profiles from the database. These profiles include the user's body type, past purchase history, style preferences, and budget.

[0673] Step 5:

[0674] The server searches the product database based on the user profile and extracted keywords, filtering products to match the request. For example, it can narrow down the search for jackets based on criteria such as color, material, and price range.

[0675] Step 6:

[0676] The server generates outfit suggestions for the user based on a filtered list of products. These suggestions include combinations of selected items and a style guide.

[0677] Step 7:

[0678] The server sends the generated proposal to the terminal. The terminal visually presents the proposal details to the user, including images, pricing information, and a purchase button.

[0679] Step 8:

[0680] Users review the proposals and provide feedback as needed. This feedback includes satisfaction levels and desired changes.

[0681] Step 9:

[0682] The device sends user feedback to the server. The server uses this information to train its AI model and improve the accuracy of future suggestions.

[0683] Step 10:

[0684] When a user purchases a suggested product, the system connects with the e-commerce site via the device. The server facilitates the purchase process and inventory check.

[0685] (Example 1)

[0686] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0687] In personal fashion choices, there is a need to efficiently and accurately generate personalized suggestions based on the user's style preferences and past purchase history. Furthermore, providing a seamless process that allows users to easily purchase suggested items is a challenge. Additionally, effectively utilizing user feedback is necessary to continuously improve the quality of suggestions.

[0688] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0689] In this invention, the server includes means for receiving fashion-related requests in natural language from a user via a communication terminal; information processing means using generative AI technology to analyze the requests and extract characteristics related to the user's wishes and preferences; and information processing means for selecting appropriate products from a product information database by referring to the user profile. As a result, the user can receive suggestions optimized for their own style and purchase products quickly and easily. Furthermore, the accuracy of suggestions can be improved based on feedback.

[0690] A "communication terminal" is an electronic device that allows users to input fashion-related requests in natural language and receive suggested information.

[0691] "Generative AI technology" is a type of artificial intelligence technology used to analyze users' requests in natural language and extract features related to their wishes and preferences.

[0692] "Information processing means" refers to the computer process by which a server analyzes user requests and profile information to select appropriate products.

[0693] A "user profile" is a dataset containing information about a user, such as their physical characteristics, past purchase history, preferred style, and budget.

[0694] A "product information database" is a database containing information about a large number of fashion products, and it is the data source referenced when generating suggestions.

[0695] A "prompt message" is a text-based explanation that provides a concrete and easy-to-understand summary of the generated fashion suggestions to the user.

[0696] An "e-commerce system" is an integrated system used when users purchase suggested products online, covering everything from product selection and payment to delivery.

[0697] This invention is embodied as an AI styling system that supports individual fashion choices. This system consists of three elements: a server, a terminal, and a user, and each component works together to provide the user with the most suitable fashion suggestions.

[0698] First, the user uses their device to input their fashion preferences and desires in natural language. Typically, a mobile device such as a smartphone or tablet is used. This information is then sent from the device to the server.

[0699] The server analyzes received requests using a generative AI model (e.g., a natural language processing model based on BERT or GPT) to break down the user's wishes into specific keywords. These keywords become important indicators used when selecting products.

[0700] Next, the server accesses an internal database to retrieve user profile information. This profile includes data such as the user's body type, past purchase history, and style preferences, and this information is used to narrow down the product selection.

[0701] The server filters products from its product information database, matching the extracted keywords and user profile. This process identifies the most suitable products for the user. The server then generates prompt messages containing detailed information about the selected products and suggested outfit combinations.

[0702] The generated prompt message is sent to the terminal and provided to the user. For example, the prompt message might say, "This spring's recommended outfit is a blue skirt paired with a white blouse, making it suitable for the office."

[0703] If a user likes a suggested product, the system integrates with the e-commerce system to facilitate a smooth purchase process. This allows users to buy products without any hassle.

[0704] Furthermore, based on user feedback, the server continues to train its AI model, improving the accuracy of its suggestions. This feedback-based learning allows the system to continuously provide suggestions tailored to each user.

[0705] This allows the system to provide users with a personalized fashion experience, thereby improving user satisfaction.

