JP2026019738A - system - Google Patents

Abstract

A system is provided.
A means for inputting user's body type information;
A means for taking and uploading full-body photographs of the user from multiple angles;
a means of collecting data on the clothing being sold;
means for synthesizing clothing onto the generated 3D model of the user;
means for displaying try-on images on a user's device;
A system including:
[Selected Figure] Figure 1

Description

The technology disclosed herein relates to a system.

Patent document 1 discloses a persona chatbot control method executed 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's character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Japanese Patent Application Laid-Open No. 2022-180282

Today, many working people are too busy to find time to go to stores, and are increasingly purchasing clothing online. However, when they actually purchase something, the size or image may differ from what they expected, leaving them feeling anxious and dissatisfied. Furthermore, since they cannot try on the clothes, they are unable to see how the overall outfit will look. This often forces them to return the item after purchase, resulting in wasted time and money for both the user and the seller. The present invention aims to solve these problems.

The present invention provides a means for users to input their own body type information and upload full-body photos taken from multiple angles. It also provides a means for collecting data on clothing sold in online stores, which generates a 3D model of the user based on the user's body type information and photographic data. By providing a means for overlaying clothing onto the 3D model, users can accurately view images of how the clothing will look when tried on on their own device. Furthermore, by providing a means for users to request coordination suggestions from a salesperson, generate images of the suggested coordination to try on, and display them on the user's device, users can enjoy creating a total outfit that suits them online.

"User's body type information" refers to the user's specific body measurements, such as the user's height, weight, and three sizes.

"Full-body photos" refer to photo data of the front, back, and side taken by the user from multiple angles.

"Clothing data" refers to detailed information about clothing sold in online stores, such as images, sizes, materials, and colors.

A "3D model" is a high-resolution three-dimensional representation generated based on the user's body shape information and full-body photograph data.

"Try-on image" refers to a virtual image of the garment being worn, generated by combining the selected garment with the user's 3D model.

"Coordination suggestions" refer to combinations of multiple items of clothing and accessories that a salesperson suggests based on the user's body type and preferences.

"Salesperson" refers to an online fashion advisor who provides coordination suggestions to users.

1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. 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. FIG. 10 is a conceptual diagram illustrating an example of the configuration of a data processing system according to a second embodiment. 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. FIG. 10 is a conceptual diagram illustrating an example of the configuration of a data processing system according to a third embodiment. 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. FIG. 10 is a conceptual diagram illustrating an example of the configuration of a data processing system according to a fourth embodiment. 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. 1 shows an emotion map onto which multiple emotions are mapped. 1 shows an emotion map onto which multiple emotions are mapped. FIG. 2 is a sequence diagram illustrating a processing flow of the data processing system according to the first embodiment. FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in application example 1. FIG. 10 is a sequence diagram showing the flow of processing of the data processing system in the second embodiment when an emotion engine is combined. FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined.

Below, an example of an embodiment of a system relating to the technology disclosed herein will be described with reference to the accompanying drawings.

First, let me explain the terminology used in the following explanation.

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

In the following embodiments, coded random access memory (RAM) is memory in which information is temporarily stored and is used by the processor as work memory.

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

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

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 just A, just B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and/or B" also applies when three or more things are expressed connected by "and/or."

[First embodiment]

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

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

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, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and 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).

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, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

The reception device 38 is equipped with a touch panel 38A, a microphone 38B, etc., and receives user input. The touch panel 38A detects contact with an indicator (e.g., a pen or finger) to receive user input via the indicator. The microphone 38B detects the user's voice to receive user input via 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.

The output device 40 is equipped with a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible by the user 20 (e.g., 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.

The communication I/F 44 is connected to the 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.

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

As shown in FIG. 2, in the data processing device 12, specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" 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.

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.

In the smart device 14, the processor 46 performs the reception output processing. 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 processing 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.

Next, we will explain the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart device 14 will be referred to as the "terminal."

This invention is a virtual try-on system that uses the user's body type information and full-body photos taken from multiple angles to generate a fitting image tailored to the user. The system begins by the user entering body type information and uploading a full-body photo using their own device. The system then utilizes a generative AI model based on the collected clothing data to synthesize the clothing onto the user's 3D model and present a virtual fitting image. In addition, users can receive coordination suggestions from sales staff, making the process of selecting and purchasing clothing even more enjoyable.

1. Enter your body type information and upload a full-body photo.

Users launch the application and enter their body information, such as their height, weight, and measurements. They also upload full-body photos taken from the front, back, and side.

The device sends the body type information entered by the user and the full-body photo taken to the server.

2. Clothing data collection

The server collects data about clothing sold online (images, sizes, materials, colors, etc.) using APIs or web scraping technology from partner online stores and stores it in a database.

3. 3D model generation and synthesis

The server analyzes the user's body shape information and uploaded full-body photos to generate a high-resolution 3D model of the user.

The server uses a generative AI model to synthesize the user's selected clothing onto the 3D model, using deep learning techniques to realistically recreate the clothing's fit and texture.

4. Showing a fitting image

The server then sends the generated try-on images taken from multiple angles to the user's device.

The device displays the received try-on images on the user interface.

Users can review the displayed try-on images and, if necessary, request images from different angles or images of other garments.

5. Coordination suggestions and purchasing procedures

If the user would like outfit suggestions, they can click the "Request outfit suggestions" button.

The server sends a request to the salesperson in charge of coordinating the outfit.

The salesperson suggests appropriate outfits based on the user's body type and preferences, and sends feedback to the server.

The server generates images of the suggested outfits to try on and displays them on the user's device.

The user reviews the suggested outfits and clicks the "Purchase" button if they decide to purchase.

The terminal sends the purchase information to the server and connects to the online store's payment system.

This invention allows users to easily select clothing that fits their body type and experience the virtual fitting process as if they were actually trying it on. Furthermore, they can smoothly complete the online purchase process while checking suggested outfits.

The processing flow is explained below.

Step 1:

Users launch the application and enter their body information, such as height, weight, and measurements. They also upload full-body photos taken from the front, back, and side.

Step 2:

The device sends the body shape information and full-body photo entered by the user to the server.

Step 3:

The server analyzes the received body shape information and full-body photo data to generate a high-resolution 3D model of the user. This analysis is performed using image recognition algorithms.

Step 4:

The server uses APIs or web scraping technology from partner online stores to collect data on the clothing being sold (images, sizes, materials, colors, etc.) and stores it in a database.

Step 5:

The server then synthesizes the clothing selected by the user onto the generated 3D model of the user, using a generative AI model to realistically recreate the fit and texture of the clothing.

Step 6:

The server then sends the generated try-on images taken from multiple angles to the user's device.

Step 7:

The device displays the received try-on images on the user interface.

Step 8:

The user reviews the displayed try-on images. If necessary, they can request try-on images from different angles or images of other garments.

Step 9:

If the user would like outfit suggestions, they can click the "Request outfit suggestions" button.

Step 10:

The server sends a request to the salesperson in charge of coordinating the outfit.

Step 11:

The salesperson suggests appropriate outfits based on the user's body type and preferences, and sends feedback to the server.

Step 12:

The server generates images of the suggested outfits to try on and sends them to the user's device.

Step 13:

The device displays the received outfit try-on image on the user interface.

Step 14:

The user reviews the suggested outfits and clicks the "Purchase" button if they decide to purchase.

Step 15:

The device sends the purchase information to the server.

Step 16:

The server records purchase information and connects it to the online store's payment system.

Step 17:

The server notifies the user of the order confirmation and delivery information.

Step 18:

The terminal will display order confirmation and shipping information to the user.

(Example 1)

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

Traditional online shopping has the problem that users cannot accurately understand how clothes will fit or how the design will look on them unless they actually try them on. Furthermore, coordination suggestions tailored to the user's preferences and the ability to check how the clothes will look when tried on are insufficient, which discourages users from making a purchase. This has led to a decline in user satisfaction with online shopping.

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

In this invention, the server includes means for inputting the user's body type information, means for taking and uploading full-body photos of the user from multiple angles, means for collecting data on clothing sold online, means for combining clothing with the generated high-resolution 3D model of the user, means for sending the generated try-on images to the user's device, and means for displaying the try-on images on the user's device. This allows users to easily select clothing that fits their body type and experience the virtual try-on experience as if they were actually trying on the clothes. In addition, users can request coordination suggestions from a salesperson and check the suggested try-on images, which increases the user's desire to purchase.

"User" refers to an individual who uses the system to enter body type information and take and upload full-body photos.

"Body type information" refers to detailed data about the user's body, such as their height, weight, and measurements.

"Full-body photos" refer to images of the user's body taken from multiple angles, including the front, back, and side.

"Data on clothing sold online" refers to information such as clothing images, sizes, materials, and colors collected from online sales sites and stores.

"High-resolution 3D model" refers to a three-dimensional computer graphics model that reproduces the user's body in detail, generated based on the user's body shape information and a full-body photograph.

"Generative AI model" refers to an artificial intelligence model trained using deep learning technology to realistically synthesize clothing onto a user's 3D model.

"Try-on image" refers to an image created by combining the selected clothing onto the user's 3D model using a generative AI model.

"User's device" refers to the electronic device used by the user, such as a smartphone, tablet, or PC.

"Coordination suggestions" refer to combinations of multiple items of clothing recommended by a salesperson based on the user's body type information and preferences.

"Salesperson" refers to a person in charge of making outfit suggestions to users through the system.

This invention is a virtual try-on system that uses the user's body type information and full-body photographs taken from multiple angles to generate a fitting image tailored to the user. In this system, the program is executed in the following steps:

First, the user launches a dedicated application on their smartphone or PC and enters their body information, including height, weight, and measurements. The user then takes full-body photos of the front, back, and side and uploads them to the application. This uploaded data is then sent to the server via the device.

The device securely transmits input and uploaded data to the server using the HTTPS protocol. The server receives this data and uses the image analysis technology OpenCV to analyze the user's body shape with high accuracy. The deep learning frameworks TensorFlow and PyTorch are used to generate a high-resolution 3D model based on the analyzed data.

After generating a 3D model for the user, the server uses APIs or web scraping technology from partner online stores to collect data about clothing sold online. This data includes clothing images, sizes, materials, colors, etc. This data is stored in a database and used to synthesize clothing onto the user's 3D model.

The server then uses a generative AI model to synthesize the clothing selected by the user onto the generated 3D model. The generative AI model is trained using deep learning technology to realistically reproduce the fit and texture of the clothing. Deep learning algorithms using TensorFlow and PyTorch are used in this process.

The generated try-on images are photographed from multiple angles and sent to the user's device as JPEG or PNG image files. The device displays the received try-on images on the application's user interface. The user can review the displayed try-on images and request images from different angles or try-on images of other garments as needed.

Furthermore, if the user wishes to receive outfit suggestions, they click the "Request outfit suggestions" button. The server sends a request to the salesperson in charge of outfit suggestions, who then suggests an appropriate outfit based on the user's body type and preferences and sends feedback to the server. Based on this feedback, the server generates a new try-on image and displays it on the user's device. Finally, the user checks the suggested outfit and clicks the "Purchase" button if they decide to purchase. This purchase information is sent to the server via the device, and the purchase process is carried out in conjunction with the online store's payment system.

Specific examples

For example, if a user wants to try on "blue jeans" and a "white T-shirt,"

1. The user enters their height as 170cm, weight as 65kg, and measurements as 90-75-90, and uploads full-body photos of the front, back, and side.

2. The device sends this information to the server.

3. The server uses web scraping technology to collect data on "blue jeans" and "white T-shirts" and stores it in a database.

4. The server uses image analysis technology to generate a high-resolution 3D model of the user, and then uses a generative AI model to synthesize jeans and a T-shirt onto the 3D model.

5. The server generates try-on images from multiple angles and sends them to the user's device.

6. The user can check the newly generated try-on image and then decide to "purchase this outfit."

Example prompt

"Enter your height, weight, and measurements, and upload full-body photos taken from the front, back, and side."

This system allows users to easily find clothes that fit their body type and experience the same sensation of trying them on in real life through virtual try-on. They can also request outfit suggestions and check the suggested try-on images, making online clothing shopping a smoother and more satisfying experience.

The flow of the identification process in Example 1 will be explained using Figure 11.

Step 1:

The user launches the application.

Specific operation: The user taps or clicks on the dedicated application on their smartphone or PC to launch it and proceeds to the first screen.

Input: None

Output: The application launches and displays a screen where the user can enter body information.

Step 2:

The user enters body type information.

Specific operation: The user enters body information such as height, weight, and measurements into the application form. They also provide full-body photos taken from the front, back, and side.

Input: Body information such as height, weight, and measurements

Output: Display of entered body shape information and full-body photo

Step 3:

Users upload full-body photos.

Specific operation: The user uploads full-body photos of the front, back, and side using the upload function within the application.

Input: Full-body photos (front, back, and side)

Output: Full-body photo upload complete message

Step 4:

The device sends the input data to the server.

Specific operation: The device sends the user's body shape information and full-body photo to the server via the HTTPS protocol.

Input: User's body type information and full-body photo

Output: The data is sent to the server and awaits processing.

Step 5:

The server analyzes body shape information and full-body photos.

Specific operation: The server performs image analysis using OpenCV and extracts the features necessary to create a 3D model based on the user's body shape information.

Input: Body information and full-body photo

Output: Feature-extracted data

Step 6:

The server generates a high-resolution 3D model.

Specific operation: The server uses TensorFlow and PyTorch for deep learning to generate a high-resolution 3D model based on the user's body shape.

Input: Feature-extracted data

Output: High-resolution 3D model

Step 7:

The server collects data on clothing sold online.

Specific operation: The server calls the API of partner online stores or uses web scraping to collect the latest clothing data (images, sizes, materials, colors, etc.).

Input: API endpoint of affiliated online store or URL of scraping target

Output: Latest clothing data stored in the clothing database

Step 8:

The server uses a generative AI model to synthesize the clothing onto the 3D model.

Specific operation: The server uses a generative AI model to synthesize clothing onto the user's 3D model based on the collected clothing data.

Input: 3D model and clothing data

Output: Try-on images from multiple angles

Step 9:

The server sends the generated try-on image to the device.

Specific operation: The server generates try-on images in JPEG or PNG format and sends them to the user's device. High-speed data transfer may also be performed via a CDN.

Input: Try-on image

Output: Try-on image sent to the device

Step 10:

The device displays the try-on image on the user interface.

Specific operation: The device displays the received try-on images on the application's user interface, allowing the user to operate them.

Input: Try-on image

Output: Try-on image displayed on the user interface

Step 11:

Users can check the fitting images and submit requests if necessary.

Specific operation: The user reviews the try-on images and, if they wish to request images from different angles or images of other garments being tried on, clicks the corresponding button in the application.

Input: User request

Output: The request is sent to the server.

Step 12:

The user requests outfit suggestions.

Specific operation: If the user would like outfit suggestions, they click the "Request outfit suggestions" button.

Input: User's outfit suggestion request

Output: The request is sent to the server.

Step 13:

The server sends the request to the salesperson.

Specific operation: The server sends a coordination suggestion request to the salesperson, along with the necessary user information.

Input: User request

Output: The request is sent to the salesperson.

Step 14:

Salespeople will provide feedback on suggestions.

Specific operation: The salesperson considers the appropriate outfit based on the user's body type and preferences, and sends feedback to the server.

Input: User's body type and preferences

Output: Feedback on outfit suggestions

Step 15:

The server generates images of outfits to try on.

Specific operation: The server generates new try-on images based on feedback from the salesperson and sends them to the user's device.

Input: Feedback on outfit suggestions

Output: Try-on image of outfit sent to device

Step 16:

The user reviews the offer and decides to purchase.

Specific operation: The user checks the newly generated outfit try-on image and, if they like it, clicks the "Purchase" button.

Input: Coordination try-on image

Output: Purchase request sent to server

Step 17:

The device sends purchase information to the server and connects with the online store.

Specific operation: The terminal sends purchase information to the server, and the server works with the online store's payment system to complete the purchase process.

Enter: Purchase information

Output: The purchase is completed and a confirmation is sent to the user.

(Application Example 1)

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

Traditionally, trying on clothes in physical stores was time-consuming and labor-intensive. Additionally, the types of clothing that could be tried on were limited, making it difficult to try out many options. Furthermore, with online shopping, customers were unable to see how the actual product would look, leading to frequent returns and exchanges after purchase. To solve these problems, a system was needed that allowed users to easily try on clothes and select the best fit for their body type.

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

In this invention, the server includes means for inputting a user's body type information, means for taking and uploading full-body photos of the user from multiple angles, means for collecting data on available items, means for overlaying items onto the generated 3D model of the user, means for presenting virtual try-on images to the user's device, means for the user to input body type information and upload a full-body photo using their own device, means for collecting and saving data on items sold online using the API or web scraping technology of affiliated online stores, means for analyzing the user's body type information and uploaded full-body photos and generating a high-resolution 3D model of the user, and means for generating try-on images from multiple angles and sending them to the user's device. This allows users to smoothly try on clothes virtually in a physical store, shortening the time it takes to actually try them on and combining the convenience of online shopping with the experience of a physical store.

"User's body type information" refers to the user's physical measurements and characteristics, such as height, weight, and three sizes.

A "full-body photo" is a photo that shows the user's entire body, and includes multiple photos taken from the front, back, and side.

"Purchasable Item Data" refers to information about products such as clothing and accessories sold at affiliated online stores and in-store, including attributes such as images, size, material, and color.

"3D model" refers to a high-resolution three-dimensional digital model generated based on the user's body shape information and full-body photograph.

"Means for synthesizing items" refers to the process of virtually applying selected clothing and accessories to the generated 3D model of the user to generate a realistic try-on image.

"Virtual try-on image" refers to an image that combines selected clothing and accessories with a 3D model of the user, simulating trying on the clothing and accessories from multiple angles.

"Affiliated Online Store API" refers to an application programming interface for automatically obtaining data on products sold by affiliated online stores.

"Web scraping technology" refers to technology that automatically extracts data from websites.

"Means for generating a high-resolution 3D model" refers to the process of analyzing a user's body shape information and full-body photograph to create a highly accurate three-dimensional digital model.

"Means to request outfit suggestions" refers to the function that allows a user to request outfit suggestions from a salesperson based on the user's preferences.

"Virtual try-on" refers to the act of allowing a user to try on an item on a digital model instead of actually trying it on.

This invention is a system that uses a user's body type information and full-body photograph to enable virtual try-on, improving the fitting experience in physical stores. The system is built using the user's device (smartphone), a series of servers, and APIs or web scraping technologies from affiliated online stores.

Program generation

The system uses the following hardware and software:

User device (smartphone): Android or iOS device with camera functionality

Server: Data processing and generative AI model execution (using TensorFlow or PyTorch)

Partner online store API or web scraping technology (Beautiful Soup, Scrapy, etc.)

Database: MySQL or PostgreSQL

Program processing overview

The server first receives the body shape information and full-body photo sent by the user from their device, and then uses image analysis technology to generate a high-resolution 3D model of the user. This 3D model is precisely created using deep learning, recreating a realistic fit to the user's body shape.

The server then uses clothing data collected from partner online stores to synthesize the selected clothing onto the user's 3D model. This synthesis process utilizes generative AI models to accurately reproduce the texture and fit of the clothing. Try-on images taken from multiple angles are generated and sent to the user's device.

Users can check the virtual try-on images on their devices and, if they like them, proceed with the purchase process. Furthermore, if users would like a coordination suggestion, they can send a request to the salesperson. The coordination suggested by the salesperson is then regenerated as a virtual try-on image and presented to the user.

Examples and prompts

As a specific prompt, when collecting clothing data using the API of a partner online store, run the following command:

curl -X GET "https://netstore.com/api/v1/products" -H "Authorization: Bearer YOUR_API_KEY"

Also, if you use web scraping technology, here's a script that uses Python's Beautiful Soup to extract product data from a specified URL:

from bs4 import BeautifulSoup

Import requests

url = "https://netstore.com/products"

response = requests.get(url)

soup = BeautifulSoup(response.content, 'html.parser')

for product in soup.find_all('div', class_='product'):

product_name = product.find('h2').get_text()

product_price = product.find('span', class_='price').get_text()

print(product_name, product_price)

This system allows users to seamlessly try on clothes virtually in a physical store, shortening the time spent trying them on in person and combining the convenience of online with the experience of a physical store.

