System

Abstract

To provide a system.SOLUTION: A system includes: means for causing learning of artificial intelligence, based on information related to fashion items, and information related to styles and trends that are popular in the fashion industry; means for determining a user's age and physical constitution, based on a photograph of the user, by using the artificial intelligence learned; proposal means for proposing articles matching a budget inputted by the user, the age and physical constitution, by inputting a specific prompt sentence to a generative AI model, and for displaying a list including the proposed articles in the user's terminal; an emotion engine which recognizes the user's feelings, by analyzing messages inputted by the user; and adjustment means for adjusting a kind and design of the articles, according to the feelings.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In conventional online shopping, users had to search for products themselves and find the one that fit their size and preferences. Also, if users wanted to get inspiration from trends or celebrity styles, they had to research them themselves and go to the trouble of finding the right product. A system that could solve these problems was needed. [Means for solving the problem]

[0005] The system of the present invention includes: a means for training an artificial intelligence based on information about fashion items and information about styles and trends popular in the fashion industry; a means for using the trained artificial intelligence to determine the age and physique of the user based on a photo submitted by the user; a suggestion means for suggesting products that suit the budget, age, and physique entered by the user by inputting a specific prompt sentence into a generative AI model, and displaying a list including the suggested products on the user's terminal; an emotion engine for recognizing the user's emotions by analyzing messages entered by the user; and an adjustment means for adjusting the type and design of the product based on the emotions. [Brief explanation of the drawings]

[0006] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 2 is a sequence diagram showing a flow of processing in the data processing system according to the first embodiment of the first form example. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1. [Figure 13] FIG. 10 is a sequence diagram showing a processing flow of a data processing system in a second embodiment of the second form example. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Embodiment Example 2. [Figure 15] FIG. 10 is a sequence diagram showing the flow of processing in a data processing system according to a third embodiment of the third embodiment. [Figure 16] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Embodiment 3. [Figure 17] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when an emotion engine is combined. [Figure 19] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the second embodiment of the second form example when an emotion engine is combined. [Figure 20] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when an emotion engine is combined. [Figure 21] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the third embodiment of the third form example when an emotion engine is combined. [Figure 22] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0007] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0008] First, the terms used in the following description will be explained.

[0009] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0011] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0012] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0013] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0014] [First embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0017] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0018] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0019] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0020] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0021] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0022] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0023] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0024] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0025] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0026] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0027] "Example 1"

[0028] The system of the present invention constantly connects apparel product data, the latest fashion trend information, and an AI API, and allows the API to learn based on this information. Specifically, the apparel product data uses product information obtained from a product database of an online shopping site, such as product images, price, size, material, brand, etc. The latest fashion trend information uses information obtained from fashion magazines and websites, such as the latest trends, celebrity styles, and seasonal styles. Based on this information, the AI ​​API learns and has the ability to suggest products that match the user's preferences and sizes.

[0029] "Example 2"

[0030] Users send their own photos through a messenger app. Specifically, users upload their full-body photos to the messenger app, and the system receives the photos. The system uses an artificial intelligence API to automatically determine the user's age and size from the photos. For example, if a user sends a full-body photo of themselves, the system analyzes the user's body shape and build from the photo and estimates the user's size based on that.

[0031] "Example 3"

[0032] The system automatically suggests products that fit the user's needs and are within their budget, and provides a link to purchase the products. Specifically, the user enters their preferences in the form of "I want clothes like this, and my budget is what." The system then suggests appropriate products based on those needs and budget. For example, if a user enters "I want casual clothes, and my budget is 5,000 yen," the system will suggest products that fit those conditions and provide a link to the product's purchase page.

[0033] The processing flow of each embodiment will be described below.

[0034] "Example 1"

[0035] Step 1: The system constantly connects apparel product data, the latest fashion trend information, and an AI API. Specifically, it uses product information obtained from the product database of the online shopping site, such as product images, price, size, material, brand, etc.

[0036] Step 2: For the latest fashion trend information, information obtained from fashion magazines and websites, such as the latest trends, celebrity styles, and seasonal styles, is used.

[0037] Step 3: Based on this information, the AI ​​API learns and has the ability to suggest products that match the user's preferences and sizes.

[0038] "Example 2"

[0039] Step 1: The user sends their photo through the messenger app. Specifically, the user uploads a full-body photo of themselves to the messenger app, and the system receives the photo.

[0040] Step 2: The system uses an artificial intelligence API to automatically determine the user's age and size from the photo. For example, if a user sends a full-body photo of themselves, the system will analyze the user's body shape and build from the photo and estimate the user's size based on that.

[0041] "Example 3"

[0042] Step 1: The system automatically suggests products that fit the user's needs and fit their budget, and provides a link to purchase the products. Specifically, the user inputs their needs in the form of "I want clothes like this, and my budget."

[0043] Step 2: The system suggests suitable products based on the user's preferences and budget. For example, if a user enters "I want casual clothes, my budget is 5,000 yen," the system suggests products that fit those criteria and provides a link to the product's purchase page.

[0044] Example 1

[0045] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0046] Conventional apparel product recommendation systems do not adequately suggest products based on the user's preferences and sizes. It is also difficult to suggest products that reflect the latest fashion trends, making it difficult to provide appropriate products that meet the user's needs. Furthermore, they are unable to adequately suggest products within the user's desired budget or based on celebrity-style styles. This leads to problems such as lower user satisfaction and a decrease in purchasing motivation.

[0047] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0048] In this invention, the server includes: means for constantly connecting apparel product data, the latest fashion trend information, and an artificial intelligence API and training the API based on the information; means for receiving input information from a user terminal and automatically suggesting products based on the user's preferences and size using the API; and means for displaying the suggested products on the user terminal and providing a link to purchase the products. This allows for product suggestions tailored to the user's preferences and size, and product suggestions that reflect the latest fashion trend information. It also allows for product suggestions within the user's desired budget and suggestions based on celebrity-style styles, improving user satisfaction and increasing purchasing motivation.

[0049] The server of the present disclosure includes: a means for training an artificial intelligence (AI) based on information about fashion items and information about styles and trends popular in the fashion industry; a means for using the trained AI to determine the user's age and physique based on a photo submitted by the user; a suggestion means for suggesting products that match the user's budget, age, and physique by inputting a specific prompt sentence into a generative AI model and displaying a list including the suggested products on the user's device; an emotion engine for recognizing the user's emotions by analyzing the message entered by the user; and an adjustment means for adjusting the type and design of the products based on the emotions. The suggestion means may suggest products that match the user's preferred style, budget, age, and physique. The suggestion means may also display the list on the device, including hyperlinks to web pages where the user can purchase the products.

[0050] "Apparel product data" refers to product information obtained from the product database of an online shopping site, and specifically includes information such as product images, prices, sizes, materials, and brands.

[0051] "Latest fashion trend information" is information obtained from fashion magazines and websites, and specifically includes information on the latest trends, celebrity styles, seasonal styles, and the like.

[0052] An "artificial intelligence API" is an application programming interface that uses machine learning and deep learning to analyze data and perform specific tasks.

[0053] "User device" means a device used by a user to enter information or view suggested products, including, for example, a web browser or a mobile application.

[0054] "Product suggestion" refers to the act of selecting and presenting appropriate apparel products to a user based on the user's preferences, size, budget, and requests.

[0055] A "product purchase link" is a URL or button for purchasing the suggested product, which the user can click to go directly to the purchase page.

[0056] This invention is a system that uses an artificial intelligence API to suggest products that suit a user's preferences and sizes based on apparel product data and the latest fashion trend information. Specific embodiments of this system are described below.

[0057] Server Processing

[0058] The server first retrieves apparel product data from the product database of an online shopping site. This data includes information such as product images, prices, sizes, materials, and brands. Next, the server collects the latest fashion trend information from fashion magazines and websites. This involves using scraping technology to obtain information such as the latest trends, celebrity styles, and seasonal styles.

[0059] The collected data requires preprocessing. The server resizes and normalizes image data, tokenizes and vectorizes text data, and cleans the data by filling in missing values ​​and removing outliers.

[0060] The server uses the preprocessed data to train an artificial intelligence API. Specifically, it trains a neural network model using a machine learning framework such as TENSORFLOW (registered trademark) or PyTorch. After training is complete, the server saves the trained model and makes it available as an API for inference.

[0061] Terminal handling

[0062] The device sends the information entered by the user to the server, specifically, to obtain the user's preferences and sizes through input fields in a web form or mobile app. The device sends the data, including the user's preferences and sizes, to the server using an HTTP request.

[0063] To display the product suggestions received from the server to the user, the device uses UI components of a web page or mobile app, displaying information such as images, prices, and brands of the suggested products to help the user select a product.

[0064] User operations

[0065] First, the user inputs their preferences and size into the device. For example, they might input information such as "I like casual styles and my size is medium." Then, the user checks the product suggestions displayed on the device. They check the images, prices, brands, and other information of the suggested products, and if they find one they like, they select it and proceed with the purchase. Specifically, they add the product to their shopping cart, enter their payment information, and complete the purchase.

[0066] Specific examples

[0067] If a user inputs "I like casual style, size M," the server will use this information to compare the latest fashion trend information with apparel product data and suggest casual style products in size M. For example, it will suggest "a denim jacket (price: 5,000 yen, brand: XYZ) that is trending this spring."

[0068] Prompt Sentence Examples

[0069] "Please suggest products that you would recommend to a user who likes casual style and wears size M."

[0070] By inputting this prompt into a generative AI model, product suggestions that match the user's preferences and size can be obtained.

[0071] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0072] Step 1:

[0073] The server retrieves apparel product data from the product database of the online shopping site. Specifically, it uses an API to collect information such as product images, prices, sizes, materials, and brands. The input is the API endpoint of the online shopping site, and the output is the retrieved apparel product data.

[0074] Step 2:

[0075] The server collects the latest fashion trend information from fashion magazines and websites. Specifically, it uses scraping technology to obtain information such as the latest trends, celebrity styles, and seasonal styles. The input is the URL of the fashion magazine or website, and the output is the collected fashion trend information.

[0076] Step 3:

[0077] The server preprocesses the collected data. Specifically, it resizes and normalizes image data, and tokenizes and vectorizes text data. It also performs data cleaning, such as filling in missing values ​​and removing outliers. The input is apparel product data and fashion trend information, and the output is the preprocessed data.

[0078] Step 4:

[0079] The server uses the preprocessed data to train an artificial intelligence API. Specifically, it uses machine learning frameworks such as TensorFlow or PyTorch to train a neural network model. The input is the preprocessed data, and the output is the trained model.

[0080] Step 5:

[0081] The server saves the trained model and exposes it as an API for inference. Specifically, it saves the model as a file and sets an API endpoint. The input is the trained model, and the output is the exposed API endpoint.

[0082] Step 6:

[0083] The device sends the information entered by the user to the server. Specifically, the user's preferences and sizes are acquired through input fields in a web form or a mobile app. The input is information about the user's preferences and sizes, and the output is an HTTP request to the server.

[0084] Step 7:

[0085] The server receives requests from users and performs inference using the trained model. Specifically, it suggests optimal products based on the user's preferences and size. The input is information about the user's preferences and size, and the output is suggested product information.

[0086] Step 8:

[0087] The terminal displays the product suggestions received from the server to the user. Specifically, it uses UI components of a web page or mobile app to display information such as images, prices, and brands of the suggested products. The input is the suggested product information, and the output is the product information displayed to the user.

[0088] Step 9:

[0089] The user checks the product suggestions displayed on the terminal, selects any products they like, and then completes the purchase. Specifically, they add the products to their shopping cart and enter payment information to complete the purchase. The input is the suggested product information and the user's payment information, and the output is confirmation of purchase completion.

[0090] (Application example 1)

[0091] Next, a description will be given of Application Example 1 of Embodiment Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0092] Conventional apparel product recommendation systems have the problem that it is difficult to efficiently recommend products that match the user's preferences and sizes, and since users cannot actually try on the products, there are problems with low post-purchase satisfaction. Furthermore, it is difficult to reflect the latest fashion trend information in real time, and it is not possible to respond quickly to user needs.

[0093] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0094] In this invention, the server includes means for constantly connecting apparel product data, the latest fashion trend information, and an artificial intelligence API and for training the API based on the information, means for allowing a user to walk around the virtual store using a smartphone or head-mounted display and for using the API to suggest products that suit the user's preferences and size, and means for scanning the user's body shape data and using the API to suggest clothes in the optimal size. This allows the user to actually try on products in the virtual store and makes it possible to suggest products based on the latest fashion trend information.

[0095] "Apparel product data" refers to product information obtained from the product database of an online shopping site, and specifically includes information such as product images, prices, sizes, materials, and brands.

[0096] "Latest fashion trend information" is information obtained from fashion magazines and websites, and specifically includes information on the latest trends, celebrity styles, seasonal styles, and the like.

[0097] The "artificial intelligence API" is an artificial intelligence application programming interface that has the ability to learn from apparel product data and the latest fashion trend information, and suggest products that suit the user's preferences and sizes.

[0098] A "smartphone" is a type of mobile phone and a multi-function device that can connect to the Internet and install applications.

[0099] A "head-mounted display" is a display device that the user wears on their head, and is a device that provides virtual reality and augmented reality experiences.

[0100] A "virtual store" is a virtual store that exists on the Internet and provides an environment where users can browse and purchase products online.

[0101] "Body type data" refers to information about the user's body dimensions and shape, and specifically includes data such as height, weight, chest circumference, waist circumference, and hip circumference.

[0102] A "product purchase link" is a web link that allows a user to purchase the suggested product online.

[0103] The system for implementing this invention constantly connects apparel product data and the latest fashion trend information, and uses an artificial intelligence (AI) API to suggest products that match the user's preferences and sizes. A specific embodiment of this system is described below.

[0104] System Configuration

[0105] Hardware

[0106] Server: Hosts the database and AI models and provides APIs.

[0107] User device: Use a smartphone or head-mounted display (HMD).

[0108] software

[0109] TensorFlow: Used for training and inference of AI models.

[0110] OpenCV: Used for image processing.

[0111] PIL (Python Imaging Library): Used for image manipulation.

[0112] Requests: Used for API communication.

[0113] Data acquisition and processing

[0114] Acquiring apparel product data

[0115] The server retrieves product information from the product database of the online shopping site, including product images, prices, sizes, materials, brands, etc.

[0116] Get the latest fashion trends

[0117] The server retrieves the latest trend information from fashion magazines and websites, including celebrity styles and seasonal styles.

[0118] AI model training and inference

[0119] The server uses TensorFlow to train an AI model based on the acquired apparel product data and the latest fashion trend information. The trained AI model is then able to suggest products that match the user's preferences and sizes.

[0120] User Interface

[0121] Use of virtual stores

[0122] Users can walk around the virtual store using their smartphone or HMD, and AI will scan their body data and suggest clothes that fit them best.

[0123] Product suggestions and purchase links

[0124] Once a user selects an item in the virtual store, the AI ​​will suggest the best fit based on the user's preferences and size, and provide a link to purchase the suggested item online.

[0125] Specific examples

[0126] For example, users can use their smartphone camera to scan their body shape, and the app will use that data to suggest clothing that best suits them. They can also use an HMD to walk around a virtual store and try on outfits suggested by AI.

[0127] Prompt Sentence Examples

[0128] Develop an application that scans the user's body data and suggests the best apparel products based on the latest fashion trends. Users can walk around a virtual store using their smartphone or HMD and try on outfits suggested by AI.

[0129] In this way, by providing a concrete form for implementing the invention, users can actually try on products in a virtual store, making it possible to receive product suggestions based on the latest fashion trends.

[0130] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0131] Step 1:

[0132] The server retrieves apparel product data from the product database of the online shopping site. Specifically, it retrieves information such as product images, prices, sizes, materials, and brands through the API. The input is the API request, and the output is a list of product data.

[0133] Step 2:

[0134] The server retrieves the latest fashion trend information from fashion magazines and websites. Specifically, it retrieves information such as the latest trends, celebrity styles, and seasonal styles through scraping or API. The input is the scraping script or API request, and the output is a list of trend information.

[0135] Step 3:

[0136] The server uses TensorFlow to train an AI model based on the acquired apparel product data and the latest fashion trend information. The input is product data and trend information, and the output is a trained AI model. Specific operations include data preprocessing, model training, and evaluation.

[0137] Step 4:

[0138] The user walks around the virtual store using a smartphone or a head-mounted display. The smartphone camera and the HMD sensor are used to scan the user's body shape data. The input is the user's body shape data, and the output is the scanned body shape data.

[0139] Step 5:

[0140] The server receives the scanned body data and uses an AI model to suggest products that match the user's preferences and size. The input is the body data and the trained AI model, and the output is a list of suggested products. Specific operations include analyzing the body data, estimating the user's preferences, and suggesting products.

[0141] Step 6:

[0142] The user tries on suggested products in a virtual store. The virtual try-on is performed using a smartphone or HMD. The input is a list of suggested products, and the output is feedback on the tried-on products. Specific operations include product selection, virtual try-on, and feedback.

[0143] Step 7:

[0144] The server provides a product purchase link for the product selected by the user. The input is the product selected by the user, and the output is the product purchase link. Specific operations include generating a purchase link and providing the link to the user.

[0145] In this manner, detailed procedures for carrying out the invention are provided by describing the specific operations performed at each processing step.

[0146] Example 2

[0147] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0148] Conventional apparel product recommendation systems have had problems such as difficulty in accurately determining a user's age and size, and insufficient product recommendations that meet the user's needs.Furthermore, there have been issues with the accuracy of analyzing photos submitted by users, resulting in low suitability of the products suggested.

[0149] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0150] In this invention, the server includes means for constantly connecting apparel product data, the latest fashion trend information, and an artificial intelligence API and training the API based on the information, means for receiving photos from a user via a messenger app and automatically determining the user's age and size using the API, means for automatically suggesting products within the user's desired budget and providing a link to purchase the products, means for saving photos sent by the user and sending them to the artificial intelligence API to receive analysis results, and means for estimating the user's age and size based on the analysis results, thereby enabling accurate determination of the user's age and size and suggesting products that meet the user's desires.

[0151] "Apparel product data" refers to data that includes information about fashion items such as clothing and accessories.

[0152] "Latest fashion trends" refers to information about styles and trends currently popular in the fashion industry.

[0153] An "artificial intelligence API" is a programming interface for image and data analysis that uses machine learning algorithms to perform specific tasks.

[0154] A "messenger app" is a software application that enables users to send and receive text messages and images.

[0155] "Means for automatically determining a user's age and size" is a function that uses an artificial intelligence API to analyze and estimate a user's age, body shape, and build from photos sent by the user.

[0156] A "purchase link" is a URL or hyperlink that allows a user to purchase a suggested product online.

[0157] The "means for saving photos" is a function for temporarily or permanently saving photos sent by users in storage.

[0158] "Means for receiving analysis results" refers to the function by which the server receives analysis results from the artificial intelligence API.

[0159] "Means for estimating age and size" is a function that estimates the user's age, body shape, and build based on the analysis results of an artificial intelligence API.

[0160] The present invention is a system that analyzes photos sent by a user via a messenger app, automatically determines the user's age and size, and suggests appropriate apparel products. Specific embodiments of this system are described below.

[0161] System configuration

[0162] The system consists of the following main components:

[0163] 1. Messenger app: A software application that allows users to send photos. Examples include WhatsApp and Facebook Messenger.

[0164] 2. Server: A central processing unit for receiving, storing, and sending photos to the AI ​​API. The server uses storage services such as Amazon S3 and Google Cloud Storage.

[0165] 3. Artificial Intelligence API: A programmatic interface for analyzing photos to determine a user's age and size. Examples include Google Cloud Vision API and Amazon Rekognition.

[0166] System Operation

[0167] 1. User submits a photo

[0168] Users can send their full-body photos using the Messenger app by tapping the "Send Photo" button within the app and selecting a full-body photo from their camera roll.

[0169] 2. The device uploads the photo to the server.

[0170] The device uploads the photo selected by the user to the server by sending the photo data to the server as an HTTP POST request.

[0171] 3. The server stores the photos

[0172] The server stores the received photos in temporary storage (e.g., Amazon S3, Google Cloud Storage), and records the photo file names and paths in a database.

[0173] 4. The server sends the photo to the AI ​​API

[0174] The server sends the saved photo to an artificial intelligence API (e.g., Google Cloud Vision API, Amazon Rekognition). The server creates an API request and sends it along with the photo data.

[0175] 5. Artificial intelligence API analyzes photos

[0176] The AI ​​API analyzes the received photos to estimate the user's age, body type, and build. The API uses image analysis algorithms to analyze facial features and body proportions.

[0177] 6. The server receives the analysis results

[0178] The server receives the analysis results from the AI ​​API, which include data on estimated age and size.

[0179] 7. The server estimates the user's age and size

[0180] The server estimates the user's age and size based on the analysis results it receives, stores the analysis results in a database, and provides feedback to the user as needed.

[0181] Specific examples

[0182] For example, if a user uploads a full-body photo of themselves to Facebook Messenger, the following specific actions will occur:

[0183] 1. A user opens the Facebook Messenger app and taps the "Send Photo" button.

[0184] 2. The user selects a full-body photo from their camera roll and presses the send button.

[0185] 3. The device sends the selected photo to the server as an HTTP POST request.

[0186] 4. The server stores the received photos in Amazon S3 and records the file path in the database.

[0187] 5. The server sends the saved photo to the Google Cloud Vision API and makes an analysis request.

[0188] 6. The Google Cloud Vision API analyzes the photo and estimates the user's age as 25 and size as medium.

[0189] 7. The server receives the analysis results and stores them in a database.

[0190] 8. The server provides feedback to the user: "Your age is 25 and your size is M."

[0191] Prompt Sentence Examples

[0192] Example prompts to input to a generative AI model:

[0193] "Analyze a user-submitted full-body photo to determine age and size. The photo can be found at the following URL: [Photo URL]"

[0194] This system allows users to purchase appropriate apparel products based on their age and size, allowing them to do so efficiently.

[0195] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0196] Step 1:

[0197] User submits a photo

[0198] A user sends a full-body photo of themselves using a messenger app. The user taps the "Send Photo" button in the app and selects a full-body photo from their camera roll. The input is the user's full-body photo, and the output is the photo data sent through the messenger app.

[0199] Step 2:

[0200] The device uploads the photo to the server.

[0201] The device uploads the photo selected by the user to the server. The device sends the photo data to the server as an HTTP POST request. The input is the user's full-body photo data, and the output is the photo data sent to the server.

[0202] Step 3:

[0203] The server stores the photos

[0204] The server stores the received photos in temporary storage (e.g., Amazon S3, Google Cloud Storage). The server records the photo file name and path in a database. The input is the photo data sent to the server, and the output is the photo file and its path information stored in the storage.

[0205] Step 4:

[0206] The server sends the photo to the AI ​​API

[0207] The server sends the stored photos to an AI API (e.g., Google Cloud Vision API, Amazon Rekognition). The server creates an API request and sends it including the photo data. The input is the path information of the photo file stored in storage, and the output is the photo data sent to the AI ​​API.

