system

Abstract

We provide the system. [Solution] A means for receiving user text information and analyzing it using natural language processing, A means for receiving user image information and analyzing it using image recognition technology, A method for selecting the optimal product from a wide product database based on analysis results using a generative AI model, A means of collecting reliable evaluation data and providing users with visual information, A means of receiving user feedback and improving the accuracy of the system's suggestions, A method for suggesting the most suitable product based on product images taken by the user in-store and their entered preferences, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern lifestyles, consumers spend a lot of time and effort choosing clothing that suits their preferences from a variety of fashion options. In such a situation, there is a need for consumers to efficiently find their preferred style within limited time and make purchases without stress. However, it is difficult for existing systems to deeply understand and appropriately propose the fashion preferences of individual users. Therefore, an object of the present invention is to automatically learn the individual fashion preferences of users, propose appropriate clothing selections, reduce the time and effort of users, and provide a better purchasing experience.

Means for Solving the Problems

[0005] This invention solves this problem by providing means for analyzing text data entered by a user using natural language processing, and means for receiving image data from a user and analyzing it using image recognition technology. Furthermore, it addresses the diverse needs of users by including means for selecting the optimal fashion item from a global clothing database based on the analysis results using a generative AI model, and means for collecting reliable review data and providing information to the user visually. In addition, by providing means for receiving feedback from users and improving the accuracy of the system's suggestions based on that data, continuous improvement and individualized responses are possible. As a result, users can make satisfactory purchasing choices in a short amount of time.

[0006] A "user" refers to an individual who uses this system to receive fashion item suggestions.

[0007] "Text data" refers to character information entered by the user, including information about their fashion preferences and style.

[0008] "Natural language processing" refers to the technology that enables computers to understand and analyze human language, and the process of extracting meaning and intent from text data.

[0009] "Image data" refers to visual information uploaded by users, including information about fashion items and styles.

[0010] "Image recognition technology" refers to the technology that allows computers to analyze images and identify the objects and features they contain.

[0011] A "generative AI model" refers to artificial intelligence technology that learns a user's preferences and generates or suggests appropriate fashion items based on those preferences.

[0012] A "clothing database" is a collection of data that aggregates information about fashion items from around the world.

[0013] "Review data" refers to information based on the opinions and ratings of purchasers, and is used to help other users make purchasing decisions.

[0014] "Feedback" refers to the evaluations and opinions that users provide regarding system proposals, and is used to improve the accuracy of those proposals. [Brief explanation of the drawing]

[0015] [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] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Embodiments for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] 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), etc.

[0019] 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.

[0020] 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.

[0021] 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).

[0022] 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."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] The system of this invention consists of three main components: a user, a terminal, and a server, and is designed to improve the user's purchasing experience through personalized fashion suggestions.

[0037] The user inputs text and image data through their device. The text data includes keywords related to the user's fashion preferences and style, while the image data includes visuals of fashion examples and items they would like to use as reference.

[0038] The device sends this information to the server. The server uses natural language processing technology to analyze the text data and identify the user's preferences. It also uses image recognition technology to analyze image data and extract information about fashion items and styles.

[0039] The server then utilizes a generative AI model to select fashion items that match the user's preferences. This model searches a global clothing database and picks out items that suit the user's tastes.

[0040] The selected items are accompanied by reliable review data, allowing users to obtain helpful information when purchasing products. The device visually displays these suggested items and their reviews through the user interface. Users can review the suggestions and proceed with the purchase if they wish to continue their interest.

[0041] Furthermore, users can provide feedback on the suggestions. This feedback is sent to the server and used as data to improve the generated AI model. For example, if a user specifies a preferred style and the system suggests a shirt that perfectly matches it, the user can provide feedback on the shirt's fit and style suitability.

[0042] This allows the system to continuously learn user preferences and incorporate them into future recommendations, resulting in a more comfortable and personalized shopping experience.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] Users input text and image data using their device. The text data includes keywords related to their fashion preferences and style, while the image data includes uploaded images of fashion items they use as reference.

[0046] Step 2:

[0047] The terminal sends text and image data received from the user to the server. Appropriate communication protocols are used to ensure security.

[0048] Step 3:

[0049] The server analyzes the received text data using natural language processing (NLP) techniques. This analysis identifies the user's fashion preferences from the entered keywords.

[0050] Step 4:

[0051] The server simultaneously analyzes the received image data using image recognition technology to extract fashion item and style information. This allows for the recognition of specific features and items contained in the image.

[0052] Step 5:

[0053] The server utilizes a generative AI model to select appropriate fashion items based on the analysis results. This AI model searches a global clothing database to find items that match the user's preferences.

[0054] Step 6:

[0055] The server collects and organizes reliable review data related to selected fashion items. This allows users to obtain information that helps them make purchasing decisions.

[0056] Step 7:

[0057] The device visually displays fashion item suggestions and review data received from the server on the user interface. Users can review this information and view details about products that interest them.

[0058] Step 8:

[0059] Users can select and purchase their favorite suggested items. Furthermore, they can send feedback on the suggested items to the server via their device.

[0060] Step 9:

[0061] The server incorporates the user feedback it receives into the system and uses it as data to improve the generated AI model. This improves the accuracy of future suggestions.

[0062] (Example 1)

[0063] 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."

[0064] In today's market, many consumers find it difficult to find clothing and accessories that suit their fashion sense and style. They want easy access to personalized fashion suggestions and reliable review information to help them make purchasing decisions. Existing systems are not always sufficient to accurately reflect individual user preferences and provide highly accurate suggestions, so this needs to be addressed.

[0065] 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.

[0066] In this invention, the server includes means for receiving text data via a user-operable terminal and analyzing it using natural language processing, means for receiving image data provided by the user and analyzing it using image recognition technology, and means for selecting appropriate fashion items from a broad collection of clothing data based on the analysis results using a generative AI model. This makes it possible to suggest fashion items that suit the user's preferences.

[0067] A "user-operable terminal" is a device that users can directly operate to input their fashion preferences and style information.

[0068] "Natural language processing" is a technology that allows computers to understand and analyze human language, and is used to extract meaning from users' text data.

[0069] "Image recognition technology" is a technology that uses computer vision algorithms to recognize objects and shapes from image data and extract information from them.

[0070] A "generative AI model" is a pre-trained artificial intelligence model used to select appropriate fashion items based on the user's preferences.

[0071] "Reliable evaluation data" refers to trustworthy information about a product provided by a third party, which users can use as a reference when making purchasing decisions.

[0072] A "broad clothing data set" is a diverse and extensive collection of clothing information used to search for necessary information from fashion items around the world.

[0073] A "user interface" is an interface that provides a means for users to interact with a system and visually displays suggested items and evaluations.

[0074] A "prompt statement" is a sentence that gives instructions to a generative AI model to select appropriate fashion items.

[0075] The system of this invention includes three main components: a user, a terminal, and a server. The user provides information about their fashion preferences and style through an operable terminal. Specifically, the user inputs text data and uploads image data of fashion items that suit their preferences.

[0076] The terminal transmits the data entered by the user to the server via a secure communication protocol. The server performs natural language processing (NLP) on the received text data to identify the user's preferences. Open-source NLP libraries such as spaCy and NLTK can be used for natural language processing. In addition, image recognition technology is applied to the image data, and analysis is performed using tools such as TENSORFLOW® or PyTorch to extract fashion items and style information.

[0077] Based on these analysis results, the server utilizes a generative AI model to select fashion items suitable for the user from a vast collection of clothing data from around the world. This generative AI model can make optimal suggestions by receiving prompts. For example, a prompt such as "Please suggest casual and simple shirts. Reference images are attached." might be used.

[0078] Furthermore, the server collects reliable evaluation data for the selected items and presents it visually to the user through the user interface. In this way, the user can review the suggested items and refer to the reviews. The user can also input and send feedback to the server, which contributes to improving future suggestions.

[0079] This system allows users to receive suggestions for fashion items that are perfectly suited to their preferences, thereby improving their shopping experience.

[0080] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0081] Step 1:

[0082] The user uses their device to input text data about their fashion preferences and style, along with image data of fashion items they would like to use as reference. Specifically, they type text on the user interface and click the "Select Image" button to upload the image. The entered data is temporarily stored on the device for the next step.

[0083] Step 2:

[0084] The terminal sends text and image data received from the user to the server. Specifically, when the send button is pressed, this data is securely transferred to the server using the HTTPS protocol. The output is the user's text and image data received on the server side.

[0085] Step 3:

[0086] The server analyzes the received text data using natural language processing (NLP) techniques. It analyzes the input text data and extracts keywords related to the user's fashion preferences and style. Specifically, it uses an NLP library to tokenize the text and identify important keywords. The output of this step is the extracted style and preference information.

[0087] Step 4:

[0088] The server performs image recognition analysis on the image data. The received image data is input into a model to identify information about fashion items and styles. Specifically, it analyzes the images using a deep learning model such as TensorFlow. The output of this step is the identified item information.

[0089] Step 5:

[0090] Based on the analysis results obtained in steps 3 and 4, the server uses a generative AI model to select fashion items that suit the user's preferences. The prompt text is input to the AI ​​model, which generates the optimal fashion items from a broad collection of clothing data. The output is a list of selected fashion items.

[0091] Step 6:

[0092] The server attaches reliable evaluation data to the selected items. It retrieves reviews from external review APIs and databases and associates them with the items. The output is a list of fashion items with attached review information.

[0093] Step 7:

[0094] The terminal visualizes suggested items and review information received from the server through a user interface. Specifically, it displays suggested items in card format and visually presents evaluation information. The output is the suggested items displayed in a format viewable by the user.

[0095] Step 8:

[0096] Users input their opinions and feedback on suggested items via their device and send them to the server. The server saves this as improvement data for the generating AI model and incorporates it into the next suggestion process. Specifically, the user enters a comment in the feedback field and presses the submit button. The output of this step is the feedback data saved by the server.

[0097] (Application Example 1)

[0098] 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."

[0099] Modern consumers are surrounded by a wealth of information, making it difficult to find products that suit their preferences from numerous options, especially when shopping in physical stores. Furthermore, there is a need for a system that effectively connects online review information to in-store purchases. Solving these challenges and providing a better shopping experience is essential.

[0100] 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.

[0101] In this invention, the server includes means for receiving user text information and analyzing it using natural language processing, means for receiving user image information and analyzing it using image recognition technology, and means for suggesting the most suitable products based on product images taken by the user in stores and their entered preferences. This enables consumers to efficiently find products that match their style when making purchases in physical stores and to receive suggestions based on reliable evaluation data.

[0102] "User text information" refers to the textual information entered by the user, and is natural language data that reflects the preferences and requests of individual consumers.

[0103] Natural language processing is a technology that enables computer systems to understand and analyze human language, and is a means of efficiently processing text information.

[0104] "User image information" refers to visual data captured or selected by the user on their device, and is information used to demonstrate the visual characteristics of a product.

[0105] "Image recognition technology" is a technique for analyzing image data to identify objects or features, and is a means of recognizing and analyzing specific patterns based on visual information.

[0106] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to generate the optimal result from input data.

[0107] "Reliable evaluation data" refers to data compiled from past users' reviews of a product, and is used as reference information when making a purchase.

[0108] "Product images taken by users in stores" refer to visual data captured by consumers directly photographing products located in stores, and serve as a factor in the actual shopping process.

[0109] "Methods for proposing the optimal product" refers to technologies and methods that identify and present the most suitable product from a large selection based on the user's preferences and requirements.

[0110] This invention is a system that enables consumers to more efficiently select products that suit their preferences in physical stores. The system mainly consists of a server and terminals, and consumers input product information in the store using the terminals. Specifically, they take pictures of products using the terminal's camera and express their product preferences through text input. This data is sent to the server, which analyzes the text information using natural language processing technology and analyzes the product images using image recognition technology.

[0111] Based on these analysis results, the server uses a generative AI model to search the database for relevant products. The server finds products that match the analysis data from a broad database and suggests them to consumers along with reliable evaluation data. This process is computationally intensive, so the server requires high-performance computing capabilities (for example, processing using TensorFlow or OpenCV).

[0112] For example, a consumer looking for a red casual dress in a store might take a picture of a red dress in the store and type "casual" and "red" into the server, which will then suggest other items. The user can also view reviews of the suggested items. Examples of such prompts include "casual dress," "red," and "suggest similar styles." The AI ​​model generates suggestions that respond to the user's request based on these prompts.

[0113] The introduction of this system will allow consumers to have a new shopping experience in physical stores. It is expected that product selection will become more personalized and efficient, improving the quality of purchasing decisions.

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

[0115] Step 1:

[0116] The user takes a picture of the product using their device and enters their preferred style and color in text. The device then sends this image information and text data to the server. The input data includes text describing the user's preferred features and the image of the product they photographed.

[0117] Step 2:

[0118] The server performs natural language processing on the received text data. The input here is text information indicating user preferences. The server analyzes the text using its built-in natural language processing library (e.g., SpaCy) and generates output that identifies the user's preferences.

[0119] Step 3:

[0120] The server analyzes the received image data using image recognition technology. The input is visual information of the product provided by the user, which is then analyzed using image processing libraries such as TensorFlow and OpenCV. As output, features such as style and shape are extracted from the product image.