[0706] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0707] Step 1:

[0708] Users use their devices to input their fashion preferences and desires in natural language. For example, they might input something like, "I want a casual dress in a bright color that's suitable for spring." This input information is sent to the server as string data.

[0709] Step 2:

[0710] The server uses a generative AI model to process incoming natural language requests. This model is composed of natural language processing techniques such as BERT and GPT, which analyze the user's request and extract keywords such as "spring," "bright colors," "casual," and "dress." This systematizes the user's wishes and preferences into specific characteristics.

[0711] Step 3:

[0712] The server retrieves user profile information from the database. This profile includes data such as the user's body type, past purchase history, and style preferences, which can be quickly retrieved using queries. This retrieved data is then used to refine product selection later.

[0713] Step 4:

[0714] The server queries and filters the product information database based on the extracted keywords and user profile information. This data processing involves matching the product metadata, identifying only products that match the criteria of "spring," "bright colors," "casual," and "dress." This process generates a list of potential products.

[0715] Step 5:

[0716] The server selects the most suitable outfit from the generated product list and generates it as a prompt message. This prompt message includes specific product names, styling suggestions, and information about related accessories and color coordination. This prompt message is then sent to the terminal.

[0717] Step 6:

[0718] Users review the suggested outfits on their devices and provide feedback. This feedback includes specific suggestions for improvement and information about their satisfaction level, such as "I prefer this color" or "The size doesn't fit." This information is then sent to the server.

[0719] Step 7:

[0720] The server analyzes the feedback received from the user and uses it to retrain the generated AI model. Specifically, the feedback is used to update the model's weights and correct biases, improving the accuracy of future suggestions. Through this learning process, the system can continuously provide more suitable suggestions to the user.

[0721] (Application Example 1)

[0722] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0723] Conventional fashion selection support systems fail to adequately provide suggestions that match the user's desired style and preferences, making it difficult to offer optimal suggestions tailored to individual needs. Furthermore, there are challenges in ensuring a smooth purchasing process for the suggested items. Users need a way to efficiently select and purchase fashion that suits them without stress.

[0724] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0725] In this invention, the server includes means for receiving fashion-related requests from a user in natural language, means for analyzing the requests using natural language processing technology to extract characteristics related to the user's wishes and preferences, means for filtering appropriate products based on the user profile, and means for generating suggestions from the selected products. This enables the provision of appropriate fashion suggestions tailored to the user's individual needs and facilitates a smooth purchasing process.

[0726] A "user" is an individual consumer who uses the system to receive fashion suggestions.

[0727] "Natural language processing technology" is a computer-based technology that analyzes and understands the content of user requests expressed in natural language.

[0728] A "user profile" is a collection of individual data that includes a user's body type, past purchase history, preferred style, and consumption trends.

[0729] A "product" is a fashion item or merchandise suggested by the system based on the user's preferences.

[0730] An "e-commerce platform" is an online commercial system that allows users to purchase goods via the internet.

[0731] "Feedback" refers to the opinions and reactions that users offer regarding the fashion suggestions they receive.

[0732] To implement this invention, it is necessary to build a system in which a user, a terminal, and a server work together. This system begins with the user entering fashion-related requests into the terminal using natural language. The terminal has an app installed as a front-end application, using a mobile framework such as React Native. Once the user has finished entering the data, it is sent to the server.

[0733] The server is built using Python and utilizes the Google Cloud Natural Language API to analyze user requests. The received requests are analyzed using natural language processing techniques to understand their intent and extract characteristics related to the user's preferences and desires. At this stage, user profile information is retrieved from a PostgreSQL database, taking into account body type, past purchase history, style preferences, and consumption trends.

[0734] Based on this information, the server uses a generative AI model to select the most suitable fashion items for the user and build visual suggestions. This involves sending a prompt message that reads, "Please suggest items that match the user's desired fashion style. Please consider the user's past purchase history and profile, paying particular attention to color and style. Also, please ensure that the purchase process is smooth when linked to the e-commerce site."