The flow of the specific processing in Application Example 1 will be explained using Figure 12.

Step 1:

The user enters their body type information into the terminal. The user enters physical attributes such as height, weight, and measurements into the terminal, and the entered data is sent to the server. At this point, the input is the user's physical numerical data, and the output is raw data sent to the server.

Step 2:

The user takes full-body photos from multiple angles and uploads them via their device. The user takes photos from the front, back, and side using the device's camera and sends the image data to the server. At this point, the input is multiple image files, and the output is image data stored on the server.

Step 3:

The server uses the API of a partner online store or web scraping technology to collect data on the items being sold. Specifically, the server sends a request to an API endpoint and receives product information in response, or parses a web page to obtain the required product data. At this point, the input is the API request or HTML content, and the output is a set of product data.

Step 4:

The server analyzes the user's body shape information and full-body photo to generate a high-resolution 3D model. The collected image data and body shape information are analyzed using a deep learning model (using TensorFlow and PyTorch) to create a highly accurate 3D model of the user. At this point, the input is body shape information and image data, and the output is a 3D model.

Step 5:

The server uses a generative AI model to synthesize the selected item onto a 3D model. The user selects from the collected product data and synthesizes it onto the 3D model to create a virtual try-on image. The generative AI model reproduces the texture and fit of the clothing with high accuracy. At this point, the input is the 3D model and product data, and the output is a try-on image.

Step 6:

The server then sends the generated try-on images, photographed from multiple angles, to the user's device. These images are displayed on the user's device, allowing the user to check the virtual try-on image. At this point, the input is the try-on image data, and the output is the virtual try-on image displayed on the user's device.

Step 7:

When a user requests a coordination suggestion, they send a request from their terminal to the server. The server receives this request and notifies the salesperson in charge. At this point, the input is the request from the user, and the output is a notification to the salesperson.

Step 8:

The salesperson creates a coordination suggestion and sends feedback to the server. The server again generates a virtual try-on image of the suggested coordination based on the user's 3D model. At this point, the input is the coordination suggestion from the salesperson, and the output is a new try-on image.

Step 9:

The server sends the generated coordinated try-on image to the user's device, where the user confirms it. If the user decides to purchase, they click the "Purchase" button on their device, and the purchase information is sent to the server. The input at this point is the virtual try-on image and the user's purchase decision, and the output is the progress of the purchase procedure.

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.

This invention combines a virtual try-on system that generates a 3D model based on the user's body type information and full-body photographs from multiple angles, then synthesizes clothing onto it, with an emotion engine that recognizes the user's emotions. This system can suggest clothing and outfits that correspond to the user's emotions, providing a more personalized shopping experience.

1. Enter your body type information and upload a full-body photo.

Users launch the application and enter their body information (height, weight, measurements, etc.). They also upload full-body photos taken from multiple angles.

The device sends this body shape information and a full-body photo to the server.

2. Clothing data collection

The server uses API or web scraping technology to collect data on the clothing being sold (images, sizes, materials, colors, etc.) from partner online stores and stores it in a database.

3. 3D model generation and clothing synthesis

The server analyzes the user's body shape information and full-body photo data to generate a high-resolution 3D model of the user, using the latest image recognition algorithms.

The server uses a generative AI model to synthesize the selected clothing onto the 3D model. This process utilizes deep learning techniques to realistically recreate the fit and texture of the clothing.

4. Showing a fitting image

The server then sends the generated try-on images taken from multiple angles to the user's device.

The device displays the received try-on images on the user interface.

The user can review the displayed try-on images and, if necessary, request images from different angles or to try on other garments.

5. Emotion Recognition Using an Emotion Engine

The device uses an emotion engine to analyze the user's facial expressions and voice to identify their emotional state. This is done by capturing data in real time using a camera and microphone.

The server evaluates the user's reaction to the try-on images based on emotional data from the emotion engine.

6. Coordination proposals and adjustments

If the user would like outfit suggestions, they can click the "Request outfit suggestions" button.

The server sends a request to the salesperson in charge of coordinating the outfit.

The salesperson suggests appropriate outfits based on the user's body type, preferences, and emotional data, and sends feedback to the server.

The server generates images of the suggested outfits to try on and displays them on the user's device. It also adjusts the suggestions in real time based on the user's emotional data.

7. Purchase Procedure

The user reviews the suggested outfits and clicks the "Purchase" button if they decide to purchase.

The terminal sends the purchase information to the server and connects to the online store's payment system.

The server records the purchase information and notifies the user of the order confirmation and shipping information.

The terminal will display order confirmation and shipping information to the user.

The system of the present invention allows users to easily select clothing that fits their body type and experience the virtual fitting process as if they were actually trying it on. Furthermore, by utilizing an emotion engine to make suggestions based on the user's emotional state, a more personalized shopping experience is realized. This series of processes increases user satisfaction and improves the online shopping experience.

The processing flow is explained below.

Step 1:

Users launch the application and enter their body information, such as height, weight, and measurements. They also upload full-body photos taken from the front, back, and side to the application.

Step 2:

The device sends the body shape information and full-body photo entered by the user to the server.

Step 3:

The server analyzes the received body shape information and full-body photo data and uses image recognition algorithms to generate a high-resolution 3D model of the user.

Step 4:

The server uses API or web scraping technology to collect data on the clothing being sold (images, sizes, materials, colors, etc.) from partner online stores and stores it in a database.

Step 5:

The server then synthesizes the clothing selected by the user onto the generated 3D model of the user, using the generative AI model to realistically reproduce the fit and texture of the clothing.

Step 6:

The server then sends the generated try-on images taken from multiple angles to the user's device.

Step 7:

The device displays the received try-on images on the user interface.

Step 8:

The user reviews the displayed try-on images. If necessary, they can request images from different angles or try on other garments.

Step 9:

The device captures the user's facial expressions with a camera or collects their voice with a microphone, and then sends this data to the emotion engine.

Step 10:

The server uses an emotion engine to analyze the user's facial expressions and voice to identify their emotional state. For example, if the user is smiling, it will be identified as "satisfied," and if they are frowning, it will be identified as "anxious."

Step 11:

The server determines the next action based on the emotional state data from the emotion engine. For example, if the user is satisfied, it continues with the suggestion, but if they are anxious, it presents a different option.

Step 12:

If the user would like outfit suggestions, they can click the "Request outfit suggestions" button.

Step 13:

The server sends a request to the salesperson in charge of coordinating the outfit.

Step 14:

The salesperson suggests appropriate outfits based on the user's body type, preferences, and emotional data, and sends feedback to the server.

Step 15:

The server generates images of the suggested outfits to try on and sends them to the user's device. It also adjusts the suggestions in real time based on the user's emotional data.

Step 16:

The device displays the received outfit try-on image on the user interface.

Step 17:

The user reviews the suggested outfits and clicks the "Purchase" button if they decide to purchase.

Step 18:

The device sends the purchase information to the server.

Step 19:

The server records the purchase information and notifies the user of the order confirmation and shipping information.

Step 20:

The terminal will display order confirmation and shipping information to the user.

(Example 2)

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

In recent years, with the spread of online shopping, there has been an increasing demand for remote try-on and personalized shopping experiences. However, current systems have difficulty adequately reproducing the fit and texture of clothing when actually trying on, and are unable to make suggestions based on the user's emotions. Therefore, there is a need for a more realistic virtual try-on system to improve the user experience.

The specific processing performed by the specific 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 inputting the user's body type information, means for taking and uploading full-body images of the user from multiple angles, means for collecting data on clothing available for sale, means for combining clothing items with the generated three-dimensional model of the user, means for presenting images of the items to be tried on on the user's device, means for analyzing the user's facial expressions and voice to recognize emotions, and means for adjusting suggestions based on emotions. This allows the user to virtually try on clothing that fits their body type and receive personalized suggestions based on their emotional state.

"Means for inputting user's body type information" refers to an interface and system for inputting data related to the user's body type, such as height, weight, and measurements.

"Means for taking and uploading full-body images of the user from multiple angles" refers to the camera and upload function for taking images of the user's entire body from different angles and uploading that image data to the system.

"Means for collecting data on clothing for sale" refers to technology for collecting and storing data such as images, sizes, materials, and colors of clothing for sale from online stores and other sources.

"Means for combining clothing items with a generated 3D model of the user" refers to an algorithm and system for realistically combining selected clothing items with a 3D model generated based on the user's body shape information and full-body image.

"Means for presenting try-on images on the user's device" refers to the interface and system for displaying the generated try-on images on the screen of the user's device (smartphone, tablet, PC, etc.).

"Means for analyzing a user's facial expressions and voice to recognize emotions" refers to algorithms and systems that analyze a user's facial expressions and voice data acquired using devices such as cameras and microphones, and identify the user's emotional state.

"Means for adjusting suggestions based on emotions" refers to technology and systems for changing and adjusting suggested clothing and outfits in real time based on the user's emotional data.

This invention is a virtual fitting system that generates a high-resolution three-dimensional model based on the user's body type information and full-body image, and then realistically combines clothing onto it. It also has the ability to analyze the user's emotions from their facial expressions and voice, and adjust clothing suggestions based on that.

This system uses the following hardware and software:

An interface for inputting the user's body shape information (such as a smartphone or PC)

A camera that captures a full-body image of the user (such as a camera built into a smartphone)

API or web scraping tool for collecting data on clothing for sale

Generative AI models for generating 3D models (e.g., deep learning models built in Python)

A user interface that displays synthesized try-on images

Emotion recognition engine for analyzing user facial expressions and voice (e.g., emotion analysis API)

This system performs the following processes:

The user enters their body type information through the launched application and takes and uploads full-body images from multiple angles. The device then sends this data to the server. The server then collects data on clothing for sale from online stores using APIs or web scraping technology and stores it in a database. The server analyzes the user's body type information and full-body images and uses a generative AI model to generate a high-resolution 3D model of the user. The server then combines the clothing selected by the user into the 3D model to generate a realistic try-on image. This try-on image is then sent to the user's device and displayed.

In addition, the device uses a camera and microphone to capture the user's facial expressions and voice in real time, and analyzes their emotions using an emotion recognition engine. The server then uses this emotional data to adjust the suggested clothing and outfits in real time.

As a concrete example, suppose a user inputs their height (170cm), weight (65kg), and measurements (B:95cm, W:75cm, H:95cm), and uploads full-body images from the front and side. Based on this, the server generates a 3D model of the user and synthesizes a navy jacket. An example prompt for this stage is: "Based on the user's height of 170cm, weight (65kg), and measurements (B:95, W:75, H:95), generate a 3D model based on full-body front and side photos and synthesize a high-resolution navy jacket. Also, recognize positive emotions from the user's smiling face and suggest further outfit recommendations."

The system allows users to virtually try on clothes that fit their body type and receive personalized suggestions based on their emotional state.

The flow of the identification process in Example 2 will be explained using Figure 13.

Program processing flow

Step 1:

The user launches the application and enters their body type information.

Input: User's body information (height, weight, measurements, etc.)

Output: Body shape information is saved in the system.

Specific operation: The user enters body type information into the application's input fields and clicks the "Submit" button. This information is sent to the server via the device.

Step 2:

Users take full-body images from multiple angles and upload them.

Input: Full-body images of the user taken from the front and side

Output: The whole-body image is saved to the system.

Specific operation: The user uses the smartphone camera to take full-body images of themselves from multiple angles, selects the images in the application, and clicks the "Upload" button. The image data is sent to the server via the device.

Step 3:

The server collects clothing data from affiliated online stores.

Input: Online store API information or web page URL

Output: Garment data (images, size, material, color, etc.) is saved in a database.

Specific operation: The server automatically collects clothing data from online stores using APIs and web scraping tools. When collecting data, it also checks for duplicates and missing data.

Step 4:

The server analyzes the user's body shape information and full-body image, and generates a 3D model using a generative AI model.

Input: User's body shape information and full-body image

Output: High-resolution 3D model of the user

How it works: The server uses deep learning algorithms to analyze the user's body shape information and full-body image to generate a 3D model. This process utilizes a GPU to speed up calculations.

Step 5:

The server synthesizes the user's selected clothing onto a 3D model.

Input: User's 3D model and selected clothing data

Output: Composite fitting image

Specific operation: The server uses a generative AI model to synthesize the selected clothing onto the user's 3D model in a way that realistically reproduces the fit and texture. As a result, a fitting image is generated.

Step 6:

The server sends the generated try-on image to the user's device.

Input: Synthesized fitting image

Output: Try-on image displayed on the user's device

Specific operation: The try-on image is encoded as images taken from multiple angles and sent from the server to the device. The device displays it on the user interface.

Step 7:

The device captures the user's facial expressions and voice and analyzes them using an emotion recognition engine.

Input: User's facial and voice data

Output: User emotion data

Specific operation: The device uses a camera and microphone to capture the user's facial expressions and voice in real time, and then analyzes this data with an emotion recognition engine to identify the user's emotional state.

Step 8:

The server analyzes the emotional data and adjusts the suggestions in real time.

Input: User emotion data

Output: Adjusted proposal content

Specific operation: Based on the emotional data, the server changes and adjusts the fitting images and outfit suggestions in real time to provide optimal suggestions.

Step 9:

The user selects the suggested outfit and completes the purchase process.

Input: User purchase decision information

Output: Purchase confirmation and shipping information

Specific operation: When the user clicks the "Purchase" button, the device sends this information to the server. The server then links the purchase information to the online store's payment system and completes the purchase process. The user is then notified of order confirmation and delivery information.

This allows users to virtually try on clothes that fit their body type, receive personalized suggestions based on their emotions, and enjoy an optimal shopping experience.

(Application Example 2)

Next, we will explain Application Example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart device 14 will be referred to as the "terminal."

Conventional virtual try-on systems were able to generate fitting images based on the user's body type information, but were unable to make suggestions that took the user's emotions into account. This made it difficult to improve the user's satisfaction with the clothing and outfits they selected. Furthermore, the lack of coordination adjustments based on real-time emotional feedback meant they were unable to fully meet the individual needs of users.

The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting the user's physique information, means for taking and uploading full-body photos of the user from multiple angles, means for collecting data on clothing for sale, means for combining clothing with the generated high-resolution 3D model of the user, means for analyzing the user's emotions and suggesting clothing and outfits based on the emotion data, and means for presenting images of the clothing to be tried on on the user's device. This makes it possible to suggest personalized clothing and outfits based on the user's emotions, improving user satisfaction. Furthermore, by adjusting the suggestions based on real-time emotion feedback, it is possible to more appropriately meet the individual needs of the user.

"User's body type information" refers to data related to the user's body measurements, such as height, weight, and three sizes.

A "full-body photo" is an image of the user taken from multiple angles (front, back, side, etc.).

"Data on clothing for sale" refers to detailed information such as clothing images, sizes, materials, and colors collected from affiliated online stores.

A "high-resolution 3D model" is a 3D model that is generated based on the user's body type information and a full-body photograph, and is rendered in great detail.

"Clothing synthesis" is a technology that uses data on clothing for sale to realistically display clothing on the generated high-resolution 3D model.

"Means for analyzing emotions and suggesting clothing and outfits based on emotional data" refers to technology that analyzes a user's facial expressions and voice, and then suggests the most suitable clothing and outfits for the user based on the emotional data obtained from this.

"Means for presenting try-on images" refers to technology that displays the generated virtual try-on images on the user's device.

"Emotional data" is data that represents emotional states such as joy, surprise, and dissatisfaction obtained from the analysis of the user's facial expressions and voice.

"Coordination" refers to the user's clothing combination and includes the selection process.

"Feedback" is the process of adjusting and re-proposing suggestions based on the user's emotional data.

This invention is a virtual fitting system that generates a 3D model based on the user's body type information and full-body photographs from multiple angles, then synthesizes clothing onto it, combined with an emotion engine that recognizes the user's emotions. This system can suggest clothing and outfits based on the user's emotions, providing a more personalized shopping experience.

The server realizes this system by integrating the following technologies: First, the server provides a means for users to input their body type information. This allows users to enter information such as their height, weight, and three sizes. It also provides a means for users to upload full-body photos taken from multiple angles. This allows users to upload photos of their front, side, and back.

The server has a means of collecting data on clothing for sale from online stores and other data sources. This data includes detailed information such as clothing images, sizes, materials, and colors. The server then uses the latest image recognition algorithms (e.g., TensorFlow) to analyze the user's body shape information and full-body photo data to generate a high-resolution 3D model. This 3D model is then used to synthesize clothing using deep learning technology to generate realistic try-on images.

Furthermore, it has a means of analyzing the user's facial expressions and voice using an emotion engine (e.g., Affectiva API) to obtain emotional data. It also incorporates a means of suggesting the most suitable clothing and outfits for the user based on the emotional data. This makes it possible to make appropriate suggestions in real time based on the user's emotions.

A means of displaying try-on images on the user's device has also been developed, allowing the user to view the generated virtual try-on image from multiple angles. After the try-on image is displayed, the user can provide feedback on their emotional data on the spot and adjust their outfit as needed.

For example, a user enters their height and weight into the app and uploads three full-body photos (front, back, and side). After the photo shoot is complete, emotion analysis is performed and if the user is happy, the system will suggest outfits in bright colors and the latest fashions. On the other hand, if the user is unhappy, the system will adjust to suggest new outfits.

An example of a prompt statement is as follows:

The user is 170cm tall and weighs 65kg. Front, back, and side photos have been uploaded. Sentiment analysis indicates that the user is currently feeling "joy." Based on this, suggest multiple outfits in bright colors and the latest fashions.

In this way, users can choose the clothing that best suits their body type and get the feeling of trying it on in real life through a virtual try-on experience. Real-time emotional feedback provides a more personalized shopping experience.

The flow of the specific processing in Application Example 2 will be explained using Figure 14.

Step 1:

Users launch the application, enter their body type information (height, weight, measurements, etc.), and upload full-body photos taken from multiple angles (front, back, side). The entered data consists of body type information and photo data, which are sent from the device to the server. As a result, data related to the user's body type and full-body photos is stored on the server.

Step 2:

The server collects data about clothing sold (images, sizes, materials, colors, etc.) from online stores and other data sources. This collection is done using APIs or web scraping technology. The acquired data is stored in a database on the server. The input is clothing data, and the output is clothing data stored in the database.

Step 3:

The server uses the latest image recognition algorithms (e.g., TensorFlow) to analyze the user's body shape information and full-body photo data and generate a high-resolution 3D model. During this process, each user's photo is pixel-analyzed to create the shape of the 3D model. The input for this step is the user's body shape information and photo data, and the output is a high-resolution 3D model.

Step 4:

The server uses a generative AI model to synthesize clothing for sale onto the generated 3D model. Utilizing deep learning technology, data processing is performed to realistically reproduce the fit and texture of the clothing. The input is a high-resolution 3D model and clothing data, and the output is a try-on image.

Step 5:

The device uses an emotion engine (e.g., Affectiva API) to analyze the user's facial expressions and voice in real time and obtain emotional data. Captured facial and voice data is input, and analyzed emotional data is output. In this step, the device obtains data using the camera and microphone.

Step 6:

The server suggests optimal clothing and outfits for the user based on emotional data. The input is emotional data, and the output is outfit suggestions tailored to the user's preferences. These suggestions are made dynamically and adjusted in real time.

Step 7:

The user's device displays the try-on images sent from the server. The input is the try-on image, and the output is the try-on image displayed on the user interface. The user can review the displayed try-on image and, if necessary, request images from different angles or to try on other clothing items.

Step 8:

If the user likes the suggested outfit, they proceed with the purchase. The user clicks the "Purchase" button, and the device sends the purchase information to the server. The input is the purchase information, and the output is purchase confirmation and delivery information. The server connects with the online store's payment system, records the order, and sends a confirmation to the user.

This allows users to virtually try on clothes that fit their body type, receive personalized outfit suggestions based on emotional data, and ultimately make a purchase.

The specific processing unit 290 transmits the results 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 results of the specific processing. The microphone 38B acquires audio indicating the user input regarding the results 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.

