system

Abstract

A system is provided.SOLUTION: A system, comprising: means for receiving a URL input by a user; means for obtaining commodity information based on the received URL; means for parsing the commodity information and generating a three dimensional model based on a parsing result; means for converting the generated three dimensional model into augmented reality data; means for sending the augmented reality data to a terminal of the user; and means for displaying the augmented reality data by the terminal of the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With the conventional method of providing product information on e-commerce sites, it is difficult for users to get a concrete understanding of how the product will look when placed in their actual home or installation location, which often makes users hesitate to purchase the product. In particular, for large items such as furniture and interior decor, there are limited ways to actually check the placement, dimensions, color, etc., which becomes an obstacle to making a purchasing decision. To solve this problem, a means is needed that allows users to specifically simulate the product. [Means for solving the problem]

[0005] To solve the above-mentioned problems, the present invention provides a system including: means for receiving a URL entered by a user and acquiring product information based on the URL; means for analyzing the acquired product information and generating a three-dimensional model based on the analysis results; means for converting the generated three-dimensional model into augmented reality data and transmitting it to a user's device; and means for displaying the augmented reality data on the user's device. This system allows users to physically view products at home or at the installation site, thereby encouraging them to purchase the products. Specifically, the system uses an algorithm to extract images and specification information from product information and analyze them to obtain shape, color, and texture information when generating the three-dimensional model. When converting the augmented reality data, the system sets a coordinate system for the model, adds appropriate augmented reality markers, and exports the data to a specific format, allowing simulations to be performed on the user's device.

[0006] The "URL receiving means" is a function that allows the system to receive the URL entered by the user.

[0007] The "product information acquisition means" is a function that collects product images and specification information from e-commerce sites and the like based on the received URL.

[0008] The "product information analysis means" is a function that analyzes the acquired product information and extracts the shape, color, texture information, etc., necessary for generating a three-dimensional model.

[0009] The "three-dimensional model generating means" is a function that constructs a three-dimensional model of the product based on the analyzed product information.

[0010] The "augmented reality data conversion means" is a function that converts the generated three-dimensional model into augmented reality data, and performs appropriate coordinate system settings and adds AR markers.

[0011] The "data transmission means" is a function for transmitting augmented reality data to the user's terminal.

[0012] The "data display means" is a function that uses the augmented reality data received at the user's terminal to display a three-dimensional model in real space. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0014] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0017] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0018] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0019] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0026] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0033] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0034] This invention relates to a system that uses generative AI to automatically generate 3D models based on product information found by users on an e-commerce site, enabling real-time augmented reality (AR) display. The program processing of this system is explained below.

[0035] System configuration

[0036] The system mainly consists of the following elements:

[0037] URL receiving method

[0038] Product information acquisition means

[0039] Product information analysis means

[0040] 3D model generation means

[0041] Augmented reality data conversion means

[0042] Data transmission method

[0043] Data display means

[0044] Program processing

[0045] User operations

[0046] 1. Enter the URL

[0047] The user launches the dedicated application and enters the URL of the product they want to convert into AR. By doing this, the user prepares to view the product in detail at home.

[0048] Device behavior

[0049] 2. Sending the URL

[0050] The device sends the URL entered by the user to the server, usually via an HTTP request.

[0051] Server Operation

[0052] 3. Collecting product information

[0053] The server accesses the e-commerce site based on the URL and collects image data and specifications of the relevant product. This collection can be done using scraping technology or API.

[0054] 4. Product information analysis

[0055] The server analyzes the collected product information, analyzing shape, color, and texture information from image data, and extracting dimensions and material information from spec information.

[0056] 5. 3D Model Generation

[0057] Based on the analyzed data, generative AI generates a 3D model of the product, which applies color and texture to the geometric data to create a realistic model.

[0058] 6. Augmented Reality Data Conversion

[0059] The server converts the generated 3D model into augmented reality data, a process that includes setting the coordinates of the model, adding AR markers, and exporting it to a specific format (e.g., USDZ or GLTF).

[0060] 7. Data transmission

[0061] The server sends the converted augmented reality data to the device using HTTP responses or WebSockets.

[0062] Device behavior

[0063] 8. Displaying Data

[0064] The device reads the received augmented reality data using a dedicated application and displays a 3D model in real space through the device's camera, allowing the user to see the product as if it were actually placed in that location.

[0065] Specific examples

[0066] Furniture purchase example

[0067] 1. User Operation

[0068] The user enters the URL of a sofa that catches their eye on an e-commerce site into a dedicated app.

[0069] 2. Send URL

[0070] The device sends this URL to the server.

[0071] 3. Information gathering

[0072] The server accesses the e-commerce site based on this URL and collects images and dimensions of the sofa.

[0073] 4. Data Analysis

[0074] The server analyzes the sofa's shape, color, and texture information from the image and extracts its dimensions and material information.

[0075] 5. Model Generation

[0076] The 3D model generation AI uses this data to generate a realistic 3D model of the sofa.

[0077] 6. Data Conversion

[0078] The server converts the generated model into augmented reality data (e.g., USDZ format).

[0079] 7. Data Transmission

[0080] The server transmits this augmented reality data to the terminal.

[0081] 8. Data Display

[0082] The device loads the augmented reality data into the app and displays, via the camera, what the sofa would look like in the user's living room.

[0083] In this way, users can see exactly how the sofa will look and feel in their home, which will make purchasing decisions easier and is expected to lead to increased sales on e-commerce sites.

[0084] The processing flow will be explained below.

[0085] Step 1:

[0086] The user launches the dedicated app and enters the URL of the product they want to convert into AR, which inserts the URL into the input field within the app.

[0087] Step 2:

[0088] The device sends the entered URL to the server using an HTTP request.

[0089] Step 3:

[0090] The server accesses the e-commerce site based on the received URL and obtains product image data and specifications using scraping technology or API calls.

[0091] Step 4:

[0092] The server analyzes the acquired product information, extracting shape, color, and texture information from the image data, and analyzing and extracting dimensions and material information from the specification information.

[0093] Step 5:

[0094] The server-based generative AI generates a 3D model of the product based on the analyzed data. First, it creates a 3D mesh based on the shape information, and then applies color and texture information to the model.

[0095] Step 6:

[0096] The server converts the generated 3D model into augmented reality data by setting the model's coordinate system, adding appropriate AR markers, and exporting it to a specific format (e.g., USDZ or GLTF).

[0097] Step 7:

[0098] The server sends the generated augmented reality data to the device using HTTP responses or WebSockets.

[0099] Step 8:

[0100] The device then loads the received augmented reality data into a dedicated app, which uses the data to display a 3D model in real space through the device's camera.

[0101] Step 9:

[0102] The user operates the device to check how the 3D model will look in the location where they want to place the product, and then rotates, moves, scales, and performs other operations on the model to simulate the optimal placement.

[0103] Example 1

[0104] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0105] In recent years, many users have begun to purchase products via the Internet, and purchasing activities on e-commerce sites have become increasingly popular. However, it is difficult for users to fully grasp the actual size and appearance of a product from online product images and descriptions alone, which often makes it difficult to make a purchasing decision. In particular, for products such as furniture and decorative items, where it is not clear whether they will fit in a particular space until they are actually placed, it is often discovered after purchase that the product does not meet expectations, resulting in frequent returns and exchanges, which is inefficient for companies. To solve these problems, there is a need for a system that allows users to check the actual placement and appearance of products at home in real time.

[0106] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0107] In this invention, the server includes means for receiving a URL entered by a user, means for acquiring product information based on the received URL, means for analyzing the product information and generating a three-dimensional model based on the analysis result, means for converting the generated three-dimensional model into augmented reality data, means for transmitting the augmented reality data to a user's terminal, and means for displaying the augmented reality data on the user's terminal. This allows users to place products they find on an e-commerce site in their home or other physical space in real time via a dedicated application, allowing them to intuitively check the size and appearance of the products and making it easier for them to make a purchasing decision.

[0108] The "URL receiving means" is a means for receiving a URL entered by a user.

[0109] The "product information acquisition means" is a means for accessing the EC site based on the received URL and acquiring information about the product.

[0110] The "product information analysis means" is a means for analyzing the acquired product information and extracting shape, color, and texture information.

[0111] The "three-dimensional model generating means" is a means for generating a three-dimensional model of a product based on the analysis results.

[0112] The "augmented reality data conversion means" is a means for converting the generated three-dimensional model into augmented reality data.

[0113] The "data transmission means" is a means for transmitting the converted augmented reality data to the user's terminal.

[0114] "Data display means" refers to means for displaying augmented reality data received by a user's terminal.

[0115] An "image analysis algorithm" is an algorithm for analyzing image data from product information and extracting shape, color, and texture information.

[0116] A "prompt statement" is an instruction statement to be input into a generative AI model, and includes information for generating a three-dimensional model based on the analysis results.

[0117] Overall system configuration

[0118] The system of this invention uses generative AI to automatically generate 3D models based on product information found by users on an e-commerce site, enabling real-time augmented reality (AR) display. It mainly consists of the following elements:

[0119] URL receiving method

[0120] Product information acquisition means

[0121] Product information analysis means

[0122] 3D model generation means

[0123] Augmented reality data conversion means

[0124] Data transmission method

[0125] Data display means

[0126] Details of each element

[0127] URL receiving method

[0128] This is a means of receiving a URL entered by the user into a dedicated application. For example, the user enters the URL of a sofa they found on an e-commerce site. This identifies the specific product to be displayed in AR.

[0129] Product information acquisition means

[0130] The device sends the received URL to the server. The server accesses the e-commerce site based on that URL and retrieves product information. Specifically, it uses a scraping tool (e.g., BeautifulSoup, Selenium) or API to collect image data from the product page, as well as specifications such as dimensions and materials.

[0131] Product information analysis means

[0132] The server analyzes the acquired product information. In this process, image analysis libraries (e.g., OpenCV, TensorFlow) are used to extract shape, color, and texture information from the image data. Specifications (dimensions and materials) are also analyzed at the same time, and the data necessary to generate a 3D model is prepared.

[0133] 3D model generation means

[0134] Based on the analyzed data, a generative AI model generates a 3D model of the product. Examples of generative AI models used include DALL-E and GAN (Generative Adversarial Network). The generated 3D model applies color and texture to the shape data, allowing it to be displayed as a realistic model.

[0135] Specific examples of prompts are as follows:

[0136] "Create a realistic 3D model using the images and specifications of the following products.

[0137] Image URL: [Image URL]

[0138] Specification information:

[0139] Dimensions: Width [xx] cm, Height [xx] cm, Depth [xx] cm

[0140] Material: [Material information]

[0141] Color: [Color information]

[0142] Please use USDZ format for the output format.

[0143] Augmented reality data conversion means

[0144] The generated 3D model is converted into augmented reality data. This conversion process involves setting the coordinates of the model, adding AR markers, and exporting it to a specific format (e.g., USDZ, GLTF). This can be done using a 3D modeling tool (e.g., Blender, Unity) or a conversion library.

[0145] Data transmission method

[0146] The converted augmented reality data is sent to the device using HTTP responses or WebSockets. The server properly packets the data and sends it to the device.

[0147] Data display means

[0148] The device reads the received augmented reality data using a dedicated application, which allows the device to display a three-dimensional model in real space through the camera. AR display uses ARKit (iOS) or ARCore (Android).

[0149] Example of operation

[0150] Furniture purchase example

[0151] A user enters the URL of a sofa they find interesting on an e-commerce site into a dedicated app. The device then sends the URL as an HTTP request to the server. The server then accesses the e-commerce site using this URL and collects the sofa's image data and dimensions. The collected data is analyzed using an image analysis library to extract shape, color, and texture information. Based on the analysis results, a generative AI model generates a 3D model, which the server then converts into augmented reality data in USDZ format. The server then sends the converted data to the device, which then displays the AR image, allowing the user to see in real time how the sofa will look in their living room.