[0735] Selected items are suggested to the user on a smartphone application and displayed along with detailed product information. If the user reviews the suggestions and wishes to purchase, the device connects to the e-commerce platform, allowing for a seamless purchase process. For example, if a user enters "I want an outfit suitable for a summer beach resort," the server can analyze the user's past data and suggest a light, coral-colored dress and hat as the most suitable beach attire. This system allows users to enjoy a simple and personalized fashion experience.

[0736] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0737] Step 1:

[0738] The user enters fashion-related requests in natural language using their device. These requests are received by an application on the device and sent to the server. The input data consists of the user's wishes and preferences in text format.

[0739] Step 2:

[0740] The server analyzes the received request data using the Google Cloud Natural Language API and extracts keywords and features contained in the user's request. The input data is a dictionary in natural language format, and the output data is a set of analyzed features.

[0741] Step 3:

[0742] The server retrieves user profiles from a PostgreSQL database, collecting data such as body type, past purchase history, style preferences, and consumption trends. Input data consists of analyzed keywords and characteristics of the user, while output data is a set of profile information.

[0743] Step 4:

[0744] The server uses a generative AI model to filter products based on collected user profile information and analyzed features. Here, a prompt is generated: "Please suggest items that match the user's desired fashion style. Consider the user's past purchase history and profile, paying particular attention to color and style. Also, ensure a smooth purchase process when linked to the e-commerce site." The input data consists of profile information and analyzed features, while the output data is a list of suitable products.

[0745] Step 5:

[0746] The server sends the suggested product list to the terminal for the user to review. The input data is a filtered list of products, and the output data is the product information displayed on the user's terminal. The user makes a purchase decision based on this information.

[0747] Step 6:

[0748] The user selects the product they wish to purchase from the suggested items and initiates the process through the terminal. The terminal connects with the e-commerce platform to facilitate the purchase process. The input data is the product selected by the user, and the output data is confirmation information for the purchase process.

[0749] This system allows users to receive fashion suggestions based on their individual preferences and complete product purchases smoothly online.

[0750] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0751] This invention is implemented as an AI styling service incorporating emotion recognition. This system consists of a server containing an emotion engine, a terminal that accepts user input, and the user themselves, in order to enhance the user's personalized fashion experience.

[0752] Users use their devices to input their fashion preferences and desires in natural language via an application or web interface. The device transmits the user's input to the server in real time. For example, a request might read, "I'm in a good mood today, so I'd like a brightly colored dress."

[0753] The server first analyzes the received input using natural language processing technology. This analysis clarifies the user's request and extracts keywords. Simultaneously, the emotion engine on the server analyzes the user's text to recognize emotional states such as joy, sadness, and excitement. This enables the system to suggest fashion items that match the user's emotional state.

[0754] Next, the server retrieves the user profile from the database. The profile includes information about body type, past purchase history, style preferences, and budget, which forms the basis of the suggestions. Based on the profile information and extracted sentiment keywords, the server searches the product database and filters for relevant products.

[0755] Referencing the selected product list, the server generates the optimal outfit. This outfit is customized to reflect the user's emotional state based on the results of an analysis by the emotion engine. It is then sent to the user's device and the suggestion is displayed visually.

[0756] Users who receive a proposal can enter feedback on their device. This feedback includes their satisfaction with the proposed coordination and any desired modifications. The device can then send this feedback to the server.

[0757] The server collects and analyzes feedback information, and uses it to train AI models, including an emotion engine, thereby improving the accuracy of suggestions for future users. In this way, the suggestion process linked to emotion recognition makes the user's fashion experience more personalized.

[0758] For example, if a user requests, "Today is a special day, so I want to wear something glamorous," the server associates the user's emotional state with "a special day" and selects items that are glamorous and in the user's preferred style. Based on this, suggestions are displayed, and the user can then make the most appropriate fashion choice.

[0759] The following describes the processing flow.

[0760] Step 1:

[0761] The user uses their device to input their fashion requests and preferences in natural language. For example, they might input, "I'm in a cheerful mood today, so I'd like a colorful outfit."

[0762] Step 2:

[0763] The terminal sends the user's natural language request to the server. Supplementary information such as a timestamp and user ID is also sent along with the request.