Data generation model 58 is what is known as generative AI (artificial intelligence). Examples of data generation model 58 include generative AI such as ChatGPT (Internet search <URL: https://openai.com/blog/chatgpt>) and Gemini (Internet search <URL: https://gemini.google.com/?hl=ja>). Data generation model 58 is obtained by performing deep learning on a neural network. A prompt containing an instruction is input to data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input. Data generation model 58 performs inference on the input inference data in accordance with the instructions indicated by the prompt, and outputs the inference results in the form of data such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and/or summarization.

In the above embodiment, an example was given in which the specific processing was performed by the data processing device 12, but the technology disclosed herein is not limited to this, and the specific processing may also be performed by the smart device 14.

[Second embodiment]

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

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

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, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and 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).

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, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

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.

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 user 20's surroundings (e.g., an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

The communication I/F 44 is connected to the 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 manner.

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

The specific processing program 56 is an example of a "program" 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 the specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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.

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.

Next, we will explain the identification process performed by the identification processing unit 290 of the data processing device 12. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

This invention is a virtual try-on system that uses the user's body type information and full-body photos taken from multiple angles to generate a fitting image tailored to the user. The system begins by the user entering body type information and uploading a full-body photo using their own device. The system then utilizes a generative AI model based on the collected clothing data to synthesize the clothing onto the user's 3D model and present a virtual fitting image. In addition, users can receive coordination suggestions from sales staff, making the process of selecting and purchasing clothing even more enjoyable.

1. Enter your body type information and upload a full-body photo.

Users launch the application and enter their body information, such as their height, weight, and measurements. They also upload full-body photos taken from the front, back, and side.

The device sends the body type information entered by the user and the full-body photo taken to the server.

2. Clothing data collection

The server collects data about clothing sold online (images, sizes, materials, colors, etc.) using APIs or web scraping technology from partner online stores and stores it in a database.

3. 3D model generation and synthesis

The server analyzes the user's body shape information and uploaded full-body photos to generate a high-resolution 3D model of the user.

The server uses a generative AI model to synthesize the user's selected clothing onto the 3D model, using deep learning techniques to realistically recreate the clothing's fit and texture.

4. Showing a fitting image

The server then sends the generated try-on images taken from multiple angles to the user's device.

The device displays the received try-on images on the user interface.

Users can review the displayed try-on images and, if necessary, request images from different angles or images of other garments.

5. Coordination suggestions and purchasing procedures

If the user would like outfit suggestions, they can click the "Request outfit suggestions" button.

The server sends a request to the salesperson in charge of coordinating the outfit.

The salesperson suggests appropriate outfits based on the user's body type and preferences, and sends feedback to the server.

The server generates images of the suggested outfits to try on and displays them on the user's device.

The user reviews the suggested outfits and clicks the "Purchase" button if they decide to purchase.

The terminal sends the purchase information to the server and connects to the online store's payment system.

This invention allows users to easily select clothing that fits their body type and experience the virtual fitting process as if they were actually trying it on. Furthermore, they can smoothly complete the online purchase process while checking suggested outfits.

The processing flow is explained below.

Step 1:

Users launch the application and enter their body information, such as height, weight, and measurements. They also upload full-body photos taken from the front, back, and side.

Step 2:

The device sends the body shape information and full-body photo entered by the user to the server.

Step 3:

The server analyzes the received body shape information and full-body photo data to generate a high-resolution 3D model of the user. This analysis is performed using image recognition algorithms.

Step 4:

The server uses APIs or web scraping technology from partner online stores to collect data on the clothing being sold (images, sizes, materials, colors, etc.) and stores it in a database.

Step 5:

The server then synthesizes the clothing selected by the user onto the generated 3D model of the user, using a generative AI model to realistically recreate the fit and texture of the clothing.

Step 6:

The server then sends the generated try-on images taken from multiple angles to the user's device.

Step 7:

The device displays the received try-on images on the user interface.

Step 8:

The user reviews the displayed try-on images. If necessary, they can request try-on images from different angles or images of other garments.

Step 9:

If the user would like outfit suggestions, they can click the "Request outfit suggestions" button.

Step 10:

The server sends a request to the salesperson in charge of coordinating the outfit.

Step 11:

The salesperson suggests appropriate outfits based on the user's body type and preferences, and sends feedback to the server.

Step 12:

The server generates images of the suggested outfits to try on and sends them to the user's device.

Step 13:

The device displays the received outfit try-on image on the user interface.

Step 14:

The user reviews the suggested outfits and clicks the "Purchase" button if they decide to purchase.

Step 15:

The device sends the purchase information to the server.

Step 16:

The server records purchase information and connects it to the online store's payment system.

Step 17:

The server notifies the user of the order confirmation and delivery information.

Step 18:

The terminal will display order confirmation and shipping information to the user.

(Example 1)

Next, we will explain Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

Traditional online shopping has the problem that users cannot accurately understand how clothes will fit or how the design will look on them unless they actually try them on. Furthermore, coordination suggestions tailored to the user's preferences and the ability to check how the clothes will look when tried on are insufficient, which discourages users from making a purchase. This has led to a decline in user satisfaction with online shopping.

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

In this invention, the server includes means for inputting the user's body type information, means for taking and uploading full-body photos of the user from multiple angles, means for collecting data on clothing sold online, means for combining clothing with the generated high-resolution 3D model of the user, means for sending the generated try-on images to the user's device, and means for displaying the try-on images on the user's device. This allows users to easily select clothing that fits their body type and experience the virtual try-on experience as if they were actually trying on the clothes. In addition, users can request coordination suggestions from a salesperson and check the suggested try-on images, which increases the user's desire to purchase.

"User" refers to an individual who uses the system to enter body type information and take and upload full-body photos.

"Body type information" refers to detailed data about the user's body, such as their height, weight, and measurements.

"Full-body photos" refer to images of the user's body taken from multiple angles, including the front, back, and side.

"Data on clothing sold online" refers to information such as clothing images, sizes, materials, and colors collected from online sales sites and stores.

"High-resolution 3D model" refers to a three-dimensional computer graphics model that reproduces the user's body in detail, generated based on the user's body shape information and a full-body photograph.

"Generative AI model" refers to an artificial intelligence model trained using deep learning technology to realistically synthesize clothing onto a user's 3D model.

"Try-on image" refers to an image created by combining the selected clothing onto the user's 3D model using a generative AI model.

"User's device" refers to the electronic device used by the user, such as a smartphone, tablet, or PC.

"Coordination suggestions" refer to combinations of multiple items of clothing recommended by a salesperson based on the user's body type information and preferences.

"Salesperson" refers to a person in charge of making outfit suggestions to users through the system.

This invention is a virtual try-on system that uses the user's body type information and full-body photographs taken from multiple angles to generate a fitting image tailored to the user. In this system, the program is executed in the following steps:

First, the user launches a dedicated application on their smartphone or PC and enters their body information, including height, weight, and measurements. The user then takes full-body photos of the front, back, and side and uploads them to the application. This uploaded data is then sent to the server via the device.

The device securely transmits input and uploaded data to the server using the HTTPS protocol. The server receives this data and uses the image analysis technology OpenCV to analyze the user's body shape with high accuracy. The deep learning frameworks TensorFlow and PyTorch are used to generate a high-resolution 3D model based on the analyzed data.

After generating a 3D model for the user, the server uses APIs or web scraping technology from partner online stores to collect data about clothing sold online. This data includes clothing images, sizes, materials, colors, etc. This data is stored in a database and used to synthesize clothing onto the user's 3D model.

The server then uses a generative AI model to synthesize the clothing selected by the user onto the generated 3D model. The generative AI model is trained using deep learning technology to realistically reproduce the fit and texture of the clothing. Deep learning algorithms using TensorFlow and PyTorch are used in this process.

The generated try-on images are photographed from multiple angles and sent to the user's device as JPEG or PNG image files. The device displays the received try-on images on the application's user interface. The user can review the displayed try-on images and request images from different angles or try-on images of other garments as needed.

Furthermore, if the user wishes to receive outfit suggestions, they click the "Request outfit suggestions" button. The server sends a request to the salesperson in charge of outfit suggestions, who then suggests an appropriate outfit based on the user's body type and preferences and sends feedback to the server. Based on this feedback, the server generates a new try-on image and displays it on the user's device. Finally, the user checks the suggested outfit and clicks the "Purchase" button if they decide to purchase. This purchase information is sent to the server via the device, and the purchase process is carried out in conjunction with the online store's payment system.

Specific examples

For example, if a user wants to try on "blue jeans" and a "white T-shirt,"

1. The user enters their height as 170cm, weight as 65kg, and measurements as 90-75-90, and uploads full-body photos of the front, back, and side.

2. The device sends this information to the server.

3. The server uses web scraping technology to collect data on "blue jeans" and "white T-shirts" and stores it in a database.

4. The server uses image analysis technology to generate a high-resolution 3D model of the user, and then uses a generative AI model to synthesize jeans and a T-shirt onto the 3D model.

5. The server generates try-on images from multiple angles and sends them to the user's device.

6. The user can check the newly generated try-on image and then decide to "purchase this outfit."

Example prompt

"Enter your height, weight, and measurements, and upload full-body photos taken from the front, back, and side."

This system allows users to easily find clothes that fit their body type and experience the same sensation of trying them on in real life through virtual try-on. They can also request outfit suggestions and check the suggested try-on images, making online clothing shopping a smoother and more satisfying experience.

The flow of the identification process in Example 1 will be explained using Figure 11.

Step 1:

The user launches the application.

Specific operation: The user taps or clicks on the dedicated application on their smartphone or PC to launch it and proceeds to the first screen.

Input: None

Output: The application launches and displays a screen where the user can enter body information.

Step 2:

The user enters body type information.

Specific operation: The user enters body information such as height, weight, and measurements into the application form. They also provide full-body photos taken from the front, back, and side.

Input: Body information such as height, weight, and measurements

Output: Display of entered body shape information and full-body photo

Step 3:

Users upload full-body photos.

Specific operation: The user uploads full-body photos of the front, back, and side using the upload function within the application.

Input: Full-body photos (front, back, and side)

Output: Full-body photo upload complete message

Step 4:

The device sends the input data to the server.

Specific operation: The device sends the user's body shape information and full-body photo to the server via the HTTPS protocol.

Input: User's body type information and full-body photo

Output: The data is sent to the server and awaits processing.

Step 5:

The server analyzes body shape information and full-body photos.

Specific operation: The server performs image analysis using OpenCV and extracts the features necessary to create a 3D model based on the user's body shape information.

Input: Body information and full-body photo

Output: Feature-extracted data

Step 6:

The server generates a high-resolution 3D model.

Specific operation: The server uses TensorFlow and PyTorch for deep learning to generate a high-resolution 3D model based on the user's body shape.

Input: Feature-extracted data

Output: High-resolution 3D model

Step 7:

The server collects data on clothing sold online.

Specific operation: The server calls the API of partner online stores or uses web scraping to collect the latest clothing data (images, sizes, materials, colors, etc.).

Input: API endpoint of affiliated online store or URL of scraping target

Output: Latest clothing data stored in the clothing database

Step 8:

The server uses a generative AI model to synthesize the clothing onto the 3D model.

Specific operation: The server uses a generative AI model to synthesize clothing onto the user's 3D model based on the collected clothing data.

Input: 3D model and clothing data

Output: Try-on images from multiple angles

Step 9:

The server sends the generated try-on image to the device.

Specific operation: The server generates try-on images in JPEG or PNG format and sends them to the user's device. High-speed data transfer may also be performed via a CDN.

Input: Try-on image

Output: Try-on image sent to the device

Step 10:

The device displays the try-on image on the user interface.

Specific operation: The device displays the received try-on image on the application's user interface, allowing the user to operate it.

Input: Try-on image

Output: Try-on image displayed on the user interface

Step 11:

Users can check the fitting images and submit requests if necessary.

Specific operation: The user reviews the try-on images and, if they wish to request images from different angles or images of other garments being tried on, clicks the corresponding button in the application.

Input: User request

Output: The request is sent to the server.

Step 12:

The user requests outfit suggestions.

Specific operation: If the user would like outfit suggestions, they click the "Request outfit suggestions" button.

Input: User's outfit suggestion request

Output: The request is sent to the server.

Step 13:

The server sends the request to the salesperson.

Specific operation: The server sends a coordination suggestion request to the salesperson, along with the necessary user information.

Input: User request

Output: The request is sent to the salesperson.

Step 14:

Salespeople will provide feedback on suggestions.

Specific operation: The salesperson considers the appropriate outfit based on the user's body type and preferences, and sends feedback to the server.

Input: User's body type and preferences

Output: Feedback on outfit suggestions

Step 15:

The server generates images of outfits to try on.

Specific operation: The server generates new try-on images based on feedback from the salesperson and sends them to the user's device.

Input: Feedback on outfit suggestions

Output: Try-on image of outfit sent to device

Step 16:

The user reviews the offer and decides to purchase.

Specific operation: The user checks the newly generated outfit try-on image and clicks the "Purchase" button if they like it.

Input: Coordination try-on image

Output: Purchase request sent to server

Step 17:

The device sends purchase information to the server and connects with the online store.

Specific operation: The terminal sends purchase information to the server, and the server works with the online store's payment system to complete the purchase process.

Enter: Purchase information

Output: The purchase is completed and a confirmation is sent to the user.

(Application Example 1)

Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

Traditionally, trying on clothes in physical stores was time-consuming and labor-intensive. Additionally, the types of clothing that could be tried on were limited, making it difficult to try out many options. Furthermore, with online shopping, customers were unable to see how the actual product would look, leading to frequent returns and exchanges after purchase. To solve these problems, a system was needed that allowed users to easily try on clothes and select the best fit for their body type.

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

In this invention, the server includes means for inputting a user's body type information, means for taking and uploading full-body photos of the user from multiple angles, means for collecting data on available items, means for overlaying items onto the generated 3D model of the user, means for presenting virtual try-on images to the user's device, means for the user to input body type information and upload a full-body photo using their own device, means for collecting and saving data on items sold online using the API or web scraping technology of affiliated online stores, means for analyzing the user's body type information and uploaded full-body photos and generating a high-resolution 3D model of the user, and means for generating try-on images from multiple angles and sending them to the user's device. This allows users to smoothly try on clothes virtually in a physical store, shortening the time it takes to actually try them on and combining the convenience of online shopping with the experience of a physical store.

"User's body type information" refers to the user's physical measurements and characteristics, such as height, weight, and three sizes.

A "full-body photo" is a photo that shows the user's entire body, including multiple photos taken from the front, back, and side.

"Purchasable Item Data" refers to information about products such as clothing and accessories sold at affiliated online stores and in-store, including attributes such as images, size, material, and color.

"3D model" refers to a high-resolution three-dimensional digital model generated based on the user's body shape information and full-body photograph.

"Means for synthesizing items" refers to the process of virtually applying selected clothing and accessories to the generated 3D model of the user to generate a realistic try-on image.

"Virtual try-on image" refers to an image that combines selected clothing and accessories with a 3D model of the user, simulating trying on the clothing and accessories from multiple angles.

"Affiliated Online Store API" refers to an application programming interface for automatically obtaining data on products sold by affiliated online stores.

"Web scraping technology" refers to technology that automatically extracts data from websites.

"Means for generating a high-resolution 3D model" refers to the process of analyzing a user's body shape information and full-body photograph to create a highly accurate three-dimensional digital model.

"Means to request outfit suggestions" refers to the function that allows a user to request outfit suggestions from a salesperson based on the user's preferences.

"Performing a virtual try-on" refers to the act of allowing a user to try on an item on a digital model instead of actually trying it on.

This invention is a system that uses a user's body type information and full-body photograph to enable virtual try-on, improving the fitting experience in physical stores. The system is built using the user's device (smartphone), a series of servers, and APIs or web scraping technologies from affiliated online stores.

Program generation

The system uses the following hardware and software:

User device (smartphone): Android or iOS device with camera functionality

Server: Data processing and generative AI model execution (using TensorFlow or PyTorch)

Partner online store API or web scraping technology (Beautiful Soup, Scrapy, etc.)

Database: MySQL or PostgreSQL

Program processing overview

The server first receives the body shape information and full-body photo sent by the user from their device, and then uses image analysis technology to generate a high-resolution 3D model of the user. This 3D model is precisely created using deep learning, recreating a realistic fit to the user's body shape.

The server then uses clothing data collected from partner online stores to synthesize the selected clothing onto the user's 3D model. This synthesis process utilizes generative AI models to accurately reproduce the texture and fit of the clothing. Try-on images taken from multiple angles are generated and sent to the user's device.

Users can check the virtual try-on images on their devices and, if they like them, proceed with the purchase process. Furthermore, if users would like a coordination suggestion, they can send a request to the salesperson. The coordination suggested by the salesperson is then regenerated as a virtual try-on image and presented to the user.

Examples and prompts

As a specific prompt, when collecting clothing data using the API of a partner online store, run the following command:

curl -X GET "https://netstore.com/api/v1/products" -H "Authorization: Bearer YOUR_API_KEY"

Also, if you use web scraping technology, here's a script that uses Python's Beautiful Soup to extract product data from a specified URL:

from bs4 import BeautifulSoup

Import requests

url = "https://netstore.com/products"

response = requests.get(url)

soup = BeautifulSoup(response.content, 'html.parser')

for product in soup.find_all('div', class_='product'):

product_name = product.find('h2').get_text()

product_price = product.find('span', class_='price').get_text()

print(product_name, product_price)

This system allows users to seamlessly try on clothes virtually in a physical store, shortening the time spent trying them on in person and combining the convenience of online shopping with the experience of a physical store.

The flow of the identification process in Application Example 1 will be explained using Figure 12.

Step 1:

The user enters their body type information into the terminal. The user enters physical attributes such as height, weight, and measurements into the terminal, and the entered data is sent to the server. At this point, the input is the user's physical numerical data, and the output is raw data sent to the server.

Step 2:

The user takes full-body photos from multiple angles and uploads them via their device. The user takes photos from the front, back, and side using the device's camera and sends the image data to the server. At this point, the input is multiple image files, and the output is image data stored on the server.

Step 3:

The server uses the API of a partner online store or web scraping technology to collect data on the items being sold. Specifically, the server sends a request to an API endpoint and receives product information in response, or parses a web page to obtain the required product data. At this point, the input is the API request or HTML content, and the output is a set of product data.

Step 4:

The server analyzes the user's body shape information and full-body photo to generate a high-resolution 3D model. The collected image data and body shape information are analyzed using a deep learning model (using TensorFlow and PyTorch) to create a highly accurate 3D model of the user. At this point, the input is body shape information and image data, and the output is a 3D model.

Step 5:

The server uses a generative AI model to synthesize the selected item onto a 3D model. The user selects from the collected product data and synthesizes it onto the 3D model to create a virtual try-on image. The generative AI model reproduces the texture and fit of the clothing with high accuracy. At this point, the input is the 3D model and product data, and the output is a try-on image.

Step 6:

The server then sends the generated try-on images, photographed from multiple angles, to the user's device. These images are displayed on the user's device, allowing the user to check the virtual try-on image. At this point, the input is the try-on image data, and the output is the virtual try-on image displayed on the user's device.

Step 7:

When a user requests a coordination suggestion, they send a request from their terminal to the server. The server receives this request and notifies the salesperson in charge. At this point, the input is the request from the user, and the output is a notification to the salesperson.

Step 8:

The salesperson creates a coordination suggestion and sends feedback to the server. The server again generates a virtual try-on image of the suggested coordination based on the user's 3D model. At this point, the input is the coordination suggestion from the salesperson, and the output is a new try-on image.

Step 9:

The server sends the generated coordinated try-on image to the user's device, where the user confirms it. If the user decides to purchase, they click the "Purchase" button on their device, and the purchase information is sent to the server. The input at this point is the virtual try-on image and the user's purchase decision, and the output is the progress of the purchase procedure.

It is also possible to further combine an emotion engine that estimates the user's emotion. 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.

This invention combines a virtual try-on system that generates a 3D model based on the user's body type information and full-body photographs from multiple angles, then synthesizes clothing onto it, with an emotion engine that recognizes the user's emotions. This system can suggest clothing and outfits that correspond to the user's emotions, providing a more personalized shopping experience.

1. Enter your body type information and upload a full-body photo.

Users launch the application and enter their body information (height, weight, measurements, etc.). They also upload full-body photos taken from multiple angles.