[0121] Step 4:

[0122] The server uses a generative AI model to select appropriate products based on the analyzed text and image information. The generative AI model compares the features extracted from each source with the features of products in the database to extract the product that best matches the user's preferences. The input is the analysis results described above, and the output is a list of suggested products.

[0123] Step 5:

[0124] The server adds reliable evaluation data to the data of the proposed product and sends it to the terminal. The server retrieves the evaluation data from the database and provides it to the user along with the proposed product. In this process, the input is the proposed product, and the output is the proposed product with evaluation information.

[0125] Step 6:

[0126] Users review suggested products and their ratings through the terminal's user interface. Based on this information, users select products and provide feedback. This user input constitutes feedback, which becomes output data for future use.

[0127] Step 7:

[0128] User feedback is sent to the server and used to improve the generative AI model. The server uses the feedback data to retrain the generative AI model and improve the accuracy of future suggestions. In this step, the input is the feedback, and the output is the improved generative AI model.

[0129] 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.

[0130] This invention is an information system for efficiently understanding a user's fashion preferences and enabling personalized suggestions, and incorporates an emotion engine that recognizes the user's emotional state.

[0131] Users first use their device to write text data about their fashion preferences and style, and upload reference fashion images. This information is then transmitted from the device to the server using a secure protocol.

[0132] The server analyzes the received text data using natural language processing technology to extract features related to fashion preferences. Simultaneously, it analyzes image data using image recognition technology to extract features related to style and items.

[0133] Furthermore, this invention uses an emotion engine to recognize the user's emotional state based on these analysis results. This emotion recognition is performed by comparing information obtained from the user's input data with an emotion pattern database.

[0134] Next, the generative AI model considers the user's preferences and emotional state to select the most suitable fashion items from a global clothing database. The selected items are then organized into personalized suggestions tailored to the user's current mood.

[0135] The server also collects and provides reliable review data for selected fashion items to the user. The terminal visually displays these fashion item suggestions and reviews on the user interface. Based on this information, the user can examine items that interest them in more detail.

[0136] Furthermore, users can send feedback to the server via their device regarding the presented items and the overall system's suggestions. This feedback is stored in a database by the server and used as training data to improve the accuracy of the system's suggestions.

[0137] For example, if a user requests a "casual style that matches a cheerful mood," the emotion engine recognizes positive emotions from the user's text and image data, and the generative AI model suggests casual fashion items with bright colors and designs that align with those emotions. Based on these suggestions, the user can proceed with a purchase and also contribute to improving the system's accuracy by providing feedback on whether the suggestions were appropriate.

[0138] The following describes the processing flow.

[0139] Step 1:

[0140] Users input text data reflecting their fashion preferences via their device and upload related fashion image data. This allows for a concrete expression of the user's style orientation and desired designs.

[0141] Step 2:

[0142] The device transmits the collected text and image data to the server via a secure communication protocol, thereby ensuring data security.

[0143] Step 3:

[0144] The server applies natural language processing (NLP) to the received text data to analyze important keywords and phrases related to the user's preferences. Based on this, it identifies the user's fashion preferences.

[0145] Step 4:

[0146] The server simultaneously analyzes the received image data using image recognition technology to extract features of fashion items and styles from the images. This provides information that complements the text data.

[0147] Step 5:

[0148] The server utilizes an emotion engine based on the analyzed text and image data to recognize the user's emotional state. For example, it determines whether the input words or images indicate emotions such as "happy" or "positive."

[0149] Step 6:

[0150] The server uses a generative AI model to select appropriate fashion items from a global clothing database, taking into account the user's fashion preferences and emotional state. This process suggests items with colors and designs that match the user's mood.

[0151] Step 7:

[0152] The server collects review data associated with selected fashion items and selects the most reliable information from it. It then prepares visual materials to convey the product's appeal to the user.

[0153] Step 8:

[0154] The device displays fashion item suggestions and review information sent from the server in its user interface. Users can review this list of suggestions and view details of items that interest them.

[0155] Step 9:

[0156] Users can select from the suggested fashion items and proceed with the purchase process. Users can also provide feedback on the suggestions, and this data is sent from the device to the server.

[0157] Step 10:

[0158] The server receives user feedback and stores it in a database. This feedback is used as valuable data to further train the generative AI model and improve the accuracy of the system's suggestions.

[0159] (Example 2)

[0160] 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".

[0161] Modern consumers want to make quick choices that match their fashion preferences, but the sheer volume of information available makes decision-making difficult. They also desire more personalized suggestions tailored to their emotional state. As a result, there is a need for a system that accurately meets consumer needs.

[0162] 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.

[0163] In this invention, the server includes means for receiving user text information and analyzing it using language analysis technology, means for receiving user image information and analyzing it using image analysis technology, and emotion analysis means for recognizing the user's emotional state based on the analyzed information. This makes it possible to select personalized fashion items according to the user's individual preferences and emotional state.

[0164] "User text information" refers to the textual information about the user's preferences and style that they input.

[0165] "Language analysis technology" refers to the technology of analyzing natural language to extract specific information or keywords.

[0166] "User image information" refers to visual information related to fashion that users upload.

[0167] "Image analysis technology" refers to the technology of identifying specific features or items from image data.

[0168] "Emotional analysis methods" refer to technologies used to infer a user's emotional state based on analyzed information.

[0169] A "generative AI model" is an artificial intelligence model that generates optimal suggestions based on analysis results and emotional states.

[0170] "Reliable evaluation data" refers to data that shows the quality and user ratings of the fashion items offered.

[0171] A "user interface" refers to the on-screen means of operation that users use to visually obtain information or input data.

[0172] The "information recording unit" refers to a database or storage system used to store user feedback and other data.

[0173] This invention is an information system that suggests personalized fashion items based on the user's fashion preferences and emotional state.

[0174] User:

[0175] Users use their devices to input text information about their fashion preferences and style, and upload reference fashion images. This data is transmitted to the server via a secure protocol.

[0176] server:

[0177] The server analyzes the received text information using language analysis techniques. In this process, it employs a general natural language processing model to extract fashion-related keywords and themes from the user's text. For example, terms like "casual" and "formal" may be identified. Simultaneously, the server analyzes the received image information using image analysis techniques to identify the style, color, and design patterns of clothing within the image. For example, specific items such as blue jeans or white sneakers may be identified.

[0178] Emotion analysis:

[0179] The server uses sentiment analysis tools to recognize the user's emotional state based on the analyzed information. This recognition is performed by comparing it with different emotional patterns. For example, if there are text and image features that suggest the user is feeling "happy," it will be judged as a positive emotional state.

[0180] Generative AI models:

[0181] The generative AI model selects the most suitable fashion items from clothing information worldwide based on the user's preferences and emotional state. This selection process involves providing the AI ​​model with appropriate instructions using prompts. An example prompt might be: "The user is expressing a happy mood and desires a casual style. Please suggest fashion items that match this."

[0182] Proposals and evaluations:

[0183] Selected fashion items are presented visually through the user interface, along with reliable evaluation data. Users can then use this information to view details and explore items that interest them further. Users can also provide feedback, which is stored in the server's data storage unit and used to update the next generation AI model. This improves the system's recommendation accuracy, enabling more personalized fashion suggestions for users.

[0184] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0185] Step 1:

[0186] Users input text information about their fashion preferences and style using their device, and upload reference fashion images. The entered text and images are transmitted from the device to the server using a secure protocol. This collects initial data about the user's fashion.

[0187] Step 2:

[0188] The server analyzes the received text information using language analysis technology. From the text data received as input, it extracts fashion-related keywords and styles using a natural language processing model and outputs them as analysis results. Specifically, it identifies styles such as "casual" and "business."

[0189] Step 3:

[0190] The server processes the received image information using image analysis technology. Based on the input image data, it uses an image recognition algorithm to identify the style and color of fashion items and outputs this information. Specifically, items such as red sweaters and denim pants are identified.

[0191] Step 4:

[0192] The server recognizes the user's emotional state based on the analysis results of text and images. Using the analyzed data as input, it compares it with an emotional pattern database using an emotional analysis tool and outputs the user's emotional state. Specifically, it identifies that the user's expression is "enjoyment."

[0193] Step 5:

[0194] The generative AI model selects the most suitable fashion items from clothing information based on analyzed fashion preferences and emotional states, referencing prompt sentences. Using the provided dataset as input, the AI ​​model outputs the items it has selected. An example prompt sentence is "Please suggest a bright, casual outfit that matches a happy mood."

[0195] Step 6:

[0196] The server collects selected fashion items and their associated reliable evaluation data, and provides this information to the terminal's user interface. The output information is displayed visually and presented to the user as options. Specifically, a list of suggested items is displayed on the screen.

[0197] Step 7:

[0198] Users provide feedback on suggested items and send it to the server via their device. User ratings and opinions are collected as input and stored as output data to improve the system's suggestion accuracy. Specifically, satisfaction levels with selected items are recorded.

[0199] (Application Example 2)

[0200] 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".

[0201] Conventional fashion recommendation systems have a problem in that they do not easily provide personalized recommendations that take into account the user's emotional state. Furthermore, they lack support for selecting products based on the user's emotional state and for efficiently using points to make purchases. Therefore, there is a need to provide optimal fashion product recommendations that respond to the user's emotions, along with intuitive purchasing support methods.

[0202] 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.

[0203] In this invention, the server includes means for receiving user text data and analyzing it using natural language processing, means for receiving user image information and analyzing it using image analysis technology, means for selecting the optimal fashion product from a global clothing information database based on the analysis results using a generative AI model, means for collecting reliable evaluation data and providing information to the user visually, means for recognizing the user's emotional state and making suggestions based on that state, means for receiving user feedback and improving the accuracy of the system's suggestions, and means for considering the user's emotional state and presenting the information necessary to purchase fashion products using points. This enables effective fashion suggestions tailored to the user's emotions and smooth purchases utilizing points.

[0204] "User text data" refers to textual information provided by users regarding their fashion preferences and style.

[0205] "Natural language processing" is a technology that allows computers to understand and analyze human language, and is used for analyzing text data.

[0206] "User image information" refers to visual data, such as fashion images, that users provide to the system.

[0207] "Image analysis technology" is a technique that uses computer vision technology to extract specific features and information from image data.

[0208] A "generative AI model" is an artificial intelligence technology that suggests items based on training data, taking into account the user's preferences and emotions.

[0209] A "clothing information database" is a source of information that accumulates data on fashion products and items from around the world.

[0210] "Rating data" refers to review information from other users that indicates the reliability of a product or service.

[0211] "User emotional state" refers to the user's psychological and emotional state, and is information that the system recognizes using its emotion engine.

[0212] "Opinions" refer to feedback that users provide about their feelings and thoughts regarding the items or services that have been suggested.

[0213] "Points" refer to virtual currency or reward systems that can be used within electronic payment services.

[0214] A specific embodiment for carrying out this invention will now be described. First, the user inputs text data and image information related to their fashion preferences and style into a terminal. This input data is transmitted to a server using a secure communication method.

[0215] The server applies natural language processing techniques to the received text data to extract information related to the user's fashion preferences. Similarly, for image information, image analysis techniques are used to extract characteristics of specific styles and fashion items. In this process, specific software such as Google® Cloud Natural Language API is used.

[0216] Furthermore, the server uses an emotion engine to recognize the user's emotional state. This emotion recognition is performed by comparing information obtained from text and image data with a pre-stored emotion pattern database.

[0217] Based on the user's emotional state and preferences, the server uses a generative AI model to select relevant fashion products from a global clothing information database. This generative AI model visually presents targeted item suggestions to the end user. Reliable evaluation data is also attached to the selected products for user reference.

[0218] Users can view suggested items on their device's user interface and purchase items they are interested in using points. For example, if a user is looking for "clothes to relax in after work," the emotion engine will detect their fatigue level and suggest items in a relaxed style that suits them. An example of a prompt message might be, "Based on the user's current emotions, please identify the most suitable relaxation fashion items."

[0219] This process makes it easier for users to acquire fashion items that best suit their emotional state, while also enabling the efficient use of points.

[0220] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0221] Step 1:

[0222] The user inputs text data and image information about their fashion preferences and style on their device. This input data is used to provide the server with the user's preferences and visual style.

[0223] Step 2:

[0224] The terminal sends the input text data and image information to the server using a secure protocol. In this process, the input is text data and image information, and the output is the secure transmission of data to the server.

[0225] Step 3:

[0226] The server analyzes the received text data using natural language processing techniques (e.g., Google Cloud Natural Language API). This extracts features related to the user's fashion preferences. The input is text data, and the output is the extracted preference features.

[0227] Step 4:

[0228] The server analyzes image information using image analysis technology. Here, features of specific fashion items or styles are extracted. The input is image information, and the output is style features.

[0229] Step 5:

[0230] The server uses an emotion engine to recognize the user's emotional state based on information obtained from text and images. The input consists of extracted features and a pre-defined database, and the output is the recognized emotional state.

[0231] Step 6:

[0232] The server uses a generative AI model to select the most suitable fashion products from a clothing information database, taking into account the user's preferences and emotional state. The input is the user's preferred characteristics and emotional state, and the output is the selected fashion item.