[0764] Step 3:

[0765] The server analyzes the received request using natural language processing technology. Specifically, it tokenizes the text and extracts keywords to clarify the user's wishes.

[0766] Step 4:

[0767] The emotion engine on the server recognizes emotions from the user's text. For example, a positive emotion is extracted from the text "feeling happy."

[0768] Step 5:

[0769] The server retrieves user profiles from the database. These profiles include body type, past purchase history, preferred style, and budget.

[0770] Step 6:

[0771] The server uses profile information and analyzed emotion data to search the product database. It narrows down the products that match the emotional state and the user's preferences, selecting a few candidates.

[0772] Step 7:

[0773] The server generates outfit suggestions that match the user's emotional state based on a list of selected items. These suggestions include specific items, color combinations, and styling examples.

[0774] Step 8:

[0775] The server sends the generated suggestions to the terminal, which then displays the suggestions to the user. The user can review the suggestions and refer to images and detailed explanations.

[0776] Step 9:

[0777] Users enter feedback on the proposal into their device. This feedback includes their satisfaction with the proposal and whether they would like to see other proposals.

[0778] Step 10:

[0779] The device sends user feedback to the server, which then uses that feedback to train the AI ​​model. This continuously improves the accuracy of the system's suggestions.

[0780] (Example 2)

[0781] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0782] In today's world, it is difficult to provide online clothing selections that cater to individual user preferences and emotions. Traditional systems have been unable to accurately understand user needs and automatically provide optimal fashion suggestions. Furthermore, there have been insufficient means to efficiently utilize user feedback to improve the accuracy of suggestions.

[0783] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0784] In this invention, the server includes means for receiving requests for clothing from a user in natural language, means for analyzing the requests using information processing technology to extract characteristics related to the user's wishes and preferences, and means for analyzing the emotional state based on the extracted characteristics to generate a design based on the emotional state. This makes it possible to quickly and accurately provide optimal fashion suggestions based on the user's individual preferences and emotions.

[0785] A "user" is an entity that utilizes a system and inputs its own requests and preferences in natural language.

[0786] "Natural language" refers to the linguistic forms that humans use on a daily basis, and not to specific programming languages.

[0787] "Clothing" refers to items such as clothes and accessories that a user chooses to wear.

[0788] "Information processing technology" refers to a series of methods and techniques for analyzing data and extracting and utilizing information with a specific intent.

[0789] "Preferences" refer to the individual preferences and tendencies that users have regarding specific styles or characteristics.

[0790] "Emotional state" refers to the feelings and psychological state a user is experiencing at a particular point in time.

[0791] "Design" refers to product and coordination suggestions generated based on the user's requirements and emotions.

[0792] "Evaluation" refers to feedback, such as opinions and impressions, that users give regarding the presented design.

[0793] A "virtual marketplace" refers to an e-commerce platform used by users to purchase goods online.

[0794] A "storage device" is a device for storing information that can store data and retrieve it as needed.

[0795] This invention is a system that provides fashion suggestions based on the user's preferences and emotional state. To implement the invention, the following specific hardware and software are used.

[0796] The user inputs their fashion-related requests in natural language using a device. This device includes computers and smartphones with internet connectivity, and preferably has a web interface or mobile application installed. An example of a user request might be, "I'm in a good mood today, so I'd like a brightly colored dress."

[0797] The device sends the input natural language request to the server in real time. The server then uses information processing technology, specifically Google's Natural Language API, to analyze the request. This analysis process extracts keywords from the request, clearly identifying the user's wishes and preferences. The server also uses sentiment analysis engines, such as OpenAI's GPT model, to analyze the user's emotional state. Based on these results, it generates a fashion design that matches the emotional state.

[0798] Next, the server retrieves the user's profile from the database. This profile includes the user's body type, past purchase history, preferences, and budget information. Based on this information, the server searches the product database and filters for suitable items. From this list of items, it generates optimal design proposals and sends them to the user's terminal.

[0799] Users review the proposed designs and send feedback, such as their satisfaction level and any desired modifications, via their devices. The server collects this feedback and uses it as training data for the generated AI model. This improves the accuracy of future fashion suggestions.