The device sends this body shape information and a full-body photo to the server.

2. Clothing data collection

The server uses API or web scraping technology to collect data on the clothing being sold (images, sizes, materials, colors, etc.) from partner online stores and stores it in a database.

3. 3D model generation and clothing synthesis

The server analyzes the user's body shape information and full-body photo data to generate a high-resolution 3D model of the user, using the latest image recognition algorithms.

The server uses a generative AI model to synthesize the selected clothing onto the 3D model. This process utilizes deep learning techniques to realistically recreate the fit and texture of the clothing.

4. Showing a fitting image

The server then sends the generated try-on images taken from multiple angles to the user's device.

The device displays the received try-on images on the user interface.

The user can review the displayed try-on images and, if necessary, request images from different angles or to try on other garments.

5. Emotion Recognition Using an Emotion Engine

The device uses an emotion engine to analyze the user's facial expressions and voice to identify their emotional state. This is done by capturing data in real time using a camera and microphone.

The server evaluates the user's reaction to the try-on images based on emotional data from the emotion engine.

6. Coordination proposals and adjustments

If the user would like outfit suggestions, they can click the "Request outfit suggestions" button.

The server sends a request to the salesperson in charge of coordinating the outfit.

The salesperson suggests appropriate outfits based on the user's body type, preferences, and emotional data, and sends feedback to the server.

The server generates images of the suggested outfits to try on and displays them on the user's device. It also adjusts the suggestions in real time based on the user's emotional data.

7. Purchase Procedure

The user reviews the suggested outfits and clicks the "Purchase" button if they decide to purchase.

The terminal sends the purchase information to the server and connects to the online store's payment system.

The server records the purchase information and notifies the user of the order confirmation and shipping information.

The terminal will display order confirmation and shipping information to the user.

The system of the present invention allows users to easily select clothing that fits their body type and experience the virtual fitting process as if they were actually trying it on. Furthermore, by utilizing an emotion engine to make suggestions based on the user's emotional state, a more personalized shopping experience is realized. This series of processes increases user satisfaction and improves the online shopping experience.

The processing flow is explained below.

Step 1:

Users launch the application and enter their body information, such as height, weight, and measurements. They also upload full-body photos taken from the front, back, and side to the application.

Step 2:

The device sends the body shape information and full-body photo entered by the user to the server.

Step 3:

The server analyzes the received body shape information and full-body photo data and uses image recognition algorithms to generate a high-resolution 3D model of the user.

Step 4:

The server uses API or web scraping technology to collect data on the clothing being sold (images, sizes, materials, colors, etc.) from partner online stores and stores it in a database.

Step 5:

The server then synthesizes the clothing selected by the user onto the generated 3D model of the user, using the generative AI model to realistically reproduce the fit and texture of the clothing.

Step 6:

The server then sends the generated try-on images taken from multiple angles to the user's device.

Step 7:

The device displays the received try-on images on the user interface.

Step 8:

The user reviews the displayed try-on images. If necessary, they can request images from different angles or try on other garments.

Step 9:

The device captures the user's facial expressions with a camera or collects their voice with a microphone, and then sends this data to the emotion engine.

Step 10:

The server uses an emotion engine to analyze the user's facial expressions and voice to identify their emotional state. For example, if the user is smiling, it will be identified as "satisfied," and if they are frowning, it will be identified as "anxious."

Step 11:

The server determines the next action based on the emotional state data from the emotion engine. For example, if the user is satisfied, it continues with the suggestion, but if they are anxious, it presents a different option.

Step 12:

If the user would like outfit suggestions, they can click the "Request outfit suggestions" button.

Step 13:

The server sends a request to the salesperson in charge of coordinating the outfit.

Step 14:

The salesperson suggests appropriate outfits based on the user's body type, preferences, and emotional data, and sends feedback to the server.

Step 15:

The server generates images of the suggested outfits to try on and sends them to the user's device. It also adjusts the suggestions in real time based on the user's emotional data.

Step 16:

The device displays the received outfit try-on image on the user interface.

Step 17:

The user reviews the suggested outfits and clicks the "Purchase" button if they decide to purchase.

Step 18:

The device sends the purchase information to the server.

Step 19:

The server records the purchase information and notifies the user of the order confirmation and shipping information.

Step 20:

The terminal will display order confirmation and shipping information to the user.

(Example 2)

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

In recent years, with the spread of online shopping, there has been an increasing demand for remote try-on and personalized shopping experiences. However, current systems have difficulty adequately reproducing the fit and texture of clothing when actually trying on, and are unable to make suggestions based on the user's emotions. Therefore, there is a need for a more realistic virtual try-on system to improve the user experience.

The specific processing performed by the specific 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 inputting the user's body type information, means for taking and uploading full-body images of the user from multiple angles, means for collecting data on clothing available for sale, means for combining clothing items with the generated three-dimensional model of the user, means for presenting images of the items to be tried on on the user's device, means for analyzing the user's facial expressions and voice to recognize emotions, and means for adjusting suggestions based on emotions. This allows the user to virtually try on clothing that fits their body type and receive personalized suggestions based on their emotional state.

"Means for inputting user's body type information" refers to an interface and system for inputting data related to the user's body type, such as height, weight, and measurements.

"Means for taking and uploading full-body images of the user from multiple angles" refers to the camera and upload function for taking images of the user's entire body from different angles and uploading that image data to the system.

"Means for collecting data on clothing for sale" refers to technology for collecting and storing data such as images, sizes, materials, and colors of clothing for sale from online stores and other sources.

"Means for combining clothing items with a generated 3D model of the user" refers to an algorithm and system for realistically combining selected clothing items with a 3D model generated based on the user's body shape information and full-body image.

"Means for presenting try-on images on the user's device" refers to the interface and system for displaying the generated try-on images on the screen of the user's device (smartphone, tablet, PC, etc.).

"Means for analyzing a user's facial expressions and voice to recognize emotions" refers to algorithms and systems that analyze a user's facial expressions and voice data acquired using devices such as cameras and microphones, and identify the user's emotional state.

"Means for adjusting suggestions based on emotions" refers to technology and systems for changing and adjusting suggested clothing and outfits in real time based on the user's emotional data.

This invention is a virtual fitting system that generates a high-resolution three-dimensional model based on the user's body type information and full-body image, and then realistically combines clothing onto it. It also has the ability to analyze the user's emotions from their facial expressions and voice, and adjust clothing suggestions based on that.

This system uses the following hardware and software:

An interface for inputting the user's body shape information (such as a smartphone or PC)

A camera that captures a full-body image of the user (such as a camera built into a smartphone)

API or web scraping tool for collecting data on clothing for sale

Generative AI models for generating 3D models (e.g., deep learning models built in Python)

A user interface that displays synthesized try-on images

Emotion recognition engine for analyzing user facial expressions and voice (e.g., emotion analysis API)

This system performs the following processes:

The user enters their body type information through the launched application and takes and uploads full-body images from multiple angles. The device then sends this data to the server. The server then collects data on clothing for sale from online stores using APIs or web scraping technology and stores it in a database. The server analyzes the user's body type information and full-body images and uses a generative AI model to generate a high-resolution 3D model of the user. The server then combines the clothing selected by the user into the 3D model to generate a realistic try-on image. This try-on image is then sent to the user's device and displayed.

In addition, the device uses a camera and microphone to capture the user's facial expressions and voice in real time, and analyzes their emotions using an emotion recognition engine. The server then uses this emotional data to adjust the suggested clothing and outfits in real time.

As a concrete example, suppose a user inputs their height (170cm), weight (65kg), and measurements (B:95cm, W:75cm, H:95cm), and uploads full-body images from the front and side. Based on this, the server generates a 3D model of the user and synthesizes a navy jacket. An example prompt for this stage is: "Based on the user's height of 170cm, weight (65kg), and measurements (B:95, W:75, H:95), generate a 3D model based on full-body front and side photos and synthesize a high-resolution navy jacket. Also, recognize positive emotions from the user's smiling face and suggest further outfit recommendations."

The system allows users to virtually try on clothes that fit their body type and receive personalized suggestions based on their emotional state.

The flow of the identification process in Example 2 will be explained using Figure 13.

Program processing flow

Step 1:

The user launches the application and enters their body type information.

Input: User's body information (height, weight, measurements, etc.)

Output: Body shape information is saved in the system.

Specific operation: The user enters body type information into the application's input fields and clicks the "Submit" button. This information is sent to the server via the device.

Step 2:

Users take full-body images from multiple angles and upload them.

Input: Full-body images of the user taken from the front and side

Output: The whole-body image is saved to the system.

Specific operation: The user uses the smartphone camera to take full-body images of themselves from multiple angles, selects the images in the application, and clicks the "Upload" button. The image data is sent to the server via the device.

Step 3:

The server collects clothing data from affiliated online stores.

Input: Online store API information or web page URL

Output: Garment data (images, size, material, color, etc.) is saved in a database.

Specific operation: The server automatically collects clothing data from online stores using APIs and web scraping tools. When collecting data, it also checks for duplicates and missing data.

Step 4:

The server analyzes the user's body shape information and full-body image, and generates a 3D model using a generative AI model.

Input: User's body shape information and full-body image

Output: High-resolution 3D model of the user

How it works: The server uses deep learning algorithms to analyze the user's body shape information and full-body image to generate a 3D model. This process utilizes a GPU to speed up calculations.

Step 5:

The server synthesizes the user's selected clothing onto a 3D model.

Input: User's 3D model and selected clothing data

Output: Composite fitting image

Specific operation: The server uses a generative AI model to synthesize the selected clothing onto the user's 3D model in a way that realistically reproduces the fit and texture. As a result, a fitting image is generated.

Step 6:

The server sends the generated try-on image to the user's device.

Input: Synthesized fitting image

Output: Try-on image displayed on the user's device

Specific operation: The try-on image is encoded as images taken from multiple angles and sent from the server to the device. The device displays this on the user interface.

Step 7:

The device captures the user's facial expressions and voice and analyzes them using an emotion recognition engine.

Input: User's facial and voice data

Output: User emotion data

Specific operation: The device uses a camera and microphone to capture the user's facial expressions and voice in real time, and then analyzes this data with an emotion recognition engine to identify the user's emotional state.

Step 8:

The server analyzes the emotional data and adjusts the suggestions in real time.

Input: User emotion data

Output: Adjusted proposal content

Specific operation: Based on the emotional data, the server changes and adjusts the fitting images and outfit suggestions in real time to provide optimal suggestions.

Step 9:

The user selects the suggested outfit and completes the purchase process.

Input: User purchase decision information

Output: Purchase confirmation and shipping information

Specific operation: When the user clicks the "Purchase" button, the device sends this information to the server. The server then links the purchase information to the online store's payment system and completes the purchase process. The user is then notified of order confirmation and delivery information.

This allows users to virtually try on clothes that fit their body type, receive personalized suggestions based on their emotions, and enjoy an optimal shopping experience.

(Application Example 2)

Next, we will explain Application Example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

Conventional virtual try-on systems were able to generate fitting images based on the user's body type information, but were unable to make suggestions that took the user's emotions into account. This made it difficult to improve the user's satisfaction with the clothing and outfits they selected. Furthermore, the lack of coordination adjustments based on real-time emotional feedback meant they were unable to fully meet the individual needs of users.

The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting the user's physique information, means for taking and uploading full-body photos of the user from multiple angles, means for collecting data on clothing for sale, means for combining clothing with the generated high-resolution 3D model of the user, means for analyzing the user's emotions and suggesting clothing and outfits based on the emotion data, and means for presenting images of the clothing to be tried on on the user's device. This makes it possible to suggest personalized clothing and outfits based on the user's emotions, improving user satisfaction. Furthermore, by adjusting the suggestions based on real-time emotion feedback, it is possible to more appropriately meet the individual needs of the user.

"User's body type information" refers to data related to the user's body measurements, such as height, weight, and three sizes.

A "full-body photo" is an image of the user taken from multiple angles (front, back, side, etc.).

"Data on clothing for sale" refers to detailed information such as clothing images, sizes, materials, and colors collected from affiliated online stores.

A "high-resolution 3D model" is a 3D model that is generated based on the user's body type information and a full-body photograph, and is rendered in great detail.

"Clothing synthesis" is a technology that uses data on clothing for sale to realistically display clothing on the generated high-resolution 3D model.

"Means for analyzing emotions and suggesting clothing and outfits based on emotional data" refers to technology that analyzes a user's facial expressions and voice, and then suggests the most suitable clothing and outfits for the user based on the emotional data obtained from this.

"Means for presenting try-on images" refers to technology that displays the generated virtual try-on images on the user's device.

"Emotional data" is data that represents emotional states such as joy, surprise, and dissatisfaction obtained from the analysis of the user's facial expressions and voice.

"Coordination" refers to the user's clothing combination and includes the selection process.

"Feedback" is the process of adjusting and re-proposing suggestions based on the user's emotional data.

This invention is a virtual fitting system that generates a 3D model based on the user's body type information and full-body photographs from multiple angles, then synthesizes clothing onto it, combined with an emotion engine that recognizes the user's emotions. This system can suggest clothing and outfits based on the user's emotions, providing a more personalized shopping experience.

The server realizes this system by integrating the following technologies: First, the server provides a means for users to input their body type information. This allows users to enter information such as their height, weight, and three sizes. It also provides a means for users to upload full-body photos taken from multiple angles. This allows users to upload photos of their front, side, and back.

The server has a means of collecting data on clothing for sale from online stores and other data sources. This data includes detailed information such as clothing images, sizes, materials, and colors. The server then uses the latest image recognition algorithms (e.g., TensorFlow) to analyze the user's body shape information and full-body photo data to generate a high-resolution 3D model. This 3D model is then used to synthesize clothing using deep learning technology to generate realistic try-on images.

Furthermore, it has a means of analyzing the user's facial expressions and voice using an emotion engine (e.g., Affectiva API) to obtain emotional data. It also incorporates a means of suggesting the most suitable clothing and outfits for the user based on the emotional data. This makes it possible to make appropriate suggestions in real time based on the user's emotions.

A means of displaying try-on images on the user's device has also been developed, allowing the user to view the generated virtual try-on image from multiple angles. After the try-on image is displayed, the user can provide feedback on their emotional data on the spot and adjust their outfit as needed.

For example, a user enters their height and weight into the app and uploads three full-body photos (front, back, and side). After the photo shoot is complete, emotion analysis is performed and if the user is happy, the system will suggest outfits in bright colors and the latest fashions. On the other hand, if the user is unhappy, the system will adjust to suggest new outfits.

An example of a prompt statement is as follows:

The user is 170cm tall and weighs 65kg. Front, back, and side photos have been uploaded. Sentiment analysis indicates that the user is currently feeling "joy." Based on this, suggest multiple outfits in bright colors and the latest fashions.

In this way, users can choose the clothing that best suits their body type and get the feeling of trying it on in real life through a virtual try-on experience. Real-time emotional feedback provides a more personalized shopping experience.

The flow of the specific processing in Application Example 2 will be explained using Figure 14.

Step 1:

Users launch the application, enter their body type information (height, weight, measurements, etc.), and upload full-body photos taken from multiple angles (front, back, side). The entered data consists of body type information and photo data, which are sent from the device to the server. As a result, data related to the user's body type and full-body photos is stored on the server.

Step 2:

The server collects data about clothing sold (images, sizes, materials, colors, etc.) from online stores and other data sources. This collection is done using APIs or web scraping technology. The acquired data is stored in a database on the server. The input is clothing data, and the output is clothing data stored in the database.

Step 3:

The server uses the latest image recognition algorithms (e.g., TensorFlow) to analyze the user's body shape information and full-body photo data and generate a high-resolution 3D model. During this process, each user's photo is pixel-analyzed to create the shape of the 3D model. The input for this step is the user's body shape information and photo data, and the output is a high-resolution 3D model.

Step 4:

The server uses a generative AI model to synthesize clothing for sale onto the generated 3D model. Utilizing deep learning technology, data processing is performed to realistically reproduce the fit and texture of the clothing. The input is a high-resolution 3D model and clothing data, and the output is a try-on image.

Step 5:

The device uses an emotion engine (e.g., Affectiva API) to analyze the user's facial expressions and voice in real time and obtain emotional data. Captured facial and voice data is input, and analyzed emotional data is output. In this step, the device obtains data using the camera and microphone.

Step 6:

The server suggests optimal clothing and outfits for the user based on emotional data. The input is emotional data, and the output is outfit suggestions tailored to the user's preferences. These suggestions are made dynamically and adjusted in real time.

Step 7:

The user's device displays the try-on images sent from the server. The input is the try-on image, and the output is the try-on image displayed on the user interface. The user can review the displayed try-on image and, if necessary, request images from different angles or to try on other clothing items.

Step 8:

If the user likes the suggested outfit, they proceed with the purchase. The user clicks the "Purchase" button, and the device sends the purchase information to the server. The input is the purchase information, and the output is purchase confirmation and delivery information. The server connects with the online store's payment system, records the order, and sends a confirmation to the user.

This allows users to virtually try on clothes that fit their body type, receive personalized outfit suggestions based on emotional data, and ultimately make a purchase.

The specific processing unit 290 transmits the results 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 results of the specific processing. The microphone 238 acquires audio indicating the user input regarding the results 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.

Data generation model 58 is what is known as generative AI (artificial intelligence). Examples of data generation model 58 include generative AI such as ChatGPT (Internet search <URL: https://openai.com/blog/chatgpt>) and Gemini (Internet search <URL: https://gemini.google.com/?hl=ja>). Data generation model 58 is obtained by performing deep learning on a neural network. A prompt containing an instruction is input to data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input. Data generation model 58 performs inference on the input inference data in accordance with the instructions indicated by the prompt, and outputs the inference results in the form of data such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and/or summarization.

In the above embodiment, an example was given in which the specific processing was performed by the data processing device 12, but the technology disclosed herein is not limited to this, and the specific processing may also be performed by the smart glasses 214.

[Third embodiment]

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

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

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, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and 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).

The headset 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, RAM 48, and storage 50. The processor 46, RAM 48, and 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.

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.

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 user 20's surroundings (e.g., an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

The communication I/F 44 is connected to the 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 manner.

Figure 6 shows an example of the main functions of the data processing device 12 and headset terminal 314. As shown in Figure 6, in the data processing device 12, specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32.

The specific processing program 56 is an example of a "program" 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 the specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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.

In the headset terminal 314, 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.

Next, we will explain the identification process performed by the identification processing unit 290 of the data processing device 12. In the following explanation, the data processing device 12 will be referred to as the "server" and the headset-type terminal 314 will be referred to as the "terminal."

This invention is a virtual try-on system that uses the user's body type information and full-body photos taken from multiple angles to generate a fitting image tailored to the user. The system begins by the user entering body type information and uploading a full-body photo using their own device. The system then utilizes a generative AI model based on the collected clothing data to synthesize the clothing onto the user's 3D model and present a virtual fitting image. In addition, users can receive coordination suggestions from sales staff, making the process of selecting and purchasing clothing even more enjoyable.

1. Enter your body type information and upload a full-body photo.

Users launch the application and enter their body information, such as their height, weight, and measurements. They also upload full-body photos taken from the front, back, and side.

The device sends the body type information entered by the user and the full-body photo taken to the server.

2. Clothing data collection

The server collects data about clothing sold online (images, sizes, materials, colors, etc.) using APIs or web scraping technology from partner online stores and stores it in a database.

3. 3D model generation and synthesis

The server analyzes the user's body shape information and uploaded full-body photos to generate a high-resolution 3D model of the user.

The server uses a generative AI model to synthesize the user's selected clothing onto the 3D model, using deep learning techniques to realistically recreate the clothing's fit and texture.

4. Showing a fitting image

The server then sends the generated try-on images taken from multiple angles to the user's device.

The device displays the received try-on images on the user interface.

Users can review the displayed try-on images and, if necessary, request images from different angles or images of other garments.

5. Coordination suggestions and purchasing procedures

If the user would like outfit suggestions, they can click the "Request outfit suggestions" button.

The server sends a request to the salesperson in charge of coordinating the outfit.

The salesperson suggests appropriate outfits based on the user's body type and preferences, and sends feedback to the server.

The server generates images of the suggested outfits to try on and displays them on the user's device.

The user reviews the suggested outfits and clicks the "Purchase" button if they decide to purchase.