[0233] Step 7:

[0234] The server adds reliable evaluation data to the selected products, visualizes it, and outputs it to the terminal. The input is the selected fashion items, and the output is visualized information with evaluation data.

[0235] Step 8:

[0236] The terminal visually displays fashion items selected by the user, and the user can consider purchasing them using points. Input is visualized information with evaluation data, and output is the user's purchase intention.

[0237] 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.

[0238] 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.

[0239] 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.

[0240] [Second Embodiment]

[0241] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0242] 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.

[0243] 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).

[0244] 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.

[0245] 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.

[0246] 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).

[0247] 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.

[0248] 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.

[0249] 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.

[0250] 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.

[0251] 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.

[0252] 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".

[0253] The system of this invention consists of three main components: a user, a terminal, and a server, and is designed to improve the user's purchasing experience through personalized fashion suggestions.

[0254] The user inputs text and image data through their device. The text data includes keywords related to the user's fashion preferences and style, while the image data includes visuals of fashion examples and items they would like to use as reference.

[0255] The device sends this information to the server. The server uses natural language processing technology to analyze the text data and identify the user's preferences. It also uses image recognition technology to analyze image data and extract information about fashion items and styles.

[0256] The server then utilizes a generative AI model to select fashion items that match the user's preferences. This model searches a global clothing database and picks out items that suit the user's tastes.

[0257] The selected items are accompanied by reliable review data, allowing users to obtain helpful information when purchasing products. The device visually displays these suggested items and their reviews through the user interface. Users can review the suggestions and proceed with the purchase if they wish to continue their interest.

[0258] Furthermore, users can provide feedback on the suggestions. This feedback is sent to the server and used as data to improve the generated AI model. For example, if a user specifies a preferred style and the system suggests a shirt that perfectly matches it, the user can provide feedback on the shirt's fit and style suitability.

[0259] This allows the system to continuously learn user preferences and incorporate them into future recommendations, resulting in a more comfortable and personalized shopping experience.

[0260] The following describes the processing flow.

[0261] Step 1:

[0262] Users input text and image data using their device. The text data includes keywords related to their fashion preferences and style, while the image data includes uploaded images of fashion items they use as reference.

[0263] Step 2:

[0264] The terminal sends text and image data received from the user to the server. Appropriate communication protocols are used to ensure security.

[0265] Step 3:

[0266] The server analyzes the received text data using natural language processing (NLP) techniques. This analysis identifies the user's fashion preferences from the entered keywords.

[0267] Step 4:

[0268] The server simultaneously analyzes the received image data using image recognition technology to extract fashion item and style information. This allows for the recognition of specific features and items contained in the image.

[0269] Step 5:

[0270] The server utilizes a generative AI model to select appropriate fashion items based on the analysis results. This AI model searches a global clothing database to find items that match the user's preferences.

[0271] Step 6:

[0272] The server collects and organizes reliable review data related to selected fashion items. This allows users to obtain information that helps them make purchasing decisions.

[0273] Step 7:

[0274] The device visually displays fashion item suggestions and review data received from the server on the user interface. Users can review this information and view details about products that interest them.

[0275] Step 8:

[0276] Users can select and purchase their favorite suggested items. Furthermore, they can send feedback on the suggested items to the server via their device.

[0277] Step 9:

[0278] The server incorporates the user feedback it receives into the system and uses it as data to improve the generated AI model. This improves the accuracy of future suggestions.

[0279] (Example 1)

[0280] 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".

[0281] In today's market, many consumers find it difficult to find clothing and accessories that suit their fashion sense and style. They want easy access to personalized fashion suggestions and reliable review information to help them make purchasing decisions. Existing systems are not always sufficient to accurately reflect individual user preferences and provide highly accurate suggestions, so this needs to be addressed.

[0282] 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.

[0283] In this invention, the server includes means for receiving text data via a user-operable terminal and analyzing it using natural language processing, means for receiving image data provided by the user and analyzing it using image recognition technology, and means for selecting appropriate fashion items from a broad collection of clothing data based on the analysis results using a generative AI model. This makes it possible to suggest fashion items that suit the user's preferences.

[0284] The "user-operable terminal" is a device for the user to directly operate and input their fashion preferences and style information.

[0285] "Natural language processing" is a technology in which a computer understands and analyzes human language, and is used to extract meaning from the user's text data.

[0286] "Image recognition technology" is a technology that uses computer vision algorithms to recognize objects and shapes from image data and extract information.

[0287] The "generative AI model" is a pre-trained artificial intelligence model used to select appropriate fashion items based on the user's preferences.

[0288] "Reliable evaluation data" is highly reliable information about products provided by a third party for the user to refer to when making a purchase decision.

[0289] The "extensive clothing data set" is a collection of diverse and rich clothing information used to search for necessary information from fashion items around the world.

[0290] The "user interface" is an interface that provides a means for the user to interact with the system and visually displays the proposed items and evaluations.

[0291] The "prompt sentence" is a sentence that gives an instruction to the generative AI model to select appropriate fashion items.

[0292] The system of this invention includes three main components: a user, a terminal, and a server. The user provides information about their fashion preferences and style through an operable terminal. Specifically, the user inputs text data and uploads image data of fashion items that suit their preferences.

[0293] The terminal sends the data entered by the user to the server via a secure communication protocol. The server performs natural language processing (NLP) on the received text data to identify the user's preferences. Open-source NLP libraries such as spaCy and NLTK can be used for natural language processing. In addition, image recognition technology is applied to the image data, and analysis is performed using TensorFlow or PyTorch to extract fashion items and style information.

[0294] Based on these analysis results, the server utilizes a generative AI model to select fashion items suitable for the user from a vast collection of clothing data from around the world. This generative AI model can make optimal suggestions by receiving prompts. For example, a prompt such as "Please suggest casual and simple shirts. Reference images are attached." might be used.

[0295] Furthermore, the server collects reliable evaluation data for the selected items and presents it visually to the user through the user interface. In this way, the user can review the suggested items and refer to the reviews. The user can also input and send feedback to the server, which contributes to improving future suggestions.

[0296] This system allows users to receive suggestions for fashion items that are perfectly suited to their preferences, thereby improving their shopping experience.

[0297] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0298] Step 1:

[0299] The user uses their device to input text data about their fashion preferences and style, along with image data of fashion items they would like to use as reference. Specifically, they type text on the user interface and click the "Select Image" button to upload the image. The entered data is temporarily stored on the device for the next step.

[0300] Step 2:

[0301] The terminal sends text and image data received from the user to the server. Specifically, when the send button is pressed, this data is securely transferred to the server using the HTTPS protocol. The output is the user's text and image data received on the server side.

[0302] Step 3:

[0303] The server analyzes the received text data using natural language processing (NLP) techniques. It analyzes the input text data and extracts keywords related to the user's fashion preferences and style. Specifically, it uses an NLP library to tokenize the text and identify important keywords. The output of this step is the extracted style and preference information.

[0304] Step 4:

[0305] The server performs image recognition analysis on the image data. The received image data is input into a model to identify information about fashion items and styles. Specifically, it analyzes the images using a deep learning model such as TensorFlow. The output of this step is the identified item information.

[0306] Step 5:

[0307] Based on the analysis results obtained in steps 3 and 4, the server utilizes the generative AI model to select fashion items suitable for the user's preferences. The server inputs the prompt sentence into the AI model to generate the optimal fashion items from a wide range of clothing data sets. The output is a list of the selected fashion items.

[0308] Step 6:

[0309] The server adds reliable evaluation data to the selected items. It obtains reviews from external review APIs or databases and associates them with the items. The output is a list of fashion items with review information added.

[0310] Step 7:

[0311] The terminal visualizes the proposed items and review information received from the server through the user interface. As a specific operation, it displays the proposed items in card format and visually presents the evaluation information. The output is the proposed items presented in a viewable state for the user.

[0312] Step 8:

[0313] The user inputs opinions and feedback on the proposed items through the terminal and sends them to the server. The server saves this as improvement data for the generative AI model and reflects it in the next proposal process. As a specific operation, the user enters comments in the feedback field and presses the send button. The output of this step is the feedback data saved by the server.

[0314] (Application Example 1)

[0315] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0316] Modern consumers are surrounded by a wealth of information, making it difficult to find products that suit their preferences from numerous options, especially when shopping in physical stores. Furthermore, there is a need for a system that effectively connects online review information to in-store purchases. Solving these challenges and providing a better shopping experience is essential.

[0317] 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.

[0318] In this invention, the server includes means for receiving user text information and analyzing it using natural language processing, means for receiving user image information and analyzing it using image recognition technology, and means for suggesting the most suitable products based on product images taken by the user in stores and their entered preferences. This enables consumers to efficiently find products that match their style when making purchases in physical stores and to receive suggestions based on reliable evaluation data.

[0319] "User text information" refers to the textual information entered by the user, and is natural language data that reflects the preferences and requests of individual consumers.

[0320] Natural language processing is a technology that enables computer systems to understand and analyze human language, and is a means of efficiently processing text information.

[0321] "User image information" refers to visual data captured or selected by the user on their device, and is information used to demonstrate the visual characteristics of a product.

[0322] "Image recognition technology" is a technique for analyzing image data to identify objects or features, and is a means of recognizing and analyzing specific patterns based on visual information.

[0323] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to generate the optimal result from input data.

[0324] "Reliable evaluation data" refers to data compiled from past users' reviews of a product, and is used as reference information when making a purchase.

[0325] "Product images taken by users in stores" refer to visual data captured by consumers directly photographing products located in stores, and serve as a factor in the actual shopping process.

[0326] "Methods for proposing the optimal product" refers to technologies and methods that identify and present the most suitable product from a large selection based on the user's preferences and requirements.

[0327] This invention is a system that enables consumers to more efficiently select products that suit their preferences in physical stores. The system mainly consists of a server and terminals, and consumers input product information in the store using the terminals. Specifically, they take pictures of products using the terminal's camera and express their product preferences through text input. This data is sent to the server, which analyzes the text information using natural language processing technology and analyzes the product images using image recognition technology.

[0328] Based on these analysis results, the server uses a generative AI model to search the database for relevant products. The server finds products that match the analysis data from a broad database and suggests them to consumers along with reliable evaluation data. This process is computationally intensive, so the server requires high-performance computing capabilities (for example, processing using TensorFlow or OpenCV).

[0329] For example, a consumer looking for a red casual dress in a store might take a picture of a red dress in the store and type "casual" and "red" into the server, which will then suggest other items. The user can also view reviews of the suggested items. Examples of such prompts include "casual dress," "red," and "suggest similar styles." The AI ​​model generates suggestions that respond to the user's request based on these prompts.

[0330] The introduction of this system will allow consumers to have a new shopping experience in physical stores. It is expected that product selection will become more personalized and efficient, improving the quality of purchasing decisions.

[0331] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0332] Step 1:

[0333] The user takes a picture of the product using their device and enters their preferred style and color in text. The device then sends this image information and text data to the server. The input data includes text describing the user's preferred features and the image of the product they photographed.

[0334] Step 2:

[0335] The server performs natural language processing on the received text data. The input here is text information indicating user preferences. The server analyzes the text using its built-in natural language processing library (e.g., SpaCy) and generates output that identifies the user's preferences.

[0336] Step 3:

[0337] The server analyzes the received image data using image recognition technology. The input is visual information of the product provided by the user, which is then analyzed using image processing libraries such as TensorFlow and OpenCV. As output, features such as style and shape are extracted from the product image.

[0338] Step 4:

[0339] The server uses a generative AI model to select appropriate products based on the analyzed text and image information. The generative AI model compares the features extracted from each source with the features of products in the database to extract the product that best matches the user's preferences. The input is the analysis results described above, and the output is a list of suggested products.

[0340] Step 5:

[0341] The server adds reliable evaluation data to the data of the proposed product and sends it to the terminal. The server retrieves the evaluation data from the database and provides it to the user along with the proposed product. In this process, the input is the proposed product, and the output is the proposed product with evaluation information.

[0342] Step 6:

[0343] Users review suggested products and their ratings through the terminal's user interface. Based on this information, users select products and provide feedback. This user input constitutes feedback, which becomes output data for future use.

[0344] Step 7:

[0345] User feedback is sent to the server and used to improve the generative AI model. The server uses the feedback data to retrain the generative AI model and improve the accuracy of future suggestions. In this step, the input is the feedback, and the output is the improved generative AI model.

[0346] 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.

[0347] This invention is an information system for efficiently understanding a user's fashion preferences and enabling personalized suggestions, and incorporates an emotion engine that recognizes the user's emotional state.

[0348] Users first use their device to write text data about their fashion preferences and style, and upload reference fashion images. This information is then transmitted from the device to the server using a secure protocol.

[0349] The server analyzes the received text data using natural language processing technology to extract features related to fashion preferences. Simultaneously, it analyzes image data using image recognition technology to extract features related to style and items.

[0350] Furthermore, this invention uses an emotion engine to recognize the user's emotional state based on these analysis results. This emotion recognition is performed by comparing information obtained from the user's input data with an emotion pattern database.

[0351] Next, the generative AI model considers the user's preferences and emotional state to select the most suitable fashion items from a global clothing database. The selected items are then organized into personalized suggestions tailored to the user's current mood.