[0800] A concrete example of a prompt message would be: "Based on the user's request, 'Today is a special day, so I want to wear something flashy,' please suggest fashion items that suit their special emotional state."

[0801] Thus, the system of the present invention implements detailed processing to provide users with personalized fashion suggestions in real time.

[0802] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0803] Step 1:

[0804] Users input fashion-related requests in natural language using their devices. Specifically, they launch an application or web interface and input a request such as, "I'm in a good mood today, so I'd like a brightly colored dress." The input data is then sent directly from the device to the server.

[0805] Step 2:

[0806] The server parses the user's natural language request that it receives. The request, as input data, is parsed using Google's Natural Language API, and keywords are extracted. For example, words like "mood," "cheerful," and "dress" are extracted. These analysis results are used in the next step.

[0807] Step 3:

[0808] The server performs sentiment analysis. Based on previously analyzed keywords, it uses OpenAI's GPT model to analyze the user's emotional state. For example, if the information indicates that the user is "in a good mood," it determines that the user's emotional state is "positive." This information is then used in subsequent design generation.

[0809] Step 4:

[0810] The server retrieves the user's profile from the database. The profile includes body type, past purchase history, preferences, and budget information. This data is retrieved as input to the server and used in the next filtering step.

[0811] Step 5:

[0812] The server searches and filters the product database. It searches the product list considering the extracted keywords and user profile. For example, it filters items that match a condition such as "bright-colored dress" and outputs the appropriate items.

[0813] Step 6:

[0814] The server generates optimal design proposals from the filtered products. This process utilizes a generative AI model, customized to suit the user's emotional state. The generated design proposals are then sent to the user's device as visual information.

[0815] Step 7:

[0816] Users review the design proposal generated on their device and provide feedback. This feedback includes their satisfaction level and any desired changes, which then becomes input data for the next server.

[0817] Step 8:

[0818] The server analyzes user feedback and uses it to train the AI ​​model. Based on the feedback data, it generates new training data as prompts for the generated AI model. This process improves the accuracy of suggestions in subsequent attempts.

[0819] (Application Example 2)

[0820] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0821] Conventional fashion recommendation systems are limited to suggestions based on the user's basic preferences, body type, and past purchase history, and have the drawback of not being able to flexibly respond to specific situations and needs that change depending on the user's emotions. Therefore, there is a need to understand the user's real-time emotional state and reflect that information to provide more personalized fashion recommendations.

[0822] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0823] In this invention, the server includes means for analyzing the user's emotional state, means for filtering appropriate products based on the analyzed emotional information and user profile, and means for generating suggestions from the selected products based on the user's current emotional state. This enables personalized fashion suggestions that match the user's real-time emotions.

[0824] "A means of receiving fashion-related requests from users in natural language" refers to an interface that acquires text data directly entered by the user and registers it as information for analysis.

[0825] "A means of analyzing data using natural language processing technology to extract features related to user wishes and preferences" refers to the process of analyzing text data received from users using machine learning algorithms to extract specific keywords and phrases.

[0826] "Methods for analyzing a user's emotional state" refer to algorithms that detect emotions from a user's facial expressions, voice, and entered text, and classify that information into specific emotional categories.

[0827] "Means for filtering appropriate products based on analyzed emotional information and user profiles" refers to a process that selects appropriate products based on emotional data and the user's past behavioral data, and creates a product list that meets the user's needs.

[0828] "A means of generating suggestions based on the user's current emotional state from selected products" refers to a process of selecting items that best match the user's emotions from a filtered product list and then providing specific coordination and purchase suggestions.

[0829] "Means of receiving user feedback on proposals and learning to improve proposal accuracy" refers to a mechanism that collects evaluations and opinions from users, analyzes that information using a machine learning model, and improves the accuracy of future proposals.

[0830] This invention realizes a fashion recommendation system that incorporates sentiment analysis to improve the user experience. Users can input their fashion requests in natural language using their smartphone or other device. The device sends this natural language data to a server, which analyzes the received data using natural language processing technology. Machine learning frameworks such as TensorFlow and PyTorch are used for the analysis.