[0152] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0153] Step 1:

[0154] The user launches the dedicated application and enters the URL of the product they want to create in AR. This operation allows the user to provide specific information about the product. The entered URL becomes the input for the next processing step.

[0155] Step 2:

[0156] The terminal sends the URL entered by the user to the server. The transmission is done via an HTTP request. This request contains the URL entered by the user. The output of the terminal is the URL transmission data to the server.

[0157] Step 3:

[0158] The server accesses the e-commerce site based on the received URL. The server uses a scraping tool (e.g., BeautifulSoup or Selenium) or an API to collect product information. Specifically, it obtains image data and specification information (dimensions, material, color, etc.). The input for this step is the sent URL, and the output is the collected product information.

[0159] Step 4:

[0160] The server analyzes the collected product information. It extracts shape, color, and texture information from image data, and analyzes dimensions and materials from spec information. This process uses an image analysis library (e.g., OpenCV or TensorFlow). The input is the collected product information, and the output is the analyzed product information.

[0161] Step 5:

[0162] The server then inputs prompts into the generative AI model based on the analyzed data to generate a 3D model of the product. The generative AI models used include DALL-E and GAN. Specific examples of prompts are as follows:

[0163] "Create a realistic 3D model using the images and specifications of the following products.

[0164] Image URL: [Image URL]

[0165] Specification information:

[0166] Dimensions: Width [xx] cm, Height [xx] cm, Depth [xx] cm

[0167] Material: [Material information]

[0168] Color: [Color information]

[0169] Please use USDZ format for the output format.

[0170] The input is analyzed product information, and the output is generated 3D model data.

[0171] Step 6:

[0172] The server converts the generated 3D model into augmented reality data (e.g., USDZ format). This conversion involves setting the coordinates of the model, adding AR markers, and exporting it to a specific format. The input is the 3D model data generated by the generative AI model, and the output is the converted augmented reality data.

[0173] Step 7:

[0174] The server then sends the converted augmented reality data to the device, using HTTP responses or WebSockets. The server's output is packets of augmented reality data sent to the user's device.

[0175] Step 8:

[0176] The device reads the received augmented reality data using a dedicated application. A three-dimensional model is displayed in real space through the device's camera. This allows the user to see the product as if it were actually placed in that location. The input is the augmented reality data sent from the server, and the output is the displayed three-dimensional model.

[0177] Specific examples

[0178] For example, a user enters the URL of a sofa they found on an e-commerce site, and their device sends the URL to a server. The server collects product information based on the URL and analyzes image data and dimensions. A generative AI model generates a 3D model and converts it into USDZ format. The data is then sent to the device and loaded into a dedicated application, allowing the user to see how the sofa would look in their living room.

[0179] (Application example 1)

[0180] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0181] With conventional food delivery services, it was difficult for users to check in advance what the food they were ordering would actually look like. This created a gap between the actual food and the photos on the delivery site, which led to a decrease in user satisfaction. Furthermore, there were cases where users hesitated to order because they lacked the visual information necessary to decide whether to order or not.

[0182] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0183] In this invention, the server includes means for receiving a URL entered by a user, means for acquiring product information based on the received URL, means for analyzing the product information and generating a three-dimensional model based on the analysis results, means for converting the generated three-dimensional model into augmented reality data, means for transmitting the augmented reality data to a user's terminal, means for displaying the augmented reality data on the user's terminal, and means for generating a three-dimensional model based on food information collected from a food delivery site and displaying it in augmented reality, thereby enabling users to check the actual appearance of food in augmented reality before delivery.

[0184] "URL receiving means" refers to a device or method that has the function of receiving a URL entered by a user.

[0185] The "product information acquisition means" refers to a device or method that has the function of collecting data about products based on the received URL.

[0186] "Product information analysis means" refers to a device or method that has the function of analyzing acquired product information and extracting necessary data.

[0187] The "three-dimensional model generating means" refers to a device or method that has the function of generating a three-dimensional model of a product based on the analysis results.

[0188] The "augmented reality data conversion means" refers to a device or method that has the function of converting the generated three-dimensional model into a data format that can be used as augmented reality content.

[0189] "Data transmission means" refers to a device or method that has the function of transmitting the converted augmented reality data to the user's terminal.

[0190] "Data display means" refers to a device or method that has the function of displaying augmented reality data on a user's terminal.

[0191] A "food delivery site" is a website or application that allows users to order food online.

[0192] "Food information" refers to data such as images and descriptions of dishes posted on food delivery sites.

[0193] "Augmented reality display means" refers to a device or method that has the function of displaying three-dimensionally modeled food information superimposed on the real world.

[0194] This invention relates to a system that uses augmented reality (AR) to display the actual food a user is considering ordering when using a food delivery service. Specifically, when a user inputs the URL of a food item, the system acquires and analyzes food information based on the URL, generates a three-dimensional model of the food, and converts it into AR data for display.

[0195] System configuration

[0196] The system mainly consists of the following elements:

[0197] URL receiving method

[0198] Product information acquisition means

[0199] Product information analysis means

[0200] 3D model generation means

[0201] Augmented reality data conversion means

[0202] Data transmission method

[0203] Data display means

[0204] Food delivery site

[0205] Food Information

[0206] Augmented reality display means

[0207] Program processing explanation

[0208] User operations

[0209] 1. Enter the URL

[0210] The user launches the dedicated application and enters the URL of the dish they are considering ordering. By doing this, the user arranges to check the appearance of the dish in detail.

[0211] Device behavior

[0212] 2. Sending the URL

[0213] The device sends the URL entered by the user to the server, usually via an HTTP request.

[0214] Server Operation

[0215] 3. Collecting product information

[0216] The server accesses the food delivery site based on the URL and collects image data and specifications of the corresponding dishes using scraping technology or API.

[0217] 4. Product information analysis

[0218] The server analyzes the collected food information, analyzing shape, color, and texture information from image data, and extracting dimensions and ingredient information from spec information.

[0219] 5. 3D Model Generation

[0220] Based on the analyzed data, the generative AI generates a 3D model of the dish, which applies color and texture to the geometric data to create a realistic model.

[0221] 6. Augmented Reality Data Conversion

[0222] The server converts the generated 3D model into augmented reality data, a process that includes setting the coordinates of the model, adding AR markers, and exporting it to a specific format (e.g., USDZ or GLTF).

[0223] 7. Data transmission

[0224] The server sends the converted augmented reality data to the device using HTTP responses or WebSockets.

[0225] Device behavior

[0226] 8. Displaying Data

[0227] The device reads the received augmented reality data using a dedicated application and displays a 3D model in real space through the device's camera, allowing the user to see the food as if it were actually placed in that location.

[0228] Examples of concrete examples and prompts

[0229] Sushi plate ordering example

[0230] 1. User Operation

[0231] Users enter the URL of a sushi plate they are interested in on a food delivery site into a dedicated app.

[0232] 2. Send URL

[0233] The device sends this URL to the server.

[0234] 3. Information gathering

[0235] The server accesses the food delivery site based on this URL and collects images and specifications of the sushi plates.

[0236] 4. Data Analysis

[0237] The server analyzes the shape, color, and texture information of the sushi plate from the image and extracts information about its dimensions and ingredients.

[0238] 5. Model Generation

[0239] The 3D model generation AI uses this data to generate a realistic 3D model of the sushi plate.

[0240] 6. Data Conversion

[0241] The server converts the generated model into augmented reality data (e.g., USDZ format).

[0242] 7. Data Transmission

[0243] The server transmits this augmented reality data to the terminal.

[0244] 8. Data Display

[0245] The device loads the augmented reality data into the app, which uses the camera to show what the sushi plate will look like at the user's table.

[0246] Example prompt sentence:

[0247] text

[0248] Generate a 3D model of a sushi plate. Get the image data and dimensions from the following URL: http: / / example.com / sushi-plate

[0249] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0250] Step 1:

[0251] The user launches the dedicated application and enters the URL of the dish they are considering ordering. The entered URL is saved in an input field in the application. This URL becomes the key to obtain detailed information about the dish.

[0252] Step 2:

[0253] The terminal sends the URL entered by the user to the server. This process is done through an HTTP request. The input is the URL entered by the user, and the output is the request sent to the server.

[0254] Step 3:

[0255] The server receives the URL and accesses the food delivery site based on that URL. The server uses this URL to collect image data and specifications for the corresponding dish using scraping technology or an API. The input is the received URL, and the output is image data and specifications for the dish.

[0256] Step 4:

[0257] The server analyzes the collected food information. In this analysis, the shape, color, and texture information of the food is extracted from the image data, and data such as dimensions and ingredients is extracted from the specification information. The input is the image data and specification information, and the output is the analysis results: shape data, color data, texture data, and dimension data.

[0258] Step 5:

[0259] The server generates a 3D model of the dish based on the analysis results. This process involves using a generative AI model to create a realistic 3D model. The input is shape data, color data, texture data, and dimension data, and the output is a 3D model.

[0260] Step 6:

[0261] The server converts the generated 3D model into augmented reality data. This conversion process includes setting the coordinates of the model, adding AR markers, and exporting it to a specific format (e.g., USDZ or GLTF). The input is the 3D model, and the output is the augmented reality data.

[0262] Step 7:

[0263] The server sends the augmented reality data to the device. This transmission process uses HTTP responses and WebSockets. The input is the augmented reality data, and the output is the data transmission to the device.

[0264] Step 8:

[0265] The device reads the received augmented reality data with a dedicated application and uses that data to display a 3D model in real space through the camera. The input is the augmented reality data, and the output is an augmented reality view of the food displayed on the user's display. The user can see the food as if it were actually placed in that location, which helps them make ordering decisions.

[0266] 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.

[0267] This invention relates to a system that uses generative AI to automatically generate 3D models based on product information found by a user on an e-commerce site, and combines this with an emotion engine to provide optimal augmented reality (AR) display and product recommendations based on the user's emotions. The program processing of this system is explained below.

[0268] System configuration

[0269] The system mainly consists of the following elements:

[0270] URL receiving method

[0271] Product information acquisition means

[0272] Product information analysis means

[0273] 3D model generation means

[0274] Augmented reality data conversion means

[0275] Data transmission method

[0276] Data display means

[0277] Emotion Engine

[0278] Program processing

[0279] User operations

[0280] 1. Enter the URL

[0281] The user launches the dedicated application and enters the URL of the product they want to convert into AR, which is then inserted into an input field within the application.

[0282] Device behavior

[0283] 2. Sending the URL

[0284] The device sends the entered URL to the server using an HTTP request.

[0285] Server Operation

[0286] 3. Collecting product information

[0287] The server accesses the e-commerce site based on the URL and retrieves product image data and specifications. This information is collected using scraping technology or API calls.

[0288] 4. Product information analysis

[0289] The server analyzes the acquired product information, extracting shape, color, and texture information from the image data, and analyzing and extracting dimensions and material information from the specification information.

[0290] 5. 3D Model Generation

[0291] The server-based generative AI generates a 3D model of the product based on the analyzed data, applying color and texture to the shape data to create a realistic model.

[0292] 6. Augmented Reality Data Conversion

[0293] The server converts the generated 3D model into augmented reality data, a process that includes setting the coordinate system of the model, adding AR markers, and exporting it to a specific format (e.g., USDZ or GLTF).