[0208] Step 5:

[0209] Artificial intelligence API analyzes photos

[0210] The AI ​​API analyzes the received photos and estimates the user's age, body shape, and build. The API uses image analysis algorithms to analyze facial features and body proportions. The input is the photo data sent to the AI ​​API, and the output is the analyzed age and size data.

[0211] Step 6:

[0212] The server receives the analysis results

[0213] The server receives the analysis results from the AI ​​API. The analysis results include data on estimated age and size. The input is the analysis result data sent from the AI ​​API, and the output is the analysis result data stored on the server.

[0214] Step 7:

[0215] The server estimates the user's age and size

[0216] The server estimates the user's age and size based on the analysis results it receives. The server stores the analysis results in a database and provides feedback to the user as needed. The input is the analysis result data stored on the server, and the output is the age and size information provided to the user.

[0217] (Application example 2)

[0218] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0219] On conventional online shopping sites, it was difficult for users to choose the right size of clothing, and because they could not try on the items, they had problems with the size not fitting after purchase. Furthermore, they were unable to provide an experience similar to that of actually trying on the items, which resulted in a time-consuming decision-making process. Furthermore, it was difficult to suggest optimal products based on the user's body type and age, making it difficult to meet individual needs.

[0220] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0221] In this invention, the server includes means for constantly connecting apparel product data, the latest fashion trend information, and an artificial intelligence API and training the API based on the information, means for receiving photos from users via a messenger app and automatically determining the user's age and size using the API, means for automatically suggesting products within the user's desired budget and providing a link to purchase the products, and means for performing a virtual try-on based on photos uploaded by the user and displaying the selected clothes superimposed on the user's photo. This allows users to easily select clothes that fit them best and provides an experience similar to actually trying them on through the virtual try-on.

[0222] "Apparel product data" refers to data that includes information about fashion items such as clothing and accessories.

[0223] "Latest fashion trend information" refers to information about fashion styles and trends that are popular in the current market.

[0224] An "artificial intelligence API" is an application programming interface that uses artificial intelligence technology to provide specific functionality.

[0225] A "messenger app" is application software that allows users to send and receive text messages and images.

[0226] "Means for automatically determining a user's age and size" refers to technology that analyzes photos sent by users and automatically determines their age, body type, and build.

[0227] The "means for providing a product purchase link" is a technique for providing a web link for the user to purchase the product selected by the user.

[0228] The "means for virtual try-on" is a technology that displays the clothes selected by the user superimposed on a photograph of the user, providing a visual experience that makes it seem as if the user is actually trying on the clothes.

[0229] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described in detail below with reference to the accompanying drawings.

[0230] First, the server is constantly connected to apparel product data and the latest fashion trend information, and this information is learned using an artificial intelligence API. Specifically, the server is placed on the cloud, and apparel product data and fashion trend information are stored in a database. As the artificial intelligence API, for example, Microsoft® Azure® Computer Vision API is used.

[0231] Users upload their full-body photos to the server through a messenger app installed on their smartphones or tablets. The server then sends the photos to an artificial intelligence API, which automatically determines the user's age and size. The results are returned to the server and added to the user's profile.

[0232] The server then automatically suggests products that fit the user's budget. This is done using an algorithm that searches a database for suitable products based on the budget information entered by the user and the determined size information. The suggested products are then notified to the user via a messenger app, and a link to purchase the product is provided.

[0233] In addition, a function is provided that allows users to virtually try on the clothes they have selected. The server acquires image data of the clothes selected by the user and displays it over a full-body photo of the user. This process uses an image processing library (e.g., OpenCV). This allows users to have a visual experience that makes them feel as if they are actually trying on the clothes.

[0234] As a concrete example, the following prompt sentence is input to the generative AI model:

[0235] "A user has uploaded a full-body photo. Please analyze the user's age and body type from this photo and suggest the best clothing size for them."

[0236] By inputting this prompt into the generative AI model, the AI ​​will analyze the user's photo and generate data to suggest clothing of the appropriate size.

[0237] As described above, the present invention provides a system that enables users to easily select clothes that fit them best and allows them to have the experience of actually trying on clothes through virtual try-on.

[0238] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0239] Step 1:

[0240] The user uploads a full-body photo through the messenger app.

[0241] Input: A full-body photo of the user

[0242] Output: Full body photo sent to the server

[0243] Specific operation: The user uses a messenger app installed on a smartphone or tablet to take a full-body photo of themselves and uploads it to the server using the app's sending function.

[0244] Step 2:

[0245] The server sends the received photos to an artificial intelligence API, which automatically determines the user's age and size.

[0246] Input: A full-body photo sent to the server

[0247] Output: User's age and size information

[0248] How it works: The server sends the received full-body photo to an AI API (such as Microsoft Azure's Computer Vision API) for photo analysis. The API determines the user's age, body type, and build from the photo and returns the results to the server.

[0249] Step 3:

[0250] Based on the results of the assessment, the server adds age and size information to the user's profile.

[0251] Input: User's age and size information

[0252] Output: Updated user profile

[0253] Specific operation: The server adds the age and size information returned from the AI ​​API to the user's profile database and updates the user's profile.

[0254] Step 4:

[0255] The server automatically suggests products that meet the user's needs and are within the user's budget.

[0256] Input: User's budget information, age and size information

[0257] Output: Suggested product list

[0258] Specific operation: The server runs an algorithm to search for appropriate products from the database based on the budget information entered by the user and the determined age and size information, and generates a list of products that are best suited to the user.

[0259] Step 5:

[0260] The server notifies the user of the suggested product list via a messenger app and provides a link to purchase the product.

[0261] Input: Suggested product list

[0262] Output: List of products notified to the user and a link to purchase

[0263] Specific operation: The server notifies the user of the generated product list and each product purchase link via the messenger app. The user can check the product list in the app and purchase the product by clicking the purchase link.

[0264] Step 6:

[0265] It provides a function for users to virtually try on selected clothes.

[0266] Input: Image data of the clothes selected by the user, a full-body photo of the user

[0267] Output: Virtual try-on image

[0268] Specific operation: The server obtains image data of the clothes selected by the user and uses an image processing library (e.g., OpenCV) to overlay it on a full-body photo of the user, giving the user a visual experience that makes them feel as if they are actually trying on the clothes.

[0269] Through these steps, users can easily choose the clothes that fit them best, and the virtual try-on experience makes them feel as if they are actually trying on the clothes.

[0270] Example 3

[0271] Next, a third embodiment of the third embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0272] Conventional apparel product recommendation systems have difficulty suggesting appropriate products based on a user's preferences and budget. Even if a user inputs specific preferences, they are unable to quickly find products that match those preferences. Furthermore, there is a lack of systems that allow users to easily obtain purchase links. To solve these problems, a system is needed that automatically suggests products based on a user's preferences and budget and provides purchase links.

[0273] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0274] In this invention, the server includes a means for a user to input their preferences and budget via a terminal and transmit the input to the server, a means for the server to analyze the received preferences and budget and input a prompt sentence to the generative AI model, and a means for the generative AI model to generate product data based on the input prompt sentence. This makes it possible to quickly suggest appropriate products based on the user's preferences and budget and provide a purchase link.

[0275] "Apparel product data" refers to data that includes information about fashion items such as clothing and accessories.

[0276] "Latest fashion trend information" refers to information about styles and designs that are popular in the current market.

[0277] An "artificial intelligence API" is an application programming interface that uses artificial intelligence technology to provide specific functions.

[0278] A "user" is an individual or organization that uses the system to search for and purchase products.

[0279] A "terminal" is a device that allows a user to access the system and input their preferences and budget.

[0280] A "server" is a computer system that receives input from a user, generates product data using a generative AI model, and returns the results to the terminal.

[0281] A "generative AI model" is an artificial intelligence model that generates appropriate product data based on an input prompt sentence.

[0282] A "prompt sentence" is an input sentence that includes the user's wishes and budget, and provides instructions to the generative AI model for generating product data.

[0283] A "product list" is a list of product information suggested by a generative AI model, including product name, price, description, and purchase link.

[0284] A "purchase link" is the URL of a web page that a user visits to purchase a suggested product.

[0285] This invention is a system that suggests appropriate products based on a user's preferences and budget and provides a link to purchase the products. The system is implemented by having the user input their preferences and budget through a terminal, and then having the server generate product data using a generative AI model and return it to the terminal.

[0286] First, the user enters their preferences into the device's input form in the form of "I want clothes like this, and my budget is what." For example, they might enter "I want casual clothes, and my budget is 5,000 yen." The device then sends this input data in JSON format to the server.

[0287] The server analyzes the received data and creates a prompt to input into a generative AI model (for example, GPT-4 (registered trademark)). The prompt takes the form of "I want casual clothes, my budget is 5,000 yen." The generative AI model generates data to suggest appropriate products based on this prompt. This data includes the product name, price, description, purchase link, etc.

[0288] The server creates a product list based on the generated data and returns it to the device in JSON format. The device then displays the received product list to the user. The user can scroll through the list to check the suggested products. For example, it might be displayed in the format "Casual T-shirt - Price: 3000 yen - Purchase link: example.com / tshirt".

[0289] Users select the product they want and click the link to purchase that product. Clicking opens a browser and takes them to the product purchase page. This allows users to easily find and purchase the product that meets their needs.

[0290] As a concrete example, if a user inputs "I want casual clothes, my budget is 5000 yen," the system will process it as follows:

[0291] 1. The user enters into the terminal, "I want casual clothes, my budget is 5,000 yen."

[0292] 2. The device sends this input data to the server in JSON format.

[0293] 3. The server analyzes the received data and generates a prompt such as "I want casual clothes, my budget is 5,000 yen."

[0294] 4. The server inputs the prompt sentence into the generative AI model (GPT-4) to generate product data.

[0295] 5. The generative AI model generates data including product name, price, description, and purchase link.

[0296] 6. The server creates a product list based on the generated data and returns it to the terminal in JSON format.

[0297] 7. The device displays the received product list to the user. For example, it may display a list like "Casual T-shirt - Price: 3000 yen - Purchase link: example.com / tshirt."

[0298] 8. The user selects the desired product and clicks the purchase link, which opens a browser and takes them to the product purchase page.

[0299] In this way, the user can easily find a product that meets their needs. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0300] Step 1:

[0301] The user enters their preferences and budget into the input form on the device.

[0302] Specific operation: The user enters "I want casual clothes, my budget is 5,000 yen" into the input form on the device.

[0303] Input: User's preferences and budget (e.g., "I want casual clothes, my budget is 5,000 yen")

[0304] Output: Input data (e.g. "I want casual clothes, my budget is 5000 yen")

[0305] Step 2:

[0306] The terminal sends the input data to the server.

[0307] Specific operation: The terminal sends the user's preferences and budget data in JSON format to the server.

[0308] Input: User's preferences and budget (JSON format)

[0309] Output: The input data sent to the server

[0310] Step 3:

[0311] The server analyzes the received data and inputs prompt sentences into the generative AI model.

[0312] Specific operation: The server analyzes the received data and generates a prompt statement such as "I want casual clothes, my budget is 5,000 yen."

[0313] Input: Input data sent to the server

[0314] Output: Generated prompt (e.g. "I want casual clothes, my budget is 5000 yen")

[0315] Step 4:

[0316] The generative AI model generates product data based on the prompt sentence.

[0317] Specific operation: Based on the input prompt, the generative AI model generates product data including the product name, price, description, and purchase link.

[0318] Input: Generated prompt text

[0319] Output: Generated product data (e.g. product name, price, description, purchase link)

[0320] Step 5:

[0321] The server creates a product list based on the generated product data and returns it to the terminal.

[0322] Specific operation: The server creates a product list based on the product data received from the generative AI model and returns it to the terminal in JSON format.

[0323] Input: Generated product data

[0324] Output: Product list returned to the terminal (JSON format)

[0325] Step 6:

[0326] The terminal displays the product list to the user.

[0327] Specific operation: The device displays the received product list to the user, who can scroll through the list to check the suggested products.

[0328] Input: Product list returned to the terminal

[0329] Output: The product list displayed to the user

[0330] Step 7:

[0331] The user selects a product and clicks the purchase link.

[0332] Specific operation: The user selects the desired product and clicks the purchase link for that product. When clicked, a browser opens and accesses the product purchase page.

[0333] Input: Product list displayed to user

[0334] Output: Access to product purchase page

[0335] (Application example 3)

[0336] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0337] Conventional online shopping systems often require a lot of time and effort for users to find the products they want. Furthermore, they lack the functionality to automatically suggest products that fit the user's budget, which hinders the user experience. Furthermore, there is no established method for effectively utilizing generative AI models to generate product suggestions based on the user's preferences.

[0338] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes means for constantly connecting apparel product data, the latest fashion trend information, and an artificial intelligence API and training the API based on the information; means for receiving photos from a user via a messenger app and automatically determining the user's age and size using the API; means for automatically suggesting products within the user's desired budget and providing a link to purchase the products; means for generating product suggestions based on the user's desired preferences using a generative AI model; and means for providing a link to purchase the suggested products via an application installed on a smartphone. This enables users to quickly and efficiently find the products they want, significantly improving the user experience.

[0339] "Apparel product data" refers to data that includes information about fashion items such as clothing and accessories.

[0340] "Latest fashion trend information" refers to information about styles and designs that are popular in the current market.

[0341] An "artificial intelligence API" is an application programming interface that uses artificial intelligence technology to provide specific functionality.

[0342] A "messenger app" is application software that allows users to send and receive text messages and images.

[0343] "Means for automatically determining a user's age and size" refers to technology that automatically determines a user's age and body size based on information and images provided by the user.

[0344] "Means for automatically suggesting products within a budget and providing links to purchase the products" refers to a technology that selects appropriate products based on the budget set by the user and provides links to the product's purchase page.

[0345] A "generative AI model" is an artificial intelligence model that generates appropriate responses and suggestions based on user input.

[0346] An "application installed on a smartphone" is a software program designed to run on a smartphone.

[0347] The "means for generating product proposals" is a technology for selecting appropriate products based on the user's wishes and conditions.

[0348] A "product purchase link" is a hyperlink to a web page for purchasing a particular product.

[0349] A system for implementing this invention is configured as follows: A server constantly connects apparel product data, the latest fashion trend information, and an artificial intelligence API, and trains the API based on the information. A user sends a photo via a messenger app, and the server automatically determines the user's age and size using the API. Furthermore, the server automatically suggests products within the user's desired budget and provides a link to purchase the products.

[0350] The server uses a generative AI model to generate product suggestions based on the user's preferences. Specifically, when the user inputs their desired product category and budget, the generative AI model suggests products that fit those criteria. For example, if a user inputs "I want casual clothes, my budget is 5,000 yen," the server uses the generative AI model to suggest casual clothes that can be purchased for less than 5,000 yen and provides a link to purchase those products.

[0351] The system works through an application installed on a smartphone, where users can input their desired product category and budget, and then view suggested product purchase links.

[0352] The hardware required is a smartphone, and the software required is Python and OpenAI (registered trademark) API. Data processing and calculation are performed by a generative AI model that generates product suggestions based on data input from the user, and the results are provided to the user.

[0353] For example, if a user inputs "I want casual clothes, my budget is 5000 yen," the server will input the following prompt sentence into the generative AI model:

[0354] "The user's desired product category is 'casual clothing' and their budget is '5,000 yen'. Please suggest products that fit this."

[0355] Based on this prompt, the generative AI model makes product suggestions, and the server provides the results to the user, allowing the user to quickly and efficiently find the products they want.

[0356] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0357] Step 1:

[0358] The user starts the smartphone application and inputs the desired product category and budget. The input data includes the product category (e.g., "casual clothes") and the budget (e.g., "5,000 yen").

[0359] Step 2:

[0360] The terminal sends the input data from the user to the server. The input data is the product category and budget. The server receives this and proceeds to the next step.

[0361] Step 3:

[0362] The server generates a prompt based on the received input data. Specifically, it generates a prompt that includes the product category and budget (e.g., "The product category the user wants is 'casual clothing' and the budget is '5000 yen'. Please suggest products that fit this.").

[0363] Step 4:

[0364] The server inputs the generated prompt sentence into the generative AI model, which generates product suggestions based on the prompt sentence. The input data is the prompt sentence, and the output data is the product suggestions.

[0365] Step 5:

[0366] The server receives the output data (product suggestions) from the generative AI model and converts them into a format for delivery to the user. Specifically, it formats the product suggestions in text format and adds a purchase link.

[0367] Step 6:

[0368] The server sends the formatted product offer and the purchase link to the terminal. The input data is the formatted product offer and the purchase link, and the output data is the information displayed to the user.

[0369] Step 7:

[0370] The terminal displays the product suggestions and purchase links received from the server to the user, who can then check the displayed information and, if necessary, click the purchase link to purchase the product.

[0371] Through the above processing steps, the user can quickly and efficiently find the product they want.

[0372] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0373] "Example 1"

[0374] In one embodiment of the present invention, an emotion engine is incorporated. This emotion engine analyzes text information in messages from users and determines their emotions. For example, if a user sends a message saying "I'm feeling good today," the emotion engine determines from the message that the user's emotion is "joy."

[0375] "Example 2"

[0376] The emotion engine also changes the way it suggests products depending on the user's emotions. For example, if the user's emotion is "joy," the emotion engine suggests products with bright colors and pop designs. On the other hand, if the user's emotion is "sadness," the emotion engine suggests products with muted colors and simple designs.

[0377] "Example 3"

[0378] Furthermore, the emotion engine learns changes in the user's emotions and reflects the learning results in product suggestions. For example, if the emotion engine learns that the user tends to select sportswear whenever they express the emotion "joy," it will suggest sportswear the next time the user expresses the emotion "joy."

[0379] The processing flow of each embodiment will be described below.

[0380] "Example 1"

[0381] Step 1: Receive a message from the user.

[0382] Step 2: The emotion engine analyzes the text information of the message.

[0383] Step 3: The emotion engine determines the user's emotion.

[0384] "Example 2"

[0385] Step 1: The emotion engine determines the user's emotion.

[0386] Step 2: The emotion engine changes how it suggests products depending on the user's emotions.

[0387] Step 3: The emotion engine presents the suggested products to the user.

[0388] "Example 3"

[0389] Step 1: The emotion engine records the user's emotion and current product selection.

[0390] Step 2: The emotion engine learns the user's emotional changes and product selection trends.

[0391] Step 3: The emotion engine reflects its learning results in product recommendations.

[0392] Example 1

[0393] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0394] Conventional apparel product recommendation systems have had problems with suggesting products that match a user's preferences and size, and are unable to make suggestions that take the user's emotions into account. Furthermore, there were no systems that could automatically determine the user's age and size using photos submitted by the user, or suggest products that correspond to their emotions. This led to issues such as lower user satisfaction and a decrease in purchasing motivation.

[0395] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0396] In this invention, the server includes: means for constantly connecting apparel product data, the latest fashion trend information, and an artificial intelligence API and training the API based on the information; means for receiving photos from a user via a messenger app and automatically determining the user's age and size using the API; means for automatically suggesting products within the user's desired budget and providing a link to purchase the products; means for analyzing text information in messages from users and including an emotion engine for determining their emotions; and means for suggesting products according to the user's emotions based on the analysis results of the emotion engine. This makes it possible to suggest products that match the user's preferences and sizes, and further makes suggestions that take the user's emotions into consideration, thereby improving user satisfaction and increasing their willingness to purchase.

[0397] "Apparel product data" refers to product information obtained from the product database of an online shopping site, and includes information such as product images, prices, sizes, materials, and brands.

[0398] "Latest fashion trend information" is information obtained from fashion magazines and websites, and includes information on the latest trends, celebrity styles, seasonal styles, and the like.

[0399] An "artificial intelligence API" is a program interface that has the ability to learn from apparel product data and the latest fashion trend information and suggest the best products to users.

[0400] A "messenger app" is application software that allows users to send text messages and photos.

[0401] The "emotion engine" is a program that analyzes the text information of messages from users and determines their emotions.

[0402] A "product purchase link" is a link to a web page that allows a user to purchase the suggested product.

[0403] "Automatic determination of user age and size" refers to the process by which an artificial intelligence API automatically determines a user's age and size using a photo provided by the user.

[0404] "Automatically suggesting products within a budget" is a process in which an artificial intelligence API automatically suggests the most suitable products within a user's desired budget range.

[0405] "Emotion-based product suggestions" is a process in which an artificial intelligence API suggests products that suit the user's emotions based on the analysis results of the emotion engine.

[0406] The present invention is a system for proposing optimal products to users based on apparel product data and the latest fashion trend information. A specific embodiment of this system will be described below.

[0407] System configuration

[0408] server

[0409] The server accesses the product database of the online shopping site and collects apparel product data. Specifically, it obtains information such as product images, prices, sizes, materials, and brands. The server also collects the latest fashion trends from fashion magazines and websites, obtaining information on the latest trends, celebrity styles, and seasonal styles. This data is provided to the AI ​​API.

[0410] Artificial intelligence API

[0411] The AI ​​API learns from apparel product data and the latest fashion trend information provided by the server. The API has the ability to suggest products that match the user's preferences and size. Specifically, it integrates product data and trend information, performs trend analysis, and builds a personalized model taking into account the user's past purchase history and preferred style.

[0412] Emotion Engine

[0413] The emotion engine analyzes the text information in messages from users and determines their emotions. For example, if a user sends a message saying, "I'm feeling good today," the emotion engine will determine from that message that the user's emotion is "joy." This information influences the selection of products the AI ​​API recommends to users.

[0414] Terminal

[0415] The device receives messages and photos from users and sends them to a server and emotion engine. When a user sends a photo through a messenger app, the device sends the photo to a server, where an AI API automatically determines the user's age and size. It also sends text messages from users to the emotion engine for emotion analysis.

[0416] Specific examples

[0417] Example 1: Collecting apparel product data

[0418] The server collects the following data from the online shopping site:

[0419] Product image: Image of red dress

[0420] Price: 10,000 yen

[0421] Size:M

[0422] Material: Cotton

[0423] Brand: XYZ

[0424] Example 2: Gathering the latest fashion trends

[0425] The server collects the following information from the fashion magazine:

[0426] The latest trend: oversized jackets

[0427] Celebrity Style: Styles worn by famous model A

[0428] Seasonal style: Autumn casual style

[0429] Example 3: Emotion Engine Analysis

[0430] If a user sends a message saying, "I'm in a good mood today," the emotion engine will interpret this as "joy." Based on this information, the AI ​​API will suggest products with bright colors and casual styles.

[0431] Prompt Sentence Examples

[0432] "Based on the latest fashion trends and apparel product data, suggest products that fit the user's preferences and sizes. Also, adjust the suggestions based on the user's emotions."

[0433] By inputting this prompt sentence into a generative AI model, a system can be created that makes optimal product suggestions to users.

[0434] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0435] Step 1:

[0436] The server accesses the product database of the online shopping site and collects apparel product data. Specifically, it obtains information such as product images, prices, sizes, materials, and brands. This data is stored in the server's database. The input is the product database of the online shopping site, and the output is the apparel product data stored in the server's database.

[0437] Step 2:

[0438] The server collects the latest fashion trend information from fashion magazines and websites. Specifically, it obtains information on the latest trends, celebrity styles, seasonal styles, etc. This data is also stored in the server's database. The input is fashion magazines and websites, and the output is the latest fashion trend information stored in the server's database.