The terminal sends the purchase information to the server and connects to the online store's payment system.

This invention allows users to easily select clothing that fits their body type and experience the virtual fitting process as if they were actually trying the clothes on. Furthermore, they can smoothly complete the online purchase process while checking suggested outfits.

The processing flow is explained below.

Step 1:

Users launch the application and enter their body information, such as height, weight, and measurements. They also upload full-body photos taken from the front, back, and side.

Step 2:

The device sends the body shape information and full-body photo entered by the user to the server.

Step 3:

The server analyzes the received body shape information and full-body photo data to generate a high-resolution 3D model of the user. This analysis is performed using image recognition algorithms.

Step 4:

The server uses APIs or web scraping technology from partner online stores to collect data on the clothing being sold (images, sizes, materials, colors, etc.) and stores it in a database.

Step 5:

The server then synthesizes the clothing selected by the user onto the generated 3D model of the user, using a generative AI model to realistically recreate the fit and texture of the clothing.

Step 6:

The server then sends the generated try-on images taken from multiple angles to the user's device.

Step 7:

The device displays the received try-on images on the user interface.

Step 8:

The user reviews the displayed try-on images. If necessary, they can request try-on images from different angles or images of other garments.

Step 9:

If the user would like outfit suggestions, they can click the "Request outfit suggestions" button.

Step 10:

The server sends a request to the salesperson in charge of coordinating the outfit.

Step 11:

The salesperson suggests appropriate outfits based on the user's body type and preferences, and sends feedback to the server.

Step 12:

The server generates images of the suggested outfits to try on and sends them to the user's device.

Step 13:

The device displays the received outfit try-on image on the user interface.

Step 14:

The user reviews the suggested outfits and clicks the "Purchase" button if they decide to purchase.

Step 15:

The device sends the purchase information to the server.

Step 16:

The server records purchase information and connects it to the online store's payment system.

Step 17:

The server notifies the user of the order confirmation and delivery information.

Step 18:

The terminal will display order confirmation and shipping information to the user.

(Example 1)

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

Traditional online shopping has the problem that users cannot accurately understand how clothes will fit or how the design will look on them unless they actually try them on. Furthermore, coordination suggestions tailored to the user's preferences and the ability to check how the clothes will look when tried on are insufficient, which discourages users from making a purchase. This has led to a decline in user satisfaction with online shopping.

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

In this invention, the server includes means for inputting the user's body type information, means for taking and uploading full-body photos of the user from multiple angles, means for collecting data on clothing sold online, means for combining clothing with the generated high-resolution 3D model of the user, means for sending the generated try-on images to the user's device, and means for displaying the try-on images on the user's device. This allows users to easily select clothing that fits their body type and experience the virtual try-on experience as if they were actually trying on the clothes. In addition, users can request coordination suggestions from a salesperson and check the suggested try-on images, which increases the user's desire to purchase.

"User" refers to an individual who uses the system to enter body type information and take and upload full-body photos.

"Body type information" refers to detailed data about the user's body, such as their height, weight, and measurements.

"Full-body photos" refer to images of the user's body taken from multiple angles, including the front, back, and side.

"Data on clothing sold online" refers to information such as clothing images, sizes, materials, and colors collected from online sales sites and stores.

"High-resolution 3D model" refers to a three-dimensional computer graphics model that reproduces the user's body in detail, generated based on the user's body shape information and a full-body photograph.

"Generative AI model" refers to an artificial intelligence model trained using deep learning technology to realistically synthesize clothing onto a user's 3D model.

"Try-on image" refers to an image created by combining the selected clothing onto the user's 3D model using a generative AI model.

"User's device" refers to the electronic device used by the user, such as a smartphone, tablet, or PC.

"Coordination suggestions" refer to combinations of multiple items of clothing recommended by a salesperson based on the user's body type information and preferences.

"Salesperson" refers to a person in charge of making outfit suggestions to users through the system.

This invention is a virtual try-on system that uses the user's body type information and full-body photographs taken from multiple angles to generate a fitting image tailored to the user. In this system, the program is executed in the following steps:

First, the user launches a dedicated application on their smartphone or PC and enters their body information, including height, weight, and measurements. The user then takes full-body photos of the front, back, and side and uploads them to the application. This uploaded data is then sent to the server via the device.

The device securely transmits input and uploaded data to the server using the HTTPS protocol. The server receives this data and uses the image analysis technology OpenCV to analyze the user's body shape with high accuracy. The deep learning frameworks TensorFlow and PyTorch are used to generate a high-resolution 3D model based on the analyzed data.

After generating a 3D model for the user, the server uses APIs or web scraping technology from partner online stores to collect data about clothing sold online. This data includes clothing images, sizes, materials, colors, etc. This data is stored in a database and used to synthesize clothing onto the user's 3D model.

The server then uses a generative AI model to synthesize the clothing selected by the user onto the generated 3D model. The generative AI model is trained using deep learning technology to realistically reproduce the fit and texture of the clothing. Deep learning algorithms using TensorFlow and PyTorch are used in this process.

The generated try-on images are photographed from multiple angles and sent to the user's device as JPEG or PNG image files. The device displays the received try-on images on the application's user interface. The user can review the displayed try-on images and request images from different angles or try-on images of other garments as needed.

Furthermore, if the user wishes to receive outfit suggestions, they click the "Request outfit suggestions" button. The server sends a request to the salesperson in charge of outfit suggestions, who then suggests an appropriate outfit based on the user's body type and preferences and sends feedback to the server. Based on this feedback, the server generates a new try-on image and displays it on the user's device. Finally, the user checks the suggested outfit and clicks the "Purchase" button if they decide to purchase. This purchase information is sent to the server via the device, and the purchase process is carried out in conjunction with the online store's payment system.

Specific examples

For example, if a user wants to try on "blue jeans" and a "white T-shirt,"

1. The user enters their height as 170cm, weight as 65kg, and measurements as 90-75-90, and uploads full-body photos of the front, back, and side.

2. The device sends this information to the server.

3. The server uses web scraping technology to collect data on "blue jeans" and "white T-shirts" and stores it in a database.

4. The server uses image analysis technology to generate a high-resolution 3D model of the user, and then uses a generative AI model to synthesize jeans and a T-shirt onto the 3D model.

5. The server generates try-on images from multiple angles and sends them to the user's device.

6. The user can check the newly generated try-on image and then decide to "purchase this outfit."

Example prompt

"Enter your height, weight, and measurements, and upload full-body photos taken from the front, back, and side."

This system allows users to easily find clothes that fit their body type and experience the same sensation of trying them on in real life through virtual try-on. They can also request outfit suggestions and check the suggested try-on images, making online clothing shopping a smoother and more satisfying experience.

The flow of the identification process in Example 1 will be explained using Figure 11.

Step 1:

The user launches the application.

Specific operation: The user taps or clicks on the dedicated application on their smartphone or PC to launch it and proceeds to the first screen.

Input: None

Output: The application launches and displays a screen where the user can enter body information.

Step 2:

The user enters body type information.

Specific operation: The user enters body information such as height, weight, and measurements into the application form. They also provide full-body photos taken from the front, back, and side.

Input: Body information such as height, weight, and measurements

Output: Display of entered body shape information and full-body photo

Step 3:

Users upload full-body photos.

Specific operation: The user uploads full-body photos of the front, back, and side using the upload function within the application.

Input: Full-body photos (front, back, and side)

Output: Full-body photo upload complete message

Step 4:

The device sends the input data to the server.

Specific operation: The device sends the user's body shape information and full-body photo to the server via the HTTPS protocol.

Input: User's body type information and full-body photo

Output: The data is sent to the server and awaits processing.

Step 5:

The server analyzes body shape information and full-body photos.

Specific operation: The server performs image analysis using OpenCV and extracts the features necessary to create a 3D model based on the user's body shape information.

Input: Body information and full-body photo

Output: Feature-extracted data

Step 6:

The server generates a high-resolution 3D model.

Specific operation: The server uses TensorFlow and PyTorch for deep learning to generate a high-resolution 3D model based on the user's body shape.

Input: Feature-extracted data

Output: High-resolution 3D model

Step 7:

The server collects data on clothing sold online.

Specific operation: The server calls the API of partner online stores or uses web scraping to collect the latest clothing data (images, sizes, materials, colors, etc.).

Input: API endpoint of affiliated online store or URL of scraping target

Output: Latest clothing data stored in the clothing database

Step 8:

The server uses a generative AI model to synthesize the clothing onto the 3D model.

Specific operation: The server uses a generative AI model to synthesize clothing onto the user's 3D model based on the collected clothing data.

Input: 3D model and clothing data

Output: Try-on images from multiple angles

Step 9:

The server sends the generated try-on image to the device.

Specific operation: The server generates try-on images in JPEG or PNG format and sends them to the user's device. High-speed data transfer may also be performed via a CDN.

Input: Try-on image

Output: Try-on image sent to the device

Step 10:

The device displays the try-on image on the user interface.

Specific operation: The device displays the received try-on image on the application's user interface, allowing the user to operate it.

Input: Try-on image

Output: Try-on image displayed on the user interface

Step 11:

Users can check the fitting images and submit requests if necessary.

Specific operation: The user reviews the try-on images and, if they wish to request images from different angles or images of other garments being tried on, clicks the corresponding button in the application.

Input: User request

Output: The request is sent to the server.

Step 12:

The user requests outfit suggestions.

Specific operation: If the user would like outfit suggestions, they click the "Request outfit suggestions" button.

Input: User's outfit suggestion request

Output: The request is sent to the server.

Step 13:

The server sends the request to the salesperson.

Specific operation: The server sends a coordination suggestion request to the salesperson, along with the necessary user information.

Input: User request

Output: The request is sent to the salesperson.

Step 14:

Salespeople will provide feedback on suggestions.

Specific operation: The salesperson considers the appropriate outfit based on the user's body type and preferences, and sends feedback to the server.

Input: User's body type and preferences

Output: Feedback on outfit suggestions

Step 15:

The server generates images of outfits to try on.

Specific operation: The server generates new try-on images based on feedback from the salesperson and sends them to the user's device.

Input: Feedback on outfit suggestions

Output: Try-on image of outfit sent to device

Step 16:

The user reviews the offer and decides to purchase.

Specific operation: The user checks the newly generated outfit try-on image and, if they like it, clicks the "Purchase" button.

Input: Coordination try-on image

Output: Purchase request sent to server

Step 17:

The device sends purchase information to the server and connects with the online store.

Specific operation: The terminal sends purchase information to the server, and the server works with the online store's payment system to complete the purchase process.

Enter: Purchase information

Output: The purchase is completed and a confirmation is sent to the user.

(Application Example 1)

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

Traditionally, trying on clothes in physical stores was time-consuming and labor-intensive. Additionally, the types of clothing that could be tried on were limited, making it difficult to try out many options. Furthermore, with online shopping, customers were unable to see how the actual product would look, leading to frequent returns and exchanges after purchase. To solve these problems, a system was needed that allowed users to easily try on clothes and select the best fit for their body type.

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

In this invention, the server includes means for inputting a user's body type information, means for taking and uploading full-body photos of the user from multiple angles, means for collecting data on available items, means for overlaying items onto the generated 3D model of the user, means for presenting virtual try-on images to the user's device, means for the user to input body type information and upload a full-body photo using their own device, means for collecting and saving data on items sold online using the API or web scraping technology of affiliated online stores, means for analyzing the user's body type information and uploaded full-body photos and generating a high-resolution 3D model of the user, and means for generating try-on images from multiple angles and sending them to the user's device. This allows users to smoothly try on clothes virtually in a physical store, shortening the time it takes to actually try them on and combining the convenience of online shopping with the experience of a physical store.

"User's body type information" refers to the user's physical measurements and characteristics, such as height, weight, and three sizes.

A "full-body photo" is a photo that shows the user's entire body, and includes multiple photos taken from the front, back, and side.

"Purchasable Item Data" refers to information about products such as clothing and accessories sold at affiliated online stores and in-store, including attributes such as images, size, material, and color.

"3D model" refers to a high-resolution three-dimensional digital model generated based on the user's body shape information and full-body photograph.

"Means for synthesizing items" refers to the process of virtually applying selected clothing and accessories to the generated 3D model of the user to generate a realistic try-on image.

"Virtual try-on image" refers to an image that combines selected clothing and accessories with a 3D model of the user, simulating trying on the clothing and accessories from multiple angles.

"Affiliated Online Store API" refers to an application programming interface for automatically obtaining data on products sold by affiliated online stores.

"Web scraping technology" refers to technology that automatically extracts data from websites.

"Means for generating a high-resolution 3D model" refers to the process of analyzing a user's body shape information and full-body photograph to create a highly accurate three-dimensional digital model.

"Means to request outfit suggestions" refers to the function that allows a user to request outfit suggestions from a salesperson based on the user's preferences.

"Virtual try-on" refers to the act of allowing a user to try on an item on a digital model instead of actually trying it on.

This invention is a system that uses a user's body type information and full-body photograph to enable virtual try-on, improving the fitting experience in physical stores. The system is built using the user's device (smartphone), a series of servers, and APIs or web scraping technologies from affiliated online stores.

Program generation

The system uses the following hardware and software:

User device (smartphone): Android or iOS device with camera functionality

Server: Data processing and generative AI model execution (using TensorFlow or PyTorch)

Partner online store API or web scraping technology (Beautiful Soup, Scrapy, etc.)

Database: MySQL or PostgreSQL

Program processing overview

The server first receives the body shape information and full-body photo sent by the user from their device, and then uses image analysis technology to generate a high-resolution 3D model of the user. This 3D model is precisely created using deep learning, recreating a realistic fit to the user's body shape.

The server then uses clothing data collected from partner online stores to synthesize the selected clothing onto the user's 3D model. This synthesis process utilizes generative AI models to accurately reproduce the texture and fit of the clothing. Try-on images taken from multiple angles are generated and sent to the user's device.

Users can check the virtual try-on images on their devices and, if they like them, proceed with the purchase process. Furthermore, if users would like a coordination suggestion, they can send a request to the salesperson. The coordination suggested by the salesperson is then regenerated as a virtual try-on image and presented to the user.

Examples and prompts

As a specific prompt, when collecting clothing data using the API of a partner online store, run the following command:

curl -X GET "https://netstore.com/api/v1/products" -H "Authorization: Bearer YOUR_API_KEY"

Also, if you use web scraping technology, here's a script that uses Python's Beautiful Soup to extract product data from a specified URL:

from bs4 import BeautifulSoup

Import requests

url = "https://netstore.com/products"

response = requests.get(url)

soup = BeautifulSoup(response.content, 'html.parser')

for product in soup.find_all('div', class_='product'):

product_name = product.find('h2').get_text()

product_price = product.find('span', class_='price').get_text()

print(product_name, product_price)

This system allows users to seamlessly try on clothes virtually in a physical store, shortening the time spent trying them on in person and combining the convenience of online shopping with the experience of a physical store.

The flow of the specific processing in Application Example 1 will be explained using Figure 12.

Step 1:

The user enters their body type information into the terminal. The user enters physical attributes such as height, weight, and measurements into the terminal, and the entered data is sent to the server. At this point, the input is the user's physical numerical data, and the output is raw data sent to the server.

Step 2:

The user takes full-body photos from multiple angles and uploads them via their device. The user takes photos from the front, back, and side using the device's camera and sends the image data to the server. At this point, the input is multiple image files, and the output is image data stored on the server.

Step 3:

The server uses the API of a partner online store or web scraping technology to collect data on the items being sold. Specifically, the server sends a request to an API endpoint and receives product information in response, or parses a web page to obtain the required product data. At this point, the input is the API request or HTML content, and the output is a set of product data.

Step 4:

The server analyzes the user's body shape information and full-body photo to generate a high-resolution 3D model. The collected image data and body shape information are analyzed using a deep learning model (using TensorFlow and PyTorch) to create a highly accurate 3D model of the user. At this point, the input is body shape information and image data, and the output is a 3D model.

Step 5:

The server uses a generative AI model to synthesize the selected item onto a 3D model. The user selects from the collected product data and synthesizes it onto the 3D model to create a virtual try-on image. The generative AI model reproduces the texture and fit of the clothing with high accuracy. At this point, the input is the 3D model and product data, and the output is a try-on image.

Step 6:

The server then sends the generated try-on images, photographed from multiple angles, to the user's device. These images are displayed on the user's device, allowing the user to check the virtual try-on image. At this point, the input is the try-on image data, and the output is the virtual try-on image displayed on the user's device.

Step 7:

When a user requests a coordination suggestion, they send a request from their terminal to the server. The server receives this request and notifies the salesperson in charge. At this point, the input is the request from the user, and the output is a notification to the salesperson.

Step 8:

The salesperson creates a coordination suggestion and sends feedback to the server. The server again generates a virtual try-on image of the suggested coordination based on the user's 3D model. At this point, the input is the coordination suggestion from the salesperson, and the output is a new try-on image.

Step 9:

The server sends the generated coordinated try-on image to the user's device, where the user confirms it. If the user decides to purchase, they click the "Purchase" button on their device, and the purchase information is sent to the server. The input at this point is the virtual try-on image and the user's purchase decision, and the output is the progress of the purchase procedure.

It is also possible to further combine an emotion engine that estimates the user's emotion. 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.

This invention combines a virtual try-on system that generates a 3D model based on the user's body type information and full-body photographs from multiple angles, then synthesizes clothing onto it, with an emotion engine that recognizes the user's emotions. This system can suggest clothing and outfits that correspond to the user's emotions, providing a more personalized shopping experience.

1. Enter your body type information and upload a full-body photo.

Users launch the application and enter their body information (height, weight, measurements, etc.). They also upload full-body photos taken from multiple angles.

The device sends this body shape information and a full-body photo to the server.

2. Clothing data collection

The server uses API or web scraping technology to collect data on the clothing being sold (images, sizes, materials, colors, etc.) from partner online stores and stores it in a database.

3. 3D model generation and clothing synthesis

The server analyzes the user's body shape information and full-body photo data to generate a high-resolution 3D model of the user, using the latest image recognition algorithms.

The server uses a generative AI model to synthesize the selected clothing onto the 3D model. This process utilizes deep learning techniques to realistically recreate the fit and texture of the clothing.

4. Showing a fitting image

The server then sends the generated try-on images taken from multiple angles to the user's device.

The device displays the received try-on images on the user interface.

The user can review the displayed try-on images and, if necessary, request images from different angles or to try on other garments.

5. Emotion Recognition Using an Emotion Engine

The device uses an emotion engine to analyze the user's facial expressions and voice to identify their emotional state. This is done by capturing data in real time using a camera and microphone.

The server evaluates the user's reaction to the try-on images based on emotional data from the emotion engine.

6. Coordination proposals and adjustments

If the user would like outfit suggestions, they can click the "Request outfit suggestions" button.

The server sends a request to the salesperson in charge of coordinating the outfit.

The salesperson suggests appropriate outfits based on the user's body type, preferences, and emotional data, and sends feedback to the server.

The server generates images of the suggested outfits to try on and displays them on the user's device. It also adjusts the suggestions in real time based on the user's emotional data.

7. Purchase Procedure

The user reviews the suggested outfits and clicks the "Purchase" button if they decide to purchase.

The terminal sends the purchase information to the server and connects to the online store's payment system.

The server records the purchase information and notifies the user of the order confirmation and shipping information.

The terminal will display order confirmation and shipping information to the user.

The system of the present invention allows users to easily select clothing that fits their body type and experience the virtual fitting process as if they were actually trying it on. Furthermore, by utilizing an emotion engine to make suggestions based on the user's emotional state, a more personalized shopping experience is realized. This series of processes increases user satisfaction and improves the online shopping experience.

The processing flow is explained below.

Step 1:

Users launch the application and enter their body information, such as height, weight, and measurements. They also upload full-body photos taken from the front, back, and side to the application.

Step 2:

The device sends the body shape information and full-body photo entered by the user to the server.

Step 3:

The server analyzes the received body shape information and full-body photo data and uses image recognition algorithms to generate a high-resolution 3D model of the user.

Step 4:

The server uses API or web scraping technology to collect data on the clothing being sold (images, sizes, materials, colors, etc.) from partner online stores and stores it in a database.