[0352] The server also collects and provides reliable review data for selected fashion items to the user. The terminal visually displays these fashion item suggestions and reviews on the user interface. Based on this information, the user can examine items that interest them in more detail.

[0353] Furthermore, users can send feedback to the server via their device regarding the presented items and the overall system's suggestions. This feedback is stored in a database by the server and used as training data to improve the accuracy of the system's suggestions.

[0354] For example, if a user requests a "casual style that matches a cheerful mood," the emotion engine recognizes positive emotions from the user's text and image data, and the generative AI model suggests casual fashion items with bright colors and designs that align with those emotions. Based on these suggestions, the user can proceed with a purchase and also contribute to improving the system's accuracy by providing feedback on whether the suggestions were appropriate.

[0355] The following describes the processing flow.

[0356] Step 1:

[0357] Users input text data reflecting their fashion preferences via their device and upload related fashion image data. This allows for a concrete expression of the user's style orientation and desired designs.

[0358] Step 2:

[0359] The device transmits the collected text and image data to the server via a secure communication protocol, thereby ensuring data security.

[0360] Step 3:

[0361] The server applies natural language processing (NLP) to the received text data to analyze important keywords and phrases related to the user's preferences. Based on this, it identifies the user's fashion preferences.

[0362] Step 4:

[0363] The server simultaneously analyzes the received image data using image recognition technology to extract features of fashion items and styles from the images. This provides information that complements the text data.

[0364] Step 5:

[0365] The server utilizes an emotion engine based on the analyzed text and image data to recognize the user's emotional state. For example, it determines whether the input words or images indicate emotions such as "happy" or "positive."

[0366] Step 6:

[0367] The server uses a generative AI model to select appropriate fashion items from a global clothing database, taking into account the user's fashion preferences and emotional state. This process suggests items with colors and designs that match the user's mood.

[0368] Step 7:

[0369] The server collects review data associated with selected fashion items and selects the most reliable information from it. It then prepares visual materials to convey the product's appeal to the user.

[0370] Step 8:

[0371] The device displays fashion item suggestions and review information sent from the server in its user interface. Users can review this list of suggestions and view details of items that interest them.

[0372] Step 9:

[0373] Users can select from the suggested fashion items and proceed with the purchase process. Users can also provide feedback on the suggestions, and this data is sent from the device to the server.

[0374] Step 10:

[0375] The server receives user feedback and stores it in a database. This feedback is used as valuable data to further train the generative AI model and improve the accuracy of the system's suggestions.

[0376] (Example 2)

[0377] 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".

[0378] Modern consumers want to make quick choices that match their fashion preferences, but the sheer volume of information available makes decision-making difficult. They also desire more personalized suggestions tailored to their emotional state. As a result, there is a need for a system that accurately meets consumer needs.

[0379] 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.

[0380] In this invention, the server includes means for receiving user text information and analyzing it using language analysis technology, means for receiving user image information and analyzing it using image analysis technology, and emotion analysis means for recognizing the user's emotional state based on the analyzed information. This makes it possible to select personalized fashion items according to the user's individual preferences and emotional state.

[0381] "User text information" refers to the textual information about the user's preferences and style that they input.

[0382] "Language analysis technology" refers to the technology of analyzing natural language to extract specific information or keywords.

[0383] "User image information" refers to visual information related to fashion that users upload.

[0384] "Image analysis technology" refers to the technology of identifying specific features or items from image data.

[0385] "Emotional analysis methods" refer to technologies used to infer a user's emotional state based on analyzed information.

[0386] A "generative AI model" is an artificial intelligence model that generates optimal suggestions based on analysis results and emotional states.

[0387] "Reliable evaluation data" refers to data that shows the quality and user ratings of the fashion items offered.

[0388] A "user interface" refers to the on-screen means of operation that users use to visually obtain information or input data.

[0389] The "information recording unit" refers to a database or storage system used to store user feedback and other data.

[0390] This invention is an information system that suggests personalized fashion items based on the user's fashion preferences and emotional state.

[0391] User:

[0392] Users use their devices to input text information about their fashion preferences and style, and upload reference fashion images. This data is transmitted to the server via a secure protocol.

[0393] server:

[0394] The server analyzes the received text information using language analysis techniques. In this process, it employs a general natural language processing model to extract fashion-related keywords and themes from the user's text. For example, terms like "casual" and "formal" may be identified. Simultaneously, the server analyzes the received image information using image analysis techniques to identify the style, color, and design patterns of clothing within the image. For example, specific items such as blue jeans or white sneakers may be identified.

[0395] Emotion analysis:

[0396] The server uses sentiment analysis tools to recognize the user's emotional state based on the analyzed information. This recognition is performed by comparing it with different emotional patterns. For example, if there are text and image features that suggest the user is feeling "happy," it will be judged as a positive emotional state.

[0397] Generative AI models:

[0398] The generative AI model selects the most suitable fashion items from clothing information worldwide based on the user's preferences and emotional state. This selection process involves providing the AI ​​model with appropriate instructions using prompts. An example prompt might be: "The user is expressing a happy mood and desires a casual style. Please suggest fashion items that match this."

[0399] Proposals and evaluations:

[0400] Selected fashion items are presented visually through the user interface, along with reliable evaluation data. Users can then use this information to view details and explore items that interest them further. Users can also provide feedback, which is stored in the server's data storage unit and used to update the next generation AI model. This improves the system's recommendation accuracy, enabling more personalized fashion suggestions for users.

[0401] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0402] Step 1:

[0403] Users input text information about their fashion preferences and style using their device, and upload reference fashion images. The entered text and images are transmitted from the device to the server using a secure protocol. This collects initial data about the user's fashion.

[0404] Step 2:

[0405] The server analyzes the received text information using language analysis technology. From the text data received as input, it extracts fashion-related keywords and styles using a natural language processing model and outputs them as analysis results. Specifically, it identifies styles such as "casual" and "business."

[0406] Step 3:

[0407] The server processes the received image information using image analysis technology. Based on the input image data, it uses an image recognition algorithm to identify the style and color of fashion items and outputs this information. Specifically, items such as red sweaters and denim pants are identified.

[0408] Step 4:

[0409] The server recognizes the user's emotional state based on the analysis results of text and images. Using the analyzed data as input, it compares it with an emotional pattern database using an emotional analysis tool and outputs the user's emotional state. Specifically, it identifies that the user's expression is "enjoyment."

[0410] Step 5:

[0411] The generative AI model selects the most suitable fashion items from clothing information based on analyzed fashion preferences and emotional states, referencing prompt sentences. Using the provided dataset as input, the AI ​​model outputs the items it has selected. An example prompt sentence is "Please suggest a bright, casual outfit that matches a happy mood."

[0412] Step 6:

[0413] The server collects selected fashion items and their associated reliable evaluation data, and provides this information to the terminal's user interface. The output information is displayed visually and presented to the user as options. Specifically, a list of suggested items is displayed on the screen.

[0414] Step 7:

[0415] Users provide feedback on suggested items and send it to the server via their device. User ratings and opinions are collected as input and stored as output data to improve the system's suggestion accuracy. Specifically, satisfaction levels with selected items are recorded.

[0416] (Application Example 2)

[0417] 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."

[0418] Conventional fashion recommendation systems have a problem in that they do not easily provide personalized recommendations that take into account the user's emotional state. Furthermore, they lack support for selecting products based on the user's emotional state and for efficiently using points to make purchases. Therefore, there is a need to provide optimal fashion product recommendations that respond to the user's emotions, along with intuitive purchasing support methods.

[0419] 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.

[0420] In this invention, the server includes means for receiving user text data and analyzing it using natural language processing, means for receiving user image information and analyzing it using image analysis technology, means for selecting the optimal fashion product from a global clothing information database based on the analysis results using a generative AI model, means for collecting reliable evaluation data and providing information to the user visually, means for recognizing the user's emotional state and making suggestions based on that state, means for receiving user feedback and improving the accuracy of the system's suggestions, and means for considering the user's emotional state and presenting the information necessary to purchase fashion products using points. This enables effective fashion suggestions tailored to the user's emotions and smooth purchases utilizing points.

[0421] "User text data" refers to textual information provided by users regarding their fashion preferences and style.

[0422] "Natural language processing" is a technology that allows computers to understand and analyze human language, and is used for analyzing text data.

[0423] "User image information" refers to visual data, such as fashion images, that users provide to the system.

[0424] "Image analysis technology" is a technique that uses computer vision technology to extract specific features and information from image data.

[0425] A "generative AI model" is an artificial intelligence technology that suggests items based on training data, taking into account the user's preferences and emotions.

[0426] A "clothing information database" is a source of information that accumulates data on fashion products and items from around the world.

[0427] "Rating data" refers to review information from other users that indicates the reliability of a product or service.

[0428] "User emotional state" refers to the user's psychological and emotional state, and is information that the system recognizes using its emotion engine.

[0429] "Opinions" refer to feedback that users provide about their feelings and thoughts regarding the items or services that have been suggested.

[0430] "Points" refer to virtual currency or reward systems that can be used within electronic payment services.

[0431] A specific embodiment for carrying out this invention will now be described. First, the user inputs text data and image information related to their fashion preferences and style into a terminal. This input data is transmitted to a server using a secure communication method.

[0432] The server applies natural language processing techniques to the received text data to extract information related to the user's fashion preferences. Similarly, for image information, image analysis techniques are used to extract characteristics of specific styles and fashion items. In this process, specific software such as the Google Cloud Natural Language API is used.

[0433] Furthermore, the server uses an emotion engine to recognize the user's emotional state. This emotion recognition is performed by comparing information obtained from text and image data with a pre-stored emotion pattern database.

[0434] Based on the user's emotional state and preferences, the server uses a generative AI model to select relevant fashion products from a global clothing information database. This generative AI model visually presents targeted item suggestions to the end user. Reliable evaluation data is also attached to the selected products for user reference.

[0435] Users can view suggested items on their device's user interface and purchase items they are interested in using points. For example, if a user is looking for "clothes to relax in after work," the emotion engine will detect their fatigue level and suggest items in a relaxed style that suits them. An example of a prompt message might be, "Based on the user's current emotions, please identify the most suitable relaxation fashion items."

[0436] This process makes it easier for users to acquire fashion items that best suit their emotional state, while also enabling the efficient use of points.

[0437] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0438] Step 1:

[0439] The user inputs text data and image information about their fashion preferences and style on their device. This input data is used to provide the server with the user's preferences and visual style.

[0440] Step 2:

[0441] The terminal sends the input text data and image information to the server using a secure protocol. In this process, the input is text data and image information, and the output is the secure transmission of data to the server.

[0442] Step 3:

[0443] The server analyzes the received text data using natural language processing techniques (e.g., Google Cloud Natural Language API). This extracts features related to the user's fashion preferences. The input is text data, and the output is the extracted preference features.

[0444] Step 4:

[0445] The server analyzes image information using image analysis technology. Here, features of specific fashion items or styles are extracted. The input is image information, and the output is style features.

[0446] Step 5:

[0447] The server uses an emotion engine to recognize the user's emotional state based on information obtained from text and images. The input consists of extracted features and a pre-defined database, and the output is the recognized emotional state.

[0448] Step 6:

[0449] The server uses a generative AI model to select the most suitable fashion products from a clothing information database, taking into account the user's preferences and emotional state. The input is the user's preferred characteristics and emotional state, and the output is the selected fashion item.

[0450] Step 7:

[0451] The server adds reliable evaluation data to the selected products, visualizes it, and outputs it to the terminal. The input is the selected fashion items, and the output is visualized information with evaluation data.

[0452] Step 8:

[0453] The terminal visually displays fashion items selected by the user, and the user can consider purchasing them using points. Input is visualized information with evaluation data, and output is the user's purchase intention.

[0454] 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.

[0455] 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.

[0456] 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.

[0457] [Third Embodiment]

[0458] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0459] 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.

[0460] 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).

[0461] 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.

[0462] 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.

[0463] 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).

[0464] 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.

[0465] 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.

[0466] 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.

[0467] 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.

[0468] 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.

[0469] 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".

[0470] The system of this invention consists of three main components: a user, a terminal, and a server, and is designed to improve the user's purchasing experience through personalized fashion suggestions.

[0471] The user inputs text and image data through their device. The text data includes keywords related to the user's fashion preferences and style, while the image data includes visuals of fashion examples and items they would like to use as reference.

[0472] The device sends this information to the server. The server uses natural language processing technology to analyze the text data and identify the user's preferences. It also uses image recognition technology to analyze image data and extract information about fashion items and styles.

[0473] The server then utilizes a generative AI model to select fashion items that match the user's preferences. This model searches a global clothing database and picks out items that suit the user's tastes.

[0474] The selected items are accompanied by reliable review data, allowing users to obtain helpful information when purchasing products. The device visually displays these suggested items and their reviews through the user interface. Users can review the suggestions and proceed with the purchase if they wish to continue their interest.

[0475] Furthermore, users can provide feedback on the suggestions. This feedback is sent to the server and used as data to improve the generated AI model. For example, if a user specifies a preferred style and the system suggests a shirt that perfectly matches it, the user can provide feedback on the shirt's fit and style suitability.

[0476] This allows the system to continuously learn user preferences and incorporate them into future recommendations, resulting in a more comfortable and personalized shopping experience.

[0477] The following describes the processing flow.