[0294] 7. Data transmission

[0295] The server sends the converted augmented reality data to the device using HTTP responses or WebSockets.

[0296] Device behavior

[0297] 8. Displaying Data

[0298] The device reads the received augmented reality data using a dedicated application and displays a three-dimensional model in real space through the device's camera, making the product appear as if it were actually placed in that location.

[0299] Emotion Engine Operation

[0300] 9. Emotional Recognition

[0301] The device captures the user's facial expressions, voice, gestures, etc. through cameras, microphones, and other sensors, and recognizes the user's emotions in real time from this data.

[0302] 10. Emotion-Based Display Adjustment

[0303] The emotion engine adjusts the display of the 3D model based on the user's emotions. For example, if the user is satisfied, the display will continue as is, but if the user is anxious, a different perspective or information will be added.

[0304] 11. Emotion-Based Product Recommendations

[0305] The emotion engine recommends related products based on the user's emotional data. For example, if a user is interested in and enjoys a particular product, it will recommend other products in the same category.

[0306] Specific examples

[0307] Furniture purchase example

[0308] 1. User Operation

[0309] The user enters the URL of a sofa that interests them on an e-commerce site into a dedicated app.

[0310] 2. Send URL

[0311] The terminal sends this URL to the server in an HTTP request.

[0312] 3. Information gathering

[0313] The server accesses the e-commerce site based on this URL and collects images and dimensions of the sofa.

[0314] 4. Data Analysis

[0315] The server analyzes the sofa's shape, color, and texture information from the image and extracts its dimensions and material information.

[0316] 5. Model Generation

[0317] The 3D model generation AI uses this data to generate a realistic 3D model of the sofa.

[0318] 6. Data Conversion

[0319] The server converts the generated model into augmented reality data (e.g., USDZ format).

[0320] 7. Data Transmission

[0321] The server transmits this augmented reality data to the terminal.

[0322] 8. Data Display

[0323] The device loads the augmented reality data into the app and displays, via the camera, what the sofa would look like in the user's living room.

[0324] 9. Emotional Recognition

[0325] The device acquires emotional data from the user's facial expressions and voice, and the emotion engine analyzes this to recognize the user's emotions.

[0326] 10. Display adjustment

[0327] The emotion engine adjusts the display of the 3D model based on the user's emotions: if the user is feeling anxious, it will show more details or a different perspective.

[0328] 11. Product Recommendations

[0329] The emotion engine will recommend other products in similar categories based on the user's emotional data, for example, if they are having fun, it will show other related sofas and furniture.

[0330] In this way, users can view realistic models of products at home and receive optimal information and recommendations based on their own emotions, which will facilitate purchasing decisions and contribute to increased sales on e-commerce sites.

[0331] The processing flow will be explained below.

[0332] Step 1:

[0333] The user launches the app and enters the URL of the product they are considering purchasing, which is then inserted into an input field within the app.

[0334] Step 2:

[0335] The terminal sends the input URL to the server using an HTTP request, and the server receives the URL.

[0336] Step 3:

[0337] The server accesses the corresponding e-commerce site based on the received URL and collects product information. Specifically, it obtains product image data and specifications (e.g., dimensions, material, price, etc.). This is done using scraping technology or API calls.

[0338] Step 4:

[0339] The server analyzes the acquired product information. Specifically, it analyzes shape, color, and texture information from the image data, and extracts dimensions and material information from the specification information. This analysis provides the basic data for generating a 3D model.

[0340] Step 5:

[0341] The server-based generative AI generates a 3D model of the product based on the analyzed data, first creating a 3D mesh based on the shape information, and then applying color and texture information to the model.

[0342] Step 6:

[0343] The server converts the generated 3D model into augmented reality data by setting the model's coordinate system, adding appropriate AR markers, and exporting it to a specific format (e.g., USDZ or GLTF).

[0344] Step 7:

[0345] The server sends the generated augmented reality data to the device using an HTTP response or WebSocket, and the device receives the augmented reality data.

[0346] Step 8:

[0347] The device then loads the received augmented reality data into a dedicated app, and the user can use the device's camera to display a 3D model in real space and check how the product will look when installed.

[0348] Step 9:

[0349] The device captures the user's facial expressions, voice, gestures, etc. through cameras, microphones, and other sensors, and sends this data to an emotion engine to recognize the user's emotions in real time.

[0350] Step 10:

[0351] The emotion engine analyzes the acquired data and recognizes the user's emotional state, for example, determining whether the user is surprised or feeling happy.

[0352] Step 11:

[0353] The emotion engine adjusts the display of the 3D model based on the user's perceived emotions, for example, providing more information or different perspectives to reassure the user if they are feeling anxious.

[0354] Step 12:

[0355] The emotion engine recommends related products based on emotion data. For example, if a user shows a strong interest in a particular product, it will also display and recommend other products in the same category or similar.

[0356] Step 13:

[0357] The user operates the device to check the provided information and recommended products and consider purchasing them. The user can rotate, scale, move, and perform other operations to simulate the optimal arrangement.

[0358] Example 2

[0359] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0360] On conventional e-commerce sites, users cannot see the actual product before purchasing it, which often leads to problems after purchase, such as the product's size or appearance being different from what they expected. Furthermore, conventional systems do not provide services that take user emotions into consideration, which can lead to a poor user experience. This leads to low user satisfaction and makes it difficult to increase sales on e-commerce sites.

[0361] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0362] In this invention, the server includes means for receiving a URL entered by a user, means for acquiring product information, means for analyzing the acquired information to generate a three-dimensional model, means for converting the generated three-dimensional model into augmented reality data, means for transmitting the augmented reality data to a terminal, means for recognizing emotions, means for adjusting the display based on the recognized emotions, and means for recommending related products. This allows the user to see an AR display of the product that is close to the real thing, and further allows the user to receive optimal information and product recommendations based on their emotions.

[0363] "URL" stands for Uniform Resource Locator and is a symbol that indicates the location of a resource on the Web.

[0364] "Product information" refers to information about the characteristics and features of a product, such as product images, specifications, dimensions, materials, and colors.

[0365] A "three-dimensional model" is a three-dimensional digital representation generated based on product information, which realistically reproduces the appearance and shape of the product.

[0366] "Augmented reality data" is data used to overlay a three-dimensional model onto real space, and is usually converted into a specific format (e.g., USDZ format or GLTF format).

[0367] A "server" is a computer system that receives requests from users, processes the necessary data, and sends it to terminals.

[0368] A "terminal" is a device used by a user, including a smartphone, tablet, etc.

[0369] An "emotion engine" is a system that recognizes emotions from a user's facial expressions, voice, gestures, etc., and provides information based on those emotions.

[0370] "Perception" is the use of sensors and algorithms to determine specific information or conditions.

[0371] "Adjusting the display content" means changing the information and layout to be displayed according to the user's emotions and situation.

[0372] "Product recommendation" refers to proposing products that are likely to interest a user based on their past behavior and current emotions.

[0373] This invention relates to a system that uses a generative AI model to automatically generate a three-dimensional model based on product information found by a user on an e-commerce site, and combines it with an emotion engine to provide optimal augmented reality (AR) display and product recommendations based on the user's emotions.

[0374] System configuration

[0375] The system mainly consists of the following elements:

[0376] server

[0377] Device (smartphone, tablet, etc.)

[0378] Emotion Engine

[0379] URL receiving method

[0380] Product information acquisition means

[0381] Product information analysis means

[0382] 3D model generation means

[0383] Augmented reality data conversion means

[0384] Data transmission method

[0385] Data display means

[0386] Hardware and software used

[0387] Hardware:

[0388] A server is a computer with high-performance data processing capabilities.

[0389] The devices are smartphones or tablets equipped with cameras, microphones, and sensors.

[0390] software:

[0391] Python library BeautifulSoup (for scraping product information)

[0392] OpenCV (for analyzing image data)

[0393] Blender Python API (to generate 3D models using generative AI models)

[0394] Three.js (for converting augmented reality data to USDZ or GLTF format)

[0395] Microsoft Azure Emotion API (for emotion recognition)

[0396] ARKit (for displaying AR on devices)

[0397] Specific processing of the program

[0398] The user launches a dedicated application and enters the URL of the product they want to use in AR. The device receives the URL and sends it to the server using an HTTP request. The server then accesses the e-commerce site based on the received URL and obtains the product's image data and specifications using scraping or an API call.

[0399] The acquired product information is analyzed by the server. Format data (shape, color, texture information) is extracted from the image data, and dimensions and material information are analyzed from the spec information. The OpenCV library is used for the analysis.

[0400] Next, a generative AI model (e.g., Blender Python API) generates a 3D model based on the parsed data, which is then converted into a data format for AR display (e.g., USDZ or GLTF) using the Three.js library.

[0401] The converted augmented reality data is sent to the device by the server using HTTP responses or WebSockets. The device reads the received data with a dedicated application and displays the model in real space through the camera. For example, you can use your smartphone camera to see how a sofa would look in your living room.

[0402] The device also uses cameras, microphones, and other sensors to capture the user's facial expressions, voice, and gestures, and the emotion engine uses this data to recognize the user's emotions in real time. The emotion engine analyzes emotions using Microsoft Azure's Emotion API.

[0403] The emotion engine adjusts the display of the 3D model based on the recognized emotion: for example, if the user is anxious, it will show additional details or different perspectives, but if the user is satisfied, it will continue to display the model as is.

[0404] The emotion engine also recommends related products based on the recognized emotion, for example, if the user is enjoying something, it will show other products in the same category.

[0405] Examples of concrete examples and prompts

[0406] Example: Purchasing furniture

[0407] A user enters the URL of a sofa that catches their eye on an e-commerce site into a dedicated app. The device then sends this URL to the server via an HTTP request. The server then accesses the e-commerce site based on this URL and uses BeautifulSoup to collect images and dimensions of the sofa.

[0408] The server then uses OpenCV to analyze the images and extract shape, color, and texture information. A generative AI model (Blender Python API) uses this data to generate a realistic 3D model. The generated model is then converted to USDZ format using Three.js. The server then sends the converted data to the device, which then uses ARKit to overlay the 3D model of the sofa on the camera image.

[0409] Example prompt sentence:

[0410] "Generate a detailed 3D model of a sofa based on the following data:

[0411] Image data: [image_url]

[0412] Product dimensions: Height 80cm, width 200cm, depth 100cm

[0413] Material: Cloth

[0414] Color: Gray

[0415] "

[0416] In this way, users can view models of products that are close to the real thing, while receiving optimal information and product recommendations that correspond to their own emotions.

[0417] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0418] Step 1:

[0419] User operation (URL input)

[0420] The user launches the dedicated application and enters the URL of the product they want to convert into AR. Specifically, they paste the URL of the product page of a sofa they found on a furniture mail-order website into the input field.

[0421] Input: Product URL

[0422] Output: The entered product URL is saved on the device.

[0423] Step 2:

[0424] Device operation (URL sending)

[0425] The device sends the entered URL to the server as an HTTP request. At this time, the device sends a POST request including the URL to the server and delivers the data.

[0426] Input: Product URL entered by the user

[0427] Output: The product URL is sent to the server.

[0428] Step 3:

[0429] Server operation (collection of product information)

[0430] The server accesses the e-commerce site based on the received URL and retrieves the product's image data and specifications. This process can be done by scraping using Python's BeautifulSoup library or by using the API provided by the e-commerce site. Specifically, BeautifulSoup is used to extract the product image URL and dimensional information from the HTML document.

[0431] Input: Product URL

[0432] Output: Product image URL, dimensions, and other specifications

[0433] Step 4:

[0434] Server operation (analysis of product information)

[0435] The server analyzes the shape, color, and texture information from the image data based on the acquired product information, and extracts dimensions and material information from the spec information. This analysis uses the OpenCV library. For example, it performs edge detection on the image to identify the shape.