Step 5:

The server then synthesizes the clothing selected by the user onto the generated 3D model of the user, using a generative AI model to realistically reproduce the fit and texture of the clothing.

Step 6:

The server then sends the generated try-on images taken from multiple angles to the user's device.

Step 7:

The device displays the received try-on images on the user interface.

Step 8:

The user reviews the displayed try-on images. If necessary, they can request images from different angles or try on other garments.

Step 9:

The device captures the user's facial expressions with a camera or collects their voice with a microphone, and then sends this data to the emotion engine.

Step 10:

The server uses an emotion engine to analyze the user's facial expressions and voice to identify their emotional state. For example, if the user is smiling, it will be identified as "satisfied," and if they are frowning, it will be identified as "anxious."

Step 11:

The server determines the next action based on the emotional state data from the emotion engine. For example, if the user is satisfied, it continues with the suggestion, but if they are anxious, it presents a different option.

Step 12:

If the user would like outfit suggestions, they can click the "Request outfit suggestions" button.

Step 13:

The server sends a request to the salesperson in charge of coordinating the outfit.

Step 14:

The salesperson suggests appropriate outfits based on the user's body type, preferences, and emotional data, and sends feedback to the server.

Step 15:

The server generates images of the suggested outfits to try on and sends them to the user's device. It also adjusts the suggestions in real time based on the user's emotional data.

Step 16:

The device displays the received try-on image of the outfit on the user interface.

Step 17:

The user reviews the suggested outfits and clicks the "Purchase" button if they decide to purchase.

Step 18:

The device sends the purchase information to the server.

Step 19:

The server records the purchase information and notifies the user of the order confirmation and shipping information.

Step 20:

The terminal will display order confirmation and shipping information to the user.

(Example 2)

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

In recent years, with the spread of online shopping, there has been an increasing demand for remote try-on and personalized shopping experiences. However, current systems have difficulty adequately reproducing the fit and texture of clothing when actually trying on, and are unable to make suggestions based on the user's emotions. Therefore, there is a need for a more realistic virtual try-on system to improve the user experience.

The specific processing performed by the specific 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 inputting the user's body type information, means for taking and uploading full-body images of the user from multiple angles, means for collecting data on clothing available for sale, means for combining clothing items with the generated three-dimensional model of the user, means for presenting images of the items to be tried on on the user's device, means for analyzing the user's facial expressions and voice to recognize emotions, and means for adjusting suggestions based on emotions. This allows the user to virtually try on clothing that fits their body type and receive personalized suggestions based on their emotional state.

"Means for inputting user's body type information" refers to an interface and system for inputting data related to the user's body type, such as height, weight, and measurements.

"Means for taking and uploading full-body images of the user from multiple angles" refers to the camera and upload function for taking images of the user's entire body from different angles and uploading that image data to the system.

"Means for collecting data on clothing for sale" refers to technology for collecting and storing data such as images, sizes, materials, and colors of clothing for sale from online stores and other sources.

"Means for combining clothing items with a generated 3D model of the user" refers to an algorithm and system for realistically combining selected clothing items with a 3D model generated based on the user's body shape information and full-body image.

"Means for presenting try-on images on the user's device" refers to the interface and system for displaying the generated try-on images on the screen of the user's device (smartphone, tablet, PC, etc.).

"Means for analyzing a user's facial expressions and voice to recognize emotions" refers to algorithms and systems that analyze a user's facial expressions and voice data acquired using devices such as cameras and microphones, and identify the user's emotional state.

"Means for adjusting suggestions based on emotions" refers to technology and systems for changing and adjusting suggested clothing and outfits in real time based on the user's emotional data.

This invention is a virtual fitting system that generates a high-resolution three-dimensional model based on the user's body type information and full-body image, and then realistically combines clothing onto it. It also has the ability to analyze the user's emotions from their facial expressions and voice, and adjust clothing suggestions based on that.

This system uses the following hardware and software:

An interface for inputting the user's body shape information (such as a smartphone or PC)

A camera that captures a full-body image of the user (such as a camera built into a smartphone)

API or web scraping tool for collecting data on clothing for sale

Generative AI models for generating 3D models (e.g., deep learning models built in Python)

A user interface that displays synthesized try-on images

Emotion recognition engine for analyzing user facial expressions and voice (e.g., emotion analysis API)

This system performs the following processes:

The user enters their body type information through the launched application and takes and uploads full-body images from multiple angles. The device then sends this data to the server. The server then collects data on clothing for sale from online stores using APIs or web scraping technology and stores it in a database. The server analyzes the user's body type information and full-body images and uses a generative AI model to generate a high-resolution 3D model of the user. The server then combines the clothing selected by the user into the 3D model to generate a realistic try-on image. This try-on image is then sent to the user's device and displayed.

In addition, the device uses a camera and microphone to capture the user's facial expressions and voice in real time, and analyzes their emotions using an emotion recognition engine. The server then uses this emotional data to adjust the suggested clothing and outfits in real time.

As a concrete example, suppose a user inputs their height (170cm), weight (65kg), and measurements (B:95cm, W:75cm, H:95cm), and uploads full-body images from the front and side. Based on this, the server generates a 3D model of the user and synthesizes a navy jacket. An example prompt for this stage is: "Based on the user's height of 170cm, weight (65kg), and measurements (B:95, W:75, H:95), generate a 3D model based on full-body front and side photos and synthesize a high-resolution navy jacket. Also, recognize positive emotions from the user's smiling face and suggest further outfit recommendations."

The system allows users to virtually try on clothes that fit their body type and receive personalized suggestions based on their emotional state.

The flow of the identification process in Example 2 will be explained using Figure 13.

Program processing flow

Step 1:

The user launches the application and enters their body type information.

Input: User's body information (height, weight, measurements, etc.)

Output: Body shape information is saved in the system.

Specific operation: The user enters body type information into the application's input fields and clicks the "Submit" button. This information is sent to the server via the device.

Step 2:

Users take full-body images from multiple angles and upload them.

Input: Full-body images of the user taken from the front and side

Output: The whole-body image is saved to the system.

Specific operation: The user uses the smartphone camera to take full-body images of themselves from multiple angles, selects the images in the application, and clicks the "Upload" button. The image data is sent to the server via the device.

Step 3:

The server collects clothing data from affiliated online stores.

Input: Online store API information or web page URL

Output: Garment data (images, size, material, color, etc.) is saved in a database.

Specific operation: The server automatically collects clothing data from online stores using APIs and web scraping tools. When collecting data, it also checks for duplicates and missing data.

Step 4:

The server analyzes the user's body shape information and full-body image, and generates a 3D model using a generative AI model.

Input: User's body shape information and full-body image

Output: High-resolution 3D model of the user

How it works: The server uses deep learning algorithms to analyze the user's body shape information and full-body image to generate a 3D model. This process utilizes a GPU to speed up calculations.

Step 5:

The server synthesizes the user's selected clothing onto a 3D model.

Input: User's 3D model and selected clothing data

Output: Composite fitting image

Specific operation: The server uses a generative AI model to synthesize the selected clothing onto the user's 3D model in a way that realistically reproduces the fit and texture. As a result, a fitting image is generated.

Step 6:

The server sends the generated try-on image to the user's device.

Input: Synthesized fitting image

Output: Try-on image displayed on the user's device

Specific operation: The try-on image is encoded as images taken from multiple angles and sent from the server to the device. The device displays this on the user interface.

Step 7:

The device captures the user's facial expressions and voice and analyzes them using an emotion recognition engine.

Input: User's facial and voice data

Output: User emotion data

Specific operation: The device uses a camera and microphone to capture the user's facial expressions and voice in real time, and then analyzes this data with an emotion recognition engine to identify the user's emotional state.

Step 8:

The server analyzes the emotional data and adjusts the suggestions in real time.

Input: User emotion data

Output: Adjusted proposal content

Specific operation: Based on the emotional data, the server changes and adjusts the fitting images and outfit suggestions in real time to provide optimal suggestions.

Step 9:

The user selects the suggested outfit and completes the purchase process.

Input: User purchase decision information

Output: Purchase confirmation and shipping information

Specific operation: When the user clicks the "Purchase" button, the device sends this information to the server. The server then links the purchase information to the online store's payment system and completes the purchase process. The user is then notified of order confirmation and delivery information.

This allows users to virtually try on clothes that fit their body type, receive personalized suggestions based on their emotions, and enjoy an optimal shopping experience.

(Application Example 2)

Next, we will explain Application Example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the headset-type terminal 314 will be referred to as the "terminal."

Conventional virtual try-on systems were able to generate fitting images based on the user's body type information, but were unable to make suggestions that took the user's emotions into account. This made it difficult to improve the user's satisfaction with the clothing and outfits they selected. Furthermore, the lack of coordination adjustments based on real-time emotional feedback meant they were unable to fully meet the individual needs of users.

The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting the user's physique information, means for taking and uploading full-body photos of the user from multiple angles, means for collecting data on clothing for sale, means for combining clothing with the generated high-resolution 3D model of the user, means for analyzing the user's emotions and suggesting clothing and outfits based on the emotion data, and means for presenting images of the clothing to be tried on on the user's device. This makes it possible to suggest personalized clothing and outfits based on the user's emotions, improving user satisfaction. Furthermore, by adjusting the suggestions based on real-time emotion feedback, it is possible to more appropriately meet the individual needs of the user.

"User's body type information" refers to data related to the user's body measurements, such as height, weight, and three sizes.

A "full-body photo" is an image of the user taken from multiple angles (front, back, side, etc.).

"Data on clothing for sale" refers to detailed information such as clothing images, sizes, materials, and colors collected from affiliated online stores.

A "high-resolution 3D model" is a 3D model that is generated based on the user's body type information and a full-body photograph, and is rendered in great detail.

"Clothing synthesis" is a technology that uses data on clothing for sale to realistically display clothing on the generated high-resolution 3D model.

"Means for analyzing emotions and suggesting clothing and outfits based on emotional data" refers to technology that analyzes a user's facial expressions and voice, and then suggests the most suitable clothing and outfits for the user based on the emotional data obtained from this.

"Means for presenting try-on images" refers to technology that displays the generated virtual try-on images on the user's device.

"Emotional data" is data that represents emotional states such as joy, surprise, and dissatisfaction obtained from the analysis of the user's facial expressions and voice.

"Coordination" refers to the user's clothing combination and includes the selection process.

"Feedback" is the process of adjusting and re-proposing suggestions based on the user's emotional data.

This invention is a virtual fitting system that generates a 3D model based on the user's body type information and full-body photographs from multiple angles, then synthesizes clothing onto it, combined with an emotion engine that recognizes the user's emotions. This system can suggest clothing and outfits based on the user's emotions, providing a more personalized shopping experience.

The server realizes this system by integrating the following technologies: First, the server provides a means for users to input their body type information. This allows users to enter information such as their height, weight, and three sizes. It also provides a means for users to upload full-body photos taken from multiple angles. This allows users to upload photos of their front, side, and back.

The server has a means of collecting data on clothing for sale from online stores and other data sources. This data includes detailed information such as clothing images, sizes, materials, and colors. The server then uses the latest image recognition algorithms (e.g., TensorFlow) to analyze the user's body shape information and full-body photo data to generate a high-resolution 3D model. This 3D model is then used to synthesize clothing using deep learning technology to generate realistic try-on images.

Furthermore, it has a means of analyzing the user's facial expressions and voice using an emotion engine (e.g., Affectiva API) to obtain emotional data. It also incorporates a means of suggesting the most suitable clothing and outfits for the user based on the emotional data. This makes it possible to make appropriate suggestions in real time based on the user's emotions.

A means of displaying try-on images on the user's device has also been developed, allowing the user to view the generated virtual try-on image from multiple angles. After the try-on image is displayed, the user can provide feedback on their emotional data on the spot and adjust their outfit as needed.

For example, a user enters their height and weight into the app and uploads three full-body photos (front, back, and side). After the photo shoot is complete, emotion analysis is performed and if the user is happy, the system will suggest outfits in bright colors and the latest fashions. On the other hand, if the user is unhappy, the system will adjust to suggest new outfits.

An example of a prompt statement is as follows:

The user is 170cm tall and weighs 65kg. Front, back, and side photos have been uploaded. Sentiment analysis indicates that the user is currently feeling "joy." Based on this, suggest multiple outfits in bright colors and the latest fashions.

In this way, users can choose the clothing that best suits their body type and get the feeling of trying it on in real life through a virtual try-on experience. Real-time emotional feedback provides a more personalized shopping experience.

The flow of the specific processing in Application Example 2 will be explained using Figure 14.

Step 1:

Users launch the application, enter their body type information (height, weight, measurements, etc.), and upload full-body photos taken from multiple angles (front, back, side). The entered data consists of body type information and photo data, which are sent from the device to the server. As a result, data related to the user's body type and full-body photos is stored on the server.

Step 2:

The server collects data about clothing sold (images, sizes, materials, colors, etc.) from online stores and other data sources. This collection is done using APIs or web scraping technology. The acquired data is stored in a database on the server. The input is clothing data, and the output is clothing data stored in the database.

Step 3:

The server uses the latest image recognition algorithms (e.g., TensorFlow) to analyze the user's body shape information and full-body photo data and generate a high-resolution 3D model. During this process, each user's photo is pixel-analyzed to create the shape of the 3D model. The input for this step is the user's body shape information and photo data, and the output is a high-resolution 3D model.

Step 4:

The server uses a generative AI model to synthesize clothing for sale onto the generated 3D model. Utilizing deep learning technology, data processing is performed to realistically reproduce the fit and texture of the clothing. The input is a high-resolution 3D model and clothing data, and the output is a try-on image.

Step 5:

The device uses an emotion engine (e.g., Affectiva API) to analyze the user's facial expressions and voice in real time and obtain emotional data. Captured facial and voice data is input, and analyzed emotional data is output. In this step, the device obtains data using the camera and microphone.

Step 6:

The server suggests optimal clothing and outfits for the user based on emotional data. The input is emotional data, and the output is outfit suggestions tailored to the user's preferences. These suggestions are made dynamically and adjusted in real time.

Step 7:

The user's device displays the try-on images sent from the server. The input is the try-on image, and the output is the try-on image displayed on the user interface. The user can review the displayed try-on image and, if necessary, request images from different angles or to try on other clothing items.

Step 8:

If the user likes the suggested outfit, they proceed with the purchase. The user clicks the "Purchase" button, and the device sends the purchase information to the server. The input is the purchase information, and the output is purchase confirmation and delivery information. The server connects with the online store's payment system, records the order, and sends a confirmation to the user.

This allows users to virtually try on clothes that fit their body type, receive personalized outfit suggestions based on emotional data, and ultimately make a purchase.

The specific processing unit 290 transmits the results of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the results of the specific processing. The microphone 238 acquires audio indicating the user input regarding the results 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.

Data generation model 58 is what is known as generative AI (artificial intelligence). Examples of data generation model 58 include generative AI such as ChatGPT (Internet search <URL: https://openai.com/blog/chatgpt>) and Gemini (Internet search <URL: https://gemini.google.com/?hl=ja>). Data generation model 58 is obtained by performing deep learning on a neural network. A prompt containing an instruction is input to data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input. Data generation model 58 performs inference on the input inference data in accordance with the instructions indicated by the prompt, and outputs the inference results in the form of data such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and/or summarization.

In the above embodiment, an example was given in which the specific processing was performed by the data processing device 12, but the technology disclosed herein is not limited to this, and the specific processing may also be performed by the headset-type terminal 314.

[Fourth embodiment]

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

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

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, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and 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).

The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I/F 44, and a control target 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and control target 443 are also connected to the bus 52.

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.

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 user 20's surroundings (e.g., an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

The communication I/F 44 is connected to the 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 manner.

The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, in the data processing device 12, specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32.

The specific processing program 56 is an example of a "program" 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 the specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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.

In the robot 414, 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.

Next, we will explain the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 will be referred to as the "terminal."

This invention is a virtual try-on system that uses the user's body type information and full-body photos taken from multiple angles to generate a fitting image tailored to the user. The system begins by the user entering body type information and uploading a full-body photo using their own device. The system then utilizes a generative AI model based on the collected clothing data to synthesize the clothing onto the user's 3D model and present a virtual fitting image. In addition, users can receive coordination suggestions from sales staff, making the process of selecting and purchasing clothing even more enjoyable.

1. Enter your body type information and upload a full-body photo.

Users launch the application and enter their body information, such as their height, weight, and measurements. They also upload full-body photos taken from the front, back, and side.

The device sends the body type information entered by the user and the full-body photo taken to the server.

2. Clothing data collection

The server uses APIs or web scraping technology from partner online stores to collect data on clothing sold online (images, sizes, materials, colors, etc.) and stores it in a database.

3. 3D model generation and synthesis

The server analyzes the user's body shape information and uploaded full-body photos to generate a high-resolution 3D model of the user.

The server uses a generative AI model to synthesize the user's selected clothing onto the 3D model, using deep learning techniques to realistically recreate the clothing's fit and texture.

4. Showing a fitting image

The server then sends the generated try-on images taken from multiple angles to the user's device.

The device displays the received try-on images on the user interface.

Users can review the displayed try-on images and, if necessary, request images from different angles or images of other garments.

5. Coordination suggestions and purchasing procedures

If the user would like outfit suggestions, they can click the "Request outfit suggestions" button.

The server sends a request to the salesperson in charge of coordinating the outfit.

The salesperson suggests appropriate outfits based on the user's body type and preferences, and sends feedback to the server.

The server generates images of the suggested outfits to try on and displays them on the user's device.

The user reviews the suggested outfits and clicks the "Purchase" button if they decide to purchase.

The terminal sends the purchase information to the server and connects to the online store's payment system.

This invention allows users to easily select clothing that fits their body type and experience the virtual fitting process as if they were actually trying the clothes on. Furthermore, they can smoothly complete the online purchase process while checking suggested outfits.

The processing flow is explained below.

Step 1:

Users launch the application and enter their body information, such as height, weight, and measurements. They also upload full-body photos taken from the front, back, and side.

Step 2:

The device sends the body shape information and full-body photo entered by the user to the server.

Step 3:

The server analyzes the received body shape information and full-body photo data to generate a high-resolution 3D model of the user. This analysis is performed using image recognition algorithms.

Step 4:

The server uses APIs or web scraping technology from partner online stores to collect data on the clothing being sold (images, sizes, materials, colors, etc.) and stores it in a database.

Step 5:

The server then synthesizes the clothing selected by the user onto the generated 3D model of the user, using a generative AI model to realistically recreate the fit and texture of the clothing.

Step 6:

The server then sends the generated try-on images taken from multiple angles to the user's device.

Step 7:

The device displays the received try-on images on the user interface.

Step 8:

The user reviews the displayed try-on images. If necessary, they can request try-on images from different angles or images of other garments.

Step 9:

If the user would like outfit suggestions, they can click the "Request outfit suggestions" button.

Step 10:

The server sends a request to the salesperson in charge of coordinating the outfit.

Step 11:

The salesperson suggests appropriate outfits based on the user's body type and preferences, and sends feedback to the server.

Step 12:

The server generates images of the suggested outfits to try on and sends them to the user's device.

Step 13:

The device displays the received outfit try-on image on the user interface.

Step 14:

The user reviews the suggested outfits and clicks the "Purchase" button if they decide to purchase.

Step 15:

The device sends the purchase information to the server.

Step 16:

The server records purchase information and connects it to the online store's payment system.

Step 17:

The server notifies the user of the order confirmation and delivery information.

Step 18:

The terminal will display order confirmation and shipping information to the user.

(Example 1)

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

Traditional online shopping has the problem that users cannot accurately understand how clothes will fit or how the design will look on them unless they actually try them on. Furthermore, coordination suggestions tailored to the user's preferences and the ability to check how the clothes will look when tried on are insufficient, which discourages users from making a purchase. This has led to a decline in user satisfaction with online shopping.

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

In this invention, the server includes means for inputting the user's body type information, means for taking and uploading full-body photos of the user from multiple angles, means for collecting data on clothing sold online, means for combining clothing with the generated high-resolution 3D model of the user, means for sending the generated try-on images to the user's device, and means for displaying the try-on images on the user's device. This allows users to easily select clothing that fits their body type and experience the virtual try-on experience as if they were actually trying on the clothes. In addition, users can request coordination suggestions from a salesperson and check the suggested try-on images, which increases the user's desire to purchase.