[0478] Step 1:

[0479] Users input text and image data using their device. The text data includes keywords related to their fashion preferences and style, while the image data includes uploaded images of fashion items they use as reference.

[0480] Step 2:

[0481] The terminal sends text and image data received from the user to the server. Appropriate communication protocols are used to ensure security.

[0482] Step 3:

[0483] The server analyzes the received text data using natural language processing (NLP) techniques. This analysis identifies the user's fashion preferences from the entered keywords.

[0484] Step 4:

[0485] The server simultaneously analyzes the received image data using image recognition technology to extract fashion item and style information. This allows for the recognition of specific features and items contained in the image.

[0486] Step 5:

[0487] The server utilizes a generative AI model to select appropriate fashion items based on the analysis results. This AI model searches a global clothing database to find items that match the user's preferences.

[0488] Step 6:

[0489] The server collects and organizes reliable review data related to selected fashion items. This allows users to obtain information that helps them make purchasing decisions.

[0490] Step 7:

[0491] The device visually displays fashion item suggestions and review data received from the server on the user interface. Users can review this information and view details about products that interest them.

[0492] Step 8:

[0493] Users can select and purchase their favorite suggested items. Furthermore, they can send feedback on the suggested items to the server via their device.

[0494] Step 9:

[0495] The server incorporates the user feedback it receives into the system and uses it as data to improve the generated AI model. This improves the accuracy of future suggestions.

[0496] (Example 1)

[0497] 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."

[0498] In today's market, many consumers find it difficult to find clothing and accessories that suit their fashion sense and style. They want easy access to personalized fashion suggestions and reliable review information to help them make purchasing decisions. Existing systems are not always sufficient to accurately reflect individual user preferences and provide highly accurate suggestions, so this needs to be addressed.

[0499] 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.

[0500] In this invention, the server includes means for receiving text data via a user-operable terminal and analyzing it using natural language processing, means for receiving image data provided by the user and analyzing it using image recognition technology, and means for selecting appropriate fashion items from a broad collection of clothing data based on the analysis results using a generative AI model. This makes it possible to suggest fashion items that suit the user's preferences.

[0501] A "user-operable terminal" is a device that users can directly operate to input their fashion preferences and style information.

[0502] "Natural language processing" is a technology that allows computers to understand and analyze human language, and is used to extract meaning from users' text data.

[0503] "Image recognition technology" is a technology that uses computer vision algorithms to recognize objects and shapes from image data and extract information from them.

[0504] A "generative AI model" is a pre-trained artificial intelligence model used to select appropriate fashion items based on the user's preferences.

[0505] "Reliable evaluation data" refers to trustworthy information about a product provided by a third party, which users can use as a reference when making purchasing decisions.

[0506] A "broad clothing data set" is a diverse and extensive collection of clothing information used to search for necessary information from fashion items around the world.

[0507] A "user interface" is an interface that provides a means for users to interact with a system and visually displays suggested items and evaluations.

[0508] A "prompt statement" is a sentence that gives instructions to a generative AI model to select appropriate fashion items.

[0509] The system of this invention includes three main components: a user, a terminal, and a server. The user provides information about their fashion preferences and style through an operable terminal. Specifically, the user inputs text data and uploads image data of fashion items that suit their preferences.

[0510] The terminal sends the data entered by the user to the server via a secure communication protocol. The server performs natural language processing (NLP) on the received text data to identify the user's preferences. Open-source NLP libraries such as spaCy and NLTK can be used for natural language processing. In addition, image recognition technology is applied to the image data, and analysis is performed using TensorFlow or PyTorch to extract fashion items and style information.

[0511] Based on these analysis results, the server utilizes a generative AI model to select fashion items suitable for the user from a vast collection of clothing data from around the world. This generative AI model can make optimal suggestions by receiving prompts. For example, a prompt such as "Please suggest casual and simple shirts. Reference images are attached." might be used.

[0512] Furthermore, the server collects reliable evaluation data for the selected items and presents it visually to the user through the user interface. In this way, the user can review the suggested items and refer to the reviews. The user can also input and send feedback to the server, which contributes to improving future suggestions.

[0513] This system allows users to receive suggestions for fashion items that are perfectly suited to their preferences, thereby improving their shopping experience.

[0514] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0515] Step 1:

[0516] The user uses their device to input text data about their fashion preferences and style, along with image data of fashion items they would like to use as reference. Specifically, they type text on the user interface and click the "Select Image" button to upload the image. The entered data is temporarily stored on the device for the next step.

[0517] Step 2:

[0518] The terminal sends text and image data received from the user to the server. Specifically, when the send button is pressed, this data is securely transferred to the server using the HTTPS protocol. The output is the user's text and image data received on the server side.

[0519] Step 3:

[0520] The server analyzes the received text data using natural language processing (NLP) techniques. It analyzes the input text data and extracts keywords related to the user's fashion preferences and style. Specifically, it uses an NLP library to tokenize the text and identify important keywords. The output of this step is the extracted style and preference information.

[0521] Step 4:

[0522] The server performs image recognition analysis on the image data. The received image data is input into a model to identify information about fashion items and styles. Specifically, it analyzes the images using a deep learning model such as TensorFlow. The output of this step is the identified item information.

[0523] Step 5:

[0524] Based on the analysis results obtained in steps 3 and 4, the server uses a generative AI model to select fashion items that suit the user's preferences. The prompt text is input to the AI ​​model, which generates the optimal fashion items from a broad collection of clothing data. The output is a list of selected fashion items.

[0525] Step 6:

[0526] The server attaches reliable evaluation data to the selected items. It retrieves reviews from external review APIs and databases and associates them with the items. The output is a list of fashion items with attached review information.

[0527] Step 7:

[0528] The terminal visualizes suggested items and review information received from the server through a user interface. Specifically, it displays suggested items in card format and visually presents evaluation information. The output is the suggested items displayed in a format viewable by the user.

[0529] Step 8:

[0530] Users input their opinions and feedback on suggested items via their device and send them to the server. The server saves this as improvement data for the generating AI model and incorporates it into the next suggestion process. Specifically, the user enters a comment in the feedback field and presses the submit button. The output of this step is the feedback data saved by the server.

[0531] (Application Example 1)

[0532] 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."

[0533] Modern consumers are surrounded by a wealth of information, making it difficult to find products that suit their preferences from numerous options, especially when shopping in physical stores. Furthermore, there is a need for a system that effectively connects online review information to in-store purchases. Solving these challenges and providing a better shopping experience is essential.

[0534] 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.

[0535] In this invention, the server includes means for receiving user text information and analyzing it using natural language processing, means for receiving user image information and analyzing it using image recognition technology, and means for suggesting the most suitable products based on product images taken by the user in stores and their entered preferences. This enables consumers to efficiently find products that match their style when making purchases in physical stores and to receive suggestions based on reliable evaluation data.

[0536] "User text information" refers to the textual information entered by the user, and is natural language data that reflects the preferences and requests of individual consumers.

[0537] Natural language processing is a technology that enables computer systems to understand and analyze human language, and is a means of efficiently processing text information.

[0538] "User image information" refers to visual data captured or selected by the user on their device, and is information used to demonstrate the visual characteristics of a product.

[0539] "Image recognition technology" is a technique for analyzing image data to identify objects or features, and is a means of recognizing and analyzing specific patterns based on visual information.

[0540] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to generate the optimal result from input data.

[0541] "Reliable evaluation data" refers to data compiled from past users' reviews of a product, and is used as reference information when making a purchase.

[0542] "Product images taken by users in stores" refer to visual data captured by consumers directly photographing products located in stores, and serve as a factor in the actual shopping process.

[0543] "Methods for proposing the optimal product" refers to technologies and methods that identify and present the most suitable product from a large selection based on the user's preferences and requirements.

[0544] This invention is a system that enables consumers to more efficiently select products that suit their preferences in physical stores. The system mainly consists of a server and terminals, and consumers input product information in the store using the terminals. Specifically, they take pictures of products using the terminal's camera and express their product preferences through text input. This data is sent to the server, which analyzes the text information using natural language processing technology and analyzes the product images using image recognition technology.

[0545] Based on these analysis results, the server uses a generative AI model to search the database for relevant products. The server finds products that match the analysis data from a broad database and suggests them to consumers along with reliable evaluation data. This process is computationally intensive, so the server requires high-performance computing capabilities (for example, processing using TensorFlow or OpenCV).

[0546] For example, a consumer looking for a red casual dress in a store might take a picture of a red dress in the store and type "casual" and "red" into the server, which will then suggest other items. The user can also view reviews of the suggested items. Examples of such prompts include "casual dress," "red," and "suggest similar styles." The AI ​​model generates suggestions that respond to the user's request based on these prompts.

[0547] The introduction of this system will allow consumers to have a new shopping experience in physical stores. It is expected that product selection will become more personalized and efficient, improving the quality of purchasing decisions.

[0548] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0549] Step 1:

[0550] The user takes a picture of the product using their device and enters their preferred style and color in text. The device then sends this image information and text data to the server. The input data includes text describing the user's preferred features and the image of the product they photographed.

[0551] Step 2:

[0552] The server performs natural language processing on the received text data. The input here is text information indicating user preferences. The server analyzes the text using its built-in natural language processing library (e.g., SpaCy) and generates output that identifies the user's preferences.

[0553] Step 3:

[0554] The server analyzes the received image data using image recognition technology. The input is visual information of the product provided by the user, which is then analyzed using image processing libraries such as TensorFlow and OpenCV. As output, features such as style and shape are extracted from the product image.

[0555] Step 4:

[0556] The server uses a generative AI model to select appropriate products based on the analyzed text and image information. The generative AI model compares the features extracted from each source with the features of products in the database to extract the product that best matches the user's preferences. The input is the analysis results described above, and the output is a list of suggested products.

[0557] Step 5:

[0558] The server adds reliable evaluation data to the data of the proposed product and sends it to the terminal. The server retrieves the evaluation data from the database and provides it to the user along with the proposed product. In this process, the input is the proposed product, and the output is the proposed product with evaluation information.

[0559] Step 6:

[0560] Users review suggested products and their ratings through the terminal's user interface. Based on this information, users select products and provide feedback. This user input constitutes feedback, which becomes output data for future use.

[0561] Step 7:

[0562] User feedback is sent to the server and used to improve the generative AI model. The server uses the feedback data to retrain the generative AI model and improve the accuracy of future suggestions. In this step, the input is the feedback, and the output is the improved generative AI model.

[0563] 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.

[0564] This invention is an information system for efficiently understanding a user's fashion preferences and enabling personalized suggestions, and incorporates an emotion engine that recognizes the user's emotional state.

[0565] Users first use their device to write text data about their fashion preferences and style, and upload reference fashion images. This information is then transmitted from the device to the server using a secure protocol.

[0566] The server analyzes the received text data using natural language processing technology to extract features related to fashion preferences. Simultaneously, it analyzes image data using image recognition technology to extract features related to style and items.

[0567] Furthermore, this invention uses an emotion engine to recognize the user's emotional state based on these analysis results. This emotion recognition is performed by comparing information obtained from the user's input data with an emotion pattern database.

[0568] Next, the generative AI model considers the user's preferences and emotional state to select the most suitable fashion items from a global clothing database. The selected items are then organized into personalized suggestions tailored to the user's current mood.

[0569] The server also collects and provides reliable review data for selected fashion items to the user. The terminal visually displays these fashion item suggestions and reviews on the user interface. Based on this information, the user can examine items that interest them in more detail.

[0570] Furthermore, users can send feedback to the server via their device regarding the presented items and the overall system's suggestions. This feedback is stored in a database by the server and used as training data to improve the accuracy of the system's suggestions.

[0571] For example, if a user requests a "casual style that matches a cheerful mood," the emotion engine recognizes positive emotions from the user's text and image data, and the generative AI model suggests casual fashion items with bright colors and designs that align with those emotions. Based on these suggestions, the user can proceed with a purchase and also contribute to improving the system's accuracy by providing feedback on whether the suggestions were appropriate.

[0572] The following describes the processing flow.

[0573] Step 1:

[0574] Users input text data reflecting their fashion preferences via their device and upload related fashion image data. This allows for a concrete expression of the user's style orientation and desired designs.

[0575] Step 2:

[0576] The device transmits the collected text and image data to the server via a secure communication protocol, thereby ensuring data security.

[0577] Step 3:

[0578] The server applies natural language processing (NLP) to the received text data to analyze important keywords and phrases related to the user's preferences. Based on this, it identifies the user's fashion preferences.

[0579] Step 4:

[0580] The server simultaneously analyzes the received image data using image recognition technology to extract features of fashion items and styles from the images. This provides information that complements the text data.

[0581] Step 5:

[0582] The server utilizes an emotion engine based on the analyzed text and image data to recognize the user's emotional state. For example, it determines whether the input words or images indicate emotions such as "happy" or "positive."

[0583] Step 6:

[0584] The server uses a generative AI model to select appropriate fashion items from a global clothing database, taking into account the user's fashion preferences and emotional state. This process suggests items with colors and designs that match the user's mood.

[0585] Step 7:

[0586] The server collects review data associated with selected fashion items and selects the most reliable information from it. It then prepares visual materials to convey the product's appeal to the user.