[0436] Input: URL of product image, dimensions, and other specifications

[0437] Output: Shape data, color data, texture data, dimension information, material information

[0438] Step 5:

[0439] Server operation (generation of 3D models)

[0440] The generative AI model installed on the server generates a 3D model of the product based on the analyzed data. Specifically, Blender's Python API is used to apply color and texture to the shape data to generate a realistic 3D model. The prompt text input to the generative AI is, "Please generate a detailed 3D model of a sofa based on the following data: image data, product size (height 80cm, width 200cm, depth 100cm), material (fabric), and color (gray)."

[0441] Input: Shape data, color data, texture data, dimension information, material information

[0442] Output: 3D model

[0443] Step 6:

[0444] Server operation (augmented reality data conversion)

[0445] The server converts the generated 3D model into augmented reality (AR) data. This process involves setting the coordinate system of the 3D model, adding AR markers, and exporting it to a specific format (USDZ or GLTF). Specifically, the Three.js library is used to export the 3D model into an AR-compatible data format.

[0446] Input: 3D model

[0447] Output: Augmented reality data (USDZ format or GLTF format)

[0448] Step 7:

[0449] Server operation (data transmission)

[0450] The server sends the converted augmented reality data to the device using an HTTP response or WebSocket. Specifically, when the device sends an HTTP request, the server returns the converted augmented reality data as an HTTP response.

[0451] Input: Augmented reality data

[0452] Output: Augmented reality data is sent to the device.

[0453] Step 8:

[0454] Terminal operation (displaying data)

[0455] The device reads the received augmented reality data using a dedicated application and displays a 3D model in real space. Specifically, it displays what the sofa would look like in the user's living room through the device's camera. For example, it uses ARKit to overlay a 3D model of the sofa on the camera image.

[0456] Input: Augmented reality data

[0457] Output: 3D model displayed in real space

[0458] Step 9:

[0459] Emotion engine operation (emotion recognition)

[0460] The device captures the user's facial expressions, voice, gestures, etc. through the camera, microphone, and other sensors, and the emotion engine recognizes the user's emotions in real time from this data. This emotion recognition is done using Microsoft Azure's Emotion API.

[0461] Input: User's facial expression data, voice data, gesture data

[0462] Output: User emotion data

[0463] Step 10:

[0464] Emotion engine operation (adjusting display content)

[0465] The emotion engine adjusts the display of the 3D model based on the user's perceived emotions, for example by adding more detailed information or showing different perspectives if the user is feeling anxious.

[0466] Input: User emotion data

[0467] Output: Adjusted display content

[0468] Step 11:

[0469] Emotion engine operation (product recommendation)

[0470] The emotion engine recommends related products based on the user's emotional data. For example, if the user enjoys a product, it will display other products in the same category. Specifically, it applies a recommendation algorithm based on the user's past preference data.

[0471] Input: User emotion data

[0472] Output: Related product recommendations

[0473] The above is the detailed program processing of this system, which allows users to check the appearance and placement of products in a realistic augmented reality model and receive optimal information and related product recommendations based on their own emotions.

[0474] (Application example 2)

[0475] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0476] Conventional e-commerce sites have the problem that it is difficult for users to form an image of the product they are considering purchasing that is similar to the actual product. Also, because product information is presented uniformly without considering the user's feelings, there are cases where the user experience is not sufficiently improved. In addition, the accuracy of product recommendations does not reflect the user's intentions, which is an issue that does not sufficiently stimulate the desire to purchase.

[0477] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0478] In this invention, the server includes means for receiving a URL entered by a user, means for acquiring product information based on the received URL, means for analyzing the product information and generating a three-dimensional model based on the analysis results, means for converting the generated three-dimensional model into augmented reality data, means for transmitting the augmented reality data to the user's terminal, means for recognizing the user's emotion and adjusting the display content of the three-dimensional model based on the recognized emotion, and means for recommending related products based on the user's emotion. This allows the user to view products in a manner close to the real thing, and enables optimal information presentation and product recommendations based on emotion.

[0479] - "URL receiving means" is a function that receives the URL entered by the user via the network.

[0480] The "product information acquisition means" is a function that acquires the necessary product information from a product database or website based on the received URL.

[0481] The "product information analysis means" is a function that analyzes the acquired product information and extracts the shape, color, texture, and the like.

[0482] The "three-dimensional model generating means" is a function that automatically generates a three-dimensional digital model based on analyzed product information.

[0483] The "augmented reality data conversion means" is a function that converts the generated three-dimensional model into a data format that can be displayed in AR.

[0484] The "data transmission means" is a function that transmits the converted augmented reality data to the user's terminal.

[0485] The "data display means" is a function that displays the received data as augmented reality on the user's terminal.

[0486] The "emotion recognition means" is a function that analyzes the user's facial expressions and voice to recognize the emotion at that time.

[0487] The "display adjustment means" is a function that adjusts the content and viewpoint of the displayed three-dimensional model based on the recognized user's emotions.

[0488] The "product recommendation means" is a function that recommends other related products to the user based on the user's emotional data.

[0489] The system of this invention generates a 3D model based on the product URL entered by the user and displays it in augmented reality (AR).It also has the ability to adjust the display content based on the user's emotions and recommend related products.

[0490] The server processes the URL received from the user and obtains product information based on that URL. The product information obtaining means collects images and specification information related to the product from a database or website. The product information analysis means then analyzes the obtained information and extracts shape, color, and texture information. Based on the results of this analysis, the 3D model generation means generates a digital 3D model of the product.

[0491] The generated three-dimensional model is converted into a format that can be displayed in AR (e.g., USDZ or GLTF format) by the augmented reality data conversion means. This converted data is transmitted to the user's terminal via the data transmission means. The received data is displayed as augmented reality by the user's terminal.

[0492] Furthermore, the emotion recognition means allows the user's device to analyze the user's facial expressions and voice to obtain emotion data. Based on the recognized emotion, the display adjustment means adjusts the display content and viewpoint of the three-dimensional model. For example, if the user is feeling anxious, a different viewpoint or additional information is displayed. Furthermore, based on the user's emotion data, the product recommendation means recommends related products. If the user finds the emotion engine to be fun, other products in the same category are displayed.

[0493] Hardware and software used

[0494] Hardware: Smartphone, smart glasses, head-mounted display (camera, sensor)

[0495] software:

[0496] EmotionRecognizer Library: Recognize user emotions

[0497] ARDisplay library: AR display of 3D models

[0498] HTTP request: Get product information

[0499] Generative AI model: 3D model generation

[0500] Specific examples

[0501] A user opens a smartphone app and enters the URL of a product they found on an e-commerce site. For example, if a user is considering purchasing furniture, they enter the URL of a sofa they are interested in into a dedicated app. The server retrieves product information based on the URL, and the generative AI model generates a 3D model using the following prompt:

[0502] Prompt: "Shape: square, Color: blue, Texture: fabric"

[0503] The generated 3D model is converted and sent to the user's smartphone, where it is displayed in real space through the camera. The user can see how the sofa would look in their living room. Furthermore, if the user looks happy at the camera, the emotion recognition means detects this and the product recommendation means displays other related furniture. For example, cushions or tables of the same color are recommended. This makes it easier for the user to make a purchase decision and allows them to check the product in a way that is close to the real thing in their own home.

[0504] Prompt Sentence Examples

[0505] "Shape: Square, Color: Blue, Texture: Fabric"

[0506] "Shape: Rectangle, Color: White, Texture: Wood Grain"

[0507] In this way, the invention improves the user experience and supports purchasing decisions.

[0508] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0509] Step 1:

[0510] The user launches the application and enters the URL of a product they found on an e-commerce site.

[0511] Input: Product URL

[0512] Output: The URL is saved on the user's device.

[0513] Specific operation: The user enters the product URL into the input field of the dedicated application.

[0514] Step 2:

[0515] The device sends the entered URL to the server.

[0516] Input: The URL entered by the user

[0517] Output: URL sent to server

[0518] Specific operation: The device sends a URL to the server using an HTTP request.

[0519] Step 3:

[0520] The server accesses the e-commerce site based on the URL and retrieves product information.

[0521] Input: User submitted URL

[0522] Output: Product image data and specifications

[0523] Specific operations: The server collects product information (images, shapes, colors, textures, dimensions, material information, etc.) through scraping technology or API calls.

[0524] Step 4:

[0525] The server analyzes the acquired product information and extracts the necessary data.

[0526] Input: Retrieved product information

[0527] Output: Analyzed shape, color, and texture information

[0528] Specific operation: Using product information analysis means, shape, color, and texture information are extracted from image data, and dimension and material information is extracted from specification information.

[0529] Step 5:

[0530] The server generates a three-dimensional model based on the analyzed data.

[0531] Input: Shape, color, texture information

[0532] Output: 3D model

[0533] How it works: Using a generative AI model, generate a 3D model based on the following prompt:

[0534] Prompt: "Shape: square, Color: blue, Texture: fabric"

[0535] Step 6:

[0536] The server converts the generated three-dimensional model into augmented reality data.

[0537] Input: 3D model

[0538] Output: Augmented reality data (e.g. USDZ format)

[0539] Specific operations: Using augmented reality data conversion means, the coordinate system of the model is set, AR markers are added, and export to a specific format.

[0540] Step 7:

[0541] The server transmits the converted augmented reality data to the terminal.

[0542] Input: Augmented reality data

[0543] Output: Augmented reality data sent to the device

[0544] Specific operation: Sends data to the user's device using an HTTP response or WebSocket.

[0545] Step 8:

[0546] The device displays the received augmented reality data.

[0547] Input: Augmented reality data

[0548] Output: 3D model displayed in real space

[0549] Specific operation: The device application displays augmented reality data in real space through the camera.

[0550] Step 9:

[0551] The device recognizes the user's emotions.

[0552] Input: User's facial expressions and voice data

[0553] Output: Recognized emotion data

[0554] Specific operation: Analyzes the user's emotions using the EmotionRecognizer library through the device's camera and microphone.

[0555] Step 10:

[0556] The server adjusts the display content of the three-dimensional model based on the emotion.

[0557] Input: Recognized emotion data

[0558] Output: Adjusted display content

[0559] Specific operation: Based on the emotion data, the display adjustment means adjusts the display viewpoint and detailed information of the three-dimensional model.

[0560] Step 11:

[0561] The server recommends related products based on the user's emotions.

[0562] Input: Recognized emotion data

[0563] Output: Recommended related products

[0564] Specific operation: Using the emotion engine, other related products are selected and displayed based on the user's emotion data.

[0565] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0566] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0567] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0568] [Second embodiment]

[0569] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0570] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0571] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0572] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0573] 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.

[0574] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0575] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0576] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0577] 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.

[0578] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0579] 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.

[0580] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0581] This invention relates to a system that uses generative AI to automatically generate 3D models based on product information found by users on an e-commerce site, enabling real-time augmented reality (AR) display. The program processing of this system is explained below.

[0582] System configuration

[0583] The system mainly consists of the following elements:

[0584] URL receiving method

[0585] Product information acquisition means

[0586] Product information analysis means

[0587] 3D model generation means

[0588] Augmented reality data conversion means

[0589] Data transmission method

[0590] Data display means

[0591] Program processing

[0592] User operations

[0593] 1. Enter the URL

[0594] The user launches the dedicated application and enters the URL of the product they want to convert into AR. By doing this, the user prepares to view the product in detail at home.