[0439] Step 3:

[0440] The server provides the collected apparel product data and the latest fashion trend information to the AI ​​API. The AI ​​API learns based on this data. Specifically, it integrates the product data and trend information and performs trend analysis. The input is the apparel product data stored in the server's database and the latest fashion trend information, and the output is a trained AI model.

[0441] Step 4:

[0442] A user sends a photo through a messenger app. The device receives the photo and sends it to the server. The server automatically determines the user's age and size using an artificial intelligence API. The input is the photo sent by the user, and the output is the determined age and size.

[0443] Step 5:

[0444] A user sends a text message through a messenger app. The device receives the message and sends it to the emotion engine. The emotion engine analyzes the text information of the message and determines its emotion. The input is the text message sent by the user, and the output is the determined emotion.

[0445] Step 6:

[0446] The AI ​​API suggests optimal products to users based on the analysis results of the emotion engine and learning data. Specifically, it selects products based on the user's emotions. The input is the determined emotion and the trained AI model, and the output is a list of suggested products.

[0447] Step 7:

[0448] The terminal displays the product suggestions received from the AI ​​API to the user. The user reviews the suggested products and decides whether to purchase them. The input is the list of suggested products, and the output is the user's purchase decision.

[0449] (Application example 1)

[0450] Next, a description will be given of Application Example 1 of Embodiment Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0451] Conventional apparel product recommendation systems have had the problem of low user satisfaction because they do not adequately consider the user's preferences and emotions when making product recommendations. In addition, there is a lack of technology to make product recommendations based on the user's emotions and preferences, making it difficult to increase the user's purchasing motivation.

[0452] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes means for constantly connecting apparel product data, the latest fashion trend information, and an artificial intelligence API and for training the API based on the information, means for receiving photos from a user via a messenger app and automatically determining the user's age and size using the API, means for automatically suggesting products within the user's desired budget and providing a link to purchase the products, means for analyzing the user's emotions and suggesting products based on the emotions, and means for suggesting products based on the user's preferences and style. This enables optimal product suggestions based on the user's emotions and preferences.

[0453] "Apparel product data" refers to product information obtained from the product database of an online shopping site, such as product images, prices, sizes, materials, brands, etc.

[0454] "Latest fashion trend information" refers to information obtained from fashion magazines and websites, such as the latest trends, celebrity styles, and seasonal styles.

[0455] The "artificial intelligence API" is an artificial intelligence application programming interface that has the ability to learn from apparel product data and the latest fashion trend information, and suggest products that suit the user's preferences and sizes.

[0456] A "messenger app" is a communication application that allows users to send text messages and photos.

[0457] "Means for automatically determining a user's age and size" refers to technology that analyzes photos sent by users and automatically determines their age and body size using an artificial intelligence API.

[0458] The "means for automatically suggesting products within a budget and providing links to purchase the products" is a technology that suggests optimal products within a user's desired budget range and provides links to purchase the products.

[0459] "Means for analyzing a user's emotions and suggesting products based on those emotions" refers to a technology that analyzes the text information in a message from a user, determines the emotion, and suggests products according to the emotion.

[0460] "Means for suggesting products based on the user's preferences and style" refers to a technology that suggests optimal products based on information about the user's preferences and style.

[0461] A system for implementing this invention is configured as follows: First, a server constantly connects to apparel product data and the latest fashion trend information, and trains an artificial intelligence (AI) API based on this information. The apparel product data is product information obtained from a product database on an online shopping site, and specifically includes information such as product images, prices, sizes, materials, and brands. The latest fashion trend information is information obtained from fashion magazines and websites, and specifically includes information such as the latest trends, celebrity styles, and seasonal styles.

[0462] Users send photos to the server via a messenger app. The server automatically determines the user's age and size using an AI API. It then automatically suggests products that fit the user's preferences and budget, and provides a link to purchase the products. This allows users to easily find and purchase products that suit them.

[0463] The server also incorporates an emotion engine that analyzes the text information in messages from users and determines their emotions. For example, if a user sends a message saying, "I'm feeling good today," the emotion engine determines from the message that the user's emotion is "joy." Based on this emotion, the server suggests the most suitable product for the user.

[0464] Furthermore, the server will suggest products based on the user's preferences and style. When the user inputs their favorite style and brand, the server will suggest the most suitable products based on that information. This allows users to easily find products that suit their tastes.

[0465] For example, if a user inputs "I'm feeling good today" and selects "casual" as their preferred style, the server will suggest products that are casual in style. If a user sends a request such as "I want something that looks like a celebrity," the server can also suggest products that meet that request.

[0466] An example of a prompt is as follows:

[0467] "How are you feeling today?"

[0468] "Please tell us your favorite styles and brands."

[0469] In this way, it becomes possible to propose optimal products based on the user's feelings and preferences.

[0470] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0471] Step 1:

[0472] The server obtains apparel product data and the latest fashion trend information. Specifically, the server obtains information such as product images, prices, sizes, materials, and brands from the product database of online shopping sites, and information such as the latest trends, celebrity styles, and seasonal styles from fashion magazines and websites. This data is input into an AI API for learning. The input is product data and trend information, and the output is a trained AI model.

[0473] Step 2:

[0474] Users send photos to a server via a messenger app. The server inputs the received photos into an AI API, which automatically determines the user's age and size. Specifically, image analysis technology is used to extract the user's physical features and estimate their age and size. The input is the user's photo, and the output is the estimated age and size.

[0475] Step 3:

[0476] Users input their desired budget through a messenger app. The server then suggests optimal products based on the user's age, size, and budget. Specifically, it uses an AI model to search a database for products that match the user's criteria and generates a link to purchase the product. The input is the user's age, size, and budget, and the output is a product suggestion and a link to purchase.

[0477] Step 4:

[0478] A user sends a text message through a messenger app. The server uses an emotion engine to analyze the text information in the message and determine the user's emotion. Specifically, it uses natural language processing technology to extract emotion from the text and suggests products based on that emotion. The input is the user's text message, and the output is the emotion determination result and product suggestions.

[0479] Step 5:

[0480] Users input their preferred style and brand through the messenger app. The server then suggests the best products based on the user's preferences and style. Specifically, it uses an AI model to search a database for products that match the user's preferences and makes product suggestions. The input is the user's preferences and style information, and the output is product suggestions.

[0481] Step 6:

[0482] The server will suggest products based on user requests, such as "something that looks like a celebrity." Specifically, it uses an AI model to search a database for products that match the request and make product suggestions. The input is the user request, and the output is product suggestions.

[0483] Example 2

[0484] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0485] Conventional apparel product recommendation systems have had issues with accurately determining a user's age and size, and are unable to suggest products that reflect the user's emotions. Furthermore, they are unable to suggest products within a user's budget based on their preferences, or to change the suggestion method based on their emotions, making it difficult to increase user satisfaction.

[0486] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for constantly connecting apparel product data, the latest fashion trend information, and an artificial intelligence API and training the API based on the information; means for receiving photos from users via a messenger app and automatically determining the user's age and size using the API; means for analyzing the user's emotions and changing the product recommendation method based on the analysis results; and means for automatically suggesting products within the user's desired budget and providing a product purchase link. This makes it possible to accurately determine the user's age and size and suggest products based on their emotions. Furthermore, product recommendations within the user's desired budget and the ability to change the recommendation method based on emotions can increase user satisfaction.

[0487] "Apparel product data" refers to data that includes information about fashion items such as clothing and accessories.

[0488] "Latest fashion trend information" refers to information about styles and designs that are popular in the current market.

[0489] An "artificial intelligence API" is a program interface that provides functions such as image analysis and natural language processing.

[0490] A "messenger app" is a software application that allows users to send and receive messages and photos.

[0491] "Means for automatically determining a user's age and size" refers to technology that analyzes photos sent by users and estimates their age and body type.

[0492] "Means for analyzing user emotions" refers to technology that reads emotions from users' messages and photos and responds appropriately based on those emotions.

[0493] The "means for changing the method of product proposal" is a technology for adjusting the type and design of the proposed products according to the user's emotions and desires.

[0494] The "means for providing a product purchase link" is a technique for providing a web link for a user to purchase the suggested product.

[0495] MODE FOR CARRYING OUT THE INVENTION

[0496] This invention is a system that allows a user to send a full-body photo of themselves via a messenger app, analyzes the photo to determine the user's age and size, and then suggests appropriate products based on the user's emotions. A specific embodiment of this system will be described below.

[0497] Hardware and software used

[0498] This system uses the following hardware and software:

[0499] Hardware: Server, user device (smartphone, PC)

[0500] Software: Messenger apps (e.g., WhatsApp, Facebook Messenger), artificial intelligence APIs (e.g., Google Cloud Vision API, Amazon Rekognition), emotion engines (e.g., IBM Watson® Tone Analyzer)

[0501] Data processing and calculation

[0502] 1. User photo submission:

[0503] Users take a full-body photo with their smartphone or computer camera and upload it to a messenger app. The user opens the messenger app, takes a full-body photo using the photo-taking function, and presses the send button to send the photo.

[0504] 2. Photo reception by server:

[0505] The server receives the user's photos sent from the messenger app and temporarily stores them. The server receives the photo data through the messenger app's API and stores it in a database.

[0506] 3. Age and size determination using AI API:

[0507] The server sends the stored photos to an AI API, which automatically determines the user's age and size from the photos. The server sends the photo data to the AI ​​API and receives the analysis results returned from the API. For example, the API estimates the user's height, weight, and age and returns the results to the server.

[0508] 4. Sentiment analysis using emotion engine:

[0509] The server uses an emotion engine to analyze the user's emotions. The server sends the user's message data to the emotion engine and receives the emotion analysis result returned from the emotion engine. For example, the emotion engine determines emotions such as "joy" or "sadness" from the user's message.

[0510] 5. Product suggestion:

[0511] The server recommends appropriate products to users based on information obtained from the AI ​​API and emotion engine. The server selects appropriate products from the product database based on the user's age, size, and emotion. For example, if the user's emotion is "joy," it selects and recommends products in bright colors to the user.

[0512] Specific examples

[0513] If a user sends a full-body photo with the message "I'm so happy today!", the server sends the photo to an AI API to determine the user's age and size. At the same time, it uses an emotion engine to determine the user's emotion as "joy." As a result, the server selects products with bright colors and suggests them to the user.

[0514] Prompt Sentence Examples

[0515] An example of a prompt sentence to be input to the generative AI model is shown below.

[0516] Prompt statement:

[0517] "A user sends a full-body photo through a messaging app. Analyze this photo to determine the user's age and size, and then suggest appropriate products based on the user's emotions. If the user's emotions are happy, suggest products with bright colors, and if the user's emotions are sad, suggest products with muted colors."

[0518] Using this prompt, the generative AI model can make appropriate product suggestions based on the user's photo and emotions.

[0519] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0520] Step 1:

[0521] A user takes a full-body photo with the camera on their smartphone or computer and uploads it to a messenger app. The user opens the messenger app, takes a full-body photo using the photo capture function, and presses the send button to send the photo. The input is the user's full-body photo, and the output is the photo data sent to the server via the messenger app.

[0522] Step 2:

[0523] The server receives the user's photos sent from the messenger app and temporarily stores them. The server receives the photo data through the messenger app's API and stores it in a database. The input is the photo data sent from the messenger app, and the output is the photo data stored on the server.

[0524] Step 3:

[0525] The server sends the stored photos to an AI API, which automatically determines the user's age and size from the photos. The server then sends the photo data to the AI ​​API and receives the analysis results returned from the API. For example, the API estimates the user's height, weight, and age and returns the results to the server. The input is the photo data stored on the server, and the output is the age and size analysis results returned from the AI ​​API.

[0526] Step 4:

[0527] The server uses an emotion engine to analyze the user's emotions. The server sends the user's message data to the emotion engine and receives the emotion analysis results returned from the emotion engine. For example, the emotion engine determines emotions such as "joy" or "sadness" from the user's message. The input is the user's message data, and the output is the emotion analysis results returned from the emotion engine.

[0528] Step 5:

[0529] The server recommends appropriate products to users based on information obtained from the AI ​​API and emotion engine. The server selects appropriate products from the product database based on the user's age, size, and emotion. For example, if the user's emotion is "joy," it selects products in bright colors and recommends them to the user. The input is the age and size analysis results and emotion analysis results, and the output is product information recommended to the user.

[0530] (Application example 2)

[0531] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0532] Conventional online shopping systems have difficulty suggesting appropriate products based on the user's body shape and size, and do not offer personalized suggestions based on the user's emotions. As a result, users have to spend a lot of time finding products that suit them, which leads to a decrease in satisfaction.

[0533] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0534] In this invention, the server includes means for constantly connecting apparel product data, the latest fashion trend information, and an artificial intelligence API and training the API based on the information, means for receiving photos from users via a messenger app and automatically determining the user's age and size using the API, means for analyzing the user's emotions and changing the product recommendation method based on the analysis results, means for automatically suggesting products within the user's desired budget and providing a link to purchase the products, and means for suggesting fashion items based on the user's photos and emotions using a generative AI model, thereby enabling personalized product recommendations based on the user's body type and emotions.

[0535] "Apparel product data" refers to data that includes information about fashion items such as clothing and accessories.

[0536] "Latest fashion trend information" refers to information about styles and designs that are popular in the current market.

[0537] An "artificial intelligence API" is a program interface for performing machine learning and data analysis.

[0538] A "messenger app" is an application that allows users to send and receive text messages and images.

[0539] "Means for automatically determining a user's age and size" refers to technology that analyzes photos sent by users and automatically estimates their age, body type, and size.

[0540] "Means for analyzing user emotions" refers to technology that reads emotions from a user's photos and text and analyzes those emotions.

[0541] The "means for changing the method of product suggestion" is a technique for changing the type and style of products suggested in accordance with the user's emotions.

[0542] A "generative AI model" is an artificial intelligence model used to suggest the most suitable fashion items based on a user's photos and emotions.

[0543] The "means for providing a product purchase link" is a technique for providing a link for a user to purchase a suggested product.

[0544] "Fashion items" are fashion-related products such as clothing, accessories, and shoes.

[0545] The system for implementing this invention is configured as follows: First, a user takes a full-body photo of themselves using a messenger app on their smartphone and uploads it to the app. The server receives the photo and automatically determines the user's age and size using an artificial intelligence API.

[0546] Next, the server uses an emotion analysis engine to analyze the user's emotions from the photo. This emotion analysis engine reads emotions from the user's facial expressions and posture, and changes the way it suggests products based on the results. For example, if the user expresses "joy," it will suggest products with bright colors and pop designs. On the other hand, if the user expresses "sadness," it will suggest products with muted colors and simple designs.

[0547] The server then uses a generative AI model to suggest fashion items based on the user's photo and emotions. The generative AI model then selects and recommends fashion items that best fit the user's body type and emotions. The suggested products are automatically selected within the user's desired budget, and a link to purchase the products is provided.

[0548] The specific hardware used is a smartphone (with a camera), and the software used is OpenCV (image processing library), EmotionRecognizer (emotion analysis library), SizeEstimator (size estimation library), and FashionRecommender (fashion item recommendation library).

[0549] For example, if a user takes a full-body photo with their smartphone and uploads it to the app, the server analyzes the photo and determines that the user's body size is "medium" and their emotion is "joy." The server then suggests medium-sized fashion items in bright colors and provides a link to purchase the items.

[0550] An example prompt is, "Analyze a full-body photo of the user and suggest the best fashion items based on their size and emotions."

[0551] In this way, personalized fashion suggestions based on the user's photos and emotions become possible.

[0552] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0553] Step 1:

[0554] A user takes a full-body photo of themselves using a messenger app on their smartphone and uploads it to the app. The input is the user's full-body photo, and the output is image data sent to the server.

[0555] Step 2:

[0556] The server receives the user's full-body photo from the messenger app. The input is the image data sent by the user, and the output is the image data ready for image analysis.

[0557] Step 3:

[0558] The server automatically determines the user's age and size using an artificial intelligence API. The input is a full-body photo of the user, and the output is an estimate of the user's age and size. Specifically, an image analysis algorithm is used to analyze the user's body shape and facial features to estimate age and size.

[0559] Step 4:

[0560] The server uses an emotion analysis engine to analyze emotions from the user's photo. The input is a full-body photo of the user, and the output is the analysis result of the user's emotions. Specifically, it uses facial expression recognition technology to read emotions from the user's facial expressions.

[0561] Step 5:

[0562] The server changes the product suggestion method based on the analysis results. The input is the analysis results of the user's age, size, and emotion, and the output is a list of suggested products. Specifically, it selects products in bright or subdued colors depending on the user's emotion.

[0563] Step 6:

[0564] The server uses a generative AI model to suggest fashion items based on the user's photo and emotions. The input is the analysis result of the user's age, size, and emotions, and the output is a list of fashion items that are best suited to the user. Specifically, the generative AI model selects fashion items that are best suited to the user's body type and emotions.

[0565] Step 7:

[0566] The server automatically suggests products that fit the user's budget and provides a link to purchase the products. The input is the user's budget information and a list of suggested products, and the output is a link to purchase the products. Specifically, the server selects products that fit the user's budget and generates a purchase link.

[0567] Step 8:

[0568] The user checks the suggested products and the provided purchase links and purchases the products as needed. The input is the product purchase link provided by the server, and the output is the user's purchase action. Specifically, the user clicks on the link to purchase the product.

[0569] Example 3

[0570] Next, a third embodiment of the third embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0571] Conventional apparel product recommendation systems do not adequately suggest products based on the user's preferences and budget. Furthermore, they are unable to consider changes in the user's emotions when making suggestions, making it difficult to increase user satisfaction. Furthermore, there is a lack of technology to accurately analyze user input and suggest appropriate products. To solve these issues, a system is needed that can accurately analyze the user's preferences and budget and make product suggestions that take emotional changes into account.

[0572] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0573] In this invention, the server includes means for constantly connecting apparel product data, the latest fashion trend information, and an artificial intelligence API and training the API based on the information, means for receiving text input from a user through a messaging application and analyzing the user's preferences and budget using the API, means for using an emotion engine that learns from the user's past emotional data and adjusts suggestions, and means for automatically suggesting products within the user's preferences and budget and providing a link to purchase the products. This enables accurate product suggestions based on the user's preferences and budget, and further increases user satisfaction by making suggestions that take into account changes in the user's emotions.

[0574] "Apparel product data" is a database containing information on fashion-related products such as clothing and accessories.

[0575] "Latest fashion trends" refers to information about styles and trends that are popular in the current market.

[0576] An "artificial intelligence API" is an application programming interface for utilizing artificial intelligence technologies such as machine learning and natural language processing.

[0577] A "messaging application" is software that allows users to send and receive text messages.

[0578] "Text input" refers to a string of characters that a user enters using a keyboard or touch screen.

[0579] "Natural language processing technology" is a technology that allows computers to understand and analyze human language.

[0580] An "emotion engine" is an algorithm or software that analyzes and learns from users' emotional data.

[0581] A "product purchase link" is a hyperlink to a web page for purchasing a particular product.

[0582] "User's wishes" are requests regarding the type and features of the product that the user wants to purchase.

[0583] The "budget" is the upper limit of the amount set by the user for purchasing products.

[0584] This invention is a system that suggests suitable products based on the user's preferences and budget and provides links to purchase them. The system constantly connects apparel product data, the latest fashion trend information, and an artificial intelligence API, analyzes user input, and adjusts suggestions using an emotion engine.

[0585] The server has a database that manages apparel product data and the latest fashion trend information. This database is built using a cloud service, and can use, for example, a general cloud database service. The server uses an artificial intelligence API to learn from this data. A general natural language processing API can be used as the artificial intelligence API.

[0586] Users access the system using a terminal and input the type of product they want and their budget in text format. For example, they might input, "I want casual clothes, my budget is 5,000 yen." The server receives this input and analyzes it using natural language processing technology. Specifically, it uses a common natural language processing API to extract the user's preferences and budget.

[0587] The server then searches a product database based on the analysis results, extracting and listing products that match the user's preferences and budget. This search can be performed using common database query techniques.

[0588] Furthermore, the server uses an emotion engine to learn the user's past emotion data. A general machine learning framework can be used for this learning. The emotion engine analyzes changes in the user's emotion and reflects them in the next recommendation. For example, if the server learns that the user tends to select sportswear whenever the user expresses the emotion "joy," the emotion engine will suggest sportswear the next time the user expresses the emotion "joy."

[0589] Finally, the server generates a purchase link for the selected product and provides it to the user, which is a direct link to an online shopping site, and the user can click the link using their terminal to purchase the product.

[0590] As a concrete example, if a user inputs "I want casual clothes, my budget is 5000 yen," the server will process it as follows:

[0591] 1. The server uses a natural language processing API to extract "casual clothes" and "5,000 yen."

[0592] 2. The server searches the product database and extracts casual clothing items priced under 5,000 yen.

[0593] 3. The server uses an emotion engine to learn the user's past emotion data and adjust the suggestions.

[0594] 4. The server generates a purchase link for the selected product and provides it to the user.

[0595] Example prompt sentence:

[0596] User: I want casual clothes, my budget is 5000 yen

[0597] Server: I found the following casual outfits within my budget. Here are the links to buy them:

[0598] Product A: [Purchase Link]

[0599] Product B: [Purchase Link]

[0600] Product C: [Purchase Link]

[0601] In this way, the system proposes products that meet the user's desires and provides a link to purchase them. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0602] Step 1:

[0603] A user accesses the system using a terminal and inputs the type of product they want and their budget in text format. For example, they might input "I want casual clothes, my budget is 5,000 yen." The input data is sent to the server.

[0604] Input: User's preferences and budget (e.g., "I want casual clothes, my budget is 5,000 yen")

[0605] Output: Text data sent to the server

[0606] Step 2:

[0607] The server analyzes the received text data using natural language processing technology. Specifically, it uses a natural language processing API to extract the user's preferences and budget. The server then performs the following processes based on the extracted keywords:

[0608] Input: Text data sent by the user

[0609] Output: Extracted keywords (e.g., "casual clothes", "5000 yen")

[0610] Specific behavior:

[0611] The server sends the text data to a natural language processing API.

[0612] Natural language processing APIs analyze text and return important keywords.

[0613] The server performs the following process based on the returned keywords:

[0614] Step 3:

[0615] The server searches the product database based on the analysis results, extracts products that match the user's preferences and budget, and lists them. This search uses database query technology.

[0616] Input: Extracted keywords (e.g., "casual clothes," "5000 yen")

[0617] Output: List of products that match the conditions

[0618] Specific behavior:

[0619] The server generates an SQL query and sends it to the database.

[0620] The database returns a list of products that match the criteria.

[0621] The server temporarily stores the returned product list.

[0622] Step 4:

[0623] The server uses an emotion engine to learn the user's past emotion data. This learning is done using a machine learning framework. The emotion engine analyzes changes in the user's emotion and reflects them in the next suggestion.

[0624] Input: User's past emotional data

[0625] Output: Adjusted product list

[0626] Specific behavior:

[0627] The server transmits the user's past emotion data to the emotion engine.