[0587] Step 8:

[0588] The device displays fashion item suggestions and review information sent from the server in its user interface. Users can review this list of suggestions and view details of items that interest them.

[0589] Step 9:

[0590] Users can select from the suggested fashion items and proceed with the purchase process. Users can also provide feedback on the suggestions, and this data is sent from the device to the server.

[0591] Step 10:

[0592] The server receives user feedback and stores it in a database. This feedback is used as valuable data to further train the generative AI model and improve the accuracy of the system's suggestions.

[0593] (Example 2)

[0594] 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."

[0595] Modern consumers want to make quick choices that match their fashion preferences, but the sheer volume of information available makes decision-making difficult. They also desire more personalized suggestions tailored to their emotional state. As a result, there is a need for a system that accurately meets consumer needs.

[0596] 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.

[0597] In this invention, the server includes means for receiving user text information and analyzing it using language analysis technology, means for receiving user image information and analyzing it using image analysis technology, and emotion analysis means for recognizing the user's emotional state based on the analyzed information. This makes it possible to select personalized fashion items according to the user's individual preferences and emotional state.

[0598] "User text information" refers to the textual information about the user's preferences and style that they input.

[0599] "Language analysis technology" refers to the technology of analyzing natural language to extract specific information or keywords.

[0600] "User image information" refers to visual information related to fashion that users upload.

[0601] "Image analysis technology" refers to the technology of identifying specific features or items from image data.

[0602] "Emotional analysis methods" refer to technologies used to infer a user's emotional state based on analyzed information.

[0603] A "generative AI model" is an artificial intelligence model that generates optimal suggestions based on analysis results and emotional states.

[0604] "Reliable evaluation data" refers to data that shows the quality and user ratings of the fashion items offered.

[0605] A "user interface" refers to the on-screen means of operation that users use to visually obtain information or input data.

[0606] The "information recording unit" refers to a database or storage system used to store user feedback and other data.

[0607] This invention is an information system that suggests personalized fashion items based on the user's fashion preferences and emotional state.

[0608] User:

[0609] Users use their devices to input text information about their fashion preferences and style, and upload reference fashion images. This data is transmitted to the server via a secure protocol.

[0610] server:

[0611] The server analyzes the received text information using language analysis techniques. In this process, it employs a general natural language processing model to extract fashion-related keywords and themes from the user's text. For example, terms like "casual" and "formal" may be identified. Simultaneously, the server analyzes the received image information using image analysis techniques to identify the style, color, and design patterns of clothing within the image. For example, specific items such as blue jeans or white sneakers may be identified.

[0612] Emotion analysis:

[0613] The server uses sentiment analysis tools to recognize the user's emotional state based on the analyzed information. This recognition is performed by comparing it with different emotional patterns. For example, if there are text and image features that suggest the user is feeling "happy," it will be judged as a positive emotional state.

[0614] Generative AI models:

[0615] The generative AI model selects the most suitable fashion items from clothing information worldwide based on the user's preferences and emotional state. This selection process involves providing the AI ​​model with appropriate instructions using prompts. An example prompt might be: "The user is expressing a happy mood and desires a casual style. Please suggest fashion items that match this."

[0616] Proposals and evaluations:

[0617] Selected fashion items are presented visually through the user interface, along with reliable evaluation data. Users can then use this information to view details and explore items that interest them further. Users can also provide feedback, which is stored in the server's data storage unit and used to update the next generation AI model. This improves the system's recommendation accuracy, enabling more personalized fashion suggestions for users.

[0618] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0619] Step 1:

[0620] Users input text information about their fashion preferences and style using their device, and upload reference fashion images. The entered text and images are transmitted from the device to the server using a secure protocol. This collects initial data about the user's fashion.

[0621] Step 2:

[0622] The server analyzes the received text information using language analysis technology. From the text data received as input, it extracts fashion-related keywords and styles using a natural language processing model and outputs them as analysis results. Specifically, it identifies styles such as "casual" and "business."

[0623] Step 3:

[0624] The server processes the received image information using image analysis technology. Based on the input image data, it uses an image recognition algorithm to identify the style and color of fashion items and outputs this information. Specifically, items such as red sweaters and denim pants are identified.

[0625] Step 4:

[0626] The server recognizes the user's emotional state based on the analysis results of text and images. Using the analyzed data as input, it compares it with an emotional pattern database using an emotional analysis tool and outputs the user's emotional state. Specifically, it identifies that the user's expression is "enjoyment."

[0627] Step 5:

[0628] The generative AI model selects the most suitable fashion items from clothing information based on analyzed fashion preferences and emotional states, referencing prompt sentences. Using the provided dataset as input, the AI ​​model outputs the items it has selected. An example prompt sentence is "Please suggest a bright, casual outfit that matches a happy mood."

[0629] Step 6:

[0630] The server collects selected fashion items and their associated reliable evaluation data, and provides this information to the terminal's user interface. The output information is displayed visually and presented to the user as options. Specifically, a list of suggested items is displayed on the screen.

[0631] Step 7:

[0632] Users provide feedback on suggested items and send it to the server via their device. User ratings and opinions are collected as input and stored as output data to improve the system's suggestion accuracy. Specifically, satisfaction levels with selected items are recorded.

[0633] (Application Example 2)

[0634] 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."

[0635] Conventional fashion recommendation systems have a problem in that they do not easily provide personalized recommendations that take into account the user's emotional state. Furthermore, they lack support for selecting products based on the user's emotional state and for efficiently using points to make purchases. Therefore, there is a need to provide optimal fashion product recommendations that respond to the user's emotions, along with intuitive purchasing support methods.

[0636] 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.

[0637] In this invention, the server includes means for receiving user text data and analyzing it using natural language processing, means for receiving user image information and analyzing it using image analysis technology, means for selecting the optimal fashion product from a global clothing information database based on the analysis results using a generative AI model, means for collecting reliable evaluation data and providing information to the user visually, means for recognizing the user's emotional state and making suggestions based on that state, means for receiving user feedback and improving the accuracy of the system's suggestions, and means for considering the user's emotional state and presenting the information necessary to purchase fashion products using points. This enables effective fashion suggestions tailored to the user's emotions and smooth purchases utilizing points.

[0638] "User text data" refers to textual information provided by users regarding their fashion preferences and style.

[0639] "Natural language processing" is a technology that allows computers to understand and analyze human language, and is used for analyzing text data.

[0640] "User image information" refers to visual data, such as fashion images, that users provide to the system.

[0641] "Image analysis technology" is a technique that uses computer vision technology to extract specific features and information from image data.

[0642] A "generative AI model" is an artificial intelligence technology that suggests items based on training data, taking into account the user's preferences and emotions.

[0643] A "clothing information database" is a source of information that accumulates data on fashion products and items from around the world.

[0644] "Rating data" refers to review information from other users that indicates the reliability of a product or service.

[0645] "User emotional state" refers to the user's psychological and emotional state, and is information that the system recognizes using its emotion engine.

[0646] "Opinions" refer to feedback that users provide about their feelings and thoughts regarding the items or services that have been suggested.

[0647] "Points" refer to virtual currency or reward systems that can be used within electronic payment services.

[0648] A specific embodiment for carrying out this invention will now be described. First, the user inputs text data and image information related to their fashion preferences and style into a terminal. This input data is transmitted to a server using a secure communication method.

[0649] The server applies natural language processing techniques to the received text data to extract information related to the user's fashion preferences. Similarly, for image information, image analysis techniques are used to extract characteristics of specific styles and fashion items. In this process, specific software such as the Google Cloud Natural Language API is used.

[0650] Furthermore, the server uses an emotion engine to recognize the user's emotional state. This emotion recognition is performed by comparing information obtained from text and image data with a pre-stored emotion pattern database.

[0651] Based on the user's emotional state and preferences, the server uses a generative AI model to select relevant fashion products from a global clothing information database. This generative AI model visually presents targeted item suggestions to the end user. Reliable evaluation data is also attached to the selected products for user reference.

[0652] Users can view suggested items on their device's user interface and purchase items they are interested in using points. For example, if a user is looking for "clothes to relax in after work," the emotion engine will detect their fatigue level and suggest items in a relaxed style that suits them. An example of a prompt message might be, "Based on the user's current emotions, please identify the most suitable relaxation fashion items."

[0653] This process makes it easier for users to acquire fashion items that best suit their emotional state, while also enabling the efficient use of points.

[0654] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0655] Step 1:

[0656] The user inputs text data and image information about their fashion preferences and style on their device. This input data is used to provide the server with the user's preferences and visual style.

[0657] Step 2:

[0658] The terminal sends the input text data and image information to the server using a secure protocol. In this process, the input is text data and image information, and the output is the secure transmission of data to the server.

[0659] Step 3:

[0660] The server analyzes the received text data using natural language processing techniques (e.g., Google Cloud Natural Language API). This extracts features related to the user's fashion preferences. The input is text data, and the output is the extracted preference features.

[0661] Step 4:

[0662] The server analyzes image information using image analysis technology. Here, features of specific fashion items or styles are extracted. The input is image information, and the output is style features.

[0663] Step 5:

[0664] The server uses an emotion engine to recognize the user's emotional state based on information obtained from text and images. The input consists of extracted features and a pre-defined database, and the output is the recognized emotional state.

[0665] Step 6:

[0666] The server uses a generative AI model to select the most suitable fashion products from a clothing information database, taking into account the user's preferences and emotional state. The input is the user's preferred characteristics and emotional state, and the output is the selected fashion item.

[0667] Step 7:

[0668] The server adds reliable evaluation data to the selected products, visualizes it, and outputs it to the terminal. The input is the selected fashion items, and the output is visualized information with evaluation data.

[0669] Step 8:

[0670] The terminal visually displays fashion items selected by the user, and the user can consider purchasing them using points. Input is visualized information with evaluation data, and output is the user's purchase intention.

[0671] 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.

[0672] 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.

[0673] 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.

[0674] [Fourth Embodiment]

[0675] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0676] 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.

[0677] 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).

[0678] 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.

[0679] 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.

[0680] 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).

[0681] 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.

[0682] 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.

[0683] 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.

[0684] 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.

[0685] 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.

[0686] 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.

[0687] 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".

[0688] The system of this invention consists of three main components: a user, a terminal, and a server, and is designed to improve the user's purchasing experience through personalized fashion suggestions.

[0689] The user inputs text and image data through their device. The text data includes keywords related to the user's fashion preferences and style, while the image data includes visuals of fashion examples and items they would like to use as reference.

[0690] The device sends this information to the server. The server uses natural language processing technology to analyze the text data and identify the user's preferences. It also uses image recognition technology to analyze image data and extract information about fashion items and styles.

[0691] The server then utilizes a generative AI model to select fashion items that match the user's preferences. This model searches a global clothing database and picks out items that suit the user's tastes.

[0692] The selected items are accompanied by reliable review data, allowing users to obtain helpful information when purchasing products. The device visually displays these suggested items and their reviews through the user interface. Users can review the suggestions and proceed with the purchase if they wish to continue their interest.

[0693] Furthermore, users can provide feedback on the suggestions. This feedback is sent to the server and used as data to improve the generated AI model. For example, if a user specifies a preferred style and the system suggests a shirt that perfectly matches it, the user can provide feedback on the shirt's fit and style suitability.

[0694] This allows the system to continuously learn user preferences and incorporate them into future recommendations, resulting in a more comfortable and personalized shopping experience.

[0695] The following describes the processing flow.

[0696] Step 1:

[0697] Users input text and image data using their device. The text data includes keywords related to their fashion preferences and style, while the image data includes uploaded images of fashion items they use as reference.

[0698] Step 2:

[0699] The terminal sends text and image data received from the user to the server. Appropriate communication protocols are used to ensure security.

[0700] Step 3:

[0701] The server analyzes the received text data using natural language processing (NLP) techniques. This analysis identifies the user's fashion preferences from the entered keywords.

[0702] Step 4:

[0703] The server simultaneously analyzes the received image data using image recognition technology to extract fashion item and style information. This allows for the recognition of specific features and items contained in the image.

[0704] Step 5:

[0705] The server utilizes a generative AI model to select appropriate fashion items based on the analysis results. This AI model searches a global clothing database to find items that match the user's preferences.

[0706] Step 6:

[0707] The server collects and organizes reliable review data related to selected fashion items. This allows users to obtain information that helps them make purchasing decisions.

[0708] Step 7:

[0709] The device visually displays fashion item suggestions and review data received from the server on the user interface. Users can review this information and view details about products that interest them.

[0710] Step 8:

[0711] Users can select and purchase their favorite suggested items. Furthermore, they can send feedback on the suggested items to the server via their device.

[0712] Step 9:

[0713] The server incorporates the user feedback it receives into the system and uses it as data to improve the generated AI model. This improves the accuracy of future suggestions.

[0714] (Example 1)

[0715] 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".

[0716] In today's market, many consumers find it difficult to find clothing and accessories that suit their fashion sense and style. They want easy access to personalized fashion suggestions and reliable review information to help them make purchasing decisions. Existing systems are not always sufficient to accurately reflect individual user preferences and provide highly accurate suggestions, so this needs to be addressed.

[0717] 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.