"User" refers to an individual who uses the system to enter body type information and take and upload full-body photos.

"Body type information" refers to detailed data about the user's body, such as their height, weight, and measurements.

"Full-body photos" refer to images of the user's body taken from multiple angles, including the front, back, and side.

"Data on clothing sold online" refers to information such as clothing images, sizes, materials, and colors collected from online sales sites and stores.

"High-resolution 3D model" refers to a three-dimensional computer graphics model that reproduces the user's body in detail, generated based on the user's body shape information and a full-body photograph.

"Generative AI model" refers to an artificial intelligence model trained using deep learning technology to realistically synthesize clothing onto a user's 3D model.

"Try-on image" refers to an image created by combining the selected clothing onto the user's 3D model using a generative AI model.

"User's device" refers to the electronic device used by the user, such as a smartphone, tablet, or PC.

"Coordination suggestions" refer to combinations of multiple items of clothing recommended by a salesperson based on the user's body type information and preferences.

"Salesperson" refers to a person in charge of making outfit suggestions to users through the system.

This invention is a virtual try-on system that uses the user's body type information and full-body photographs taken from multiple angles to generate a fitting image tailored to the user. In this system, the program is executed in the following steps:

First, the user launches a dedicated application on their smartphone or PC and enters their body information, including height, weight, and measurements. The user then takes full-body photos of the front, back, and side and uploads them to the application. This uploaded data is then sent to the server via the device.

The device securely transmits input and uploaded data to the server using the HTTPS protocol. The server receives this data and uses the image analysis technology OpenCV to analyze the user's body shape with high accuracy. Based on the analyzed data, the deep learning frameworks TensorFlow and PyTorch are used to generate a high-resolution 3D model.

After generating a 3D model for the user, the server uses APIs or web scraping technology from partner online stores to collect data about clothing sold online. This data includes clothing images, sizes, materials, colors, etc. This data is stored in a database and used to synthesize clothing onto the user's 3D model.

The server then uses a generative AI model to synthesize the clothing selected by the user onto the generated 3D model. The generative AI model is trained using deep learning technology to realistically reproduce the fit and texture of the clothing. Deep learning algorithms using TensorFlow and PyTorch are used in this process.

The generated try-on images are photographed from multiple angles and sent to the user's device as JPEG or PNG image files. The device displays the received try-on images on the application's user interface. The user can review the displayed try-on images and request images from different angles or try-on images of other garments as needed.

Furthermore, if the user wishes to receive outfit suggestions, they click the "Request outfit suggestions" button. The server sends a request to the salesperson in charge of outfit suggestions, who then suggests an appropriate outfit based on the user's body type and preferences and sends feedback to the server. Based on this feedback, the server generates a new try-on image and displays it on the user's device. Finally, the user checks the suggested outfit and clicks the "Purchase" button if they decide to purchase. This purchase information is sent to the server via the device, and the purchase process is carried out in conjunction with the online store's payment system.

Specific examples

For example, if a user wants to try on "blue jeans" and a "white T-shirt,"

1. The user enters their height as 170cm, weight as 65kg, and measurements as 90-75-90, and uploads full-body photos of the front, back, and side.

2. The device sends this information to the server.

3. The server uses web scraping technology to collect data on "blue jeans" and "white T-shirts" and stores it in a database.

4. The server uses image analysis technology to generate a high-resolution 3D model of the user, and then uses a generative AI model to synthesize jeans and a T-shirt onto the 3D model.

5. The server generates try-on images from multiple angles and sends them to the user's device.

6. The user can check the newly generated try-on image and then decide to "purchase this outfit."

Example prompt

"Enter your height, weight, and measurements, and upload full-body photos taken from the front, back, and side."

This system allows users to easily find clothes that fit their body type and experience the same sensation of trying them on in real life through virtual try-on. They can also request outfit suggestions and check the suggested try-on images, making online clothing shopping a smoother and more satisfying experience.

The flow of the identification process in Example 1 will be explained using Figure 11.

Step 1:

The user launches the application.

Specific operation: The user taps or clicks on the dedicated application on their smartphone or PC to launch it and proceeds to the first screen.

Input: None

Output: The application launches and displays a screen where the user can enter body information.

Step 2:

The user enters body type information.

Specific operation: The user enters body information such as height, weight, and measurements into the application form. They also provide full-body photos taken from the front, back, and side.

Input: Body information such as height, weight, and measurements

Output: Display of entered body shape information and full-body photo

Step 3:

Users upload full-body photos.

Specific operation: The user uploads full-body photos of the front, back, and side using the upload function within the application.

Input: Full-body photos (front, back, and side)

Output: Full-body photo upload complete message

Step 4:

The device sends the input data to the server.

Specific operation: The device sends the user's body shape information and full-body photo to the server via the HTTPS protocol.

Input: User's body type information and full-body photo

Output: The data is sent to the server and awaits processing.

Step 5:

The server analyzes body shape information and full-body photos.

Specific operation: The server performs image analysis using OpenCV and extracts the features necessary to create a 3D model based on the user's body shape information.

Input: Body information and full-body photo

Output: Feature-extracted data

Step 6:

The server generates a high-resolution 3D model.

Specific operation: The server uses TensorFlow and PyTorch for deep learning to generate a high-resolution 3D model based on the user's body shape.

Input: Feature-extracted data

Output: High-resolution 3D model

Step 7:

The server collects data on clothing sold online.

Specific operation: The server calls the API of partner online stores or uses web scraping to collect the latest clothing data (images, sizes, materials, colors, etc.).

Input: API endpoint of affiliated online store or URL of scraping target

Output: Latest clothing data stored in the clothing database

Step 8:

The server uses a generative AI model to synthesize the clothing onto the 3D model.

Specific operation: The server uses a generative AI model to synthesize clothing onto the user's 3D model based on the collected clothing data.

Input: 3D model and clothing data

Output: Try-on images from multiple angles

Step 9:

The server sends the generated try-on image to the device.

Specific operation: The server generates try-on images in JPEG or PNG format and sends them to the user's device. High-speed data transfer may also be performed via a CDN.

Input: Try-on image

Output: Try-on image sent to the device

Step 10:

The device displays the try-on image on the user interface.

Specific operation: The device displays the received try-on image on the application's user interface, allowing the user to operate it.

Input: Try-on image

Output: Try-on image displayed on the user interface

Step 11:

Users can check the fitting images and submit requests if necessary.

Specific operation: The user reviews the try-on images and clicks the corresponding button in the application to request images from different angles or images of other garments being tried on.

Input: User request

Output: The request is sent to the server.

Step 12:

The user requests outfit suggestions.

Specific operation: If the user would like outfit suggestions, they click the "Request outfit suggestions" button.

Input: User's outfit suggestion request

Output: The request is sent to the server.

Step 13:

The server sends the request to the salesperson.

Specific operation: The server sends a coordination suggestion request to the salesperson, along with the necessary user information.

Input: User request

Output: The request is sent to the salesperson.

Step 14:

Salespeople will provide feedback on suggestions.

Specific operation: The salesperson considers the appropriate outfit based on the user's body type and preferences, and sends feedback to the server.

Input: User's body type and preferences

Output: Feedback on outfit suggestions

Step 15:

The server generates images of outfits to try on.

Specific operation: The server generates new try-on images based on feedback from the salesperson and sends them to the user's device.

Input: Feedback on outfit suggestions

Output: Try-on image of outfit sent to device

Step 16:

The user reviews the offer and decides to purchase.

Specific operation: The user checks the newly generated outfit try-on image and, if they like it, clicks the "Purchase" button.

Input: Coordination try-on image

Output: Purchase request sent to server

Step 17:

The device sends purchase information to the server and connects with the online store.

Specific operation: The terminal sends purchase information to the server, and the server works with the online store's payment system to complete the purchase process.

Enter: Purchase information

Output: The purchase is completed and a confirmation is sent to the user.

(Application Example 1)

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

Traditionally, trying on clothes in physical stores was time-consuming and labor-intensive. Additionally, the types of clothing that could be tried on were limited, making it difficult to try out many options. Furthermore, with online shopping, customers were unable to see how the actual product would look, leading to frequent returns and exchanges after purchase. To solve these problems, a system was needed that allowed users to easily try on clothes and select the best fit for their body type.

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

In this invention, the server includes means for inputting a user's body type information, means for taking and uploading full-body photos of the user from multiple angles, means for collecting data on available items, means for overlaying items onto the generated 3D model of the user, means for presenting virtual try-on images to the user's device, means for the user to input body type information and upload a full-body photo using their own device, means for collecting and saving data on items sold online using the API or web scraping technology of affiliated online stores, means for analyzing the user's body type information and uploaded full-body photos and generating a high-resolution 3D model of the user, and means for generating try-on images from multiple angles and sending them to the user's device. This allows users to smoothly try on clothes virtually in a physical store, shortening the time it takes to actually try them on and combining the convenience of online shopping with the experience of a physical store.

"User's body type information" refers to the user's physical measurements and characteristics, such as height, weight, and three sizes.

A "full-body photo" is a photo that shows the user's entire body, and includes multiple photos taken from the front, back, and side.

"Purchasable Item Data" refers to information about products such as clothing and accessories sold in affiliated online stores and physical stores, including attributes such as images, size, material, and color.

"3D model" refers to a high-resolution three-dimensional digital model generated based on the user's body shape information and full-body photograph.

"Means for synthesizing items" refers to the process of virtually applying selected clothing and accessories to the generated 3D model of the user to generate a realistic try-on image.

"Virtual try-on image" refers to an image that combines selected clothing and accessories with a 3D model of the user, simulating trying on the clothing and accessories from multiple angles.

"Affiliated Online Store API" refers to an application programming interface for automatically obtaining data on products sold by affiliated online stores.

"Web scraping technology" refers to technology that automatically extracts data from websites.

"Means for generating a high-resolution 3D model" refers to the process of analyzing a user's body shape information and full-body photograph to create a highly accurate three-dimensional digital model.

"Means to request outfit suggestions" refers to the function that allows a user to request outfit suggestions from a salesperson based on the user's preferences.

"Virtual try-on" refers to the act of allowing a user to try on an item on a digital model instead of actually trying it on.

This invention is a system that uses a user's body type information and full-body photograph to enable virtual try-on, improving the fitting experience in physical stores. The system is built using the user's device (smartphone), a series of servers, and APIs or web scraping technologies from affiliated online stores.

Program generation

The system uses the following hardware and software:

User device (smartphone): Android or iOS device with camera functionality

Server: Data processing and generative AI model execution (using TensorFlow or PyTorch)

Partner online store API or web scraping technology (Beautiful Soup, Scrapy, etc.)

Database: MySQL or PostgreSQL

Program processing overview

The server first receives the body shape information and full-body photo sent by the user from their device, and then uses image analysis technology to generate a high-resolution 3D model of the user. This 3D model is precisely created using deep learning, recreating a realistic fit to the user's body shape.

The server then uses clothing data collected from partner online stores to synthesize the selected clothing onto the user's 3D model. This synthesis process utilizes generative AI models to accurately reproduce the texture and fit of the clothing. Try-on images taken from multiple angles are generated and sent to the user's device.

Users can check the virtual try-on images on their devices and, if they like them, proceed with the purchase process. Furthermore, if users would like a coordination suggestion, they can send a request to the salesperson. The coordination suggested by the salesperson is then regenerated as a virtual try-on image and presented to the user.

Examples and prompts

As a specific prompt, when collecting clothing data using the API of a partner online store, run the following command:

curl -X GET "https://netstore.com/api/v1/products" -H "Authorization: Bearer YOUR_API_KEY"

Also, if you use web scraping technology, here's a script that uses Python's Beautiful Soup to extract product data from a specified URL:

from bs4 import BeautifulSoup

Import requests

url = "https://netstore.com/products"

response = requests.get(url)

soup = BeautifulSoup(response.content, 'html.parser')

for product in soup.find_all('div', class_='product'):

product_name = product.find('h2').get_text()

product_price = product.find('span', class_='price').get_text()

print(product_name, product_price)

This system allows users to seamlessly try on clothes virtually in a physical store, shortening the time spent trying them on in person and combining the convenience of online with the experience of a physical store.

The flow of the specific processing in Application Example 1 will be explained using Figure 12.

Step 1:

The user enters their body type information into the terminal. The user enters physical attributes such as height, weight, and measurements into the terminal, and the entered data is sent to the server. At this point, the input is the user's physical numerical data, and the output is raw data sent to the server.

Step 2:

The user takes full-body photos from multiple angles and uploads them via their device. The user takes photos from the front, back, and side using the device's camera and sends the image data to the server. At this point, the input is multiple image files, and the output is image data stored on the server.

Step 3:

The server uses the API of a partner online store or web scraping technology to collect data on the items being sold. Specifically, the server sends a request to an API endpoint and receives product information in response, or parses a web page to obtain the required product data. At this point, the input is the API request or HTML content, and the output is a set of product data.

Step 4:

The server analyzes the user's body shape information and full-body photo to generate a high-resolution 3D model. The collected image data and body shape information are analyzed using a deep learning model (using TensorFlow and PyTorch) to create a highly accurate 3D model of the user. At this point, the input is body shape information and image data, and the output is a 3D model.

Step 5:

The server uses a generative AI model to synthesize the selected item onto a 3D model. The user selects from the collected product data and synthesizes it onto the 3D model to create a virtual try-on image. The generative AI model reproduces the texture and fit of the clothing with high accuracy. At this point, the input is the 3D model and product data, and the output is a try-on image.

Step 6:

The server then sends the generated try-on images, photographed from multiple angles, to the user's device. These images are displayed on the user's device, allowing the user to check the virtual try-on image. At this point, the input is the try-on image data, and the output is the virtual try-on image displayed on the user's device.

Step 7:

When a user requests a coordination suggestion, they send a request from their terminal to the server. The server receives this request and notifies the salesperson in charge. At this point, the input is the request from the user, and the output is a notification to the salesperson.

Step 8:

The salesperson creates a coordination suggestion and sends feedback to the server. The server again generates a virtual try-on image of the suggested coordination based on the user's 3D model. At this point, the input is the coordination suggestion from the salesperson, and the output is a new try-on image.

Step 9:

The server sends the generated coordinated try-on image to the user's device, where the user confirms it. If the user decides to purchase, they click the "Purchase" button on their device, and the purchase information is sent to the server. The input at this point is the virtual try-on image and the user's purchase decision, and the output is the progress of the purchase procedure.

It is also possible to further combine an emotion engine that estimates the user's emotion. 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.

This invention combines a virtual try-on system that generates a 3D model based on the user's body type information and full-body photographs from multiple angles, then synthesizes clothing onto it, with an emotion engine that recognizes the user's emotions. This system can suggest clothing and outfits that correspond to the user's emotions, providing a more personalized shopping experience.

1. Enter your body type information and upload a full-body photo.

Users launch the application and enter their body information (height, weight, measurements, etc.). They also upload full-body photos taken from multiple angles.

The device sends this body shape information and a full-body photo to the server.

2. Clothing data collection

The server uses API or web scraping technology to collect data on the clothing being sold (images, sizes, materials, colors, etc.) from partner online stores and stores it in a database.

3. 3D model generation and clothing synthesis

The server analyzes the user's body shape information and full-body photo data to generate a high-resolution 3D model of the user, using the latest image recognition algorithms.

The server uses a generative AI model to synthesize the selected clothing onto the 3D model. This process utilizes deep learning techniques to realistically recreate the fit and texture of the clothing.

4. Showing a fitting image

The server then sends the generated try-on images taken from multiple angles to the user's device.

The device displays the received try-on images on the user interface.

The user can review the displayed try-on images and, if necessary, request images from different angles or to try on other garments.

5. Emotion Recognition Using an Emotion Engine

The device uses an emotion engine to analyze the user's facial expressions and voice to identify their emotional state. This is done by capturing data in real time using a camera and microphone.

The server evaluates the user's reaction to the try-on images based on emotional data from the emotion engine.

6. Coordination proposals and adjustments

If the user would like outfit suggestions, they can click the "Request outfit suggestions" button.

The server sends a request to the salesperson in charge of coordinating the outfit.

The salesperson suggests appropriate outfits based on the user's body type, preferences, and emotional data, and sends feedback to the server.

The server generates images of the suggested outfits to try on and displays them on the user's device. It also adjusts the suggestions in real time based on the user's emotional data.

7. Purchase Procedure

The user reviews the suggested outfits and clicks the "Purchase" button if they decide to purchase.

The terminal sends the purchase information to the server and connects to the online store's payment system.

The server records the purchase information and notifies the user of the order confirmation and shipping information.

The terminal will display order confirmation and shipping information to the user.

The system of the present invention allows users to easily select clothing that fits their body type and experience the virtual fitting process as if they were actually trying it on. Furthermore, by utilizing an emotion engine to make suggestions based on the user's emotional state, a more personalized shopping experience is realized. This series of processes increases user satisfaction and improves the online shopping experience.

The processing flow is explained below.

Step 1:

Users launch the application and enter their body information, such as height, weight, and measurements. They also upload full-body photos taken from the front, back, and side to the application.

Step 2:

The device sends the body shape information and full-body photo entered by the user to the server.

Step 3:

The server analyzes the received body shape information and full-body photo data and uses image recognition algorithms to generate a high-resolution 3D model of the user.

Step 4:

The server uses API or web scraping technology to collect data on the clothing being sold (images, sizes, materials, colors, etc.) from partner online stores and stores it in a database.

Step 5:

The server then synthesizes the clothing selected by the user onto the generated 3D model of the user, using the generative AI model to realistically reproduce the fit and texture of the clothing.

Step 6:

The server then sends the generated try-on images taken from multiple angles to the user's device.

Step 7:

The device displays the received try-on images on the user interface.

Step 8:

The user reviews the displayed try-on images. If necessary, they can request images from different angles or try on other garments.

Step 9:

The device captures the user's facial expressions with a camera or collects their voice with a microphone, and then sends this data to the emotion engine.

Step 10:

The server uses an emotion engine to analyze the user's facial expressions and voice to identify their emotional state. For example, if the user is smiling, it will be identified as "satisfied," and if they are frowning, it will be identified as "anxious."

Step 11:

The server determines the next action based on the emotional state data from the emotion engine. For example, if the user is satisfied, it continues with the suggestion, but if they are anxious, it presents a different option.

Step 12:

If the user would like outfit suggestions, they can click the "Request outfit suggestions" button.

Step 13:

The server sends a request to the salesperson in charge of coordinating the outfit.

Step 14:

The salesperson suggests appropriate outfits based on the user's body type, preferences, and emotional data, and sends feedback to the server.

Step 15:

The server generates images of the suggested outfits to try on and sends them to the user's device. It also adjusts the suggestions in real time based on the user's emotional data.

Step 16:

The device displays the received outfit try-on image on the user interface.

Step 17:

The user reviews the suggested outfits and clicks the "Purchase" button if they decide to purchase.

Step 18:

The device sends the purchase information to the server.

Step 19:

The server records the purchase information and notifies the user of the order confirmation and shipping information.

Step 20:

The terminal will display order confirmation and shipping information to the user.

(Example 2)

Next, Example 2 will be described. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

In recent years, with the spread of online shopping, there has been an increasing demand for remote try-on and personalized shopping experiences. However, current systems have difficulty adequately reproducing the fit and texture of clothing when actually trying on, and are unable to make suggestions based on the user's emotions. Therefore, there is a need for a more realistic virtual try-on system to improve the user experience.

The specific processing performed by the specific 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 inputting the user's body type information, means for taking and uploading full-body images of the user from multiple angles, means for collecting data on clothing available for sale, means for combining clothing items with the generated three-dimensional model of the user, means for presenting images of the items to be tried on on the user's device, means for analyzing the user's facial expressions and voice to recognize emotions, and means for adjusting suggestions based on emotions. This allows the user to virtually try on clothing that fits their body type and receive personalized suggestions based on their emotional state.

"Means for inputting user's body type information" refers to an interface and system for inputting data related to the user's body type, such as height, weight, and measurements.

"Means for taking and uploading full-body images of the user from multiple angles" refers to the camera and upload function for taking images of the user's entire body from different angles and uploading that image data to the system.