[0628] The emotion engine learns from the data and provides feedback to adjust its suggestions.

[0629] The server adjusts the product listing based on the feedback.

[0630] Step 5:

[0631] The server generates a purchase link for the selected product and provides it to the user, which is a direct link to an online shopping site. The user can click the link using their terminal to purchase the product.

[0632] Input: Adjusted product list

[0633] Output: Product purchase link

[0634] Specific behavior:

[0635] The server generates a purchase link for each product.

[0636] The server sends the generated link to the user.

[0637] The user uses the terminal to click on the link and purchase the product.

[0638] (Application example 3)

[0639] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0640] Conventional online shopping systems have a function to suggest products based on the user's preferences and budget, but they do not consider the user's emotions or past purchase history. Therefore, to increase user satisfaction, more personalized product suggestions based on emotions and past data are needed.

[0641] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes means for constantly connecting apparel product data, the latest fashion trend information, and an artificial intelligence API and for training the API based on the information; means for receiving photos from a user via a messenger app and automatically determining the user's age and size using the API; means for automatically suggesting products within the user's desired budget and providing a link to purchase the products; and means for analyzing the user's emotions using an emotion engine and suggesting products based on the user's past purchase history and emotion data. This enables personalized product suggestions that take into account the user's emotions and past purchase history.

[0642] "Apparel product data" is a database containing information about clothing and fashion items.

[0643] "Latest fashion trends" refers to information about styles and trends currently popular in the fashion industry.

[0644] An "artificial intelligence API" is an application programming interface that uses artificial intelligence technology to provide specific functionality.

[0645] A "messenger app" is application software that allows users to send and receive text messages and images.

[0646] "Means for automatically determining a user's age and size" refers to technology that automatically determines a user's age and clothing size based on photos and data provided by the user.

[0647] "Means for automatically suggesting products within a budget and providing links to purchase the products" refers to a technology that selects appropriate products within a budget set by the user and provides links to the product's purchase page.

[0648] An "emotion engine" is software that analyzes a user's emotions and executes specific actions based on the results.

[0649] "Past purchase history" is a record of products previously purchased by a user.

[0650] "Emotion data" is information relating to the user's emotional state.

[0651] "Personalized product offers" are product offers that are customized based on a user's individual preferences and characteristics.

[0652] A system for implementing the present invention is configured as follows.

[0653] First, the server constantly connects to apparel product data and the latest fashion trend information, and uses an AI API to learn from this information, making it possible to suggest products based on the latest trends.

[0654] Next, the user sends a photo of themselves via a messaging app to the server, which analyzes the photo and uses an AI API to automatically determine the user's age and size. This information is then used to suggest the most suitable products for the user.

[0655] Furthermore, the user inputs the desired product category and budget. Based on this information, the server automatically suggests suitable products within the budget and provides a link to purchase those products. At this point, the emotion engine analyzes the user's emotions and suggests products based on past purchase history and emotional data. This emotion engine realizes personalized product suggestions that take into account the user's emotional state.

[0656] As a specific example, if a user inputs "I want casual clothes, my budget is 5,000 yen" and the emotion engine detects the emotion of "joy," the server will suggest casual clothing items within 5,000 yen that have been previously associated with the emotion of "joy."

[0657] An example of a prompt is as follows:

[0658] "Please enter your desired product category: Casual clothing"

[0659] "Please enter your budget: 5000"

[0660] In this way, it becomes possible to propose optimal products based on the user's wishes and feelings.

[0661] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0662] Step 1:

[0663] A user sends their own photo to the server through a messenger app. The input is the user's photo, and the output is the image data sent to the server. Specifically, the user takes a photo using the camera on their smartphone and uploads the image using the sending function of the messenger app.

[0664] Step 2:

[0665] The server analyzes the received photo and automatically determines the user's age and size using an artificial intelligence API. The input is the user's photo data, and the output is the user's age and size information. Specifically, the server runs an image analysis algorithm to perform facial recognition and body shape estimation.

[0666] Step 3:

[0667] The user inputs the desired product category and budget. The input is the product category and budget information, and the output is the desired data sent to the server. Specifically, the user enters information such as "casual clothes" or "5,000 yen" into the text input field of the messenger app and presses the send button.

[0668] Step 4:

[0669] The server automatically suggests appropriate products within the user's budget based on the product category and budget desired by the user. The input is the product category and budget information, and the output is a list of suggested products. Specifically, the server searches the apparel product database and extracts products that match the criteria.

[0670] Step 5:

[0671] The server uses an emotion engine to analyze the user's emotions and suggest products based on their past purchase history and emotional data. The input is the user's emotional data and past purchase history, and the output is product suggestions based on their emotions. Specifically, the server runs an emotion analysis algorithm to determine the user's emotional state.

[0672] Step 6:

[0673] The server provides the user with a purchase link for the suggested products. The input is a list of suggested products, and the output is a purchase link. Specifically, the server generates a purchase page URL for each product and sends it to the user via a messenger app.

[0674] Step 7:

[0675] The user clicks on the provided purchase link to purchase the product. The input is the purchase link, and the output is confirmation of purchase completion. Specifically, the user opens the browser on their smartphone, clicks on the link, and completes the purchase procedure.

[0676] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0677] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0678] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are listed.

[0679] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0680] [Second embodiment]

[0681] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0682] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0683] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0684] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0685] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0686] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0687] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0688] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0689] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0690] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0691] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0692] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0693] "Example 1"

[0694] The system of the present invention constantly connects apparel product data, the latest fashion trend information, and an AI API, and allows the API to learn based on this information. Specifically, the apparel product data uses product information obtained from a product database of an online shopping site, such as product images, price, size, material, brand, etc. The latest fashion trend information uses information obtained from fashion magazines and websites, such as the latest trends, celebrity styles, and seasonal styles. Based on this information, the AI ​​API learns and has the ability to suggest products that match the user's preferences and sizes.

[0695] "Example 2"

[0696] Users send their own photos through a messenger app. Specifically, users upload their full-body photos to the messenger app, and the system receives the photos. The system uses an artificial intelligence API to automatically determine the user's age and size from the photos. For example, if a user sends a full-body photo of themselves, the system analyzes the user's body shape and build from the photo and estimates the user's size based on that.

[0697] "Example 3"

[0698] The system automatically suggests products that fit the user's needs and are within their budget, and provides a link to purchase the products. Specifically, the user enters their preferences in the form of "I want clothes like this, and my budget is what." The system then suggests appropriate products based on those needs and budget. For example, if a user enters "I want casual clothes, and my budget is 5,000 yen," the system will suggest products that fit those conditions and provide a link to the product's purchase page.

[0699] The processing flow of each embodiment will be described below.

[0700] "Example 1"

[0701] Step 1: The system constantly connects apparel product data, the latest fashion trend information, and an AI API. Specifically, it uses product information obtained from the product database of the online shopping site, such as product images, price, size, material, brand, etc.

[0702] Step 2: For the latest fashion trend information, information obtained from fashion magazines and websites, such as the latest trends, celebrity styles, and seasonal styles, is used.

[0703] Step 3: Based on this information, the AI ​​API learns and has the ability to suggest products that match the user's preferences and sizes.

[0704] "Example 2"

[0705] Step 1: The user sends their photo through the messenger app. Specifically, the user uploads a full-body photo of themselves to the messenger app, and the system receives the photo.

[0706] Step 2: The system uses an artificial intelligence API to automatically determine the user's age and size from the photo. For example, if a user sends a full-body photo of themselves, the system will analyze the user's body shape and build from the photo and estimate the user's size based on that.

[0707] "Example 3"

[0708] Step 1: The system automatically suggests products that fit the user's needs and fit their budget, and provides a link to purchase the products. Specifically, the user inputs their needs in the form of "I want clothes like this, and my budget."

[0709] Step 2: The system suggests suitable products based on the user's preferences and budget. For example, if a user enters "I want casual clothes, my budget is 5,000 yen," the system suggests products that fit those criteria and provides a link to the product's purchase page.

[0710] Example 1

[0711] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0712] Conventional apparel product recommendation systems do not adequately suggest products based on the user's preferences and sizes. It is also difficult to suggest products that reflect the latest fashion trends, making it difficult to provide appropriate products that meet the user's needs. Furthermore, they are unable to adequately suggest products within the user's desired budget or based on celebrity-style styles. This leads to problems such as lower user satisfaction and a decrease in purchasing motivation.

[0713] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0714] In this invention, the server includes: means for constantly connecting apparel product data, the latest fashion trend information, and an artificial intelligence API and training the API based on the information; means for receiving input information from a user terminal and automatically suggesting products based on the user's preferences and size using the API; and means for displaying the suggested products on the user terminal and providing a link to purchase the products. This allows for product suggestions tailored to the user's preferences and size, and product suggestions that reflect the latest fashion trend information. It also allows for product suggestions within the user's desired budget and suggestions based on celebrity-style styles, improving user satisfaction and increasing purchasing motivation.

[0715] "Apparel product data" refers to product information obtained from the product database of an online shopping site, and specifically includes information such as product images, prices, sizes, materials, and brands.

[0716] "Latest fashion trend information" is information obtained from fashion magazines and websites, and specifically includes information on the latest trends, celebrity styles, seasonal styles, and the like.

[0717] An "artificial intelligence API" is an application programming interface that uses machine learning and deep learning to analyze data and perform specific tasks.

[0718] "User device" means a device used by a user to enter information or view suggested products, including, for example, a web browser or a mobile application.

[0719] "Product suggestion" refers to the act of selecting and presenting appropriate apparel products to a user based on the user's preferences, size, budget, and requests.

[0720] A "product purchase link" is a URL or button for purchasing the suggested product, which the user can click to go directly to the purchase page.

[0721] This invention is a system that uses an artificial intelligence API to suggest products that suit a user's preferences and sizes based on apparel product data and the latest fashion trend information. Specific embodiments of this system are described below.

[0722] Server Processing

[0723] The server first retrieves apparel product data from the product database of an online shopping site. This data includes information such as product images, prices, sizes, materials, and brands. Next, the server collects the latest fashion trend information from fashion magazines and websites. This involves using scraping technology to obtain information such as the latest trends, celebrity styles, and seasonal styles.

[0724] The collected data requires preprocessing. The server resizes and normalizes image data, tokenizes and vectorizes text data, and cleans the data by filling in missing values ​​and removing outliers.

[0725] The server uses the preprocessed data to train an artificial intelligence API. Specifically, it trains a neural network model using a machine learning framework such as TensorFlow or PyTorch. After training is complete, the server saves the trained model and makes it available as an API for inference.

[0726] Terminal handling

[0727] The device sends the information entered by the user to the server, specifically, to obtain the user's preferences and sizes through input fields in a web form or mobile app. The device sends the data, including the user's preferences and sizes, to the server using an HTTP request.

[0728] To display the product suggestions received from the server to the user, the device uses UI components of a web page or mobile app, displaying information such as images, prices, and brands of the suggested products to help the user select a product.

[0729] User operations

[0730] First, the user inputs their preferences and size into the device. For example, they might input information such as "I like casual styles and my size is medium." Then, the user checks the product suggestions displayed on the device. They check the images, prices, brands, and other information of the suggested products, and if they find one they like, they select it and proceed with the purchase. Specifically, they add the product to their shopping cart, enter their payment information, and complete the purchase.

[0731] Specific examples

[0732] If a user inputs "I like casual style, size M," the server will use this information to compare the latest fashion trend information with apparel product data and suggest casual style products in size M. For example, it will suggest "a denim jacket (price: 5,000 yen, brand: XYZ) that is trending this spring."

[0733] Prompt Sentence Examples

[0734] "Please suggest products that you would recommend to a user who likes casual style and wears size M."

[0735] By inputting this prompt into a generative AI model, product suggestions that match the user's preferences and size can be obtained.

[0736] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0737] Step 1:

[0738] The server retrieves apparel product data from the product database of the online shopping site. Specifically, it uses an API to collect information such as product images, prices, sizes, materials, and brands. The input is the API endpoint of the online shopping site, and the output is the retrieved apparel product data.

[0739] Step 2:

[0740] The server collects the latest fashion trend information from fashion magazines and websites. Specifically, it uses scraping technology to obtain information such as the latest trends, celebrity styles, and seasonal styles. The input is the URL of the fashion magazine or website, and the output is the collected fashion trend information.

[0741] Step 3:

[0742] The server preprocesses the collected data. Specifically, it resizes and normalizes image data, and tokenizes and vectorizes text data. It also performs data cleaning, such as filling in missing values ​​and removing outliers. The input is apparel product data and fashion trend information, and the output is the preprocessed data.

[0743] Step 4:

[0744] The server uses the preprocessed data to train an artificial intelligence API. Specifically, it uses machine learning frameworks such as TensorFlow or PyTorch to train a neural network model. The input is the preprocessed data, and the output is the trained model.

[0745] Step 5:

[0746] The server saves the trained model and exposes it as an API for inference. Specifically, it saves the model as a file and sets an API endpoint. The input is the trained model, and the output is the exposed API endpoint.

[0747] Step 6:

[0748] The device sends the information entered by the user to the server. Specifically, the user's preferences and sizes are acquired through input fields in a web form or a mobile app. The input is information about the user's preferences and sizes, and the output is an HTTP request to the server.

[0749] Step 7:

[0750] The server receives requests from users and performs inference using the trained model. Specifically, it suggests optimal products based on the user's preferences and size. The input is information about the user's preferences and size, and the output is suggested product information.

[0751] Step 8:

[0752] The terminal displays the product suggestions received from the server to the user. Specifically, it uses UI components of a web page or mobile app to display information such as images, prices, and brands of the suggested products. The input is the suggested product information, and the output is the product information displayed to the user.

[0753] Step 9:

[0754] The user checks the product suggestions displayed on the terminal, selects any products they like, and then completes the purchase. Specifically, they add the products to their shopping cart and enter payment information to complete the purchase. The input is the suggested product information and the user's payment information, and the output is confirmation of purchase completion.

[0755] (Application example 1)

[0756] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0757] Conventional apparel product recommendation systems have the problem that it is difficult to efficiently recommend products that match the user's preferences and sizes, and since users cannot actually try on the products, there are problems with low post-purchase satisfaction. Furthermore, it is difficult to reflect the latest fashion trend information in real time, and it is not possible to respond quickly to user needs.

[0758] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0759] In this invention, the server includes means for constantly connecting apparel product data, the latest fashion trend information, and an artificial intelligence API and for training the API based on the information, means for allowing a user to walk around the virtual store using a smartphone or head-mounted display and for using the API to suggest products that suit the user's preferences and size, and means for scanning the user's body shape data and using the API to suggest clothes in the optimal size. This allows the user to actually try on products in the virtual store and makes it possible to suggest products based on the latest fashion trend information.

[0760] "Apparel product data" refers to product information obtained from the product database of an online shopping site, and specifically includes information such as product images, prices, sizes, materials, and brands.

[0761] "Latest fashion trend information" is information obtained from fashion magazines and websites, and specifically includes information on the latest trends, celebrity styles, seasonal styles, and the like.

[0762] The "artificial intelligence API" is an artificial intelligence application programming interface that has the ability to learn from apparel product data and the latest fashion trend information, and suggest products that suit the user's preferences and sizes.

[0763] A "smartphone" is a type of mobile phone and a multi-function device that can connect to the Internet and install applications.

[0764] A "head-mounted display" is a display device that the user wears on their head, and is a device that provides virtual reality and augmented reality experiences.

[0765] A "virtual store" is a virtual store that exists on the Internet and provides an environment where users can browse and purchase products online.

[0766] "Body type data" refers to information about the user's body dimensions and shape, and specifically includes data such as height, weight, chest circumference, waist circumference, and hip circumference.

[0767] A "product purchase link" is a web link that allows a user to purchase the suggested product online.

[0768] The system for implementing this invention constantly connects apparel product data and the latest fashion trend information, and uses an artificial intelligence (AI) API to suggest products that match the user's preferences and sizes. A specific embodiment of this system is described below.

[0769] System Configuration

[0770] Hardware

[0771] Server: Hosts the database and AI models and provides APIs.

[0772] User device: Use a smartphone or head-mounted display (HMD).

[0773] software

[0774] TensorFlow: Used for training and inference of AI models.

[0775] OpenCV: Used for image processing.

[0776] PIL (Python Imaging Library): Used for image manipulation.

[0777] Requests: Used for API communication.

[0778] Data acquisition and processing

[0779] Acquiring apparel product data

[0780] The server retrieves product information from the product database of the online shopping site, including product images, prices, sizes, materials, brands, etc.

[0781] Get the latest fashion trends

[0782] The server retrieves the latest trend information from fashion magazines and websites, including celebrity styles and seasonal styles.

[0783] AI model training and inference

[0784] The server uses TensorFlow to train an AI model based on the acquired apparel product data and the latest fashion trend information. The trained AI model is then able to suggest products that match the user's preferences and sizes.

[0785] User Interface

[0786] Use of virtual stores

[0787] Users can walk around the virtual store using their smartphone or HMD, and AI will scan their body data and suggest clothes that fit them best.

[0788] Product suggestions and purchase links

[0789] Once a user selects an item in the virtual store, the AI ​​will suggest the best fit based on the user's preferences and size, and provide a link to purchase the suggested item online.

[0790] Specific examples

[0791] For example, users can use their smartphone camera to scan their body shape, and the app will use that data to suggest clothing that best suits them. They can also use an HMD to walk around a virtual store and try on outfits suggested by AI.

[0792] Prompt Sentence Examples

[0793] Develop an application that scans the user's body data and suggests the best apparel products based on the latest fashion trends. Users can walk around a virtual store using their smartphone or HMD and try on outfits suggested by AI.

[0794] In this way, by providing a concrete form for implementing the invention, users can actually try on products in a virtual store, making it possible to receive product suggestions based on the latest fashion trends.

[0795] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0796] Step 1:

[0797] The server retrieves apparel product data from the product database of the online shopping site. Specifically, it retrieves information such as product images, prices, sizes, materials, and brands through the API. The input is the API request, and the output is a list of product data.

[0798] Step 2:

[0799] The server retrieves the latest fashion trend information from fashion magazines and websites. Specifically, it retrieves information such as the latest trends, celebrity styles, and seasonal styles through scraping or API. The input is the scraping script or API request, and the output is a list of trend information.

[0800] Step 3:

[0801] The server uses TensorFlow to train an AI model based on the acquired apparel product data and the latest fashion trend information. The input is product data and trend information, and the output is a trained AI model. Specific operations include data preprocessing, model training, and evaluation.

[0802] Step 4:

[0803] The user walks around the virtual store using a smartphone or a head-mounted display. The smartphone camera and the HMD sensor are used to scan the user's body shape data. The input is the user's body shape data, and the output is the scanned body shape data.

[0804] Step 5:

[0805] The server receives the scanned body data and uses an AI model to suggest products that match the user's preferences and size. The input is the body data and the trained AI model, and the output is a list of suggested products. Specific operations include analyzing the body data, estimating the user's preferences, and suggesting products.

[0806] Step 6:

[0807] The user tries on suggested products in a virtual store. The virtual try-on is performed using a smartphone or HMD. The input is a list of suggested products, and the output is feedback on the tried-on products. Specific operations include product selection, virtual try-on, and feedback.

[0808] Step 7:

[0809] The server provides a product purchase link for the product selected by the user. The input is the product selected by the user, and the output is the product purchase link. Specific operations include generating a purchase link and providing the link to the user.

[0810] In this manner, detailed procedures for carrying out the invention are provided by describing the specific operations performed at each processing step.

[0811] Example 2

[0812] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0813] Conventional apparel product recommendation systems have had problems such as difficulty in accurately determining a user's age and size, and insufficient product recommendations that meet the user's needs.Furthermore, there have been issues with the accuracy of analyzing photos submitted by users, resulting in low suitability of the products suggested.

[0814] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0815] In this invention, the server includes means for constantly connecting apparel product data, the latest fashion trend information, and an artificial intelligence API and training the API based on the information, means for receiving photos from a user via a messenger app and automatically determining the user's age and size using the API, means for automatically suggesting products within the user's desired budget and providing a link to purchase the products, means for saving photos sent by the user and sending them to the artificial intelligence API to receive analysis results, and means for estimating the user's age and size based on the analysis results, thereby enabling accurate determination of the user's age and size and suggesting products that meet the user's desires.

[0816] "Apparel product data" refers to data that includes information about fashion items such as clothing and accessories.

[0817] "Latest fashion trends" refers to information about styles and trends currently popular in the fashion industry.

[0818] An "artificial intelligence API" is a programming interface for image and data analysis that uses machine learning algorithms to perform specific tasks.

[0819] A "messenger app" is a software application that enables users to send and receive text messages and images.

[0820] "Means for automatically determining a user's age and size" is a function that uses an artificial intelligence API to analyze and estimate a user's age, body shape, and build from photos sent by the user.

[0821] A "purchase link" is a URL or hyperlink that allows a user to purchase a suggested product online.

[0822] The "means for saving photos" is a function for temporarily or permanently saving photos sent by users in storage.

[0823] "Means for receiving analysis results" refers to the function by which the server receives analysis results from the artificial intelligence API.

[0824] "Means for estimating age and size" is a function that estimates the user's age, body shape, and build based on the analysis results of an artificial intelligence API.

[0825] The present invention is a system that analyzes photos sent by a user via a messenger app, automatically determines the user's age and size, and suggests appropriate apparel products. Specific embodiments of this system are described below.

[0826] System configuration

[0827] The system consists of the following main components:

[0828] 1. Messenger app: A software application that allows users to send photos. Examples include WhatsApp and Facebook Messenger.

[0829] 2. Server: A central processing unit that receives, stores, and sends photos to the AI ​​API. The server uses storage services such as Amazon S3 and Google Cloud Storage.

[0830] 3. Artificial Intelligence API: A programmatic interface for analyzing photos to determine a user's age and size. Examples include Google Cloud Vision API and Amazon Rekognition.

[0831] System Operation

[0832] 1. User submits a photo

[0833] Users can send their full-body photos using the Messenger app by tapping the "Send Photo" button within the app and selecting a full-body photo from their camera roll.

[0834] 2. The device uploads the photo to the server.

[0835] The device uploads the photo selected by the user to the server by sending the photo data to the server as an HTTP POST request.

[0836] 3. The server stores the photos

[0837] The server stores the received photos in temporary storage (e.g., Amazon S3, Google Cloud Storage), and records the photo file names and paths in a database.

[0838] 4. The server sends the photo to the AI ​​API

[0839] The server sends the saved photo to an artificial intelligence API (e.g., Google Cloud Vision API, Amazon Rekognition). The server creates an API request and sends it along with the photo data.

[0840] 5. Artificial intelligence API analyzes photos

[0841] The AI ​​API analyzes the received photos to estimate the user's age, body type, and build. The API uses image analysis algorithms to analyze facial features and body proportions.

[0842] 6. The server receives the analysis results

[0843] The server receives the analysis results from the AI ​​API, which include data on estimated age and size.

[0844] 7. The server estimates the user's age and size

[0845] The server estimates the user's age and size based on the analysis results it receives, stores the analysis results in a database, and provides feedback to the user as needed.