[0595] Device behavior

[0596] 2. Sending the URL

[0597] The device sends the URL entered by the user to the server, usually via an HTTP request.

[0598] Server Operation

[0599] 3. Collecting product information

[0600] The server accesses the e-commerce site based on the URL and collects image data and specifications of the relevant product. This collection can be done using scraping technology or API.

[0601] 4. Product information analysis

[0602] The server analyzes the collected product information, analyzing shape, color, and texture information from image data, and extracting dimensions and material information from spec information.

[0603] 5. 3D Model Generation

[0604] Based on the analyzed data, generative AI generates a 3D model of the product, which applies color and texture to the geometric data to create a realistic model.

[0605] 6. Augmented Reality Data Conversion

[0606] The server converts the generated 3D model into augmented reality data, a process that includes setting the coordinates of the model, adding AR markers, and exporting it to a specific format (e.g., USDZ or GLTF).

[0607] 7. Data transmission

[0608] The server sends the converted augmented reality data to the device using HTTP responses or WebSockets.

[0609] Device behavior

[0610] 8. Displaying Data

[0611] The device reads the received augmented reality data using a dedicated application and displays a 3D model in real space through the device's camera, allowing the user to see the product as if it were actually placed in that location.

[0612] Specific examples

[0613] Furniture purchase example

[0614] 1. User Operation

[0615] The user enters the URL of a sofa that catches their eye on an e-commerce site into a dedicated app.

[0616] 2. Send URL

[0617] The device sends this URL to the server.

[0618] 3. Information gathering

[0619] The server accesses the e-commerce site based on this URL and collects images and dimensions of the sofa.

[0620] 4. Data Analysis

[0621] The server analyzes the sofa's shape, color, and texture information from the image and extracts its dimensions and material information.

[0622] 5. Model Generation

[0623] The 3D model generation AI uses this data to generate a realistic 3D model of the sofa.

[0624] 6. Data Conversion

[0625] The server converts the generated model into augmented reality data (e.g., USDZ format).

[0626] 7. Data Transmission

[0627] The server transmits this augmented reality data to the terminal.

[0628] 8. Data Display

[0629] The device loads the augmented reality data into the app and displays, via the camera, what the sofa would look like in the user's living room.

[0630] In this way, users can see exactly how the sofa will look and feel in their home, which will make purchasing decisions easier and is expected to lead to increased sales on e-commerce sites.

[0631] The processing flow will be explained below.

[0632] Step 1:

[0633] The user launches the dedicated app and enters the URL of the product they want to convert into AR, which inserts the URL into the input field within the app.

[0634] Step 2:

[0635] The device sends the entered URL to the server using an HTTP request.

[0636] Step 3:

[0637] The server accesses the e-commerce site based on the received URL and obtains product image data and specifications using scraping technology or API calls.

[0638] Step 4:

[0639] The server analyzes the acquired product information, extracting shape, color, and texture information from the image data, and analyzing and extracting dimensions and material information from the specification information.

[0640] Step 5:

[0641] The server-based generative AI generates a 3D model of the product based on the analyzed data. First, it creates a 3D mesh based on the shape information, and then applies color and texture information to the model.

[0642] Step 6:

[0643] The server converts the generated 3D model into augmented reality data by setting the model's coordinate system, adding appropriate AR markers, and exporting it to a specific format (e.g., USDZ or GLTF).

[0644] Step 7:

[0645] The server sends the generated augmented reality data to the device using HTTP responses or WebSockets.

[0646] Step 8:

[0647] The device then loads the received augmented reality data into a dedicated app, which uses the data to display a 3D model in real space through the device's camera.

[0648] Step 9:

[0649] The user operates the device to check how the 3D model will look in the location where they want to place the product, and then rotates, moves, scales, and performs other operations on the model to simulate the optimal placement.

[0650] Example 1

[0651] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0652] In recent years, many users have begun to purchase products via the Internet, and purchasing activities on e-commerce sites have become increasingly popular. However, it is difficult for users to fully grasp the actual size and appearance of a product from online product images and descriptions alone, which often makes it difficult to make a purchasing decision. In particular, for products such as furniture and decorative items, where it is not clear whether they will fit in a particular space until they are actually placed, it is often discovered after purchase that the product does not meet expectations, resulting in frequent returns and exchanges, which is inefficient for companies. To solve these problems, there is a need for a system that allows users to check the actual placement and appearance of products at home in real time.

[0653] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0654] In this invention, the server includes means for receiving a URL entered by a user, means for acquiring product information based on the received URL, means for analyzing the product information and generating a three-dimensional model based on the analysis result, means for converting the generated three-dimensional model into augmented reality data, means for transmitting the augmented reality data to a user's terminal, and means for displaying the augmented reality data on the user's terminal. This allows users to place products they find on an e-commerce site in their home or other physical space in real time via a dedicated application, allowing them to intuitively check the size and appearance of the products and making it easier for them to make a purchasing decision.

[0655] The "URL receiving means" is a means for receiving a URL entered by a user.

[0656] The "product information acquisition means" is a means for accessing the EC site based on the received URL and acquiring information about the product.

[0657] The "product information analysis means" is a means for analyzing the acquired product information and extracting shape, color, and texture information.

[0658] The "three-dimensional model generating means" is a means for generating a three-dimensional model of a product based on the analysis results.

[0659] The "augmented reality data conversion means" is a means for converting the generated three-dimensional model into augmented reality data.

[0660] The "data transmission means" is a means for transmitting the converted augmented reality data to the user's terminal.

[0661] "Data display means" refers to means for displaying augmented reality data received by a user's terminal.

[0662] An "image analysis algorithm" is an algorithm for analyzing image data from product information and extracting shape, color, and texture information.

[0663] A "prompt statement" is an instruction statement to be input into a generative AI model, and includes information for generating a three-dimensional model based on the analysis results.

[0664] Overall system configuration

[0665] The system of this invention uses generative AI to automatically generate 3D models based on product information found by users on an e-commerce site, enabling real-time augmented reality (AR) display. It mainly consists of the following elements:

[0666] URL receiving method

[0667] Product information acquisition means

[0668] Product information analysis means

[0669] 3D model generation means

[0670] Augmented reality data conversion means

[0671] Data transmission method

[0672] Data display means

[0673] Details of each element

[0674] URL receiving method

[0675] This is a means of receiving a URL entered by the user into a dedicated application. For example, the user enters the URL of a sofa they found on an e-commerce site. This identifies the specific product to be displayed in AR.

[0676] Product information acquisition means

[0677] The device sends the received URL to the server. The server accesses the e-commerce site based on that URL and retrieves product information. Specifically, it uses a scraping tool (e.g., BeautifulSoup, Selenium) or API to collect image data from the product page, as well as specifications such as dimensions and materials.

[0678] Product information analysis means

[0679] The server analyzes the acquired product information. In this process, image analysis libraries (e.g., OpenCV, TensorFlow) are used to extract shape, color, and texture information from the image data. Specifications (dimensions and materials) are also analyzed at the same time, and the data necessary to generate a 3D model is prepared.

[0680] 3D model generation means

[0681] Based on the analyzed data, a generative AI model generates a 3D model of the product. Examples of generative AI models used include DALL-E and GAN (Generative Adversarial Network). The generated 3D model applies color and texture to the shape data, allowing it to be displayed as a realistic model.

[0682] Specific examples of prompts are as follows:

[0683] "Create a realistic 3D model using the images and specifications of the following products.

[0684] Image URL: [Image URL]

[0685] Specification information:

[0686] Dimensions: Width [xx] cm, Height [xx] cm, Depth [xx] cm

[0687] Material: [Material information]

[0688] Color: [Color information]

[0689] Please use USDZ format for the output format.

[0690] Augmented reality data conversion means

[0691] The generated 3D model is converted into augmented reality data. This conversion process involves setting the coordinates of the model, adding AR markers, and exporting it to a specific format (e.g., USDZ, GLTF). This can be done using a 3D modeling tool (e.g., Blender, Unity) or a conversion library.

[0692] Data transmission method

[0693] The converted augmented reality data is sent to the device using HTTP responses or WebSockets. The server properly packets the data and sends it to the device.

[0694] Data display means

[0695] The device reads the received augmented reality data using a dedicated application, which allows the device to display a three-dimensional model in real space through the camera. AR display uses ARKit (iOS) or ARCore (Android).

[0696] Example of operation

[0697] Furniture purchase example

[0698] A user enters the URL of a sofa they find interesting on an e-commerce site into a dedicated app. The device then sends the URL as an HTTP request to the server. The server then accesses the e-commerce site using this URL and collects the sofa's image data and dimensions. The collected data is analyzed using an image analysis library to extract shape, color, and texture information. Based on the analysis results, a generative AI model generates a 3D model, which the server then converts into augmented reality data in USDZ format. The server then sends the converted data to the device, which then displays the AR image, allowing the user to see in real time how the sofa will look in their living room.

[0699] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0700] Step 1:

[0701] The user launches the dedicated application and enters the URL of the product they want to create in AR. This operation allows the user to provide specific information about the product. The entered URL becomes the input for the next processing step.

[0702] Step 2:

[0703] The terminal sends the URL entered by the user to the server. The transmission is done via an HTTP request. This request contains the URL entered by the user. The output of the terminal is the URL transmission data to the server.

[0704] Step 3:

[0705] The server accesses the e-commerce site based on the received URL. The server uses a scraping tool (e.g., BeautifulSoup or Selenium) or an API to collect product information. Specifically, it obtains image data and specification information (dimensions, material, color, etc.). The input for this step is the sent URL, and the output is the collected product information.

[0706] Step 4:

[0707] The server analyzes the collected product information. It extracts shape, color, and texture information from image data, and analyzes dimensions and materials from spec information. This process uses an image analysis library (e.g., OpenCV or TensorFlow). The input is the collected product information, and the output is the analyzed product information.

[0708] Step 5:

[0709] The server then inputs prompts into the generative AI model based on the analyzed data to generate a 3D model of the product. The generative AI models used include DALL-E and GAN. Specific examples of prompts are as follows:

[0710] "Create a realistic 3D model using the images and specifications of the following products.

[0711] Image URL: [Image URL]

[0712] Specification information:

[0713] Dimensions: Width [xx] cm, Height [xx] cm, Depth [xx] cm

[0714] Material: [Material information]

[0715] Color: [Color information]

[0716] Please use USDZ format for the output format.

[0717] The input is analyzed product information, and the output is generated 3D model data.

[0718] Step 6:

[0719] The server converts the generated 3D model into augmented reality data (e.g., USDZ format). This conversion involves setting the coordinates of the model, adding AR markers, and exporting it to a specific format. The input is the 3D model data generated by the generative AI model, and the output is the converted augmented reality data.

[0720] Step 7:

[0721] The server then sends the converted augmented reality data to the device, using HTTP responses or WebSockets. The server's output is packets of augmented reality data sent to the user's device.

[0722] Step 8:

[0723] The device reads the received augmented reality data using a dedicated application. A three-dimensional model is displayed in real space through the device's camera. This allows the user to see the product as if it were actually placed in that location. The input is the augmented reality data sent from the server, and the output is the displayed three-dimensional model.

[0724] Specific examples

[0725] For example, a user enters the URL of a sofa they found on an e-commerce site, and their device sends the URL to a server. The server collects product information based on the URL and analyzes image data and dimensions. A generative AI model generates a 3D model and converts it into USDZ format. The data is then sent to the device and loaded into a dedicated application, allowing the user to see how the sofa would look in their living room.

[0726] (Application example 1)

[0727] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0728] With conventional food delivery services, it was difficult for users to check in advance what the food they were ordering would actually look like. This created a gap between the actual food and the photos on the delivery site, which led to a decrease in user satisfaction. Furthermore, there were cases where users hesitated to order because they lacked the visual information necessary to decide whether to order or not.