[0831] The server extracts keywords from the user's request while simultaneously analyzing the user's emotional state. Emotional analysis utilizes algorithms that analyze facial expressions and tone of voice from images and audio, often leveraging libraries such as OpenCV.

[0832] The server then filters out appropriate products based on the user's emotional information and profile data. Profile data includes past purchase history, body type, style preferences, and budget. From the products retrieved through the database search, suggestions are generated that match the user's emotional state.

[0833] The generated suggestions are visually displayed on the device, allowing the user to review them. Users can submit feedback on the suggestions, which is collected on the server and used to train the generating AI model. This continuously improves the accuracy of the suggestions.

[0834] For example, if a user enters into the application, "I'm in a good mood today, so I want some brightly colored clothes," the server will analyze the emotion as "joy" and suggest brightly colored clothing that fits the happy theme. It is also possible to create more specific suggestions by inputting prompts such as, "Analyze the user's facial expression and suggest casual wear that indicates a 'relaxed' state," into the AI ​​model.

[0835] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0836] Step 1:

[0837] The terminal receives fashion-related requests entered by the user in natural language. This input is sent to the server in text data format. The received text is prepared as data for the next parsing process.

[0838] Step 2:

[0839] The server analyzes the received text data using natural language processing techniques. The input is raw data, and the output extracts specific features related to the user's wishes and preferences. In this process, a generative AI model is used to extract keywords from the text and identify the user's intent.

[0840] Step 3:

[0841] The server analyzes the user's emotional state. Input is the user's facial expressions, voice, or text data, and the server identifies the user's emotions through an emotion analysis algorithm. Output is an emotion category such as "joy" or "sadness." This process involves video analysis using tools like OpenCV.

[0842] Step 4:

[0843] The server filters appropriate products based on analyzed sentiment data and a user profile database. The input is sentiment data and profile information, and the output is a filtered product list. Filtering includes algorithmic searching.

[0844] Step 5:

[0845] The server generates optimal suggestions from the selected products based on the user's current emotional state. The input is a filtered product list and emotional data, while the output is specific fashion suggestions. The suggestion generation utilizes a generative AI model to provide coordinated outfit suggestions.

[0846] Step 6:

[0847] Users who receive a suggestion send feedback from their device to the server. The input is the user's evaluation and suggestions for improvement, and the output is training data for future suggestions. The data obtained as feedback is reflected in the AI ​​model, contributing to the improvement of suggestion accuracy.

[0848] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0849] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0850] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0851] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0852] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0853] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0854] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0855] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0856] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0857] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0858] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0859] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0860] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0861] 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.

[0862] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0863] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0864] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0865] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0866] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0867] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0868] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0869] The following is further disclosed regarding the embodiments described above.

[0870] (Claim 1)

[0871] A means of receiving fashion-related requests from users in natural language,

[0872] A means for analyzing the aforementioned requests using natural language processing technology and extracting features related to the user's wishes and preferences,

[0873] A means of filtering appropriate products based on user profiles,

[0874] A means of generating proposals from selected products,

[0875] A means of providing the generated suggestions to the user,

[0876] A system that includes means for receiving user feedback and learning to improve the accuracy of suggestions.

[0877] (Claim 2)

[0878] The system according to claim 1, comprising means for obtaining user profile information from a database and analyzing the user's body type, past purchase history, preferred style, and budget.

[0879] (Claim 3)

[0880] The system according to claim 1, having means for linking with an e-commerce site to enable a user to purchase a suggested product.

[0881] "Example 1"

[0882] (Claim 1)

[0883] A means of receiving fashion-related requests from users in natural language via a communication terminal,

[0884] An information processing means using generative AI technology to analyze the aforementioned requests and extract features related to the user's wishes and preferences,

[0885] An information processing means that selects an appropriate product from a product information database by referring to the user profile,

[0886] A means of generating suggestions tailored to the user from selected products and providing them as prompt messages,

[0887] A means of providing the generated proposal to the user via the communication terminal,

[0888] A learning means for receiving feedback on suggestions from users and improving the accuracy of suggestions through learning using the aforementioned generation AI technology,

[0889] To assist users in purchasing suggested products, a means of linking information with the e-commerce system,

[0890] A system that includes this.