[0846] Specific examples

[0847] For example, if a user uploads a full-body photo of themselves to Facebook Messenger, the following specific actions will occur:

[0848] 1. A user opens the Facebook Messenger app and taps the "Send Photo" button.

[0849] 2. The user selects a full-body photo from their camera roll and presses the send button.

[0850] 3. The device sends the selected photo to the server as an HTTP POST request.

[0851] 4. The server stores the received photos in Amazon S3 and records the file path in the database.

[0852] 5. The server sends the saved photo to the Google Cloud Vision API and makes an analysis request.

[0853] 6. The Google Cloud Vision API analyzes the photo and estimates the user's age as 25 and size as medium.

[0854] 7. The server receives the analysis results and stores them in a database.

[0855] 8. The server provides feedback to the user: "Your age is 25 and your size is M."

[0856] Prompt Sentence Examples

[0857] Example prompts to input to a generative AI model:

[0858] "Analyze a user-submitted full-body photo to determine age and size. The photo can be found at the following URL: [Photo URL]"

[0859] This system allows users to purchase appropriate apparel products based on their age and size, allowing them to do so efficiently.

[0860] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0861] Step 1:

[0862] User submits a photo

[0863] A user sends a full-body photo of themselves using a messenger app. The user taps the "Send Photo" button in the app and selects a full-body photo from their camera roll. The input is the user's full-body photo, and the output is the photo data sent through the messenger app.

[0864] Step 2:

[0865] The device uploads the photo to the server.

[0866] The device uploads the photo selected by the user to the server. The device sends the photo data to the server as an HTTP POST request. The input is the user's full-body photo data, and the output is the photo data sent to the server.

[0867] Step 3:

[0868] The server stores the photos

[0869] The server stores the received photos in temporary storage (e.g., Amazon S3, Google Cloud Storage). The server records the photo file name and path in a database. The input is the photo data sent to the server, and the output is the photo file and its path information stored in the storage.

[0870] Step 4:

[0871] The server sends the photo to the AI ​​API

[0872] The server sends the stored photos to an AI API (e.g., Google Cloud Vision API, Amazon Rekognition). The server creates an API request and sends it including the photo data. The input is the path information of the photo file stored in storage, and the output is the photo data sent to the AI ​​API.

[0873] Step 5:

[0874] Artificial intelligence API analyzes photos

[0875] The AI ​​API analyzes the received photos and estimates the user's age, body shape, and build. The API uses image analysis algorithms to analyze facial features and body proportions. The input is the photo data sent to the AI ​​API, and the output is the analyzed age and size data.

[0876] Step 6:

[0877] The server receives the analysis results

[0878] The server receives the analysis results from the AI ​​API. The analysis results include data on estimated age and size. The input is the analysis result data sent from the AI ​​API, and the output is the analysis result data stored on the server.

[0879] Step 7:

[0880] The server estimates the user's age and size

[0881] The server estimates the user's age and size based on the analysis results it receives. The server stores the analysis results in a database and provides feedback to the user as needed. The input is the analysis result data stored on the server, and the output is the age and size information provided to the user.

[0882] (Application example 2)

[0883] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0884] On conventional online shopping sites, it was difficult for users to choose the right size of clothing, and because they could not try on the items, they had problems with the size not fitting after purchase. Furthermore, they were unable to provide an experience similar to that of actually trying on the items, which resulted in a time-consuming decision-making process. Furthermore, it was difficult to suggest optimal products based on the user's body type and age, making it difficult to meet individual needs.

[0885] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0886] In this invention, the server includes means for constantly connecting apparel product data, the latest fashion trend information, and an artificial intelligence API and training the API based on the information, means for receiving photos from users via a messenger app and automatically determining the user's age and size using the API, means for automatically suggesting products within the user's desired budget and providing a link to purchase the products, and means for performing a virtual try-on based on photos uploaded by the user and displaying the selected clothes superimposed on the user's photo. This allows users to easily select clothes that fit them best and provides an experience similar to actually trying them on through the virtual try-on.

[0887] "Apparel product data" refers to data that includes information about fashion items such as clothing and accessories.

[0888] "Latest fashion trend information" refers to information about fashion styles and trends that are popular in the current market.

[0889] An "artificial intelligence API" is an application programming interface that uses artificial intelligence technology to provide specific functionality.

[0890] A "messenger app" is application software that allows users to send and receive text messages and images.

[0891] "Means for automatically determining a user's age and size" refers to technology that analyzes photos sent by users and automatically determines their age, body type, and build.

[0892] The "means for providing a product purchase link" is a technique for providing a web link for the user to purchase the product selected by the user.

[0893] The "means for virtual try-on" is a technology that displays the clothes selected by the user superimposed on a photograph of the user, providing a visual experience that makes it seem as if the user is actually trying on the clothes.

[0894] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described in detail below with reference to the accompanying drawings.

[0895] First, the server is constantly connected to apparel product data and the latest fashion trend information, and this information is learned using an artificial intelligence API. Specifically, the server is placed on the cloud, and apparel product data and fashion trend information are stored in a database. For example, Microsoft Azure's Computer Vision API is used as the artificial intelligence API.

[0896] Users upload their full-body photos to the server through a messenger app installed on their smartphones or tablets. The server then sends the photos to an artificial intelligence API, which automatically determines the user's age and size. The results are returned to the server and added to the user's profile.

[0897] The server then automatically suggests products that fit the user's budget. This is done using an algorithm that searches a database for suitable products based on the budget information entered by the user and the determined size information. The suggested products are then notified to the user via a messenger app, and a link to purchase the product is provided.

[0898] In addition, a function is provided that allows users to virtually try on the clothes they have selected. The server acquires image data of the clothes selected by the user and displays it over a full-body photo of the user. This process uses an image processing library (e.g., OpenCV). This allows users to have a visual experience that makes them feel as if they are actually trying on the clothes.

[0899] As a concrete example, the following prompt sentence is input to the generative AI model:

[0900] "A user has uploaded a full-body photo. Please analyze the user's age and body type from this photo and suggest the best clothing size for them."

[0901] By inputting this prompt into the generative AI model, the AI ​​will analyze the user's photo and generate data to suggest clothing of the appropriate size.

[0902] As described above, the present invention provides a system that enables users to easily select clothes that fit them best and allows them to have the experience of actually trying on clothes through virtual try-on.

[0903] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0904] Step 1:

[0905] The user uploads a full-body photo through the messenger app.

[0906] Input: A full-body photo of the user

[0907] Output: Full body photo sent to the server

[0908] Specific operation: The user uses a messenger app installed on a smartphone or tablet to take a full-body photo of themselves and uploads it to the server using the app's sending function.

[0909] Step 2:

[0910] The server sends the received photos to an artificial intelligence API, which automatically determines the user's age and size.

[0911] Input: A full-body photo sent to the server

[0912] Output: User's age and size information

[0913] How it works: The server sends the received full-body photo to an AI API (such as Microsoft Azure's Computer Vision API) for photo analysis. The API determines the user's age, body type, and build from the photo and returns the results to the server.

[0914] Step 3:

[0915] Based on the results of the assessment, the server adds age and size information to the user's profile.

[0916] Input: User's age and size information

[0917] Output: Updated user profile

[0918] Specific operation: The server adds the age and size information returned from the AI ​​API to the user's profile database and updates the user's profile.

[0919] Step 4:

[0920] The server automatically suggests products that meet the user's needs and are within the user's budget.

[0921] Input: User's budget information, age and size information

[0922] Output: Suggested product list

[0923] Specific operation: The server runs an algorithm to search for appropriate products from the database based on the budget information entered by the user and the determined age and size information, and generates a list of products that are best suited to the user.

[0924] Step 5:

[0925] The server notifies the user of the suggested product list via a messenger app and provides a link to purchase the product.

[0926] Input: Suggested product list

[0927] Output: List of products notified to the user and a link to purchase

[0928] Specific operation: The server notifies the user of the generated product list and each product purchase link via the messenger app. The user can check the product list in the app and purchase the product by clicking the purchase link.

[0929] Step 6:

[0930] It provides a function for users to virtually try on selected clothes.

[0931] Input: Image data of the clothes selected by the user, a full-body photo of the user

[0932] Output: Virtual try-on image

[0933] Specific operation: The server obtains image data of the clothes selected by the user and uses an image processing library (e.g., OpenCV) to overlay it on a full-body photo of the user, giving the user a visual experience that makes them feel as if they are actually trying on the clothes.

[0934] Through these steps, users can easily choose the clothes that fit them best, and the virtual try-on experience makes them feel as if they are actually trying on the clothes.

[0935] Example 3

[0936] Next, a description will be given of Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0937] Conventional apparel product recommendation systems have difficulty suggesting appropriate products based on a user's preferences and budget. Even if a user inputs specific preferences, they are unable to quickly find products that match those preferences. Furthermore, there is a lack of systems that allow users to easily obtain purchase links. To solve these problems, a system is needed that automatically suggests products based on a user's preferences and budget and provides purchase links.

[0938] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0939] In this invention, the server includes a means for a user to input their preferences and budget via a terminal and transmit the input to the server, a means for the server to analyze the received preferences and budget and input a prompt sentence to the generative AI model, and a means for the generative AI model to generate product data based on the input prompt sentence. This makes it possible to quickly suggest appropriate products based on the user's preferences and budget and provide a purchase link.

[0940] "Apparel product data" refers to data that includes information about fashion items such as clothing and accessories.

[0941] "Latest fashion trend information" refers to information about styles and designs that are popular in the current market.

[0942] An "artificial intelligence API" is an application programming interface that uses artificial intelligence technology to provide specific functions.

[0943] A "user" is an individual or organization that uses the system to search for and purchase products.

[0944] A "terminal" is a device that allows a user to access the system and input their preferences and budget.

[0945] A "server" is a computer system that receives input from a user, generates product data using a generative AI model, and returns the results to the terminal.

[0946] A "generative AI model" is an artificial intelligence model that generates appropriate product data based on an input prompt sentence.

[0947] A "prompt sentence" is an input sentence that includes the user's wishes and budget, and provides instructions to the generative AI model for generating product data.

[0948] A "product list" is a list of product information suggested by a generative AI model, including product name, price, description, and purchase link.

[0949] A "purchase link" is the URL of a web page that a user visits to purchase a suggested product.

[0950] This invention is a system that suggests appropriate products based on a user's preferences and budget and provides a link to purchase the products. The system is implemented by having the user input their preferences and budget through a terminal, and then having the server generate product data using a generative AI model and return it to the terminal.

[0951] First, the user enters their preferences into the device's input form in the form of "I want clothes like this, and my budget is what." For example, they might enter "I want casual clothes, and my budget is 5,000 yen." The device then sends this input data in JSON format to the server.

[0952] The server analyzes the received data and creates a prompt to be input into a generative AI model (for example, GPT-4). The prompt takes the form of "I want casual clothes, my budget is 5,000 yen." The generative AI model generates data to suggest appropriate products based on this prompt. This data includes the product name, price, description, and purchase link.

[0953] The server creates a product list based on the generated data and returns it to the device in JSON format. The device then displays the received product list to the user. The user can scroll through the list to check the suggested products. For example, it might be displayed in the format "Casual T-shirt - Price: 3000 yen - Purchase link: example.com / tshirt".

[0954] Users select the product they want and click the link to purchase that product. Clicking opens a browser and takes them to the product purchase page. This allows users to easily find and purchase the product that meets their needs.

[0955] As a concrete example, if a user inputs "I want casual clothes, my budget is 5000 yen," the system will process it as follows:

[0956] 1. The user enters into the terminal, "I want casual clothes, my budget is 5,000 yen."

[0957] 2. The device sends this input data to the server in JSON format.

[0958] 3. The server analyzes the received data and generates a prompt such as "I want casual clothes, my budget is 5,000 yen."

[0959] 4. The server inputs the prompt sentence into the generative AI model (GPT-4) to generate product data.

[0960] 5. The generative AI model generates data including product name, price, description, and purchase link.

[0961] 6. The server creates a product list based on the generated data and returns it to the terminal in JSON format.

[0962] 7. The device displays the received product list to the user. For example, it may display a list like "Casual T-shirt - Price: 3000 yen - Purchase link: example.com / tshirt."

[0963] 8. The user selects the desired product and clicks the purchase link, which opens a browser and takes them to the product purchase page.

[0964] In this way, the user can easily find a product that meets their needs. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0965] Step 1:

[0966] The user enters their preferences and budget into the input form on the device.

[0967] Specific operation: The user enters "I want casual clothes, my budget is 5,000 yen" into the input form on the device.

[0968] Input: User's preferences and budget (e.g., "I want casual clothes, my budget is 5,000 yen")

[0969] Output: Input data (e.g. "I want casual clothes, my budget is 5000 yen")

[0970] Step 2:

[0971] The terminal sends the input data to the server.

[0972] Specific operation: The terminal sends the user's preferences and budget data in JSON format to the server.

[0973] Input: User's preferences and budget (JSON format)

[0974] Output: The input data sent to the server

[0975] Step 3:

[0976] The server analyzes the received data and inputs prompt sentences into the generative AI model.

[0977] Specific operation: The server analyzes the received data and generates a prompt statement such as "I want casual clothes, my budget is 5,000 yen."

[0978] Input: Input data sent to the server

[0979] Output: Generated prompt (e.g. "I want casual clothes, my budget is 5000 yen")

[0980] Step 4:

[0981] The generative AI model generates product data based on the prompt sentence.

[0982] Specific operation: Based on the input prompt, the generative AI model generates product data including the product name, price, description, and purchase link.

[0983] Input: Generated prompt text

[0984] Output: Generated product data (e.g. product name, price, description, purchase link)

[0985] Step 5:

[0986] The server creates a product list based on the generated product data and returns it to the terminal.

[0987] Specific operation: The server creates a product list based on the product data received from the generative AI model and returns it to the terminal in JSON format.

[0988] Input: Generated product data

[0989] Output: Product list returned to the terminal (JSON format)

[0990] Step 6:

[0991] The terminal displays the product list to the user.

[0992] Specific operation: The device displays the received product list to the user, who can scroll through the list to check the suggested products.

[0993] Input: Product list returned to the terminal

[0994] Output: The product list displayed to the user

[0995] Step 7:

[0996] The user selects a product and clicks the purchase link.

[0997] Specific operation: The user selects the desired product and clicks the purchase link for that product. When clicked, a browser opens and accesses the product purchase page.

[0998] Input: Product list displayed to user

[0999] Output: Access to product purchase page

[1000] (Application example 3)

[1001] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1002] Conventional online shopping systems often require a lot of time and effort for users to find the products they want. Furthermore, they lack the functionality to automatically suggest products that fit the user's budget, which hinders the user experience. Furthermore, there is no established method for effectively utilizing generative AI models to generate product suggestions based on the user's preferences.

[1003] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes means for constantly connecting apparel product data, the latest fashion trend information, and an artificial intelligence API and training the API based on the information; means for receiving photos from a user via a messenger app and automatically determining the user's age and size using the API; means for automatically suggesting products within the user's desired budget and providing a link to purchase the products; means for generating product suggestions based on the user's desired preferences using a generative AI model; and means for providing a link to purchase the suggested products via an application installed on a smartphone. This enables users to quickly and efficiently find the products they want, significantly improving the user experience.

[1004] "Apparel product data" refers to data that includes information about fashion items such as clothing and accessories.

[1005] "Latest fashion trend information" refers to information about styles and designs that are popular in the current market.

[1006] An "artificial intelligence API" is an application programming interface that uses artificial intelligence technology to provide specific functionality.

[1007] A "messenger app" is application software that allows users to send and receive text messages and images.

[1008] "Means for automatically determining a user's age and size" refers to technology that automatically determines a user's age and body size based on information and images provided by the user.

[1009] "Means for automatically suggesting products within a budget and providing links to purchase the products" refers to a technology that selects appropriate products based on the budget set by the user and provides links to the product's purchase page.

[1010] A "generative AI model" is an artificial intelligence model that generates appropriate responses and suggestions based on user input.

[1011] An "application installed on a smartphone" is a software program designed to run on a smartphone.

[1012] The "means for generating product proposals" is a technology for selecting appropriate products based on the user's wishes and conditions.

[1013] A "product purchase link" is a hyperlink to a web page for purchasing a particular product.

[1014] A system for implementing this invention is configured as follows: A server constantly connects apparel product data, the latest fashion trend information, and an artificial intelligence API, and trains the API based on the information. A user sends a photo via a messenger app, and the server automatically determines the user's age and size using the API. Furthermore, the server automatically suggests products within the user's desired budget and provides a link to purchase the products.

[1015] The server uses a generative AI model to generate product suggestions based on the user's preferences. Specifically, when the user inputs their desired product category and budget, the generative AI model suggests products that fit those criteria. For example, if a user inputs "I want casual clothes, my budget is 5,000 yen," the server uses the generative AI model to suggest casual clothes that can be purchased for less than 5,000 yen and provides a link to purchase those products.

[1016] The system works through an application installed on a smartphone, where users can input their desired product category and budget, and then view suggested product purchase links.

[1017] The hardware required is a smartphone, and the software required is Python and the OpenAI API. Data processing and calculations are carried out by a generative AI model that generates product suggestions based on user input data, and the results are provided to the user.

[1018] For example, if a user inputs "I want casual clothes, my budget is 5000 yen," the server will input the following prompt sentence into the generative AI model:

[1019] "The user's desired product category is 'casual clothing' and their budget is '5,000 yen'. Please suggest products that fit this."

[1020] Based on this prompt, the generative AI model makes product suggestions, and the server provides the results to the user, allowing the user to quickly and efficiently find the products they want.

[1021] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1022] Step 1:

[1023] The user starts the smartphone application and inputs the desired product category and budget. The input data includes the product category (e.g., "casual clothes") and the budget (e.g., "5,000 yen").

[1024] Step 2:

[1025] The terminal sends the input data from the user to the server. The input data is the product category and budget. The server receives this and proceeds to the next step.

[1026] Step 3:

[1027] The server generates a prompt based on the received input data. Specifically, it generates a prompt that includes the product category and budget (e.g., "The product category the user wants is 'casual clothing' and the budget is '5000 yen'. Please suggest products that fit this.").

[1028] Step 4:

[1029] The server inputs the generated prompt sentence into the generative AI model, which generates product suggestions based on the prompt sentence. The input data is the prompt sentence, and the output data is the product suggestions.

[1030] Step 5:

[1031] The server receives the output data (product suggestions) from the generative AI model and converts them into a format for delivery to the user. Specifically, it formats the product suggestions in text format and adds a purchase link.

[1032] Step 6:

[1033] The server sends the formatted product offer and the purchase link to the terminal. The input data is the formatted product offer and the purchase link, and the output data is the information displayed to the user.

[1034] Step 7:

[1035] The terminal displays the product suggestions and purchase links received from the server to the user, who can then check the displayed information and, if necessary, click the purchase link to purchase the product.

[1036] Through the above processing steps, the user can quickly and efficiently find the product they want.

[1037] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1038] "Example 1"

[1039] In one embodiment of the present invention, an emotion engine is incorporated. This emotion engine analyzes text information in messages from users and determines their emotions. For example, if a user sends a message saying "I'm feeling good today," the emotion engine determines from the message that the user's emotion is "joy."

[1040] "Example 2"

[1041] The emotion engine also changes the way it suggests products depending on the user's emotions. For example, if the user's emotion is "joy," the emotion engine suggests products with bright colors and pop designs. On the other hand, if the user's emotion is "sadness," the emotion engine suggests products with muted colors and simple designs.

[1042] "Example 3"

[1043] Furthermore, the emotion engine learns changes in the user's emotions and reflects the learning results in product suggestions. For example, if the emotion engine learns that the user tends to select sportswear whenever they express the emotion "joy," it will suggest sportswear the next time the user expresses the emotion "joy."

[1044] The processing flow of each embodiment will be described below.

[1045] "Example 1"

[1046] Step 1: Receive a message from the user.

[1047] Step 2: The emotion engine analyzes the text information of the message.

[1048] Step 3: The emotion engine determines the user's emotion.

[1049] "Example 2"

[1050] Step 1: The emotion engine determines the user's emotion.

[1051] Step 2: The emotion engine changes how it suggests products depending on the user's emotions.

[1052] Step 3: The emotion engine presents the suggested products to the user.

[1053] "Example 3"

[1054] Step 1: The emotion engine records the user's emotion and current product selection.

[1055] Step 2: The emotion engine learns the user's emotional changes and product selection trends.

[1056] Step 3: The emotion engine reflects its learning results in product recommendations.

[1057] Example 1

[1058] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1059] Conventional apparel product recommendation systems have had problems with suggesting products that match a user's preferences and size, and are unable to make suggestions that take the user's emotions into account. Furthermore, there were no systems that could automatically determine the user's age and size using photos submitted by the user, or suggest products that correspond to their emotions. This led to issues such as lower user satisfaction and a decrease in purchasing motivation.

[1060] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1061] In this invention, the server includes: means for constantly connecting apparel product data, the latest fashion trend information, and an artificial intelligence API and training the API based on the information; means for receiving photos from a user via a messenger app and automatically determining the user's age and size using the API; means for automatically suggesting products within the user's desired budget and providing a link to purchase the products; means for analyzing text information in messages from users and including an emotion engine for determining their emotions; and means for suggesting products according to the user's emotions based on the analysis results of the emotion engine. This makes it possible to suggest products that match the user's preferences and sizes, and further makes suggestions that take the user's emotions into consideration, thereby improving user satisfaction and increasing their willingness to purchase.

[1062] "Apparel product data" refers to product information obtained from the product database of an online shopping site, and includes information such as product images, prices, sizes, materials, and brands.

[1063] "Latest fashion trend information" is information obtained from fashion magazines and websites, and includes information on the latest trends, celebrity styles, seasonal styles, and the like.

[1064] An "artificial intelligence API" is a program interface that has the ability to learn from apparel product data and the latest fashion trend information and suggest the best products to users.

[1065] A "messenger app" is application software that allows users to send text messages and photos.

[1066] The "emotion engine" is a program that analyzes the text information of messages from users and determines their emotions.

[1067] A "product purchase link" is a link to a web page that allows a user to purchase the suggested product.

[1068] "Automatic determination of user age and size" refers to the process by which an artificial intelligence API automatically determines a user's age and size using a photo provided by the user.

[1069] "Automatically suggesting products within a budget" is a process in which an artificial intelligence API automatically suggests the most suitable products within a user's desired budget range.

[1070] "Emotion-based product suggestions" is a process in which an artificial intelligence API suggests products that suit the user's emotions based on the analysis results of the emotion engine.

[1071] The present invention is a system for proposing optimal products to users based on apparel product data and the latest fashion trend information. A specific embodiment of this system will be described below.

[1072] System configuration

[1073] server

[1074] The server accesses the product database of the online shopping site and collects apparel product data. Specifically, it obtains information such as product images, prices, sizes, materials, and brands. The server also collects the latest fashion trends from fashion magazines and websites, obtaining information on the latest trends, celebrity styles, and seasonal styles. This data is provided to the AI ​​API.

[1075] Artificial intelligence API

[1076] The AI ​​API learns from apparel product data and the latest fashion trend information provided by the server. The API has the ability to suggest products that match the user's preferences and size. Specifically, it integrates product data and trend information, performs trend analysis, and builds a personalized model taking into account the user's past purchase history and preferred style.