[0718] In this invention, the server includes means for receiving text data via a user-operable terminal and analyzing it using natural language processing, means for receiving image data provided by the user and analyzing it using image recognition technology, and means for selecting appropriate fashion items from a broad collection of clothing data based on the analysis results using a generative AI model. This makes it possible to suggest fashion items that suit the user's preferences.

[0719] A "user-operable terminal" is a device that users can directly operate to input their fashion preferences and style information.

[0720] "Natural language processing" is a technology that allows computers to understand and analyze human language, and is used to extract meaning from users' text data.

[0721] "Image recognition technology" is a technology that uses computer vision algorithms to recognize objects and shapes from image data and extract information from them.

[0722] A "generative AI model" is a pre-trained artificial intelligence model used to select appropriate fashion items based on the user's preferences.

[0723] "Reliable evaluation data" refers to trustworthy information about a product provided by a third party, which users can use as a reference when making purchasing decisions.

[0724] A "broad clothing data set" is a diverse and extensive collection of clothing information used to search for necessary information from fashion items around the world.

[0725] A "user interface" is an interface that provides a means for users to interact with a system and visually displays suggested items and evaluations.

[0726] A "prompt statement" is a sentence that gives instructions to a generative AI model to select appropriate fashion items.

[0727] The system of this invention includes three main components: a user, a terminal, and a server. The user provides information about their fashion preferences and style through an operable terminal. Specifically, the user inputs text data and uploads image data of fashion items that suit their preferences.

[0728] The terminal sends the data entered by the user to the server via a secure communication protocol. The server performs natural language processing (NLP) on the received text data to identify the user's preferences. Open-source NLP libraries such as spaCy and NLTK can be used for natural language processing. In addition, image recognition technology is applied to the image data, and analysis is performed using TensorFlow or PyTorch to extract fashion items and style information.

[0729] Based on these analysis results, the server utilizes a generative AI model to select fashion items suitable for the user from a vast collection of clothing data from around the world. This generative AI model can make optimal suggestions by receiving prompts. For example, a prompt such as "Please suggest casual and simple shirts. Reference images are attached." might be used.

[0730] Furthermore, the server collects reliable evaluation data for the selected items and presents it visually to the user through the user interface. In this way, the user can review the suggested items and refer to the reviews. The user can also input and send feedback to the server, which contributes to improving future suggestions.

[0731] This system allows users to receive suggestions for fashion items that are perfectly suited to their preferences, thereby improving their shopping experience.

[0732] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0733] Step 1:

[0734] The user uses their device to input text data about their fashion preferences and style, along with image data of fashion items they would like to use as reference. Specifically, they type text on the user interface and click the "Select Image" button to upload the image. The entered data is temporarily stored on the device for the next step.

[0735] Step 2:

[0736] The terminal sends text and image data received from the user to the server. Specifically, when the send button is pressed, this data is securely transferred to the server using the HTTPS protocol. The output is the user's text and image data received on the server side.

[0737] Step 3:

[0738] The server analyzes the received text data using natural language processing (NLP) techniques. It analyzes the input text data and extracts keywords related to the user's fashion preferences and style. Specifically, it uses an NLP library to tokenize the text and identify important keywords. The output of this step is the extracted style and preference information.

[0739] Step 4:

[0740] The server performs image recognition analysis on the image data. The received image data is input into a model to identify information about fashion items and styles. Specifically, it analyzes the images using a deep learning model such as TensorFlow. The output of this step is the identified item information.

[0741] Step 5:

[0742] Based on the analysis results obtained in steps 3 and 4, the server uses a generative AI model to select fashion items that suit the user's preferences. The prompt text is input to the AI ​​model, which generates the optimal fashion items from a broad collection of clothing data. The output is a list of selected fashion items.

[0743] Step 6:

[0744] The server attaches reliable evaluation data to the selected items. It retrieves reviews from external review APIs and databases and associates them with the items. The output is a list of fashion items with attached review information.

[0745] Step 7:

[0746] The terminal visualizes suggested items and review information received from the server through a user interface. Specifically, it displays suggested items in card format and visually presents evaluation information. The output is the suggested items displayed in a format viewable by the user.

[0747] Step 8:

[0748] Users input their opinions and feedback on suggested items via their device and send them to the server. The server saves this as improvement data for the generating AI model and incorporates it into the next suggestion process. Specifically, the user enters a comment in the feedback field and presses the submit button. The output of this step is the feedback data saved by the server.

[0749] (Application Example 1)

[0750] 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".

[0751] Modern consumers are surrounded by a wealth of information, making it difficult to find products that suit their preferences from numerous options, especially when shopping in physical stores. Furthermore, there is a need for a system that effectively connects online review information to in-store purchases. Solving these challenges and providing a better shopping experience is essential.

[0752] 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.

[0753] In this invention, the server includes means for receiving user text information and analyzing it using natural language processing, means for receiving user image information and analyzing it using image recognition technology, and means for suggesting the most suitable products based on product images taken by the user in stores and their entered preferences. This enables consumers to efficiently find products that match their style when making purchases in physical stores and to receive suggestions based on reliable evaluation data.

[0754] "User text information" refers to the textual information entered by the user, and is natural language data that reflects the preferences and requests of individual consumers.

[0755] Natural language processing is a technology that enables computer systems to understand and analyze human language, and is a means of efficiently processing text information.

[0756] "User image information" refers to visual data captured or selected by the user on their device, and is information used to demonstrate the visual characteristics of a product.

[0757] "Image recognition technology" is a technique for analyzing image data to identify objects or features, and is a means of recognizing and analyzing specific patterns based on visual information.

[0758] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to generate the optimal result from input data.

[0759] "Reliable evaluation data" refers to data compiled from past users' reviews of a product, and is used as reference information when making a purchase.

[0760] "Product images taken by users in stores" refer to visual data captured by consumers directly photographing products located in stores, and serve as a factor in the actual shopping process.

[0761] "Methods for proposing the optimal product" refers to technologies and methods that identify and present the most suitable product from a large selection based on the user's preferences and requirements.

[0762] This invention is a system that enables consumers to more efficiently select products that suit their preferences in physical stores. The system mainly consists of a server and terminals, and consumers input product information in the store using the terminals. Specifically, they take pictures of products using the terminal's camera and express their product preferences through text input. This data is sent to the server, which analyzes the text information using natural language processing technology and analyzes the product images using image recognition technology.

[0763] Based on these analysis results, the server uses a generative AI model to search the database for relevant products. The server finds products that match the analysis data from a broad database and suggests them to consumers along with reliable evaluation data. This process is computationally intensive, so the server requires high-performance computing capabilities (for example, processing using TensorFlow or OpenCV).

[0764] For example, a consumer looking for a red casual dress in a store might take a picture of a red dress in the store and type "casual" and "red" into the server, which will then suggest other items. The user can also view reviews of the suggested items. Examples of such prompts include "casual dress," "red," and "suggest similar styles." The AI ​​model generates suggestions that respond to the user's request based on these prompts.

[0765] The introduction of this system will allow consumers to have a new shopping experience in physical stores. It is expected that product selection will become more personalized and efficient, improving the quality of purchasing decisions.

[0766] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0767] Step 1:

[0768] The user takes a picture of the product using their device and enters their preferred style and color in text. The device then sends this image information and text data to the server. The input data includes text describing the user's preferred features and the image of the product they photographed.

[0769] Step 2:

[0770] The server performs natural language processing on the received text data. The input here is text information indicating user preferences. The server analyzes the text using its built-in natural language processing library (e.g., SpaCy) and generates output that identifies the user's preferences.

[0771] Step 3:

[0772] The server analyzes the received image data using image recognition technology. The input is visual information of the product provided by the user, which is then analyzed using image processing libraries such as TensorFlow and OpenCV. As output, features such as style and shape are extracted from the product image.

[0773] Step 4:

[0774] The server uses a generative AI model to select appropriate products based on the analyzed text and image information. The generative AI model compares the features extracted from each source with the features of products in the database to extract the product that best matches the user's preferences. The input is the analysis results described above, and the output is a list of suggested products.

[0775] Step 5:

[0776] The server adds reliable evaluation data to the data of the proposed product and sends it to the terminal. The server retrieves the evaluation data from the database and provides it to the user along with the proposed product. In this process, the input is the proposed product, and the output is the proposed product with evaluation information.

[0777] Step 6:

[0778] Users review suggested products and their ratings through the terminal's user interface. Based on this information, users select products and provide feedback. This user input constitutes feedback, which becomes output data for future use.

[0779] Step 7:

[0780] User feedback is sent to the server and used to improve the generative AI model. The server uses the feedback data to retrain the generative AI model and improve the accuracy of future suggestions. In this step, the input is the feedback, and the output is the improved generative AI model.

[0781] 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.

[0782] This invention is an information system for efficiently understanding a user's fashion preferences and enabling personalized suggestions, and incorporates an emotion engine that recognizes the user's emotional state.

[0783] Users first use their device to write text data about their fashion preferences and style, and upload reference fashion images. This information is then transmitted from the device to the server using a secure protocol.

[0784] The server analyzes the received text data using natural language processing technology to extract features related to fashion preferences. Simultaneously, it analyzes image data using image recognition technology to extract features related to style and items.

[0785] Furthermore, this invention uses an emotion engine to recognize the user's emotional state based on these analysis results. This emotion recognition is performed by comparing information obtained from the user's input data with an emotion pattern database.

[0786] Next, the generative AI model considers the user's preferences and emotional state to select the most suitable fashion items from a global clothing database. The selected items are then organized into personalized suggestions tailored to the user's current mood.

[0787] The server also collects and provides reliable review data for selected fashion items to the user. The terminal visually displays these fashion item suggestions and reviews on the user interface. Based on this information, the user can examine items that interest them in more detail.

[0788] Furthermore, users can send feedback to the server via their device regarding the presented items and the overall system's suggestions. This feedback is stored in a database by the server and used as training data to improve the accuracy of the system's suggestions.

[0789] For example, if a user requests a "casual style that matches a cheerful mood," the emotion engine recognizes positive emotions from the user's text and image data, and the generative AI model suggests casual fashion items with bright colors and designs that align with those emotions. Based on these suggestions, the user can proceed with a purchase and also contribute to improving the system's accuracy by providing feedback on whether the suggestions were appropriate.

[0790] The following describes the processing flow.

[0791] Step 1:

[0792] Users input text data reflecting their fashion preferences via their device and upload related fashion image data. This allows for a concrete expression of the user's style orientation and desired designs.

[0793] Step 2:

[0794] The device transmits the collected text and image data to the server via a secure communication protocol, thereby ensuring data security.

[0795] Step 3:

[0796] The server applies natural language processing (NLP) to the received text data to analyze important keywords and phrases related to the user's preferences. Based on this, it identifies the user's fashion preferences.

[0797] Step 4:

[0798] The server simultaneously analyzes the received image data using image recognition technology to extract features of fashion items and styles from the images. This provides information that complements the text data.

[0799] Step 5:

[0800] The server utilizes an emotion engine based on the analyzed text and image data to recognize the user's emotional state. For example, it determines whether the input words or images indicate emotions such as "happy" or "positive."

[0801] Step 6:

[0802] The server uses a generative AI model to select appropriate fashion items from a global clothing database, taking into account the user's fashion preferences and emotional state. This process suggests items with colors and designs that match the user's mood.

[0803] Step 7:

[0804] The server collects review data associated with selected fashion items and selects the most reliable information from it. It then prepares visual materials to convey the product's appeal to the user.

[0805] Step 8:

[0806] The device displays fashion item suggestions and review information sent from the server in its user interface. Users can review this list of suggestions and view details of items that interest them.

[0807] Step 9:

[0808] Users can select from the suggested fashion items and proceed with the purchase process. Users can also provide feedback on the suggestions, and this data is sent from the device to the server.

[0809] Step 10:

[0810] The server receives user feedback and stores it in a database. This feedback is used as valuable data to further train the generative AI model and improve the accuracy of the system's suggestions.

[0811] (Example 2)

[0812] 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".

[0813] Modern consumers want to make quick choices that match their fashion preferences, but the sheer volume of information available makes decision-making difficult. They also desire more personalized suggestions tailored to their emotional state. As a result, there is a need for a system that accurately meets consumer needs.

[0814] 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.

[0815] In this invention, the server includes means for receiving user text information and analyzing it using language analysis technology, means for receiving user image information and analyzing it using image analysis technology, and emotion analysis means for recognizing the user's emotional state based on the analyzed information. This makes it possible to select personalized fashion items according to the user's individual preferences and emotional state.

[0816] "User text information" refers to the textual information about the user's preferences and style that they input.

[0817] "Language analysis technology" refers to the technology of analyzing natural language to extract specific information or keywords.

[0818] "User image information" refers to visual information related to fashion that users upload.

[0819] "Image analysis technology" refers to the technology of identifying specific features or items from image data.

[0820] "Emotional analysis methods" refer to technologies used to infer a user's emotional state based on analyzed information.

[0821] A "generative AI model" is an artificial intelligence model that generates optimal suggestions based on analysis results and emotional states.

[0822] "Reliable evaluation data" refers to data that shows the quality and user ratings of the fashion items offered.

[0823] A "user interface" refers to the on-screen means of operation that users use to visually obtain information or input data.

[0824] The "information recording unit" refers to a database or storage system used to store user feedback and other data.