[0729] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0730] In this invention, the server includes means for receiving a URL entered by a user, means for acquiring product information based on the received URL, means for analyzing the product information and generating a three-dimensional model based on the analysis results, means for converting the generated three-dimensional model into augmented reality data, means for transmitting the augmented reality data to a user's terminal, means for displaying the augmented reality data on the user's terminal, and means for generating a three-dimensional model based on food information collected from a food delivery site and displaying it in augmented reality, thereby enabling users to check the actual appearance of food in augmented reality before delivery.

[0731] "URL receiving means" refers to a device or method that has the function of receiving a URL entered by a user.

[0732] The "product information acquisition means" refers to a device or method that has the function of collecting data about products based on the received URL.

[0733] "Product information analysis means" refers to a device or method that has the function of analyzing acquired product information and extracting necessary data.

[0734] The "three-dimensional model generating means" refers to a device or method that has the function of generating a three-dimensional model of a product based on the analysis results.

[0735] The "augmented reality data conversion means" refers to a device or method that has the function of converting the generated three-dimensional model into a data format that can be used as augmented reality content.

[0736] "Data transmission means" refers to a device or method that has the function of transmitting the converted augmented reality data to the user's terminal.

[0737] "Data display means" refers to a device or method that has the function of displaying augmented reality data on a user's terminal.

[0738] A "food delivery site" is a website or application that allows users to order food online.

[0739] "Food information" refers to data such as images and descriptions of dishes posted on food delivery sites.

[0740] "Augmented reality display means" refers to a device or method that has the function of displaying three-dimensionally modeled food information superimposed on the real world.

[0741] This invention relates to a system that uses augmented reality (AR) to display the actual food a user is considering ordering when using a food delivery service. Specifically, when a user inputs the URL of a food item, the system acquires and analyzes food information based on the URL, generates a three-dimensional model of the food, and converts it into AR data for display.

[0742] System configuration

[0743] The system mainly consists of the following elements:

[0744] URL receiving method

[0745] Product information acquisition means

[0746] Product information analysis means

[0747] 3D model generation means

[0748] Augmented reality data conversion means

[0749] Data transmission method

[0750] Data display means

[0751] Food delivery site

[0752] Food Information

[0753] Augmented reality display means

[0754] Program processing explanation

[0755] User operations

[0756] 1. Enter the URL

[0757] The user launches the dedicated application and enters the URL of the dish they are considering ordering. By doing this, the user arranges to check the appearance of the dish in detail.

[0758] Device behavior

[0759] 2. Sending the URL

[0760] The device sends the URL entered by the user to the server, usually via an HTTP request.

[0761] Server Operation

[0762] 3. Collecting product information

[0763] The server accesses the food delivery site based on the URL and collects image data and specifications of the corresponding dishes using scraping technology or API.

[0764] 4. Product information analysis

[0765] The server analyzes the collected food information, analyzing shape, color, and texture information from image data, and extracting dimensions and ingredient information from spec information.

[0766] 5. 3D Model Generation

[0767] Based on the analyzed data, the generative AI generates a 3D model of the dish, which applies color and texture to the geometric data to create a realistic model.

[0768] 6. Augmented Reality Data Conversion

[0769] The server converts the generated 3D model into augmented reality data, a process that includes setting the coordinates of the model, adding AR markers, and exporting it to a specific format (e.g., USDZ or GLTF).

[0770] 7. Data transmission

[0771] The server sends the converted augmented reality data to the device using HTTP responses or WebSockets.

[0772] Device behavior

[0773] 8. Displaying Data

[0774] The device reads the received augmented reality data using a dedicated application and displays a 3D model in real space through the device's camera, allowing the user to see the food as if it were actually placed in that location.

[0775] Examples of concrete examples and prompts

[0776] Sushi plate ordering example

[0777] 1. User Operation

[0778] Users enter the URL of a sushi plate they are interested in on a food delivery site into a dedicated app.

[0779] 2. Send URL

[0780] The device sends this URL to the server.

[0781] 3. Information gathering

[0782] The server accesses the food delivery site based on this URL and collects images and specifications of the sushi plates.

[0783] 4. Data Analysis

[0784] The server analyzes the shape, color, and texture information of the sushi plate from the image and extracts information about its dimensions and ingredients.

[0785] 5. Model Generation

[0786] The 3D model generation AI uses this data to generate a realistic 3D model of the sushi plate.

[0787] 6. Data Conversion

[0788] The server converts the generated model into augmented reality data (e.g., USDZ format).

[0789] 7. Data Transmission

[0790] The server transmits this augmented reality data to the terminal.

[0791] 8. Data Display

[0792] The device loads the augmented reality data into the app, which uses the camera to show what the sushi plate will look like at the user's table.

[0793] Example prompt sentence:

[0794] text

[0795] Generate a 3D model of a sushi plate. Get the image data and dimensions from the following URL: http: / / example.com / sushi-plate

[0796] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0797] Step 1:

[0798] The user launches the dedicated application and enters the URL of the dish they are considering ordering. The entered URL is saved in an input field in the application. This URL becomes the key to obtain detailed information about the dish.

[0799] Step 2:

[0800] The terminal sends the URL entered by the user to the server. This process is done through an HTTP request. The input is the URL entered by the user, and the output is the request sent to the server.

[0801] Step 3:

[0802] The server receives the URL and accesses the food delivery site based on that URL. The server uses this URL to collect image data and specifications for the corresponding dish using scraping technology or an API. The input is the received URL, and the output is image data and specifications for the dish.

[0803] Step 4:

[0804] The server analyzes the collected food information. In this analysis, the shape, color, and texture information of the food is extracted from the image data, and data such as dimensions and ingredients is extracted from the specification information. The input is the image data and specification information, and the output is the analysis results: shape data, color data, texture data, and dimension data.

[0805] Step 5:

[0806] The server generates a 3D model of the dish based on the analysis results. This process involves using a generative AI model to create a realistic 3D model. The input is shape data, color data, texture data, and dimension data, and the output is a 3D model.

[0807] Step 6:

[0808] The server converts the generated 3D model into augmented reality data. This conversion process includes setting the coordinates of the model, adding AR markers, and exporting it to a specific format (e.g., USDZ or GLTF). The input is the 3D model, and the output is the augmented reality data.

[0809] Step 7:

[0810] The server sends the augmented reality data to the device. This transmission process uses HTTP responses and WebSockets. The input is the augmented reality data, and the output is the data transmission to the device.

[0811] Step 8:

[0812] The device reads the received augmented reality data with a dedicated application and uses that data to display a 3D model in real space through the camera. The input is the augmented reality data, and the output is an augmented reality view of the food displayed on the user's display. The user can see the food as if it were actually placed in that location, which helps them make ordering decisions.

[0813] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0814] This invention relates to a system that uses generative AI to automatically generate 3D models based on product information found by a user on an e-commerce site, and combines this with an emotion engine to provide optimal augmented reality (AR) display and product recommendations based on the user's emotions. The program processing of this system is explained below.

[0815] System configuration

[0816] The system mainly consists of the following elements:

[0817] URL receiving method

[0818] Product information acquisition means

[0819] Product information analysis means

[0820] 3D model generation means

[0821] Augmented reality data conversion means

[0822] Data transmission method

[0823] Data display means

[0824] Emotion Engine

[0825] Program processing

[0826] User operations

[0827] 1. Enter the URL

[0828] The user launches the dedicated application and enters the URL of the product they want to convert into AR, which is then inserted into an input field within the application.

[0829] Device behavior

[0830] 2. Sending the URL

[0831] The device sends the entered URL to the server using an HTTP request.

[0832] Server Operation

[0833] 3. Collecting product information

[0834] The server accesses the e-commerce site based on the URL and retrieves product image data and specifications. This information is collected using scraping technology or API calls.

[0835] 4. Product information analysis

[0836] The server analyzes the acquired product information, extracting shape, color, and texture information from the image data, and analyzing and extracting dimensions and material information from the specification information.

[0837] 5. 3D Model Generation

[0838] The server-based generative AI generates a 3D model of the product based on the analyzed data, applying color and texture to the shape data to create a realistic model.

[0839] 6. Augmented Reality Data Conversion

[0840] The server converts the generated 3D model into augmented reality data, a process that includes setting the coordinate system of the model, adding AR markers, and exporting it to a specific format (e.g., USDZ or GLTF).

[0841] 7. Data transmission

[0842] The server sends the converted augmented reality data to the device using HTTP responses or WebSockets.

[0843] Device behavior

[0844] 8. Displaying Data

[0845] The device reads the received augmented reality data using a dedicated application and displays a three-dimensional model in real space through the device's camera, making the product appear as if it were actually placed in that location.

[0846] Emotion Engine Operation

[0847] 9. Emotional Recognition

[0848] The device captures the user's facial expressions, voice, gestures, etc. through cameras, microphones, and other sensors, and recognizes the user's emotions in real time from this data.

[0849] 10. Emotion-Based Display Adjustment

[0850] The emotion engine adjusts the display of the 3D model based on the user's emotions. For example, if the user is satisfied, the display will continue as is, but if the user is anxious, a different perspective or information will be added.

[0851] 11. Emotion-Based Product Recommendations

[0852] The emotion engine recommends related products based on the user's emotional data. For example, if a user is interested in and enjoys a particular product, it will recommend other products in the same category.

[0853] Specific examples

[0854] Furniture purchase example

[0855] 1. User Operation

[0856] The user enters the URL of a sofa that interests them on an e-commerce site into a dedicated app.

[0857] 2. Send URL

[0858] The terminal sends this URL to the server in an HTTP request.

[0859] 3. Information gathering

[0860] The server accesses the e-commerce site based on this URL and collects images and dimensions of the sofa.

[0861] 4. Data Analysis

[0862] The server analyzes the sofa's shape, color, and texture information from the image and extracts its dimensions and material information.

[0863] 5. Model Generation

[0864] The 3D model generation AI uses this data to generate a realistic 3D model of the sofa.

[0865] 6. Data Conversion

[0866] The server converts the generated model into augmented reality data (e.g., USDZ format).

[0867] 7. Data Transmission

[0868] The server transmits this augmented reality data to the terminal.

[0869] 8. Data Display

[0870] The device loads the augmented reality data into the app and displays, via the camera, what the sofa would look like in the user's living room.

[0871] 9. Emotional Recognition

[0872] The device acquires emotional data from the user's facial expressions and voice, and the emotion engine analyzes this to recognize the user's emotions.

[0873] 10. Display adjustment

[0874] The emotion engine adjusts the display of the 3D model based on the user's emotions: if the user is feeling anxious, it will show more details or a different perspective.

[0875] 11. Product Recommendations

[0876] The emotion engine will recommend other products in similar categories based on the user's emotional data, for example, if they are having fun, it will show other related sofas and furniture.

[0877] In this way, users can view realistic models of products at home and receive optimal information and recommendations based on their own emotions, which will facilitate purchasing decisions and contribute to increased sales on e-commerce sites.

[0878] The processing flow will be explained below.

[0879] Step 1:

[0880] The user launches the app and enters the URL of the product they are considering purchasing, which is then inserted into an input field within the app.

[0881] Step 2:

[0882] The terminal sends the input URL to the server using an HTTP request, and the server receives the URL.

[0883] Step 3:

[0884] The server accesses the corresponding e-commerce site based on the received URL and collects product information. Specifically, it obtains product image data and specifications (e.g., dimensions, material, price, etc.). This is done using scraping technology or API calls.