[0891] (Claim 2)

[0892] The system according to claim 1, comprising information processing means for obtaining user profile information from an information database and analyzing the user's physical characteristics, past purchase history, preferred style, and budget.

[0893] (Claim 3)

[0894] The system according to claim 1, comprising information processing means that performs a learning process to make more accurate suggestions by using generative AI technology tailored to the individual preferences of users, based on feedback from users on their suggestions.

[0895] "Application Example 1"

[0896] (Claim 1)

[0897] A means of receiving fashion-related requests from users in natural language,

[0898] A means for analyzing the aforementioned requests using natural language processing technology and extracting features related to the user's wishes and preferences,

[0899] A means of filtering appropriate products based on user profiles,

[0900] A means of generating proposals from selected products,

[0901] A means of providing the generated suggestions to the user,

[0902] A means of receiving user feedback and learning to improve the accuracy of suggestions,

[0903] A means to enable users to purchase suggested products in conjunction with an e-commerce platform,

[0904] A means for users to input information using a smart device, confirm suggested styles, and smoothly complete the purchase process.

[0905] A system that includes means to improve personalized fashion recommendations by referring to purchase history and past profile data.

[0906] (Claim 2)

[0907] The system according to claim 1, comprising means for obtaining user profile information from information storage and analyzing the user's body type, past purchase history, preferred style, and spending amount.

[0908] (Claim 3)

[0909] The system according to claim 1, having means for linking with an e-commerce platform to enable a user to purchase a proposed product.

[0910] "Example 2 of combining an emotion engine"

[0911] (Claim 1)

[0912] A means for receiving requests regarding clothing from users in natural language,

[0913] A means for analyzing the aforementioned requests using information processing technology and extracting characteristics related to the user's wishes and preferences,

[0914] A means for analyzing emotional states based on extracted features and generating designs based on those emotional states,

[0915] A means for filtering appropriate items based on user record information,

[0916] A means of generating design proposals from selected items,

[0917] A means of providing the generated design proposal to the user,

[0918] A system that includes means for receiving feedback from users and learning to improve design accuracy.

[0919] (Claim 2)

[0920] The system according to claim 1, comprising means for obtaining user record information from a storage device and analyzing the user's body type, past purchase history, preferences, and budget.

[0921] (Claim 3)

[0922] The system according to claim 1, having means for linking with a virtual marketplace to enable a user to purchase an item presented to them.

[0923] "Application example 2 when combining with an emotional engine"

[0924] (Claim 1)

[0925] A means of receiving fashion-related requests from users in natural language,

[0926] A means for analyzing the aforementioned requests using natural language processing technology and extracting features related to the user's wishes and preferences,

[0927] A means of analyzing the user's emotional state,

[0928] A means of filtering appropriate products based on analyzed sentiment information and user profiles,

[0929] A means for generating suggestions from selected products based on the user's current emotional state,

[0930] A system that includes means for receiving user feedback on suggestions and learning to improve the accuracy of those suggestions.

[0931] (Claim 2)

[0932] The system according to claim 1, comprising means for obtaining user profile information from a database and analyzing the user's body type, past purchase history, preferred style, and budget.

[0933] (Claim 3)

[0934] The system according to claim 1, having means for linking with an e-commerce system to enable a user to purchase a suggested product. [Explanation of symbols]

[0935] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of receiving fashion-related requests from users in natural language, A means for analyzing the aforementioned requests using natural language processing technology and extracting features related to the user's wishes and preferences, A means of filtering appropriate products based on user profiles, A means of generating proposals from selected products, A means of providing the generated suggestions to the user, A means of receiving user feedback and learning to improve the accuracy of suggestions, A means to enable users to purchase suggested products in conjunction with an e-commerce platform, A means for users to input information using a smart device, confirm suggested styles, and smoothly complete the purchase process. A system that includes means to improve personalized fashion recommendations by referring to purchase history and past profile data.

2. The system according to claim 1, comprising means for obtaining user profile information from information storage and analyzing the user's body type, past purchase history, preferred style, and spending amount.

3. The system according to claim 1, having means for linking with an e-commerce platform to enable a user to purchase a proposed product.

Images