[1077] Emotion Engine

[1078] The emotion engine analyzes the text information in messages from users and determines their emotions. For example, if a user sends a message saying, "I'm feeling good today," the emotion engine will determine from that message that the user's emotion is "joy." This information influences the selection of products the AI ​​API recommends to users.

[1079] Terminal

[1080] The device receives messages and photos from users and sends them to a server and emotion engine. When a user sends a photo through a messenger app, the device sends the photo to a server, where an AI API automatically determines the user's age and size. It also sends text messages from users to the emotion engine for emotion analysis.

[1081] Specific examples

[1082] Example 1: Collecting apparel product data

[1083] The server collects the following data from the online shopping site:

[1084] Product image: Image of red dress

[1085] Price: 10,000 yen

[1086] Size:M

[1087] Material: Cotton

[1088] Brand: XYZ

[1089] Example 2: Gathering the latest fashion trends

[1090] The server collects the following information from the fashion magazine:

[1091] The latest trend: oversized jackets

[1092] Celebrity Style: Styles worn by famous model A

[1093] Seasonal style: Autumn casual style

[1094] Example 3: Emotion Engine Analysis

[1095] If a user sends a message saying, "I'm in a good mood today," the emotion engine will interpret this as "joy." Based on this information, the AI ​​API will suggest products with bright colors and casual styles.

[1096] Prompt Sentence Examples

[1097] "Based on the latest fashion trends and apparel product data, suggest products that fit the user's preferences and sizes. Also, adjust the suggestions based on the user's emotions."

[1098] By inputting this prompt sentence into a generative AI model, a system can be created that makes optimal product suggestions to users.

[1099] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1100] Step 1:

[1101] The server accesses the product database of the online shopping site and collects apparel product data. Specifically, it obtains information such as product images, prices, sizes, materials, and brands. This data is stored in the server's database. The input is the product database of the online shopping site, and the output is the apparel product data stored in the server's database.

[1102] Step 2:

[1103] The server collects the latest fashion trend information from fashion magazines and websites. Specifically, it obtains information on the latest trends, celebrity styles, seasonal styles, etc. This data is also stored in the server's database. The input is fashion magazines and websites, and the output is the latest fashion trend information stored in the server's database.

[1104] Step 3:

[1105] The server provides the collected apparel product data and the latest fashion trend information to the AI ​​API. The AI ​​API learns based on this data. Specifically, it integrates the product data and trend information and performs trend analysis. The input is the apparel product data stored in the server's database and the latest fashion trend information, and the output is a trained AI model.

[1106] Step 4:

[1107] A user sends a photo through a messenger app. The device receives the photo and sends it to the server. The server automatically determines the user's age and size using an artificial intelligence API. The input is the photo sent by the user, and the output is the determined age and size.

[1108] Step 5:

[1109] A user sends a text message through a messenger app. The device receives the message and sends it to the emotion engine. The emotion engine analyzes the text information of the message and determines its emotion. The input is the text message sent by the user, and the output is the determined emotion.

[1110] Step 6:

[1111] The AI ​​API suggests optimal products to users based on the analysis results of the emotion engine and learning data. Specifically, it selects products based on the user's emotions. The input is the determined emotion and the trained AI model, and the output is a list of suggested products.

[1112] Step 7:

[1113] The terminal displays the product suggestions received from the AI ​​API to the user. The user reviews the suggested products and decides whether to purchase them. The input is the list of suggested products, and the output is the user's purchase decision.

[1114] (Application example 1)

[1115] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1116] Conventional apparel product recommendation systems have had the problem of low user satisfaction because they do not adequately consider the user's preferences and emotions when making product recommendations. In addition, there is a lack of technology to make product recommendations based on the user's emotions and preferences, making it difficult to increase the user's purchasing motivation.

[1117] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes means for constantly connecting apparel product data, the latest fashion trend information, and an artificial intelligence API and for training the API based on the information, means for receiving photos from a user via a messenger app and automatically determining the user's age and size using the API, means for automatically suggesting products within the user's desired budget and providing a link to purchase the products, means for analyzing the user's emotions and suggesting products based on the emotions, and means for suggesting products based on the user's preferences and style. This enables optimal product suggestions based on the user's emotions and preferences.

[1118] "Apparel product data" refers to product information obtained from the product database of an online shopping site, such as product images, prices, sizes, materials, brands, etc.

[1119] "Latest fashion trend information" refers to information obtained from fashion magazines and websites, such as the latest trends, celebrity styles, and seasonal styles.

[1120] The "artificial intelligence API" is an artificial intelligence application programming interface that has the ability to learn from apparel product data and the latest fashion trend information, and suggest products that suit the user's preferences and sizes.

[1121] A "messenger app" is a communication application that allows users to send text messages and photos.

[1122] "Means for automatically determining a user's age and size" refers to technology that analyzes photos sent by users and automatically determines their age and body size using an artificial intelligence API.

[1123] The "means for automatically suggesting products within a budget and providing links to purchase the products" is a technology that suggests optimal products within a user's desired budget range and provides links to purchase the products.

[1124] "Means for analyzing a user's emotions and suggesting products based on those emotions" refers to a technology that analyzes the text information in a message from a user, determines the emotion, and suggests products according to the emotion.

[1125] "Means for suggesting products based on the user's preferences and style" refers to a technology that suggests optimal products based on information about the user's preferences and style.

[1126] A system for implementing this invention is configured as follows: First, a server constantly connects to apparel product data and the latest fashion trend information, and trains an artificial intelligence (AI) API based on this information. The apparel product data is product information obtained from a product database on an online shopping site, and specifically includes information such as product images, prices, sizes, materials, and brands. The latest fashion trend information is information obtained from fashion magazines and websites, and specifically includes information such as the latest trends, celebrity styles, and seasonal styles.

[1127] Users send photos to the server via a messenger app. The server automatically determines the user's age and size using an AI API. It then automatically suggests products that fit the user's preferences and budget, and provides a link to purchase the products. This allows users to easily find and purchase products that suit them.

[1128] The server also incorporates an emotion engine that analyzes the text information in messages from users and determines their emotions. For example, if a user sends a message saying, "I'm feeling good today," the emotion engine determines from the message that the user's emotion is "joy." Based on this emotion, the server suggests the most suitable product for the user.

[1129] Furthermore, the server will suggest products based on the user's preferences and style. When the user inputs their favorite style and brand, the server will suggest the most suitable products based on that information. This allows users to easily find products that suit their tastes.

[1130] For example, if a user inputs "I'm feeling good today" and selects "casual" as their preferred style, the server will suggest products that are casual in style. If a user sends a request such as "I want something that looks like a celebrity," the server can also suggest products that meet that request.

[1131] An example of a prompt is as follows:

[1132] "How are you feeling today?"

[1133] "Please tell us your favorite styles and brands."

[1134] In this way, it becomes possible to propose optimal products based on the user's feelings and preferences.

[1135] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1136] Step 1:

[1137] The server obtains apparel product data and the latest fashion trend information. Specifically, the server obtains information such as product images, prices, sizes, materials, and brands from the product database of online shopping sites, and information such as the latest trends, celebrity styles, and seasonal styles from fashion magazines and websites. This data is input into an AI API for learning. The input is product data and trend information, and the output is a trained AI model.

[1138] Step 2:

[1139] Users send photos to a server via a messenger app. The server inputs the received photos into an AI API, which automatically determines the user's age and size. Specifically, image analysis technology is used to extract the user's physical features and estimate their age and size. The input is the user's photo, and the output is the estimated age and size.

[1140] Step 3:

[1141] Users input their desired budget through a messenger app. The server then suggests optimal products based on the user's age, size, and budget. Specifically, it uses an AI model to search a database for products that match the user's criteria and generates a link to purchase the product. The input is the user's age, size, and budget, and the output is a product suggestion and a link to purchase.

[1142] Step 4:

[1143] A user sends a text message through a messenger app. The server uses an emotion engine to analyze the text information in the message and determine the user's emotion. Specifically, it uses natural language processing technology to extract emotion from the text and suggests products based on that emotion. The input is the user's text message, and the output is the emotion determination result and product suggestions.

[1144] Step 5:

[1145] Users input their preferred style and brand through the messenger app. The server then suggests the best products based on the user's preferences and style. Specifically, it uses an AI model to search a database for products that match the user's preferences and makes product suggestions. The input is the user's preferences and style information, and the output is product suggestions.

[1146] Step 6:

[1147] The server will suggest products based on user requests, such as "something that looks like a celebrity." Specifically, it uses an AI model to search a database for products that match the request and make product suggestions. The input is the user request, and the output is product suggestions.

[1148] Example 2

[1149] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1150] Conventional apparel product recommendation systems have had issues with accurately determining a user's age and size, and are unable to suggest products that reflect the user's emotions. Furthermore, they are unable to suggest products within a user's budget based on their preferences, or to change the suggestion method based on their emotions, making it difficult to increase user satisfaction.

[1151] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for constantly connecting apparel product data, the latest fashion trend information, and an artificial intelligence API and training the API based on the information; means for receiving photos from users via a messenger app and automatically determining the user's age and size using the API; means for analyzing the user's emotions and changing the product recommendation method based on the analysis results; and means for automatically suggesting products within the user's desired budget and providing a product purchase link. This makes it possible to accurately determine the user's age and size and suggest products based on their emotions. Furthermore, product recommendations within the user's desired budget and the ability to change the recommendation method based on emotions can increase user satisfaction.

[1152] "Apparel product data" refers to data that includes information about fashion items such as clothing and accessories.

[1153] "Latest fashion trend information" refers to information about styles and designs that are popular in the current market.

[1154] An "artificial intelligence API" is a program interface that provides functions such as image analysis and natural language processing.

[1155] A "messenger app" is a software application that allows users to send and receive messages and photos.

[1156] "Means for automatically determining a user's age and size" refers to technology that analyzes photos sent by users and estimates their age and body type.

[1157] "Means for analyzing user emotions" refers to technology that reads emotions from users' messages and photos and responds appropriately based on those emotions.

[1158] The "means for changing the method of product proposal" is a technology for adjusting the type and design of the proposed products according to the user's emotions and desires.

[1159] The "means for providing a product purchase link" is a technique for providing a web link for a user to purchase the suggested product.

[1160] MODE FOR CARRYING OUT THE INVENTION

[1161] This invention is a system that allows a user to send a full-body photo of themselves via a messenger app, analyzes the photo to determine the user's age and size, and then suggests appropriate products based on the user's emotions. A specific embodiment of this system will be described below.

[1162] Hardware and software used

[1163] This system uses the following hardware and software:

[1164] Hardware: Server, user device (smartphone, PC)

[1165] Software: Messenger apps (e.g., WhatsApp, Facebook Messenger), artificial intelligence APIs (e.g., Google Cloud Vision API, Amazon Rekognition), emotion engines (e.g., IBM Watson Tone Analyzer)

[1166] Data processing and calculation

[1167] 1. User photo submission:

[1168] Users take a full-body photo with their smartphone or computer camera and upload it to a messenger app. The user opens the messenger app, takes a full-body photo using the photo-taking function, and presses the send button to send the photo.

[1169] 2. Photo reception by server:

[1170] The server receives the user's photos sent from the messenger app and temporarily stores them. The server receives the photo data through the messenger app's API and stores it in a database.

[1171] 3. Age and size determination using AI API:

[1172] The server sends the stored photos to an AI API, which automatically determines the user's age and size from the photos. The server sends the photo data to the AI ​​API and receives the analysis results returned from the API. For example, the API estimates the user's height, weight, and age and returns the results to the server.

[1173] 4. Sentiment analysis using emotion engine:

[1174] The server uses an emotion engine to analyze the user's emotions. The server sends the user's message data to the emotion engine and receives the emotion analysis result returned from the emotion engine. For example, the emotion engine determines emotions such as "joy" or "sadness" from the user's message.

[1175] 5. Product suggestion:

[1176] The server recommends appropriate products to users based on information obtained from the AI ​​API and emotion engine. The server selects appropriate products from the product database based on the user's age, size, and emotion. For example, if the user's emotion is "joy," it selects and recommends products in bright colors to the user.

[1177] Specific examples

[1178] If a user sends a full-body photo with the message "I'm so happy today!", the server sends the photo to an AI API to determine the user's age and size. At the same time, it uses an emotion engine to determine the user's emotion as "joy." As a result, the server selects products with bright colors and suggests them to the user.

[1179] Prompt Sentence Examples

[1180] An example of a prompt sentence to be input to the generative AI model is shown below.

[1181] Prompt statement:

[1182] "A user sends a full-body photo through a messaging app. Analyze this photo to determine the user's age and size, and then suggest appropriate products based on the user's emotions. If the user's emotions are happy, suggest products with bright colors, and if the user's emotions are sad, suggest products with muted colors."

[1183] Using this prompt, the generative AI model can make appropriate product suggestions based on the user's photo and emotions.

[1184] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1185] Step 1:

[1186] A user takes a full-body photo with the camera on their smartphone or computer and uploads it to a messenger app. The user opens the messenger app, takes a full-body photo using the photo capture function, and presses the send button to send the photo. The input is the user's full-body photo, and the output is the photo data sent to the server via the messenger app.

[1187] Step 2:

[1188] The server receives the user's photos sent from the messenger app and temporarily stores them. The server receives the photo data through the messenger app's API and stores it in a database. The input is the photo data sent from the messenger app, and the output is the photo data stored on the server.

[1189] Step 3:

[1190] The server sends the stored photos to an AI API, which automatically determines the user's age and size from the photos. The server then sends the photo data to the AI ​​API and receives the analysis results returned from the API. For example, the API estimates the user's height, weight, and age and returns the results to the server. The input is the photo data stored on the server, and the output is the age and size analysis results returned from the AI ​​API.

[1191] Step 4:

[1192] The server uses an emotion engine to analyze the user's emotions. The server sends the user's message data to the emotion engine and receives the emotion analysis results returned from the emotion engine. For example, the emotion engine determines emotions such as "joy" or "sadness" from the user's message. The input is the user's message data, and the output is the emotion analysis results returned from the emotion engine.

[1193] Step 5:

[1194] The server recommends appropriate products to users based on information obtained from the AI ​​API and emotion engine. The server selects appropriate products from the product database based on the user's age, size, and emotion. For example, if the user's emotion is "joy," it selects products in bright colors and recommends them to the user. The input is the age and size analysis results and emotion analysis results, and the output is product information recommended to the user.

[1195] (Application example 2)

[1196] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1197] Conventional online shopping systems have difficulty suggesting appropriate products based on the user's body shape and size, and do not offer personalized suggestions based on the user's emotions. As a result, users have to spend a lot of time finding products that suit them, which leads to a decrease in satisfaction.

[1198] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1199] In this invention, the server includes means for constantly connecting apparel product data, the latest fashion trend information, and an artificial intelligence API and training the API based on the information, means for receiving photos from users via a messenger app and automatically determining the user's age and size using the API, means for analyzing the user's emotions and changing the product recommendation method based on the analysis results, means for automatically suggesting products within the user's desired budget and providing a link to purchase the products, and means for suggesting fashion items based on the user's photos and emotions using a generative AI model, thereby enabling personalized product recommendations based on the user's body type and emotions.

[1200] "Apparel product data" refers to data that includes information about fashion items such as clothing and accessories.

[1201] "Latest fashion trend information" refers to information about styles and designs that are popular in the current market.

[1202] An "artificial intelligence API" is a program interface for performing machine learning and data analysis.

[1203] A "messenger app" is an application that allows users to send and receive text messages and images.

[1204] "Means for automatically determining a user's age and size" refers to technology that analyzes photos sent by users and automatically estimates their age, body type, and size.

[1205] "Means for analyzing user emotions" refers to technology that reads emotions from a user's photos and text and analyzes those emotions.

[1206] The "means for changing the method of product suggestion" is a technique for changing the type and style of products suggested in accordance with the user's emotions.

[1207] A "generative AI model" is an artificial intelligence model used to suggest the most suitable fashion items based on a user's photos and emotions.

[1208] The "means for providing a product purchase link" is a technique for providing a link for a user to purchase a suggested product.

[1209] "Fashion items" are fashion-related products such as clothing, accessories, and shoes.

[1210] The system for implementing this invention is configured as follows: First, a user takes a full-body photo of themselves using a messenger app on their smartphone and uploads it to the app. The server receives the photo and automatically determines the user's age and size using an artificial intelligence API.

[1211] Next, the server uses an emotion analysis engine to analyze the user's emotions from the photo. This emotion analysis engine reads emotions from the user's facial expressions and posture, and changes the way it suggests products based on the results. For example, if the user expresses "joy," it will suggest products with bright colors and pop designs. On the other hand, if the user expresses "sadness," it will suggest products with muted colors and simple designs.

[1212] The server then uses a generative AI model to suggest fashion items based on the user's photo and emotions. The generative AI model then selects and recommends fashion items that best fit the user's body type and emotions. The suggested products are automatically selected within the user's desired budget, and a link to purchase the products is provided.

[1213] The specific hardware used is a smartphone (with a camera), and the software used is OpenCV (image processing library), EmotionRecognizer (emotion analysis library), SizeEstimator (size estimation library), and FashionRecommender (fashion item recommendation library).

[1214] For example, if a user takes a full-body photo with their smartphone and uploads it to the app, the server analyzes the photo and determines that the user's body size is "medium" and their emotion is "joy." The server then suggests medium-sized fashion items in bright colors and provides a link to purchase the items.

[1215] An example prompt is, "Analyze a full-body photo of the user and suggest the best fashion items based on their size and emotions."

[1216] In this way, personalized fashion suggestions based on the user's photos and emotions become possible.

[1217] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1218] Step 1:

[1219] A user takes a full-body photo of themselves using a messenger app on their smartphone and uploads it to the app. The input is the user's full-body photo, and the output is image data sent to the server.

[1220] Step 2:

[1221] The server receives the user's full-body photo from the messenger app. The input is the image data sent by the user, and the output is the image data ready for image analysis.

[1222] Step 3:

[1223] The server automatically determines the user's age and size using an artificial intelligence API. The input is a full-body photo of the user, and the output is an estimate of the user's age and size. Specifically, an image analysis algorithm is used to analyze the user's body shape and facial features to estimate age and size.

[1224] Step 4:

[1225] The server uses an emotion analysis engine to analyze emotions from the user's photo. The input is a full-body photo of the user, and the output is the analysis result of the user's emotions. Specifically, it uses facial expression recognition technology to read emotions from the user's facial expressions.

[1226] Step 5:

[1227] The server changes the product suggestion method based on the analysis results. The input is the analysis results of the user's age, size, and emotion, and the output is a list of suggested products. Specifically, it selects products in bright or subdued colors depending on the user's emotion.

[1228] Step 6:

[1229] The server uses a generative AI model to suggest fashion items based on the user's photo and emotions. The input is the analysis result of the user's age, size, and emotions, and the output is a list of fashion items that are best suited to the user. Specifically, the generative AI model selects fashion items that are best suited to the user's body type and emotions.

[1230] Step 7:

[1231] The server automatically suggests products that fit the user's budget and provides a link to purchase the products. The input is the user's budget information and a list of suggested products, and the output is a link to purchase the products. Specifically, the server selects products that fit the user's budget and generates a purchase link.

[1232] Step 8:

[1233] The user checks the suggested products and the provided purchase links and purchases the products as needed. The input is the product purchase link provided by the server, and the output is the user's purchase action. Specifically, the user clicks on the link to purchase the product.

[1234] Example 3

[1235] Next, a description will be given of Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1236] Conventional apparel product recommendation systems do not adequately suggest products based on the user's preferences and budget. Furthermore, they are unable to consider changes in the user's emotions when making suggestions, making it difficult to increase user satisfaction. Furthermore, there is a lack of technology to accurately analyze user input and suggest appropriate products. To solve these issues, a system is needed that can accurately analyze the user's preferences and budget and make product suggestions that take emotional changes into account.

[1237] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1238] In this invention, the server includes means for constantly connecting apparel product data, the latest fashion trend information, and an artificial intelligence API and training the API based on the information, means for receiving text input from a user through a messaging application and analyzing the user's preferences and budget using the API, means for using an emotion engine that learns from the user's past emotional data and adjusts suggestions, and means for automatically suggesting products within the user's preferences and budget and providing a link to purchase the products. This enables accurate product suggestions based on the user's preferences and budget, and further increases user satisfaction by making suggestions that take into account changes in the user's emotions.

[1239] "Apparel product data" is a database containing information on fashion-related products such as clothing and accessories.

[1240] "Latest fashion trends" refers to information about styles and trends that are popular in the current market.

[1241] An "artificial intelligence API" is an application programming interface for utilizing artificial intelligence technologies such as machine learning and natural language processing.

[1242] A "messaging application" is software that allows users to send and receive text messages.

[1243] "Text input" refers to a string of characters that a user enters using a keyboard or touch screen.

[1244] "Natural language processing technology" is a technology that allows computers to understand and analyze human language.

[1245] An "emotion engine" is an algorithm or software that analyzes and learns from users' emotional data.

[1246] A "product purchase link" is a hyperlink to a web page for purchasing a particular product.

[1247] "User's wishes" are requests regarding the type and features of the product that the user wants to purchase.

[1248] The "budget" is the upper limit of the amount set by the user for purchasing products.

[1249] This invention is a system that suggests suitable products based on the user's preferences and budget and provides links to purchase them. The system constantly connects apparel product data, the latest fashion trend information, and an artificial intelligence API, analyzes user input, and adjusts suggestions using an emotion engine.

[1250] The server has a database that manages apparel product data and the latest fashion trend information. This database is built using a cloud service, and can use, for example, a general cloud database service. The server uses an artificial intelligence API to learn from this data. A general natural language processing API can be used as the artificial intelligence API.

[1251] Users access the system using a terminal and input the type of product they want and their budget in text format. For example, they might input, "I want casual clothes, my budget is 5,000 yen." The server receives this input and analyzes it using natural language processing technology. Specifically, it uses a common natural language processing API to extract the user's preferences and budget.

[1252] The server then searches a product database based on the analysis results, extracting and listing products that match the user's preferences and budget. This search can be performed using common database query techniques.

[1253] Furthermore, the server uses an emotion engine to learn the user's past emotion data. A general machine learning framework can be used for this learning. The emotion engine analyzes changes in the user's emotion and reflects them in the next recommendation. For example, if the server learns that the user tends to select sportswear whenever the user expresses the emotion "joy," the emotion engine will suggest sportswear the next time the user expresses the emotion "joy."

[1254] Finally, the server generates a purchase link for the selected product and provides it to the user, which is a direct link to an online shopping site, and the user can click the link using their terminal to purchase the product.

[1255] As a concrete example, if a user inputs "I want casual clothes, my budget is 5000 yen," the server will process it as follows:

[1256] 1. The server uses a natural language processing API to extract "casual clothes" and "5,000 yen."

[1257] 2. The server searches the product database and extracts casual clothing items priced under 5,000 yen.

[1258] 3. The server uses an emotion engine to learn the user's past emotion data and adjust the suggestions.

[1259] 4. The server generates a purchase link for the selected product and provides it to the user.