"Means for collecting data on clothing for sale" refers to technology for collecting and storing data such as images, sizes, materials, and colors of clothing for sale from online stores and other sources.

"Means for combining clothing items with a generated 3D model of the user" refers to an algorithm and system for realistically combining selected clothing items with a 3D model generated based on the user's body shape information and full-body image.

"Means for presenting try-on images on the user's device" refers to the interface and system for displaying the generated try-on images on the screen of the user's device (smartphone, tablet, PC, etc.).

"Means for analyzing a user's facial expressions and voice to recognize emotions" refers to algorithms and systems that analyze a user's facial expressions and voice data acquired using devices such as cameras and microphones, and identify the user's emotional state.

"Means for adjusting suggestions based on emotions" refers to technology and systems for changing and adjusting suggested clothing and outfits in real time based on the user's emotional data.

This invention is a virtual fitting system that generates a high-resolution three-dimensional model based on the user's body type information and full-body image, and then realistically combines clothing onto it. It also has the ability to analyze the user's emotions from their facial expressions and voice, and adjust clothing suggestions based on that.

This system uses the following hardware and software:

An interface for inputting the user's body shape information (such as a smartphone or PC)

A camera that captures a full-body image of the user (such as a camera built into a smartphone)

API or web scraping tool for collecting data on clothing for sale

Generative AI models for generating 3D models (e.g., deep learning models built in Python)

A user interface that displays synthesized try-on images

Emotion recognition engine for analyzing user facial expressions and voice (e.g., emotion analysis API)

This system performs the following processes:

The user enters their body type information through the launched application and takes and uploads full-body images from multiple angles. The device then sends this data to the server. The server then collects data on clothing for sale from online stores using APIs or web scraping technology and stores it in a database. The server analyzes the user's body type information and full-body images and uses a generative AI model to generate a high-resolution 3D model of the user. The server then combines the clothing selected by the user into the 3D model to generate a realistic try-on image. This try-on image is then sent to the user's device and displayed.

In addition, the device uses a camera and microphone to capture the user's facial expressions and voice in real time, and analyzes their emotions using an emotion recognition engine. The server then uses this emotional data to adjust the suggested clothing and outfits in real time.

As a concrete example, suppose a user inputs their height (170cm), weight (65kg), and measurements (B:95cm, W:75cm, H:95cm), and uploads full-body images from the front and side. Based on this, the server generates a 3D model of the user and synthesizes a navy jacket. An example prompt for this stage is: "Based on the user's height of 170cm, weight (65kg), and measurements (B:95, W:75, H:95), generate a 3D model based on full-body front and side photos and synthesize a high-resolution navy jacket. Also, recognize positive emotions from the user's smiling face and suggest further outfit recommendations."

The system allows users to virtually try on clothes that fit their body type and receive personalized suggestions based on their emotional state.

The flow of the identification process in Example 2 will be explained using Figure 13.

Program processing flow

Step 1:

The user launches the application and enters their body type information.

Input: User's body information (height, weight, measurements, etc.)

Output: Body shape information is saved in the system.

Specific operation: The user enters body type information into the application's input fields and clicks the "Submit" button. This information is sent to the server via the device.

Step 2:

Users take full-body images from multiple angles and upload them.

Input: Full-body images of the user taken from the front and side

Output: The whole-body image is saved to the system.

Specific operation: The user uses the smartphone camera to take full-body images of themselves from multiple angles, selects the images in the application, and clicks the "Upload" button. The image data is sent to the server via the device.

Step 3:

The server collects clothing data from affiliated online stores.

Input: Online store API information or web page URL

Output: Garment data (images, size, material, color, etc.) is saved in a database.

Specific operation: The server automatically collects clothing data from online stores using APIs and web scraping tools. When collecting data, it also checks for duplicates and missing data.

Step 4:

The server analyzes the user's body shape information and full-body image, and generates a 3D model using a generative AI model.

Input: User's body shape information and full-body image

Output: High-resolution 3D model of the user

How it works: The server uses deep learning algorithms to analyze the user's body shape information and full-body image to generate a 3D model. This process utilizes a GPU to speed up calculations.

Step 5:

The server synthesizes the user's selected clothing onto a 3D model.

Input: User's 3D model and selected clothing data

Output: Composite fitting image

Specific operation: The server uses a generative AI model to synthesize the selected clothing onto the user's 3D model in a way that realistically reproduces the fit and texture. As a result, a fitting image is generated.

Step 6:

The server sends the generated try-on image to the user's device.

Input: Synthesized fitting image

Output: Try-on image displayed on the user's device

Specific operation: The try-on image is encoded as images taken from multiple angles and sent from the server to the device. The device displays this on the user interface.

Step 7:

The device captures the user's facial expressions and voice and analyzes them using an emotion recognition engine.

Input: User's facial and voice data

Output: User emotion data

Specific operation: The device uses a camera and microphone to capture the user's facial expressions and voice in real time, and then analyzes this data with an emotion recognition engine to identify the user's emotional state.

Step 8:

The server analyzes the emotional data and adjusts the suggestions in real time.

Input: User emotion data

Output: Adjusted proposal content

Specific operation: Based on the emotional data, the server changes and adjusts the fitting images and outfit suggestions in real time to provide optimal suggestions.

Step 9:

The user selects the suggested outfit and completes the purchase process.

Input: User purchase decision information

Output: Purchase confirmation and shipping information

Specific operation: When the user clicks the "Purchase" button, the device sends this information to the server. The server then links the purchase information to the online store's payment system and completes the purchase process. The user is then notified of order confirmation and delivery information.

This allows users to virtually try on clothes that fit their body type, receive personalized suggestions based on their emotions, and enjoy an optimal shopping experience.

(Application Example 2)

Next, we will explain Application Example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 will be referred to as the "terminal."

Conventional virtual try-on systems were able to generate fitting images based on the user's body type information, but were unable to make suggestions that took the user's emotions into account. This made it difficult to improve the user's satisfaction with the clothing and outfits they selected. Furthermore, the lack of coordination adjustments based on real-time emotional feedback meant they were unable to fully meet the individual needs of users.

The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting the user's physique information, means for taking and uploading full-body photos of the user from multiple angles, means for collecting data on clothing for sale, means for combining clothing with the generated high-resolution 3D model of the user, means for analyzing the user's emotions and suggesting clothing and outfits based on the emotion data, and means for presenting images of the clothing to be tried on on the user's device. This makes it possible to suggest personalized clothing and outfits based on the user's emotions, improving user satisfaction. Furthermore, by adjusting the suggestions based on real-time emotion feedback, it is possible to more appropriately meet the individual needs of the user.

"User's body type information" refers to data related to the user's body measurements, such as height, weight, and three sizes.

A "full-body photo" is an image of the user taken from multiple angles (front, back, side, etc.).

"Data on clothing for sale" refers to detailed information such as clothing images, sizes, materials, and colors collected from affiliated online stores.

A "high-resolution 3D model" is a 3D model that is generated based on the user's body type information and a full-body photograph, and is rendered in great detail.

"Clothing synthesis" is a technology that uses data on clothing for sale to realistically display clothing on the generated high-resolution 3D model.

"Means for analyzing emotions and suggesting clothing and outfits based on emotional data" refers to technology that analyzes a user's facial expressions and voice, and then suggests the most suitable clothing and outfits for the user based on the emotional data obtained from this.

"Means for presenting try-on images" refers to technology that displays the generated virtual try-on images on the user's device.

"Emotional data" is data that represents emotional states such as joy, surprise, and dissatisfaction obtained from the analysis of the user's facial expressions and voice.

"Coordination" refers to the user's clothing combination and includes the selection process.

"Feedback" is the process of adjusting and re-proposing suggestions based on the user's emotional data.

This invention is a virtual fitting system that generates a 3D model based on the user's body type information and full-body photographs from multiple angles, then synthesizes clothing onto it, combined with an emotion engine that recognizes the user's emotions. This system can suggest clothing and outfits based on the user's emotions, providing a more personalized shopping experience.

The server realizes this system by integrating the following technologies: First, the server provides a means for users to input their body type information. This allows users to enter information such as their height, weight, and three sizes. It also provides a means for users to upload full-body photos taken from multiple angles. This allows users to upload photos of their front, side, and back.

The server has a means of collecting data on clothing for sale from online stores and other data sources. This data includes detailed information such as clothing images, sizes, materials, and colors. The server then uses the latest image recognition algorithms (e.g., TensorFlow) to analyze the user's body shape information and full-body photo data to generate a high-resolution 3D model. This 3D model is then used to synthesize clothing using deep learning technology to generate realistic try-on images.

Furthermore, it has a means of analyzing the user's facial expressions and voice using an emotion engine (e.g., Affectiva API) to obtain emotional data. It also incorporates a means of suggesting the most suitable clothing and outfits for the user based on the emotional data. This makes it possible to make appropriate suggestions in real time based on the user's emotions.

A means of displaying try-on images on the user's device has also been developed, allowing the user to view the generated virtual try-on image from multiple angles. After the try-on image is displayed, the user can provide feedback on their emotional data on the spot and adjust their outfit as needed.

For example, a user enters their height and weight into the app and uploads three full-body photos (front, back, and side). After the photo shoot is complete, emotion analysis is performed and if the user is happy, the system will suggest outfits in bright colors and the latest fashions. On the other hand, if the user is unhappy, the system will adjust to suggest new outfits.

An example of a prompt statement is as follows:

The user is 170cm tall and weighs 65kg. Front, back, and side photos have been uploaded. Sentiment analysis indicates that the user is currently feeling "joy." Based on this, suggest multiple outfits in bright colors and the latest fashions.

In this way, users can choose the clothing that best suits their body type and get the feeling of trying it on in real life through a virtual try-on experience. Real-time emotional feedback provides a more personalized shopping experience.

The flow of the specific processing in Application Example 2 will be explained using Figure 14.

Step 1:

Users launch the application, enter their body type information (height, weight, measurements, etc.), and upload full-body photos taken from multiple angles (front, back, side). The entered data consists of body type information and photo data, which are sent from the device to the server. As a result, data related to the user's body type and full-body photos is stored on the server.

Step 2:

The server collects data about clothing sold (images, sizes, materials, colors, etc.) from online stores and other data sources. This collection is done using APIs or web scraping technology. The acquired data is stored in a database on the server. The input is clothing data, and the output is clothing data stored in the database.

Step 3:

The server uses the latest image recognition algorithms (e.g., TensorFlow) to analyze the user's body shape information and full-body photo data and generate a high-resolution 3D model. During this process, each user's photo is pixel-analyzed to create the shape of the 3D model. The input for this step is the user's body shape information and photo data, and the output is a high-resolution 3D model.

Step 4:

The server uses a generative AI model to synthesize clothing for sale onto the generated 3D model. Utilizing deep learning technology, data processing is performed to realistically reproduce the fit and texture of the clothing. The input is a high-resolution 3D model and clothing data, and the output is a try-on image.

Step 5:

The device uses an emotion engine (e.g., Affectiva API) to analyze the user's facial expressions and voice in real time and obtain emotional data. Captured facial and voice data is input, and analyzed emotional data is output. In this step, the device obtains data using the camera and microphone.

Step 6:

The server suggests optimal clothing and outfits for the user based on emotional data. The input is emotional data, and the output is outfit suggestions tailored to the user's preferences. These suggestions are made dynamically and adjusted in real time.

Step 7:

The user's device displays the try-on images sent from the server. The input is the try-on image, and the output is the try-on image displayed on the user interface. The user can review the displayed try-on image and, if necessary, request images from different angles or to try on other clothing items.

Step 8:

If the user likes the suggested outfit, they proceed with the purchase. The user clicks the "Purchase" button, and the device sends the purchase information to the server. The input is the purchase information, and the output is purchase confirmation and delivery information. The server connects with the online store's payment system, records the order, and sends a confirmation to the user.

This allows users to virtually try on clothes that fit their body type, receive personalized outfit suggestions based on emotional data, and ultimately make a purchase.

The specific processing unit 290 transmits the results of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the results of the specific processing. The microphone 238 acquires audio indicating the user input regarding the results 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.

Data generation model 58 is what is known as generative AI (artificial intelligence). Examples of data generation model 58 include generative AI such as ChatGPT (Internet search <URL: https://openai.com/blog/chatgpt>) and Gemini (Internet search <URL: https://gemini.google.com/?hl=ja>). Data generation model 58 is obtained by performing deep learning on a neural network. A prompt containing an instruction is input to data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input. Data generation model 58 performs inference on the input inference data in accordance with the instructions indicated by the prompt, and outputs the inference results in the form of data such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and/or summarization.

In the above embodiment, an example was given in which the specific processing was performed by the data processing device 12, but the technology disclosed herein is not limited to this, and the specific processing may also be performed by the robot 414.

The emotion identification model 59, which serves as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see Figure 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

Figure 9 shows an emotion map 400 on which multiple emotions are mapped. In emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both emotions and mental states. Emotions that are generally generated from reactions that occur in the brain are arranged on the left side of the concentric circles. Emotions that are generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged above and below the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the top side of the concentric circles, and the emotion of "discomfort" is arranged on the bottom side. In this way, emotion map 400 maps multiple emotions based on the structure by which emotions are generated, with emotions that tend to occur simultaneously being mapped close together.

These emotions are distributed in the 3 o'clock direction on emotion map 400, and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness takes precedence over internal sensations, resulting in a sense of calm.

The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible (expressed in behavior) the emotion becomes.

Here, human emotions are based on various balances such as posture and blood sugar levels, and when these balances deviate from the ideal, it indicates discomfort, and when they approach the ideal, it indicates pleasure. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and remaining battery life, so that when these balances deviate from the ideal, it indicates discomfort, and when they approach the ideal, it indicates pleasure. Emotion maps may be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and emotional brain physiological signal analysis systems, Tokushima University, doctoral dissertation: https://ci.nii.ac.jp/naid/500000375379). The left half of the emotion map is lined with emotions belonging to an area called "reaction," where sensation is dominant. The right half of the emotion map is lined with emotions belonging to an area called "situation," where situational awareness is dominant.

The emotion map defines two emotions that encourage learning. One is the negative emotion around the middle of "repentance" or "reflection" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot experiences positive feelings such as "I want more" or "I want to know more."

The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are close to each other have similar values, as in the emotion map 900 shown in Figure 10. Figure 10 shows an example in which multiple emotions, such as "relieved," "calm," and "reassuring," have similar emotion values.

The system according to the present disclosure has been described above primarily in terms of the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may also be implemented as a general information processing system. The present disclosure may also be implemented, for example, as a software program that runs on a personal computer or an application that runs on a smartphone, etc. The method according to the present disclosure may also be provided to users in the form of SaaS (Software as a Service).

In the above embodiment, an example was given in which a specific process was performed by a single computer 22, but the technology of the present disclosure is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including the computer 22. For example, the data generation model 58 may be provided in a device external to the data processing device 12, and data may be generated in that external device in response to input data.

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

Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

It is not necessary to store the entire specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entire specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

The following types of processors can be used as hardware resources for executing specific processes. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource for executing specific processes by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which are processors with a circuit configuration designed specifically for executing specific processes. All processors have built-in or connected memory, and all use the memory to execute specific processes.

The hardware resource that executes the specific processing may be composed of one of these various processors, or may be composed of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). The hardware resource that executes the specific processing may also be a single processor.

As an example of a configuration using a single processor, first, there is a configuration in which one processor is configured using a combination of one or more CPUs and software, and this processor functions as a hardware resource that executes specific processing. Second, there is a configuration in which a processor is used to realize the functions of an entire system, including multiple hardware resources that execute specific processing, on a single IC chip, as typified by SoC (System-on-a-chip). In this way, specific processing is realized using one or more of the various processors listed above as hardware resources.

More specifically, the hardware structure of these various processors can be an electrical circuit that combines circuit elements such as semiconductor devices. Furthermore, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps can be added, or the processing order can be rearranged, all within the scope of the spirit of the invention.

The above-described written content and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above explanation of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or substitutions may be made to the above-described written content and illustrations, as long as they do not deviate from the spirit of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described written content and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

All publications, patent applications, and technical standards mentioned in this specification are incorporated by reference herein to the same extent as if each individual publication, patent application, and technical standard was specifically and individually indicated to be incorporated by reference.

The following is further disclosed regarding the above embodiments.

(Claim 1)

A means for inputting the user's body shape information,

A means for users to take and upload full-body photos from multiple angles,

Means of collecting data on the clothes being sold,

A means of synthesizing clothing onto the generated 3D model of the user,

A means of displaying try-on images on the user's device,

A system including

(Claim 2)

The system of claim 1 further comprises means for requesting a salesperson to suggest outfits based on the user's preferences.

(Claim 3)

The system of claim 1 further comprises means for generating a try-on image of the proposed outfit and presenting it on the user's terminal.

"Example 1"

(Claim 1)

A means for inputting the user's body shape information,

A means for users to take and upload full-body photos from multiple angles,

Means of collecting data on clothing sold online,

A means of synthesizing clothing onto the generated high-resolution 3D model of the user,

A means for sending the generated try-on images to the user's device;

A means of displaying try-on images on the user's device,

A system including

(Claim 2)

The system of claim 1 further comprises means for requesting a salesperson to suggest outfits based on the user's preferences.

(Claim 3)

The system described in claim 1 further comprises means for generating an image of the proposed outfit to be tried on and presenting it on the user's terminal.

"Application Example 1"

(Claim 1)

A means for inputting the user's body shape information,

A means for users to take and upload full-body photos from multiple angles,

Means of collecting data on items available for purchase,

A means for synthesizing items onto the generated user's 3D model;

A means of presenting virtual try-on images to the user's device,

Users can enter their body type information and upload a full-body photo using their own device.

Means of collecting and storing data on items sold online using APIs or web scraping technology from affiliated online stores;

A means for analyzing the user's body shape information and uploaded full-body photos to generate a high-resolution 3D model of the user;

A means for generating try-on images from multiple angles and sending them to the user's device;

A system including

(Claim 2)

A way to request a salesperson to suggest outfits based on the user's preferences,

The system of claim 1 further comprises means for sending a request for outfit suggestions to the server, generating an image of the suggested outfits to try on, and presenting it on the user's terminal.

(Claim 3)

The system described in claim 1, further comprising means for generating a try-on image of the proposed outfit and presenting it on the user's terminal.

"Example 2: Combining Emotion Engines"

(Claim 1)

A means for inputting the user's body shape information,

A means to take and upload full-body images of the user from multiple angles,

Means of collecting data on the clothes being sold,

A means for synthesizing clothing onto the generated 3D model of the user;

A means of displaying try-on images on the user's device,

A means of analyzing the user's facial expressions and voice to recognize emotions,

Methods for adjusting suggestions based on emotions,

A system including

(Claim 2)

The system of claim 1 further comprises means for requesting a salesperson to suggest outfits based on the user's preferences.

(Claim 3)

The system of claim 1 further comprises means for generating a try-on image of the proposed outfit and presenting it on the user's terminal.

"Application Example 2: Combining Emotion Engines"

(Claim 1)

A means for inputting the user's body shape information,

A means for users to take and upload full-body photos from multiple angles,

Means of collecting data on clothing sold,

A means of synthesizing clothing onto the generated high-resolution 3D model of the user,

A method for analyzing user emotions and suggesting clothing and outfits based on emotional data,

A means of displaying try-on images on the user's device,

A system including

(Claim 2)

The system of claim 1 further comprises means for requesting a salesperson to suggest outfits based on the user's preferences, and adjusts the suggestions in real time using emotional data.

(Claim 3)

The system of claim 1 further comprises means for generating try-on images of the proposed outfits, presenting them on the user's terminal, and providing feedback on the outfits based on emotional data.

10, 210, 310, 410 Data processing system 12 Data processing device 14 Smart device 214 Smart glasses 314 Headset type terminal 414 Robot

Claims (3)

A means for inputting user body type information;
A means for taking and uploading full-body photographs of the user from multiple angles;
a means of collecting data on the clothing being sold;
means for synthesizing clothing onto the generated 3D model of the user;
means for displaying try-on images on a user's device;
A system including: The system of claim 1 further comprises means for requesting a salesperson to suggest outfits based on the user's preferences. The system of claim 1 further comprises means for generating a try-on image of the proposed outfit and presenting it on the user's terminal.