[0885] Step 4:

[0886] The server analyzes the acquired product information. Specifically, it analyzes shape, color, and texture information from the image data, and extracts dimensions and material information from the specification information. This analysis provides the basic data for generating a 3D model.

[0887] Step 5:

[0888] The server-based generative AI generates a 3D model of the product based on the analyzed data, first creating a 3D mesh based on the shape information, and then applying color and texture information to the model.

[0889] Step 6:

[0890] The server converts the generated 3D model into augmented reality data by setting the model's coordinate system, adding appropriate AR markers, and exporting it to a specific format (e.g., USDZ or GLTF).

[0891] Step 7:

[0892] The server sends the generated augmented reality data to the device using an HTTP response or WebSocket, and the device receives the augmented reality data.

[0893] Step 8:

[0894] The device then loads the received augmented reality data into a dedicated app, and the user can use the device's camera to display a 3D model in real space and check how the product will look when installed.

[0895] Step 9:

[0896] The device captures the user's facial expressions, voice, gestures, etc. through cameras, microphones, and other sensors, and sends this data to an emotion engine to recognize the user's emotions in real time.

[0897] Step 10:

[0898] The emotion engine analyzes the acquired data and recognizes the user's emotional state, for example, determining whether the user is surprised or feeling happy.

[0899] Step 11:

[0900] The emotion engine adjusts the display of the 3D model based on the user's perceived emotions, for example, providing more information or different perspectives to reassure the user if they are feeling anxious.

[0901] Step 12:

[0902] The emotion engine recommends related products based on emotion data. For example, if a user shows a strong interest in a particular product, it will also display and recommend other products in the same category or similar.

[0903] Step 13:

[0904] The user operates the device to check the provided information and recommended products and consider purchasing them. The user can rotate, scale, move, and perform other operations to simulate the optimal arrangement.

[0905] Example 2

[0906] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0907] On conventional e-commerce sites, users cannot see the actual product before purchasing it, which often leads to problems after purchase, such as the product's size or appearance being different from what they expected. Furthermore, conventional systems do not provide services that take user emotions into consideration, which can lead to a poor user experience. This leads to low user satisfaction and makes it difficult to increase sales on e-commerce sites.

[0908] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0909] In this invention, the server includes means for receiving a URL entered by a user, means for acquiring product information, means for analyzing the acquired information to generate a three-dimensional model, means for converting the generated three-dimensional model into augmented reality data, means for transmitting the augmented reality data to a terminal, means for recognizing emotions, means for adjusting the display based on the recognized emotions, and means for recommending related products. This allows the user to see an AR display of the product that is close to the real thing, and further allows the user to receive optimal information and product recommendations based on their emotions.

[0910] "URL" stands for Uniform Resource Locator and is a symbol that indicates the location of a resource on the Web.

[0911] "Product information" refers to information about the characteristics and features of a product, such as product images, specifications, dimensions, materials, and colors.

[0912] A "three-dimensional model" is a three-dimensional digital representation generated based on product information, which realistically reproduces the appearance and shape of the product.

[0913] "Augmented reality data" is data used to overlay a three-dimensional model onto real space, and is usually converted into a specific format (e.g., USDZ format or GLTF format).

[0914] A "server" is a computer system that receives requests from users, processes the necessary data, and sends it to terminals.

[0915] A "terminal" is a device used by a user, including a smartphone, tablet, etc.

[0916] An "emotion engine" is a system that recognizes emotions from a user's facial expressions, voice, gestures, etc., and provides information based on those emotions.

[0917] "Perception" is the use of sensors and algorithms to determine specific information or conditions.

[0918] "Adjusting the display content" means changing the information and layout to be displayed according to the user's emotions and situation.

[0919] "Product recommendation" refers to proposing products that are likely to interest a user based on their past behavior and current emotions.

[0920] This invention relates to a system that uses a generative AI model to automatically generate a three-dimensional model based on product information found by a user on an e-commerce site, and combines it with an emotion engine to provide optimal augmented reality (AR) display and product recommendations based on the user's emotions.

[0921] System configuration

[0922] The system mainly consists of the following elements:

[0923] server

[0924] Device (smartphone, tablet, etc.)

[0925] Emotion Engine

[0926] URL receiving method

[0927] Product information acquisition means

[0928] Product information analysis means

[0929] 3D model generation means

[0930] Augmented reality data conversion means

[0931] Data transmission method

[0932] Data display means

[0933] Hardware and software used

[0934] Hardware:

[0935] A server is a computer with high-performance data processing capabilities.

[0936] The devices are smartphones or tablets equipped with cameras, microphones, and sensors.

[0937] software:

[0938] Python library BeautifulSoup (for scraping product information)

[0939] OpenCV (for analyzing image data)

[0940] Blender Python API (to generate 3D models using generative AI models)

[0941] Three.js (for converting augmented reality data to USDZ or GLTF format)

[0942] Microsoft Azure Emotion API (for emotion recognition)

[0943] ARKit (for displaying AR on devices)

[0944] Specific processing of the program

[0945] The user launches a dedicated application and enters the URL of the product they want to use in AR. The device receives the URL and sends it to the server using an HTTP request. The server then accesses the e-commerce site based on the received URL and obtains the product's image data and specifications using scraping or an API call.

[0946] The acquired product information is analyzed by the server. Format data (shape, color, texture information) is extracted from the image data, and dimensions and material information are analyzed from the spec information. The OpenCV library is used for the analysis.

[0947] Next, a generative AI model (e.g., Blender Python API) generates a 3D model based on the parsed data, which is then converted into a data format for AR display (e.g., USDZ or GLTF) using the Three.js library.

[0948] The converted augmented reality data is sent to the device by the server using HTTP responses or WebSockets. The device reads the received data with a dedicated application and displays the model in real space through the camera. For example, you can use your smartphone camera to see how a sofa would look in your living room.

[0949] The device also uses cameras, microphones, and other sensors to capture the user's facial expressions, voice, and gestures, and the emotion engine uses this data to recognize the user's emotions in real time. The emotion engine analyzes emotions using Microsoft Azure's Emotion API.

[0950] The emotion engine adjusts the display of the 3D model based on the recognized emotion: for example, if the user is anxious, it will show additional details or different perspectives, but if the user is satisfied, it will continue to display the model as is.

[0951] The emotion engine also recommends related products based on the recognized emotion, for example, if the user is enjoying something, it will show other products in the same category.

[0952] Examples of concrete examples and prompts

[0953] Example: Purchasing furniture

[0954] A user enters the URL of a sofa that catches their eye on an e-commerce site into a dedicated app. The device then sends this URL to the server via an HTTP request. The server then accesses the e-commerce site based on this URL and uses BeautifulSoup to collect images and dimensions of the sofa.

[0955] The server then uses OpenCV to analyze the images and extract shape, color, and texture information. A generative AI model (Blender Python API) uses this data to generate a realistic 3D model. The generated model is then converted to USDZ format using Three.js. The server then sends the converted data to the device, which then uses ARKit to overlay the 3D model of the sofa on the camera image.

[0956] Example prompt sentence:

[0957] "Generate a detailed 3D model of a sofa based on the following data:

[0958] Image data: [image_url]

[0959] Product dimensions: Height 80cm, width 200cm, depth 100cm

[0960] Material: Cloth

[0961] Color: Gray

[0962] "

[0963] In this way, users can view models of products that are close to the real thing, while receiving optimal information and product recommendations that correspond to their own emotions.

[0964] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0965] Step 1:

[0966] User operation (URL input)

[0967] The user launches the dedicated application and enters the URL of the product they want to convert into AR. Specifically, they paste the URL of the product page of a sofa they found on a furniture mail-order website into the input field.

[0968] Input: Product URL

[0969] Output: The entered product URL is saved on the device.

[0970] Step 2:

[0971] Device operation (URL sending)

[0972] The device sends the entered URL to the server as an HTTP request. At this time, the device sends a POST request including the URL to the server and delivers the data.

[0973] Input: Product URL entered by the user

[0974] Output: The product URL is sent to the server.

[0975] Step 3:

[0976] Server operation (collection of product information)

[0977] The server accesses the e-commerce site based on the received URL and retrieves the product's image data and specifications. This process can be done by scraping using Python's BeautifulSoup library or by using the API provided by the e-commerce site. Specifically, BeautifulSoup is used to extract the product image URL and dimensional information from the HTML document.

[0978] Input: Product URL

[0979] Output: Product image URL, dimensions, and other specifications

[0980] Step 4:

[0981] Server operation (analysis of product information)

[0982] The server analyzes the shape, color, and texture information from the image data based on the acquired product information, and extracts dimensions and material information from the spec information. This analysis uses the OpenCV library. For example, it performs edge detection on the image to identify the shape.

[0983] Input: URL of product image, dimensions, and other specifications

[0984] Output: Shape data, color data, texture data, dimension information, material information

[0985] Step 5:

[0986] Server operation (generation of 3D models)

[0987] The generative AI model installed on the server generates a 3D model of the product based on the analyzed data. Specifically, Blender's Python API is used to apply color and texture to the shape data to generate a realistic 3D model. The prompt text input to the generative AI is, "Please generate a detailed 3D model of a sofa based on the following data: image data, product size (height 80cm, width 200cm, depth 100cm), material (fabric), and color (gray)."

[0988] Input: Shape data, color data, texture data, dimension information, material information

[0989] Output: 3D model

[0990] Step 6:

[0991] Server operation (augmented reality data conversion)

[0992] The server converts the generated 3D model into augmented reality (AR) data. This process involves setting the coordinate system of the 3D model, adding AR markers, and exporting it to a specific format (USDZ or GLTF). Specifically, the Three.js library is used to export the 3D model into an AR-compatible data format.

[0993] Input: 3D model

[0994] Output: Augmented reality data (USDZ format or GLTF format)

[0995] Step 7:

[0996] Server operation (data transmission)

[0997] The server sends the converted augmented reality data to the device using an HTTP response or WebSocket. Specifically, when the device sends an HTTP request, the server returns the converted augmented reality data as an HTTP response.

[0998] Input: Augmented reality data

[0999] Output: Augmented reality data is sent to the device.

[1000] Step 8:

[1001] Terminal operation (displaying data)

[1002] The device reads the received augmented reality data using a dedicated application and displays a 3D model in real space. Specifically, it displays what the sofa would look like in the user's living room through the device's camera. For example, it uses ARKit to overlay a 3D model of the sofa on the camera image.

[1003] Input: Augmented reality data

[1004] Output: 3D model displayed in real space

[1005] Step 9:

[1006] Emotion engine operation (emotion recognition)

[1007] The device captures the user's facial expressions, voice, gestures, etc. through the camera, microphone, and other sensors, and the emotion engine recognizes the user's emotions in real time from this data. This emotion recognition is done using Microsoft Azure's Emotion API.

[1008] Input: User's facial expression data, voice data, gesture data

[1009] Output: User emotion data

[1010] Step 10:

[1011] Emotion engine operation (adjusting display content)

[1012] The emotion engine adjusts the display of the 3D model based on the user's perceived emotions, for example by adding more detailed information or showing different perspectives if the user is feeling anxious.

[1013] Input: User emotion data

[1014] Output: Adjusted display content

[1015] Step 11:

[1016] Emotion engine operation (product recommendation)

[1017] The emotion engine recommends related products based on the user's emotional data. For example, if the user enjoys a product, it will display other products in the same category. Specifically, it applies a recommendation algorithm based on the user's past preference data.

[1018] Input: User emotion data

[1019] Output: Related product recommendations

[1020] The above is the detailed program processing of this system, which allows users to check the appearance and placement of products in a realistic augmented reality model and receive optimal information and related product recommendations based on their own emotions.