[1260] Example prompt sentence:

[1261] User: I want casual clothes, my budget is 5000 yen

[1262] Server: I found the following casual outfits within my budget. Here are the links to buy them:

[1263] Product A: [Purchase Link]

[1264] Product B: [Purchase Link]

[1265] Product C: [Purchase Link]

[1266] In this way, the system proposes products that meet the user's desires and provides a link to purchase them. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1267] Step 1:

[1268] A user accesses the system using a terminal and inputs the type of product they want and their budget in text format. For example, they might input "I want casual clothes, my budget is 5,000 yen." The input data is sent to the server.

[1269] Input: User's preferences and budget (e.g., "I want casual clothes, my budget is 5,000 yen")

[1270] Output: Text data sent to the server

[1271] Step 2:

[1272] The server analyzes the received text data using natural language processing technology. Specifically, it uses a natural language processing API to extract the user's preferences and budget. The server then performs the following processes based on the extracted keywords:

[1273] Input: Text data sent by the user

[1274] Output: Extracted keywords (e.g., "casual clothes", "5000 yen")

[1275] Specific behavior:

[1276] The server sends the text data to a natural language processing API.

[1277] Natural language processing APIs analyze text and return important keywords.

[1278] The server performs the following process based on the returned keywords:

[1279] Step 3:

[1280] The server searches the product database based on the analysis results, extracts products that match the user's preferences and budget, and lists them. This search uses database query technology.

[1281] Input: Extracted keywords (e.g., "casual clothes," "5000 yen")

[1282] Output: List of products that match the conditions

[1283] Specific behavior:

[1284] The server generates an SQL query and sends it to the database.

[1285] The database returns a list of products that match the criteria.

[1286] The server temporarily stores the returned product list.

[1287] Step 4:

[1288] The server uses an emotion engine to learn the user's past emotion data. This learning is done using a machine learning framework. The emotion engine analyzes changes in the user's emotion and reflects them in the next suggestion.

[1289] Input: User's past emotional data

[1290] Output: Adjusted product list

[1291] Specific behavior:

[1292] The server transmits the user's past emotion data to the emotion engine.

[1293] The emotion engine learns from the data and provides feedback to adjust its suggestions.

[1294] The server adjusts the product listing based on the feedback.

[1295] Step 5:

[1296] The server generates a purchase link for the selected product and provides it to the user, which is a direct link to an online shopping site. The user can click the link using their terminal to purchase the product.

[1297] Input: Adjusted product list

[1298] Output: Product purchase link

[1299] Specific behavior:

[1300] The server generates a purchase link for each product.

[1301] The server sends the generated link to the user.

[1302] The user uses the terminal to click on the link and purchase the product.

[1303] (Application example 3)

[1304] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1305] Conventional online shopping systems have a function to suggest products based on the user's preferences and budget, but they do not consider the user's emotions or past purchase history. Therefore, to increase user satisfaction, more personalized product suggestions based on emotions and past data are needed.

[1306] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes means for constantly connecting apparel product data, the latest fashion trend information, and an artificial intelligence API and for training the API based on the information; means for receiving photos from a user via a messenger app and automatically determining the user's age and size using the API; means for automatically suggesting products within the user's desired budget and providing a link to purchase the products; and means for analyzing the user's emotions using an emotion engine and suggesting products based on the user's past purchase history and emotion data. This enables personalized product suggestions that take into account the user's emotions and past purchase history.

[1307] "Apparel product data" is a database containing information about clothing and fashion items.

[1308] "Latest fashion trends" refers to information about styles and trends currently popular in the fashion industry.

[1309] An "artificial intelligence API" is an application programming interface that uses artificial intelligence technology to provide specific functionality.

[1310] A "messenger app" is application software that allows users to send and receive text messages and images.

[1311] "Means for automatically determining a user's age and size" refers to technology that automatically determines a user's age and clothing size based on photos and data provided by the user.

[1312] "Means for automatically suggesting products within a budget and providing links to purchase the products" refers to a technology that selects appropriate products within a budget set by the user and provides links to the product's purchase page.

[1313] An "emotion engine" is software that analyzes a user's emotions and executes specific actions based on the results.

[1314] "Past purchase history" is a record of products previously purchased by a user.

[1315] "Emotion data" is information relating to the user's emotional state.

[1316] "Personalized product offers" are product offers that are customized based on a user's individual preferences and characteristics.

[1317] A system for implementing the present invention is configured as follows.

[1318] First, the server constantly connects to apparel product data and the latest fashion trend information, and uses an AI API to learn from this information, making it possible to suggest products based on the latest trends.

[1319] Next, the user sends a photo of themselves via a messaging app to the server, which analyzes the photo and uses an AI API to automatically determine the user's age and size. This information is then used to suggest the most suitable products for the user.

[1320] Furthermore, the user inputs the desired product category and budget. Based on this information, the server automatically suggests suitable products within the budget and provides a link to purchase those products. At this point, the emotion engine analyzes the user's emotions and suggests products based on past purchase history and emotional data. This emotion engine realizes personalized product suggestions that take into account the user's emotional state.

[1321] As a specific example, if a user inputs "I want casual clothes, my budget is 5,000 yen" and the emotion engine detects the emotion of "joy," the server will suggest casual clothing items within 5,000 yen that have been previously associated with the emotion of "joy."

[1322] An example of a prompt is as follows:

[1323] "Please enter your desired product category: Casual clothing"

[1324] "Please enter your budget: 5000"

[1325] In this way, it becomes possible to propose optimal products based on the user's wishes and feelings.

[1326] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1327] Step 1:

[1328] A user sends their own photo to the server through a messenger app. The input is the user's photo, and the output is the image data sent to the server. Specifically, the user takes a photo using the camera on their smartphone and uploads the image using the sending function of the messenger app.

[1329] Step 2:

[1330] The server analyzes the received photo and automatically determines the user's age and size using an artificial intelligence API. The input is the user's photo data, and the output is the user's age and size information. Specifically, the server runs an image analysis algorithm to perform facial recognition and body shape estimation.

[1331] Step 3:

[1332] The user inputs the desired product category and budget. The input is the product category and budget information, and the output is the desired data sent to the server. Specifically, the user enters information such as "casual clothes" or "5,000 yen" into the text input field of the messenger app and presses the send button.

[1333] Step 4:

[1334] The server automatically suggests appropriate products within the user's budget based on the product category and budget desired by the user. The input is the product category and budget information, and the output is a list of suggested products. Specifically, the server searches the apparel product database and extracts products that match the criteria.

[1335] Step 5:

[1336] The server uses an emotion engine to analyze the user's emotions and suggest products based on their past purchase history and emotional data. The input is the user's emotional data and past purchase history, and the output is product suggestions based on their emotions. Specifically, the server runs an emotion analysis algorithm to determine the user's emotional state.

[1337] Step 6:

[1338] The server provides the user with a purchase link for the suggested products. The input is a list of suggested products, and the output is a purchase link. Specifically, the server generates a purchase page URL for each product and sends it to the user via a messenger app.

[1339] Step 7:

[1340] The user clicks on the provided purchase link to purchase the product. The input is the purchase link, and the output is confirmation of purchase completion. Specifically, the user opens the browser on their smartphone, clicks on the link, and completes the purchase procedure.

[1341] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1342] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1343] Another example of generative AI is Gemini (internet search engine). <url: https: gemini.google.com ?hl="ja">) are listed.

[1344] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1345] [Third embodiment]

[1346] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1347] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1348] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1349] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1350] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1351] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1352] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1353] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1354] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1355] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1356] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1357] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1358] "Example 1"

[1359] The system of the present invention constantly connects apparel product data, the latest fashion trend information, and an AI API, and allows the API to learn based on this information. Specifically, the apparel product data uses product information obtained from a product database of an online shopping site, such as product images, price, size, material, brand, etc. The latest fashion trend information uses information obtained from fashion magazines and websites, such as the latest trends, celebrity styles, and seasonal styles. Based on this information, the AI ​​API learns and has the ability to suggest products that match the user's preferences and sizes.

[1360] "Example 2"

[1361] Users send their own photos through a messenger app. Specifically, users upload their full-body photos to the messenger app, and the system receives the photos. The system uses an artificial intelligence API to automatically determine the user's age and size from the photos. For example, if a user sends a full-body photo of themselves, the system analyzes the user's body shape and build from the photo and estimates the user's size based on that.

[1362] "Example 3"

[1363] The system automatically suggests products that fit the user's needs and are within their budget, and provides a link to purchase the products. Specifically, the user enters their preferences in the form of "I want clothes like this, and my budget is what." The system then suggests appropriate products based on those needs and budget. For example, if a user enters "I want casual clothes, and my budget is 5,000 yen," the system will suggest products that fit those conditions and provide a link to the product's purchase page.

[1364] The processing flow of each embodiment will be described below.

[1365] "Example 1"

[1366] Step 1: The system constantly connects apparel product data, the latest fashion trend information, and an AI API. Specifically, it uses product information obtained from the product database of the online shopping site, such as product images, price, size, material, brand, etc.

[1367] Step 2: For the latest fashion trend information, information obtained from fashion magazines and websites, such as the latest trends, celebrity styles, and seasonal styles, is used.

[1368] Step 3: Based on this information, the AI ​​API learns and has the ability to suggest products that match the user's preferences and sizes.

[1369] "Example 2"

[1370] Step 1: The user sends their photo through the messenger app. Specifically, the user uploads a full-body photo of themselves to the messenger app, and the system receives the photo.

[1371] Step 2: The system uses an artificial intelligence API to automatically determine the user's age and size from the photo. For example, if a user sends a full-body photo of themselves, the system will analyze the user's body shape and build from the photo and estimate the user's size based on that.

[1372] "Example 3"

[1373] Step 1: The system automatically suggests products that fit the user's needs and fit their budget, and provides a link to purchase the products. Specifically, the user inputs their needs in the form of "I want clothes like this, and my budget."

[1374] Step 2: The system suggests suitable products based on the user's preferences and budget. For example, if a user enters "I want casual clothes, my budget is 5,000 yen," the system suggests products that fit those criteria and provides a link to the product's purchase page.

[1375] Example 1

[1376] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1377] Conventional apparel product recommendation systems do not adequately suggest products based on the user's preferences and sizes. It is also difficult to suggest products that reflect the latest fashion trends, making it difficult to provide appropriate products that meet the user's needs. Furthermore, they are unable to adequately suggest products within the user's desired budget or based on celebrity-style styles. This leads to problems such as lower user satisfaction and a decrease in purchasing motivation.

[1378] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1379] In this invention, the server includes: means for constantly connecting apparel product data, the latest fashion trend information, and an artificial intelligence API and training the API based on the information; means for receiving input information from a user terminal and automatically suggesting products based on the user's preferences and size using the API; and means for displaying the suggested products on the user terminal and providing a link to purchase the products. This allows for product suggestions tailored to the user's preferences and size, and product suggestions that reflect the latest fashion trend information. It also allows for product suggestions within the user's desired budget and suggestions based on celebrity-style styles, improving user satisfaction and increasing purchasing motivation.

[1380] "Apparel product data" refers to product information obtained from the product database of an online shopping site, and specifically includes information such as product images, prices, sizes, materials, and brands.

[1381] "Latest fashion trend information" is information obtained from fashion magazines and websites, and specifically includes information on the latest trends, celebrity styles, seasonal styles, and the like.

[1382] An "artificial intelligence API" is an application programming interface that uses machine learning and deep learning to analyze data and perform specific tasks.

[1383] "User device" means a device used by a user to enter information or view suggested products, including, for example, a web browser or a mobile application.

[1384] "Product suggestion" refers to the act of selecting and presenting appropriate apparel products to a user based on the user's preferences, size, budget, and requests.

[1385] A "product purchase link" is a URL or button for purchasing the suggested product, which the user can click to go directly to the purchase page.

[1386] This invention is a system that uses an artificial intelligence API to suggest products that suit a user's preferences and sizes based on apparel product data and the latest fashion trend information. Specific embodiments of this system are described below.

[1387] Server Processing

[1388] The server first retrieves apparel product data from the product database of an online shopping site. This data includes information such as product images, prices, sizes, materials, and brands. Next, the server collects the latest fashion trend information from fashion magazines and websites. This involves using scraping technology to obtain information such as the latest trends, celebrity styles, and seasonal styles.

[1389] The collected data requires preprocessing. The server resizes and normalizes image data, tokenizes and vectorizes text data, and cleans the data by filling in missing values ​​and removing outliers.

[1390] The server uses the preprocessed data to train an artificial intelligence API. Specifically, it trains a neural network model using a machine learning framework such as TensorFlow or PyTorch. After training is complete, the server saves the trained model and makes it available as an API for inference.

[1391] Terminal handling

[1392] The device sends the information entered by the user to the server, specifically, to obtain the user's preferences and sizes through input fields in a web form or mobile app. The device sends the data, including the user's preferences and sizes, to the server using an HTTP request.

[1393] To display the product suggestions received from the server to the user, the device uses UI components of a web page or mobile app, displaying information such as images, prices, and brands of the suggested products to help the user select a product.

[1394] User operations

[1395] First, the user inputs their preferences and size into the device. For example, they might input information such as "I like casual styles and my size is medium." Then, the user checks the product suggestions displayed on the device. They check the images, prices, brands, and other information of the suggested products, and if they find one they like, they select it and proceed with the purchase. Specifically, they add the product to their shopping cart, enter their payment information, and complete the purchase.

[1396] Specific examples

[1397] If a user inputs "I like casual style, size M," the server will use this information to compare the latest fashion trend information with apparel product data and suggest casual style products in size M. For example, it will suggest "a denim jacket (price: 5,000 yen, brand: XYZ) that is trending this spring."

[1398] Prompt Sentence Examples

[1399] "Please suggest products that you would recommend to a user who likes casual style and wears size M."

[1400] By inputting this prompt into a generative AI model, product suggestions that match the user's preferences and size can be obtained.

[1401] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1402] Step 1:

[1403] The server retrieves apparel product data from the product database of the online shopping site. Specifically, it uses an API to collect information such as product images, prices, sizes, materials, and brands. The input is the API endpoint of the online shopping site, and the output is the retrieved apparel product data.

[1404] Step 2:

[1405] The server collects the latest fashion trend information from fashion magazines and websites. Specifically, it uses scraping technology to obtain information such as the latest trends, celebrity styles, and seasonal styles. The input is the URL of the fashion magazine or website, and the output is the collected fashion trend information.

[1406] Step 3:

[1407] The server preprocesses the collected data. Specifically, it resizes and normalizes image data, and tokenizes and vectorizes text data. It also performs data cleaning, such as filling in missing values ​​and removing outliers. The input is apparel product data and fashion trend information, and the output is the preprocessed data.

[1408] Step 4:

[1409] The server uses the preprocessed data to train an artificial intelligence API. Specifically, it uses machine learning frameworks such as TensorFlow or PyTorch to train a neural network model. The input is the preprocessed data, and the output is the trained model.

[1410] Step 5:

[1411] The server saves the trained model and exposes it as an API for inference. Specifically, it saves the model as a file and sets an API endpoint. The input is the trained model, and the output is the exposed API endpoint.

[1412] Step 6:

[1413] The device sends the information entered by the user to the server. Specifically, the user's preferences and sizes are acquired through input fields in a web form or a mobile app. The input is information about the user's preferences and sizes, and the output is an HTTP request to the server.

[1414] Step 7:

[1415] The server receives requests from users and performs inference using the trained model. Specifically, it suggests optimal products based on the user's preferences and size. The input is information about the user's preferences and size, and the output is suggested product information.

[1416] Step 8:

[1417] The terminal displays the product suggestions received from the server to the user. Specifically, it uses UI components of a web page or mobile app to display information such as images, prices, and brands of the suggested products. The input is the suggested product information, and the output is the product information displayed to the user.

[1418] Step 9:

[1419] The user checks the product suggestions displayed on the terminal, selects any products they like, and then completes the purchase. Specifically, they add the products to their shopping cart and enter payment information to complete the purchase. The input is the suggested product information and the user's payment information, and the output is confirmation of purchase completion.

[1420] (Application example 1)

[1421] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1422] Conventional apparel product recommendation systems have the problem that it is difficult to efficiently recommend products that match the user's preferences and sizes, and since users cannot actually try on the products, there are problems with low post-purchase satisfaction. Furthermore, it is difficult to reflect the latest fashion trend information in real time, and it is not possible to respond quickly to user needs.

[1423] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1424] In this invention, the server includes means for constantly connecting apparel product data, the latest fashion trend information, and an artificial intelligence API and for training the API based on the information, means for allowing a user to walk around the virtual store using a smartphone or head-mounted display and for using the API to suggest products that suit the user's preferences and size, and means for scanning the user's body shape data and using the API to suggest clothes in the optimal size. This allows the user to actually try on products in the virtual store and makes it possible to suggest products based on the latest fashion trend information.

[1425] "Apparel product data" refers to product information obtained from the product database of an online shopping site, and specifically includes information such as product images, prices, sizes, materials, and brands.

[1426] "Latest fashion trend information" is information obtained from fashion magazines and websites, and specifically includes information on the latest trends, celebrity styles, seasonal styles, and the like.

[1427] The "artificial intelligence API" is an artificial intelligence application programming interface that has the ability to learn from apparel product data and the latest fashion trend information, and suggest products that suit the user's preferences and sizes.

[1428] A "smartphone" is a type of mobile phone and a multi-function device that can connect to the Internet and install applications.

[1429] A "head-mounted display" is a display device that the user wears on their head, and is a device that provides virtual reality and augmented reality experiences.

[1430] A "virtual store" is a virtual store that exists on the Internet and provides an environment where users can browse and purchase products online.

[1431] "Body type data" refers to information about the user's body dimensions and shape, and specifically includes data such as height, weight, chest circumference, waist circumference, and hip circumference.

[1432] A "product purchase link" is a web link that allows a user to purchase the suggested product online.

[1433] The system for implementing this invention constantly connects apparel product data and the latest fashion trend information, and uses an artificial intelligence (AI) API to suggest products that match the user's preferences and sizes. A specific embodiment of this system is described below.

[1434] System Configuration

[1435] Hardware

[1436] Server: Hosts the database and AI models and provides APIs.

[1437] User device: Use a smartphone or head-mounted display (HMD).

[1438] software

[1439] TensorFlow: Used for training and inference of AI models.

[1440] OpenCV: Used for image processing.

[1441] PIL (Python Imaging Library): Used for image manipulation.

[1442] Requests: Used for API communication.

[1443] Data acquisition and processing

[1444] Acquiring apparel product data

[1445] The server retrieves product information from the product database of the online shopping site, including product images, prices, sizes, materials, brands, etc.

[1446] Get the latest fashion trends

[1447] The server retrieves the latest trend information from fashion magazines and websites, including celebrity styles and seasonal styles.

[1448] AI model training and inference

[1449] The server uses TensorFlow to train an AI model based on the acquired apparel product data and the latest fashion trend information. The trained AI model is then able to suggest products that match the user's preferences and sizes.

[1450] User Interface

[1451] Use of virtual stores

[1452] Users can walk around the virtual store using their smartphone or HMD, and AI will scan their body data and suggest clothes that fit them best.

[1453] Product suggestions and purchase links

[1454] Once a user selects an item in the virtual store, the AI ​​will suggest the best fit based on the user's preferences and size, and provide a link to purchase the suggested item online.

[1455] Specific examples

[1456] For example, users can use their smartphone camera to scan their body shape, and the app will use that data to suggest clothing that best suits them. They can also use an HMD to walk around a virtual store and try on outfits suggested by AI.

[1457] Prompt Sentence Examples

[1458] Develop an application that scans the user's body data and suggests the best apparel products based on the latest fashion trends. Users can walk around a virtual store using their smartphone or HMD and try on outfits suggested by AI.

[1459] In this way, by providing a concrete form for implementing the invention, users can actually try on products in a virtual store, making it possible to receive product suggestions based on the latest fashion trends.

[1460] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1461] Step 1:

[1462] The server retrieves apparel product data from the product database of the online shopping site. Specifically, it retrieves information such as product images, prices, sizes, materials, and brands through the API. The input is the API request, and the output is a list of product data.

[1463] Step 2:

[1464] The server retrieves the latest fashion trend information from fashion magazines and websites. Specifically, it retrieves information such as the latest trends, celebrity styles, and seasonal styles through scraping or API. The input is the scraping script or API request, and the output is a list of trend information.

[1465] Step 3:

[1466] The server uses TensorFlow to train an AI model based on the acquired apparel product data and the latest fashion trend information. The input is product data and trend information, and the output is a trained AI model. Specific operations include data preprocessing, model training, and evaluation.

[1467] Step 4:

[1468] The user walks around the virtual store using a smartphone or a head-mounted display. The smartphone camera and the HMD sensor are used to scan the user's body shape data. The input is the user's body shape data, and the output is the scanned body shape data.

[1469] Step 5:

[1470] The server receives the scanned body data and uses an AI model to suggest products that match the user's preferences and size. The input is the body data and the trained AI model, and the output is a list of suggested products. Specific operations include analyzing the body data, estimating the user's preferences, and suggesting products.

[1471] Step 6:

[1472] The user tries on suggested products in a virtual store. The virtual try-on is performed using a smartphone or HMD. The input is a list of suggested products, and the output is feedback on the tried-on products. Specific operations include product selection, virtual try-on, and feedback.

[1473] Step 7:

[1474] The server provides a product purchase link for the product selected by the user. The input is the product selected by the user, and the output is the product purchase link. Specific operations include generating a purchase link and providing the link to the user.

[1475] In this manner, detailed procedures for carrying out the invention are provided by describing the specific operations performed at each processing step.

[1476] Example 2

[1477] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1478] Conventional apparel product recommendation systems have had problems such as difficulty in accurately determining a user's age and size, and insufficient product recommendations that meet the user's needs.Furthermore, there have been issues with the accuracy of analyzing photos submitted by users, resulting in low suitability of the products suggested.

[1479] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1480] In this invention, the server includes means for constantly connecting apparel product data, the latest fashion trend information, and an artificial intelligence API and training the API based on the information, means for receiving photos from a user via a messenger app and automatically determining the user's age and size using the API, means for automatically suggesting products within the user's desired budget and providing a link to purchase the products, means for saving photos sent by the user and sending them to the artificial intelligence API to receive analysis results, and means for estimating the user's age and size based on the analysis results, thereby enabling accurate determination of the user's age and size and suggesting products that meet the user's desires.

[1481] "Apparel product data" refers to data that includes information about fashion items such as clothing and accessories.

[1482] "Latest fashion trends" refers to information about styles and trends currently popular in the fashion industry.

[1483] An "artificial intelligence API" is a programming interface for image and data analysis that uses machine learning algorithms to perform specific tasks.

[1484] A "messenger app" is a software application that enables users to send and receive text messages and images.

[1485] "Means for automatically determining a user's age and size" is a function that uses an artificial intelligence API to analyze and estimate a user's age, body shape, and build from photos sent by the user.

[1486] A "purchase link" is a URL or hyperlink that allows a user to purchase a suggested product online.

[1487] The "means for saving photos" is a function for temporarily or permanently saving photos sent by users in storage.