[0825] This invention is an information system that suggests personalized fashion items based on the user's fashion preferences and emotional state.

[0826] User:

[0827] Users use their devices to input text information about their fashion preferences and style, and upload reference fashion images. This data is transmitted to the server via a secure protocol.

[0828] server:

[0829] The server analyzes the received text information using language analysis techniques. In this process, it employs a general natural language processing model to extract fashion-related keywords and themes from the user's text. For example, terms like "casual" and "formal" may be identified. Simultaneously, the server analyzes the received image information using image analysis techniques to identify the style, color, and design patterns of clothing within the image. For example, specific items such as blue jeans or white sneakers may be identified.

[0830] Emotion analysis:

[0831] The server uses sentiment analysis tools to recognize the user's emotional state based on the analyzed information. This recognition is performed by comparing it with different emotional patterns. For example, if there are text and image features that suggest the user is feeling "happy," it will be judged as a positive emotional state.

[0832] Generative AI models:

[0833] The generative AI model selects the most suitable fashion items from clothing information worldwide based on the user's preferences and emotional state. This selection process involves providing the AI ​​model with appropriate instructions using prompts. An example prompt might be: "The user is expressing a happy mood and desires a casual style. Please suggest fashion items that match this."

[0834] Proposals and evaluations:

[0835] Selected fashion items are presented visually through the user interface, along with reliable evaluation data. Users can then use this information to view details and explore items that interest them further. Users can also provide feedback, which is stored in the server's data storage unit and used to update the next generation AI model. This improves the system's recommendation accuracy, enabling more personalized fashion suggestions for users.

[0836] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0837] Step 1:

[0838] Users input text information about their fashion preferences and style using their device, and upload reference fashion images. The entered text and images are transmitted from the device to the server using a secure protocol. This collects initial data about the user's fashion.

[0839] Step 2:

[0840] The server analyzes the received text information using language analysis technology. From the text data received as input, it extracts fashion-related keywords and styles using a natural language processing model and outputs them as analysis results. Specifically, it identifies styles such as "casual" and "business."

[0841] Step 3:

[0842] The server processes the received image information using image analysis technology. Based on the input image data, it uses an image recognition algorithm to identify the style and color of fashion items and outputs this information. Specifically, items such as red sweaters and denim pants are identified.

[0843] Step 4:

[0844] The server recognizes the user's emotional state based on the analysis results of text and images. Using the analyzed data as input, it compares it with an emotional pattern database using an emotional analysis tool and outputs the user's emotional state. Specifically, it identifies that the user's expression is "enjoyment."

[0845] Step 5:

[0846] The generative AI model selects the most suitable fashion items from clothing information based on analyzed fashion preferences and emotional states, referencing prompt sentences. Using the provided dataset as input, the AI ​​model outputs the items it has selected. An example prompt sentence is "Please suggest a bright, casual outfit that matches a happy mood."

[0847] Step 6:

[0848] The server collects selected fashion items and their associated reliable evaluation data, and provides this information to the terminal's user interface. The output information is displayed visually and presented to the user as options. Specifically, a list of suggested items is displayed on the screen.

[0849] Step 7:

[0850] Users provide feedback on suggested items and send it to the server via their device. User ratings and opinions are collected as input and stored as output data to improve the system's suggestion accuracy. Specifically, satisfaction levels with selected items are recorded.

[0851] (Application Example 2)

[0852] 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".

[0853] Conventional fashion recommendation systems have a problem in that they do not easily provide personalized recommendations that take into account the user's emotional state. Furthermore, they lack support for selecting products based on the user's emotional state and for efficiently using points to make purchases. Therefore, there is a need to provide optimal fashion product recommendations that respond to the user's emotions, along with intuitive purchasing support methods.

[0854] 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.

[0855] In this invention, the server includes means for receiving user text data and analyzing it using natural language processing, means for receiving user image information and analyzing it using image analysis technology, means for selecting the optimal fashion product from a global clothing information database based on the analysis results using a generative AI model, means for collecting reliable evaluation data and providing information to the user visually, means for recognizing the user's emotional state and making suggestions based on that state, means for receiving user feedback and improving the accuracy of the system's suggestions, and means for considering the user's emotional state and presenting the information necessary to purchase fashion products using points. This enables effective fashion suggestions tailored to the user's emotions and smooth purchases utilizing points.

[0856] "User text data" refers to textual information provided by users regarding their fashion preferences and style.

[0857] "Natural language processing" is a technology that allows computers to understand and analyze human language, and is used for analyzing text data.

[0858] "User image information" refers to visual data, such as fashion images, that users provide to the system.

[0859] "Image analysis technology" is a technique that uses computer vision technology to extract specific features and information from image data.

[0860] A "generative AI model" is an artificial intelligence technology that suggests items based on training data, taking into account the user's preferences and emotions.

[0861] A "clothing information database" is a source of information that accumulates data on fashion products and items from around the world.

[0862] "Rating data" refers to review information from other users that indicates the reliability of a product or service.

[0863] "User emotional state" refers to the user's psychological and emotional state, and is information that the system recognizes using its emotion engine.

[0864] "Opinions" refer to feedback that users provide about their feelings and thoughts regarding the items or services that have been suggested.

[0865] "Points" refer to virtual currency or reward systems that can be used within electronic payment services.

[0866] A specific embodiment for carrying out this invention will now be described. First, the user inputs text data and image information related to their fashion preferences and style into a terminal. This input data is transmitted to a server using a secure communication method.

[0867] The server applies natural language processing techniques to the received text data to extract information related to the user's fashion preferences. Similarly, for image information, image analysis techniques are used to extract characteristics of specific styles and fashion items. In this process, specific software such as the Google Cloud Natural Language API is used.

[0868] Furthermore, the server uses an emotion engine to recognize the user's emotional state. This emotion recognition is performed by comparing information obtained from text and image data with a pre-stored emotion pattern database.

[0869] Based on the user's emotional state and preferences, the server uses a generative AI model to select relevant fashion products from a global clothing information database. This generative AI model visually presents targeted item suggestions to the end user. Reliable evaluation data is also attached to the selected products for user reference.

[0870] Users can view suggested items on their device's user interface and purchase items they are interested in using points. For example, if a user is looking for "clothes to relax in after work," the emotion engine will detect their fatigue level and suggest items in a relaxed style that suits them. An example of a prompt message might be, "Based on the user's current emotions, please identify the most suitable relaxation fashion items."

[0871] This process makes it easier for users to acquire fashion items that best suit their emotional state, while also enabling the efficient use of points.

[0872] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0873] Step 1:

[0874] The user inputs text data and image information about their fashion preferences and style on their device. This input data is used to provide the server with the user's preferences and visual style.

[0875] Step 2:

[0876] The terminal sends the input text data and image information to the server using a secure protocol. In this process, the input is text data and image information, and the output is the secure transmission of data to the server.

[0877] Step 3:

[0878] The server analyzes the received text data using natural language processing techniques (e.g., Google Cloud Natural Language API). This extracts features related to the user's fashion preferences. The input is text data, and the output is the extracted preference features.

[0879] Step 4:

[0880] The server analyzes image information using image analysis technology. Here, features of specific fashion items or styles are extracted. The input is image information, and the output is style features.

[0881] Step 5:

[0882] The server uses an emotion engine to recognize the user's emotional state based on information obtained from text and images. The input consists of extracted features and a pre-defined database, and the output is the recognized emotional state.

[0883] Step 6:

[0884] The server uses a generative AI model to select the most suitable fashion products from a clothing information database, taking into account the user's preferences and emotional state. The input is the user's preferred characteristics and emotional state, and the output is the selected fashion item.

[0885] Step 7:

[0886] The server adds reliable evaluation data to the selected products, visualizes it, and outputs it to the terminal. The input is the selected fashion items, and the output is visualized information with evaluation data.

[0887] Step 8:

[0888] The terminal visually displays fashion items selected by the user, and the user can consider purchasing them using points. Input is visualized information with evaluation data, and output is the user's purchase intention.

[0889] 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.

[0890] 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.

[0891] 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.

[0892] 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.

[0893] 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.

[0894] 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.

[0895] 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.

[0896] 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.

[0897] 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."

[0898] 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.

[0899] 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.

[0900] 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.

[0901] 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.

[0902] 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.

[0903] 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.

[0904] 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.

[0905] 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.

[0906] 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.

[0907] 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.

[0908] 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.

[0909] 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.

[0910] The following is further disclosed regarding the embodiments described above.

[0911] (Claim 1)

[0912] A means of receiving user text data and analyzing it using natural language processing,

[0913] A means for receiving user image data and analyzing it using image recognition technology,

[0914] A method for selecting the most suitable fashion items from a global clothing database based on analysis results using a generative AI model,

[0915] A means of collecting reliable review data and providing users with visual information,

[0916] A means of receiving user feedback and improving the accuracy of the system's suggestions,

[0917] A system that includes this.

[0918] (Claim 2)

[0919] The system according to claim 1, further comprising means for visually displaying suggestions and reviews of received fashion items through a user interface.

[0920] (Claim 3)

[0921] The system according to claim 1, further comprising means for storing user feedback in a database and using it as data for updating the generated AI model.

[0922] "Example 1"

[0923] (Claim 1)

[0924] A means of receiving text data via a user-operable terminal and analyzing it using natural language processing,

[0925] A means of receiving image data provided by a user and analyzing it using image recognition technology,

[0926] A method for selecting appropriate fashion items from a broad collection of clothing data based on analysis results using a generative AI model,

[0927] A means of collecting reliable evaluation data and providing it to users as visual information,

[0928] A means of receiving user feedback and improving the accuracy of system suggestions,

[0929] A means of visually displaying fashion items and their ratings through a user interface,

[0930] A system that includes this.

[0931] (Claim 2)

[0932] The system according to claim 1, further comprising means for storing user opinions in a data storage device and using them as data for updating a generated AI model.

[0933] (Claim 3)

[0934] The system according to claim 1, further comprising means for generating a prompt statement and providing a method for a generating AI model to select the optimal fashion item based on that statement.

[0935] "Application Example 1"

[0936] (Claim 1)

[0937] A means for receiving user text information and analyzing it using natural language processing,

[0938] A means for receiving user image information and analyzing it using image recognition technology,

[0939] A method for selecting the optimal product from a wide product database based on analysis results using a generative AI model,

[0940] A means of collecting reliable evaluation data and providing users with visual information,

[0941] A means of receiving user feedback and improving the accuracy of the system's suggestions,

[0942] A method for suggesting the most suitable product based on product images taken by the user in-store and their entered preferences,

[0943] A system that includes this.

[0944] (Claim 2)

[0945] The system according to claim 1, further comprising means for visually displaying received product suggestions and evaluations through a user interface.

[0946] (Claim 3)

[0947] The system according to claim 1, further comprising means for storing user evaluations in an information infrastructure and using them as data for updating a generated AI model.

[0948] "Example 2 of combining an emotion engine"

[0949] (Claim 1)

[0950] A means of receiving user text information and analyzing it using language analysis technology,

[0951] A means for receiving user image information and analyzing it using image analysis technology,

[0952] An emotion analysis method that recognizes the user's emotional state based on the analyzed information,

[0953] A method for selecting the optimal fashion item from clothing information worldwide based on analysis results and emotional state using a generative AI model,

[0954] A means of collecting reliable evaluation data and providing information to users visually,

[0955] A means of receiving user feedback and improving the accuracy of the system's suggestions,

[0956] A system that includes this.

[0957] (Claim 2)

[0958] The system according to claim 1, further comprising means for visually displaying suggestions and reviews of received fashion items through a user interface.

[0959] (Claim 3)

[0960] The system according to claim 1, further comprising means for storing user feedback in an information recording unit and using it as information for updating the generated AI model.

[0961] "Application example 2 when combining with an emotional engine"

[0962] (Claim 1)

[0963] A means of receiving user text data and analyzing it using natural language processing,

[0964] A means for receiving user image information and analyzing it using image analysis technology,

[0965] A method for selecting the optimal fashion product from a global clothing information database based on analysis results using a generative AI model,

[0966] A means of collecting reliable evaluation data and providing users with visual information,

[0967] A means of recognizing the user's emotional state and making suggestions based on that state,

[0968] A means of receiving user feedback and improving the accuracy of system suggestions,

[0969] A system that includes this.

[0970] (Claim 2)

[0971] The system according to claim 1, further comprising means for considering the user's emotional state and presenting the information necessary for the user to purchase fashion products using points.

[0972] (Claim 3)

[0973] The system according to claim 1, further comprising means for storing user feedback in an information storage and using it as data for updating the generated AI model. [Explanation of symbols]

[0974] 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 for receiving user text information and analyzing it using natural language processing, A means for receiving user image information and analyzing it using image recognition technology, A method for selecting the optimal product from a wide product database based on analysis results using a generative AI model, A means of collecting reliable evaluation data and providing users with visual information, A means of receiving user feedback and improving the accuracy of the system's suggestions, A method for suggesting the most suitable product based on product images taken by the user in-store and their entered preferences, A system that includes this.

2. The system according to claim 1, further comprising means for visually displaying received product suggestions and evaluations through a user interface.

3. The system according to claim 1, further comprising means for storing user evaluations in an information infrastructure and using them as data for updating the generated AI model.

Images