[1488] "Means for receiving analysis results" refers to the function by which the server receives analysis results from the artificial intelligence API.

[1489] "Means for estimating age and size" is a function that estimates the user's age, body shape, and build based on the analysis results of an artificial intelligence API.

[1490] The present invention is a system that analyzes photos sent by a user via a messenger app, automatically determines the user's age and size, and suggests appropriate apparel products. Specific embodiments of this system are described below.

[1491] System configuration

[1492] The system consists of the following main components:

[1493] 1. Messenger app: A software application that allows users to send photos. Examples include WhatsApp and Facebook Messenger.

[1494] 2. Server: A central processing unit that receives, stores, and sends photos to the AI ​​API. The server uses storage services such as Amazon S3 and Google Cloud Storage.

[1495] 3. Artificial Intelligence API: A programmatic interface for analyzing photos to determine a user's age and size. Examples include Google Cloud Vision API and Amazon Rekognition.

[1496] System Operation

[1497] 1. User submits a photo

[1498] Users can send their full-body photos using the Messenger app by tapping the "Send Photo" button within the app and selecting a full-body photo from their camera roll.

[1499] 2. The device uploads the photo to the server.

[1500] The device uploads the photo selected by the user to the server by sending the photo data to the server as an HTTP POST request.

[1501] 3. The server stores the photos

[1502] The server stores the received photos in temporary storage (e.g., Amazon S3, Google Cloud Storage), and records the photo file names and paths in a database.

[1503] 4. The server sends the photo to the AI ​​API

[1504] The server sends the saved photo to an artificial intelligence API (e.g., Google Cloud Vision API, Amazon Rekognition). The server creates an API request and sends it along with the photo data.

[1505] 5. Artificial intelligence API analyzes photos

[1506] The AI ​​API analyzes the received photos to estimate the user's age, body type, and build. The API uses image analysis algorithms to analyze facial features and body proportions.

[1507] 6. The server receives the analysis results

[1508] The server receives the analysis results from the AI ​​API, which include data on estimated age and size.

[1509] 7. The server estimates the user's age and size

[1510] The server estimates the user's age and size based on the analysis results it receives, stores the analysis results in a database, and provides feedback to the user as needed.

[1511] Specific examples

[1512] For example, if a user uploads a full-body photo of themselves to Facebook Messenger, the following specific actions will occur:

[1513] 1. A user opens the Facebook Messenger app and taps the "Send Photo" button.

[1514] 2. The user selects a full-body photo from their camera roll and presses the send button.

[1515] 3. The device sends the selected photo to the server as an HTTP POST request.

[1516] 4. The server stores the received photos in Amazon S3 and records the file path in the database.

[1517] 5. The server sends the saved photo to the Google Cloud Vision API and makes an analysis request.

[1518] 6. The Google Cloud Vision API analyzes the photo and estimates the user's age as 25 and size as medium.

[1519] 7. The server receives the analysis results and stores them in a database.

[1520] 8. The server provides feedback to the user: "Your age is 25 and your size is M."

[1521] Prompt Sentence Examples

[1522] Example prompts to input to a generative AI model:

[1523] "Analyze a user-submitted full-body photo to determine age and size. The photo can be found at the following URL: [Photo URL]"

[1524] This system allows users to purchase appropriate apparel products based on their age and size, allowing them to do so efficiently.

[1525] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1526] Step 1:

[1527] User submits a photo

[1528] A user sends a full-body photo of themselves using a messenger app. The user taps the "Send Photo" button in the app and selects a full-body photo from their camera roll. The input is the user's full-body photo, and the output is the photo data sent through the messenger app.

[1529] Step 2:

[1530] The device uploads the photo to the server.

[1531] The device uploads the photo selected by the user to the server. The device sends the photo data to the server as an HTTP POST request. The input is the user's full-body photo data, and the output is the photo data sent to the server.

[1532] Step 3:

[1533] The server stores the photos

[1534] The server stores the received photos in temporary storage (e.g., Amazon S3, Google Cloud Storage). The server records the photo file name and path in a database. The input is the photo data sent to the server, and the output is the photo file and its path information stored in the storage.

[1535] Step 4:

[1536] The server sends the photo to the AI ​​API

[1537] The server sends the stored photos to an AI API (e.g., Google Cloud Vision API, Amazon Rekognition). The server creates an API request and sends it including the photo data. The input is the path information of the photo file stored in storage, and the output is the photo data sent to the AI ​​API.

[1538] Step 5:

[1539] Artificial intelligence API analyzes photos

[1540] The AI ​​API analyzes the received photos and estimates the user's age, body shape, and build. The API uses image analysis algorithms to analyze facial features and body proportions. The input is the photo data sent to the AI ​​API, and the output is the analyzed age and size data.

[1541] Step 6:

[1542] The server receives the analysis results

[1543] The server receives the analysis results from the AI ​​API. The analysis results include data on estimated age and size. The input is the analysis result data sent from the AI ​​API, and the output is the analysis result data stored on the server.

[1544] Step 7:

[1545] The server estimates the user's age and size

[1546] The server estimates the user's age and size based on the analysis results it receives. The server stores the analysis results in a database and provides feedback to the user as needed. The input is the analysis result data stored on the server, and the output is the age and size information provided to the user.

[1547] (Application example 2)

[1548] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1549] On conventional online shopping sites, it was difficult for users to choose the right size of clothing, and because they could not try on the items, they had problems with the size not fitting after purchase. Furthermore, they were unable to provide an experience similar to that of actually trying on the items, which resulted in a time-consuming decision-making process. Furthermore, it was difficult to suggest optimal products based on the user's body type and age, making it difficult to meet individual needs.

[1550] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1551] In this invention, the server includes means for constantly connecting apparel product data, the latest fashion trend information, and an artificial intelligence API and training the API based on the information, means for receiving photos from users via a messenger app and automatically determining the user's age and size using the API, means for automatically suggesting products within the user's desired budget and providing a link to purchase the products, and means for performing a virtual try-on based on photos uploaded by the user and displaying the selected clothes superimposed on the user's photo. This allows users to easily select clothes that fit them best and provides an experience similar to actually trying them on through the virtual try-on.

[1552] "Apparel product data" refers to data that includes information about fashion items such as clothing and accessories.

[1553] "Latest fashion trend information" refers to information about fashion styles and trends that are popular in the current market.

[1554] An "artificial intelligence API" is an application programming interface that uses artificial intelligence technology to provide specific functionality.

[1555] A "messenger app" is application software that allows users to send and receive text messages and images.

[1556] "Means for automatically determining a user's age and size" refers to technology that analyzes photos sent by users and automatically determines their age, body type, and build.

[1557] The "means for providing a product purchase link" is a technique for providing a web link for the user to purchase the product selected by the user.

[1558] The "means for virtual try-on" is a technology that displays the clothes selected by the user superimposed on a photograph of the user, providing a visual experience that makes it seem as if the user is actually trying on the clothes.

[1559] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described in detail below with reference to the accompanying drawings.

[1560] First, the server is constantly connected to apparel product data and the latest fashion trend information, and this information is learned using an artificial intelligence API. Specifically, the server is placed on the cloud, and apparel product data and fashion trend information are stored in a database. For example, Microsoft Azure's Computer Vision API is used as the artificial intelligence API.

[1561] Users upload their full-body photos to the server through a messenger app installed on their smartphones or tablets. The server then sends the photos to an artificial intelligence API, which automatically determines the user's age and size. The results are returned to the server and added to the user's profile.

[1562] The server then automatically suggests products that fit the user's budget. This is done using an algorithm that searches a database for suitable products based on the budget information entered by the user and the determined size information. The suggested products are then notified to the user via a messenger app, and a link to purchase the product is provided.

[1563] In addition, a function is provided that allows users to virtually try on the clothes they have selected. The server acquires image data of the clothes selected by the user and displays it over a full-body photo of the user. This process uses an image processing library (e.g., OpenCV). This allows users to have a visual experience that makes them feel as if they are actually trying on the clothes.

[1564] As a concrete example, the following prompt sentence is input to the generative AI model:

[1565] "A user has uploaded a full-body photo. Please analyze the user's age and body type from this photo and suggest the best clothing size for them."

[1566] By inputting this prompt into the generative AI model, the AI ​​will analyze the user's photo and generate data to suggest clothing of the appropriate size.

[1567] As described above, the present invention provides a system that enables users to easily select clothes that fit them best and allows them to have the experience of actually trying on clothes through virtual try-on.

[1568] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1569] Step 1:

[1570] The user uploads a full-body photo through the messenger app.

[1571] Input: A full-body photo of the user

[1572] Output: Full body photo sent to the server

[1573] Specific operation: The user uses a messenger app installed on a smartphone or tablet to take a full-body photo of themselves and uploads it to the server using the app's sending function.

[1574] Step 2:

[1575] The server sends the received photos to an artificial intelligence API, which automatically determines the user's age and size.

[1576] Input: A full-body photo sent to the server

[1577] Output: User's age and size information

[1578] How it works: The server sends the received full-body photo to an AI API (such as Microsoft Azure's Computer Vision API) for photo analysis. The API determines the user's age, body type, and build from the photo and returns the results to the server.

[1579] Step 3:

[1580] Based on the results of the assessment, the server adds age and size information to the user's profile.

[1581] Input: User's age and size information

[1582] Output: Updated user profile

[1583] Specific operation: The server adds the age and size information returned from the AI ​​API to the user's profile database and updates the user's profile.

[1584] Step 4:

[1585] The server automatically suggests products that meet the user's needs and are within the user's budget.

[1586] Input: User's budget information, age and size information

[1587] Output: Suggested product list

[1588] Specific operation: The server runs an algorithm to search for appropriate products from the database based on the budget information entered by the user and the determined age and size information, and generates a list of products that are best suited to the user.

[1589] Step 5:

[1590] The server notifies the user of the suggested product list via a messenger app and provides a link to purchase the product.

[1591] Input: Suggested product list

[1592] Output: List of products notified to the user and a link to purchase

[1593] Specific operation: The server notifies the user of the generated product list and each product purchase link via the messenger app. The user can check the product list in the app and purchase the product by clicking the purchase link.

[1594] Step 6:

[1595] It provides a function for users to virtually try on selected clothes.

[1596] Input: Image data of the clothes selected by the user, a full-body photo of the user

[1597] Output: Virtual try-on image

[1598] Specific operation: The server obtains image data of the clothes selected by the user and uses an image processing library (e.g., OpenCV) to overlay it on a full-body photo of the user, giving the user a visual experience that makes them feel as if they are actually trying on the clothes.

[1599] Through these steps, users can easily choose the clothes that fit them best, and the virtual try-on experience makes them feel as if they are actually trying on the clothes.

[1600] Example 3

[1601] Next, a third embodiment of the third embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1602] Conventional apparel product recommendation systems have difficulty suggesting appropriate products based on a user's preferences and budget. Even if a user inputs specific preferences, they are unable to quickly find products that match those preferences. Furthermore, there is a lack of systems that allow users to easily obtain purchase links. To solve these problems, a system is needed that automatically suggests products based on a user's preferences and budget and provides purchase links.

[1603] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1604] In this invention, the server includes a means for a user to input their preferences and budget via a terminal and transmit the input to the server, a means for the server to analyze the received preferences and budget and input a prompt sentence to the generative AI model, and a means for the generative AI model to generate product data based on the input prompt sentence. This makes it possible to quickly suggest appropriate products based on the user's preferences and budget and provide a purchase link.

[1605] "Apparel product data" refers to data that includes information about fashion items such as clothing and accessories.

[1606] "Latest fashion trend information" refers to information about styles and designs that are popular in the current market.

[1607] An "artificial intelligence API" is an application programming interface that uses artificial intelligence technology to provide specific functions.

[1608] A "user" is an individual or organization that uses the system to search for and purchase products.

[1609] A "terminal" is a device that allows a user to access the system and input their preferences and budget.

[1610] A "server" is a computer system that receives input from a user, generates product data using a generative AI model, and returns the results to the terminal.

[1611] A "generative AI model" is an artificial intelligence model that generates appropriate product data based on an input prompt sentence.

[1612] A "prompt sentence" is an input sentence that includes the user's wishes and budget, and provides instructions to the generative AI model for generating product data.

[1613] A "product list" is a list of product information suggested by a generative AI model, including product name, price, description, and purchase link.

[1614] A "purchase link" is the URL of a web page that a user visits to purchase a suggested product.

[1615] This invention is a system that suggests appropriate products based on a user's preferences and budget and provides a link to purchase the products. The system is implemented by having the user input their preferences and budget through a terminal, and then having the server generate product data using a generative AI model and return it to the terminal.

[1616] First, the user enters their preferences into the device's input form in the form of "I want clothes like this, and my budget is what." For example, they might enter "I want casual clothes, and my budget is 5,000 yen." The device then sends this input data in JSON format to the server.

[1617] The server analyzes the received data and creates a prompt to be input into a generative AI model (for example, GPT-4). The prompt takes the form of "I want casual clothes, my budget is 5,000 yen." The generative AI model generates data to suggest appropriate products based on this prompt. This data includes the product name, price, description, and purchase link.

[1618] The server creates a product list based on the generated data and returns it to the device in JSON format. The device then displays the received product list to the user. The user can scroll through the list to check the suggested products. For example, it might be displayed in the format "Casual T-shirt - Price: 3000 yen - Purchase link: example.com / tshirt".

[1619] Users select the product they want and click the link to purchase that product. Clicking opens a browser and takes them to the product purchase page. This allows users to easily find and purchase the product that meets their needs.

[1620] As a concrete example, if a user inputs "I want casual clothes, my budget is 5000 yen," the system will process it as follows:

[1621] 1. The user enters into the terminal, "I want casual clothes, my budget is 5,000 yen."

[1622] 2. The device sends this input data to the server in JSON format.

[1623] 3. The server analyzes the received data and generates a prompt such as "I want casual clothes, my budget is 5,000 yen."

[1624] 4. The server inputs the prompt sentence into the generative AI model (GPT-4) to generate product data.

[1625] 5. The generative AI model generates data including product name, price, description, and purchase link.

[1626] 6. The server creates a product list based on the generated data and returns it to the terminal in JSON format.

[1627] 7. The device displays the received product list to the user. For example, it may display a list like "Casual T-shirt - Price: 3000 yen - Purchase link: example.com / tshirt."

[1628] 8. The user selects the desired product and clicks the purchase link, which opens a browser and takes them to the product purchase page.

[1629] In this way, the user can easily find a product that meets their needs. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1630] Step 1:

[1631] The user enters their preferences and budget into the input form on the device.

[1632] Specific operation: The user enters "I want casual clothes, my budget is 5,000 yen" into the input form on the device.

[1633] Input: User's preferences and budget (e.g., "I want casual clothes, my budget is 5,000 yen")

[1634] Output: Input data (e.g. "I want casual clothes, my budget is 5000 yen")

[1635] Step 2:

[1636] The terminal sends the input data to the server.

[1637] Specific operation: The terminal sends the user's preferences and budget data in JSON format to the server.

[1638] Input: User's preferences and budget (JSON format)

[1639] Output: The input data sent to the server

[1640] Step 3:

[1641] The server analyzes the received data and inputs prompt sentences into the generative AI model.

[1642] Specific operation: The server analyzes the received data and generates a prompt statement such as "I want casual clothes, my budget is 5,000 yen."

[1643] Input: Input data sent to the server

[1644] Output: Generated prompt (e.g. "I want casual clothes, my budget is 5000 yen")

[1645] Step 4:

[1646] The generative AI model generates product data based on the prompt sentence.

[1647] Specific operation: Based on the input prompt, the generative AI model generates product data including the product name, price, description, and purchase link.

[1648] Input: Generated prompt text

[1649] Output: Generated product data (e.g. product name, price, description, purchase link)

[1650] Step 5:

[1651] The server creates a product list based on the generated product data and returns it to the terminal.

[1652] Specific operation: The server creates a product list based on the product data received from the generative AI model and returns it to the terminal in JSON format.

[1653] Input: Generated product data

[1654] Output: Product list returned to the terminal (JSON format)

[1655] Step 6:

[1656] The terminal displays the product list to the user.

[1657] Specific operation: The device displays the received product list to the user, who can scroll through the list to check the suggested products.

[1658] Input: Product list returned to the terminal

[1659] Output: The product list displayed to the user

[1660] Step 7:

[1661] The user selects a product and clicks the purchase link.

[1662] Specific operation: The user selects the desired product and clicks the purchase link for that product. When clicked, a browser opens and accesses the product purchase page.

[1663] Input: Product list displayed to user

[1664] Output: Access to product purchase page

[1665] (Application example 3)

[1666] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1667] Conventional online shopping systems often require a lot of time and effort for users to find the products they want. Furthermore, they lack the functionality to automatically suggest products that fit the user's budget, which hinders the user experience. Furthermore, there is no established method for effectively utilizing generative AI models to generate product suggestions based on the user's preferences.

[1668] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes means for constantly connecting apparel product data, the latest fashion trend information, and an artificial intelligence API and training the API based on the information; means for receiving photos from a user via a messenger app and automatically determining the user's age and size using the API; means for automatically suggesting products within the user's desired budget and providing a link to purchase the products; means for generating product suggestions based on the user's desired preferences using a generative AI model; and means for providing a link to purchase the suggested products via an application installed on a smartphone. This enables users to quickly and efficiently find the products they want, significantly improving the user experience.

[1669] "Apparel product data" refers to data that includes information about fashion items such as clothing and accessories.

[1670] "Latest fashion trend information" refers to information about styles and designs that are popular in the current market.

[1671] An "artificial intelligence API" is an application programming interface that uses artificial intelligence technology to provide specific functionality.

[1672] A "messenger app" is application software that allows users to send and receive text messages and images.

[1673] "Means for automatically determining a user's age and size" refers to technology that automatically determines a user's age and body size based on information and images provided by the user.

[1674] "Means for automatically suggesting products within a budget and providing links to purchase the products" refers to a technology that selects appropriate products based on the budget set by the user and provides links to the product's purchase page.

[1675] A "generative AI model" is an artificial intelligence model that generates appropriate responses and suggestions based on user input.

[1676] An "application installed on a smartphone" is a software program designed to run on a smartphone.

[1677] The "means for generating product proposals" is a technology for selecting appropriate products based on the user's wishes and conditions.

[1678] A "product purchase link" is a hyperlink to a web page for purchasing a particular product.

[1679] A system for implementing this invention is configured as follows: A server constantly connects apparel product data, the latest fashion trend information, and an artificial intelligence API, and trains the API based on the information. A user sends a photo via a messenger app, and the server automatically determines the user's age and size using the API. Furthermore, the server automatically suggests products within the user's desired budget and provides a link to purchase the products.

[1680] The server uses a generative AI model to generate product suggestions based on the user's preferences. Specifically, when the user inputs their desired product category and budget, the generative AI model suggests products that fit those criteria. For example, if a user inputs "I want casual clothes, my budget is 5,000 yen," the server uses the generative AI model to suggest casual clothes that can be purchased for less than 5,000 yen and provides a link to purchase those products.

[1681] The system works through an application installed on a smartphone, where users can input their desired product category and budget, and then view suggested product purchase links.

[1682] The hardware required is a smartphone, and the software required is Python and the OpenAI API. Data processing and calculations are carried out by a generative AI model that generates product suggestions based on user input data, and the results are provided to the user.

[1683] For example, if a user inputs "I want casual clothes, my budget is 5000 yen," the server will input the following prompt sentence into the generative AI model:

[1684] "The user's desired product category is 'casual clothing' and their budget is '5,000 yen'. Please suggest products that fit this."

[1685] Based on this prompt, the generative AI model makes product suggestions, and the server provides the results to the user, allowing the user to quickly and efficiently find the products they want.

[1686] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1687] Step 1:

[1688] The user starts the smartphone application and inputs the desired product category and budget. The input data includes the product category (e.g., "casual clothes") and the budget (e.g., "5,000 yen").

[1689] Step 2:

[1690] The terminal sends the input data from the user to the server. The input data is the product category and budget. The server receives this and proceeds to the next step.

[1691] Step 3:

[1692] The server generates a prompt based on the received input data. Specifically, it generates a prompt that includes the product category and budget (e.g., "The product category the user wants is 'casual clothing' and the budget is '5000 yen'. Please suggest products that fit this.").

[1693] Step 4:

[1694] The server inputs the generated prompt sentence into the generative AI model, which generates product suggestions based on the prompt sentence. The input data is the prompt sentence, and the output data is the product suggestions.

[1695] Step 5:

[1696] The server receives the output data (product suggestions) from the generative AI model and converts them into a format for delivery to the user. Specifically, it formats the product suggestions in text format and adds a purchase link.

[1697] Step 6:

[1698] The server sends the formatted product offer and the purchase link to the terminal. The input data is the formatted product offer and the purchase link, and the output data is the information displayed to the user.

[1699] Step 7:

[1700] The terminal displays the product suggestions and purchase links received from the server to the user, who can then check the displayed information and, if necessary, click the purchase link to purchase the product.

[1701] Through the above processing steps, the user can quickly and efficiently find the product they want.

[1702] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1703] "Example 1"

[1704] In one embodiment of the present invention, an emotion engine is incorporated. This emotion engine analyzes text information in messages from users and determines their emotions. For example, if a user sends a message saying "I'm feeling good today," the emotion engine determines from the message that the user's emotion is "joy."

[1705] "Example 2"

[1706] The emotion engine also changes the way it suggests products depending on the user's emotions. For example, if the user's emotion is "joy," the emotion engine suggests products with bright colors and pop designs. On the other hand, if the user's emotion is "sadness," the emotion engine suggests products with muted colors and simple designs.

[1707] "Example 3"

[1708] Furthermore, the emotion engine learns changes in the user's emotions and reflects the learning results in product suggestions. For example, if the emotion engine learns that the user tends to select sportswear whenever they express the emotion "joy," it will suggest sportswear the next time the user expresses the emotion "joy."

[1709] The processing flow of each embodiment will be described below.

[1710] "Example 1"

[1711] Step 1: Receive a message from the user.

[1712] Step 2: The emotion engine analyzes the text information of the message.

[1713] Step 3: The emotion engine determines the user's emotion.

[1714] "Example 2"

[1715] Step 1: The emotion engine determines the user's emotion.

[1716] Step 2: The emotion engine changes how it suggests products depending on the user's emotions.

[1717] Step 3: The emotion engine presents the suggested products to the user.

[1718] "Example 3"

[1719] Step 1: The ...

Claims

1. A means for training an artificial intelligence based on information about fashion items and information about styles and trends in the fashion industry; A means for determining the age and physical build of a user based on a photograph provided by the user using the trained artificial intelligence; A suggestion means for suggesting products that match the budget, age, and build input by the user by inputting a specific prompt sentence into a generative AI model, and displaying a list including the suggested products on the user's terminal; an emotion engine that recognizes the emotion of the user by analyzing a message input by the user; An adjustment means for adjusting the type and design of the product based on the emotion; A system including:

2. The system according to claim 1 , wherein the suggestion means suggests products that suit the user's preferred style, budget, age, and build.

3. The system according to claim 1 , wherein the suggestion means displays on the terminal a hyperlink web link of a web page for the user to purchase the product in the list.

Images