[1021] (Application example 2)

[1022] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1023] Conventional e-commerce sites have the problem that it is difficult for users to form an image of the product they are considering purchasing that is similar to the actual product. Also, because product information is presented uniformly without considering the user's feelings, there are cases where the user experience is not sufficiently improved. In addition, the accuracy of product recommendations does not reflect the user's intentions, which is an issue that does not sufficiently stimulate the desire to purchase.

[1024] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1025] In this invention, the server includes means for receiving a URL entered by a user, means for acquiring product information based on the received URL, means for analyzing the product information and generating a three-dimensional model based on the analysis results, means for converting the generated three-dimensional model into augmented reality data, means for transmitting the augmented reality data to the user's terminal, means for recognizing the user's emotion and adjusting the display content of the three-dimensional model based on the recognized emotion, and means for recommending related products based on the user's emotion. This allows the user to view products in a manner close to the real thing, and enables optimal information presentation and product recommendations based on emotion.

[1026] - "URL receiving means" is a function that receives the URL entered by the user via the network.

[1027] The "product information acquisition means" is a function that acquires the necessary product information from a product database or website based on the received URL.

[1028] The "product information analysis means" is a function that analyzes the acquired product information and extracts the shape, color, texture, and the like.

[1029] The "three-dimensional model generating means" is a function that automatically generates a three-dimensional digital model based on analyzed product information.

[1030] The "augmented reality data conversion means" is a function that converts the generated three-dimensional model into a data format that can be displayed in AR.

[1031] The "data transmission means" is a function that transmits the converted augmented reality data to the user's terminal.

[1032] The "data display means" is a function that displays the received data as augmented reality on the user's terminal.

[1033] The "emotion recognition means" is a function that analyzes the user's facial expressions and voice to recognize the emotion at that time.

[1034] The "display adjustment means" is a function that adjusts the content and viewpoint of the displayed three-dimensional model based on the recognized user's emotions.

[1035] The "product recommendation means" is a function that recommends other related products to the user based on the user's emotional data.

[1036] The system of this invention generates a 3D model based on the product URL entered by the user and displays it in augmented reality (AR).It also has the ability to adjust the display content based on the user's emotions and recommend related products.

[1037] The server processes the URL received from the user and obtains product information based on that URL. The product information obtaining means collects images and specification information related to the product from a database or website. The product information analysis means then analyzes the obtained information and extracts shape, color, and texture information. Based on the results of this analysis, the 3D model generation means generates a digital 3D model of the product.

[1038] The generated three-dimensional model is converted into a format that can be displayed in AR (e.g., USDZ or GLTF format) by the augmented reality data conversion means. This converted data is transmitted to the user's terminal via the data transmission means. The received data is displayed as augmented reality by the user's terminal.

[1039] Furthermore, the emotion recognition means allows the user's device to analyze the user's facial expressions and voice to obtain emotion data. Based on the recognized emotion, the display adjustment means adjusts the display content and viewpoint of the three-dimensional model. For example, if the user is feeling anxious, a different viewpoint or additional information is displayed. Furthermore, based on the user's emotion data, the product recommendation means recommends related products. If the user finds the emotion engine to be fun, other products in the same category are displayed.

[1040] Hardware and software used

[1041] Hardware: Smartphone, smart glasses, head-mounted display (camera, sensor)

[1042] software:

[1043] EmotionRecognizer Library: Recognize user emotions

[1044] ARDisplay library: AR display of 3D models

[1045] HTTP request: Get product information

[1046] Generative AI model: 3D model generation

[1047] Specific examples

[1048] A user opens a smartphone app and enters the URL of a product they found on an e-commerce site. For example, if a user is considering purchasing furniture, they enter the URL of a sofa they are interested in into a dedicated app. The server retrieves product information based on the URL, and the generative AI model generates a 3D model using the following prompt:

[1049] Prompt: "Shape: square, Color: blue, Texture: fabric"

[1050] The generated 3D model is converted and sent to the user's smartphone, where it is displayed in real space through the camera. The user can see how the sofa would look in their living room. Furthermore, if the user looks happy at the camera, the emotion recognition means detects this and the product recommendation means displays other related furniture. For example, cushions or tables of the same color are recommended. This makes it easier for the user to make a purchase decision and allows them to check the product in a way that is close to the real thing in their own home.

[1051] Prompt Sentence Examples

[1052] "Shape: Square, Color: Blue, Texture: Fabric"

[1053] "Shape: Rectangle, Color: White, Texture: Wood Grain"

[1054] In this way, the invention improves the user experience and supports purchasing decisions.

[1055] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1056] Step 1:

[1057] The user launches the application and enters the URL of a product they found on an e-commerce site.

[1058] Input: Product URL

[1059] Output: The URL is saved on the user's device.

[1060] Specific operation: The user enters the product URL into the input field of the dedicated application.

[1061] Step 2:

[1062] The device sends the entered URL to the server.

[1063] Input: The URL entered by the user

[1064] Output: URL sent to server

[1065] Specific operation: The device sends a URL to the server using an HTTP request.

[1066] Step 3:

[1067] The server accesses the e-commerce site based on the URL and retrieves product information.

[1068] Input: User submitted URL

[1069] Output: Product image data and specifications

[1070] Specific operations: The server collects product information (images, shapes, colors, textures, dimensions, material information, etc.) through scraping technology or API calls.

[1071] Step 4:

[1072] The server analyzes the acquired product information and extracts the necessary data.

[1073] Input: Retrieved product information

[1074] Output: Analyzed shape, color, and texture information

[1075] Specific operation: Using product information analysis means, shape, color, and texture information are extracted from image data, and dimension and material information is extracted from specification information.

[1076] Step 5:

[1077] The server generates a three-dimensional model based on the analyzed data.

[1078] Input: Shape, color, texture information

[1079] Output: 3D model

[1080] How it works: Using a generative AI model, generate a 3D model based on the following prompt:

[1081] Prompt: "Shape: square, Color: blue, Texture: fabric"

[1082] Step 6:

[1083] The server converts the generated three-dimensional model into augmented reality data.

[1084] Input: 3D model

[1085] Output: Augmented reality data (e.g. USDZ format)

[1086] Specific operations: Using augmented reality data conversion means, the coordinate system of the model is set, AR markers are added, and export to a specific format.

[1087] Step 7:

[1088] The server transmits the converted augmented reality data to the terminal.

[1089] Input: Augmented reality data

[1090] Output: Augmented reality data sent to the device

[1091] Specific operation: Sends data to the user's device using an HTTP response or WebSocket.

[1092] Step 8:

[1093] The device displays the received augmented reality data.

[1094] Input: Augmented reality data

[1095] Output: 3D model displayed in real space

[1096] Specific operation: The device application displays augmented reality data in real space through the camera.

[1097] Step 9:

[1098] The device recognizes the user's emotions.

[1099] Input: User's facial expressions and voice data

[1100] Output: Recognized emotion data

[1101] Specific operation: Analyzes the user's emotions using the EmotionRecognizer library through the device's camera and microphone.

[1102] Step 10:

[1103] The server adjusts the display content of the three-dimensional model based on the emotion.

[1104] Input: Recognized emotion data

[1105] Output: Adjusted display content

[1106] Specific operation: Based on the emotion data, the display adjustment means adjusts the display viewpoint and detailed information of the three-dimensional model.

[1107] Step 11:

[1108] The server recommends related products based on the user's emotions.

[1109] Input: Recognized emotion data

[1110] Output: Recommended related products

[1111] Specific operation: Using the emotion engine, other related products are selected and displayed based on the user's emotion data.

[1112] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1113] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1114] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1115] [Third embodiment]

[1116] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1117] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1118] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1119] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1120] 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.

[1121] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1122] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1123] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1124] 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.

[1125] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1126] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1127] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1128] This invention relates to a system that uses generative AI to automatically generate 3D models based on product information found by users on an e-commerce site, enabling real-time augmented reality (AR) display. The program processing of this system is explained below.

[1129] System configuration

[1130] The system mainly consists of the following elements:

[1131] URL receiving method

[1132] Product information acquisition means

[1133] Product information analysis means

[1134] 3D model generation means

[1135] Augmented reality data conversion means

[1136] Data transmission method

[1137] Data display means

[1138] Program processing

[1139] User operations

[1140] 1. Enter the URL

[1141] The user launches the dedicated application and enters the URL of the product they want to convert into AR. By doing this, the user prepares to view the product in detail at home.

[1142] Device behavior

[1143] 2. Sending the URL

[1144] The device sends the URL entered by the user to the server, usually via an HTTP request.

[1145] Server Operation

[1146] 3. Collecting product information

[1147] The server accesses the e-commerce site based on the URL and collects image data and specifications of the relevant product. This collection can be done using scraping technology or API.

[1148] 4. Product information analysis

[1149] The server analyzes the collected product information, analyzing shape, color, and texture information from image data, and extracting dimensions and material information from spec information.

[1150] 5. 3D Model Generation

[1151] Based on the analyzed data, generative AI generates a 3D model of the product, which applies color and texture to the geometric data to create a realistic model.

[1152] 6. Augmented Reality Data Conversion

[1153] The server converts the generated 3D model into augmented reality data, a process that includes setting the coordinates of the model, adding AR markers, and exporting it to a specific format (e.g., USDZ or GLTF).

[1154] 7. Data transmission

[1155] The server sends the converted augmented reality data to the device using HTTP responses or WebSockets.

[1156] Device behavior

[1157] 8. Displaying Data

[1158] The device reads the received augmented reality data using a dedicated application and displays a 3D model in real space through the device's camera, allowing the user to see the product as if it were actually placed in that location.

[1159] Specific examples

[1160] Furniture purchase example

[1161] 1. User Operation

[1162] The user enters the URL of a sofa that catches their eye on an e-commerce site into a dedicated app.

[1163] 2. Send URL

[1164] The device sends this URL to the server.

[1165] 3. Information gathering

[1166] The server accesses the e-commerce site based on this URL and collects images and dimensions of the sofa.

[1167] 4. Data Analysis

[1168] The server analyzes the sofa's shape, color, and texture information from the image and extracts its dimensions and material information.

[1169] 5. Model Generation

[1170] The 3D model generation AI uses this data to generate a realistic 3D model of the sofa.

[1171] 6. Data Conversion

[1172] The server converts the generated model into augmented reality data (e.g., USDZ format).

[1173] 7. Data Transmission

[1174] The server transmits this augmented reality data to the terminal.

[1175] 8. Data Display

[1176] The device loads the augmented reality data into the app and displays, via the camera, what the sofa would look like in the user's living room.

[1177] In this way, users can see exactly how the sofa will look and feel in their home, which will make purchasing decisions easier and is expected to lead to increased sales on e-commerce sites.

[1178] The processing flow will be explained below.

[1179] Step 1:

[1180] The user launches the dedicated app and enters the URL of the product they want to convert into AR, which inserts the URL into the input field within the app.

[1181] Step 2:

[1182] The device sends the entered URL to the server using an HTTP request.

[1183] Step 3:

[1184] The server accesses the e-commerce site based on the received URL and obtains product image data and specifications using scraping technology or API calls.

[1185] Step 4:

[1186] The server analyzes the acquired product information, extracting shape, color, and texture information from the image data, and analyzing and extracting dimensions and material information from the specification information.

[1187] Step 5:

[1188] The server-based generative AI generates a 3D model of the product based on the analyzed data. First, it creates a 3D mesh based on the shape information, and then applies color and texture information to the model.

[1189] Step 6:

[1190] The server converts the generated 3D model into augmented reality data by setting the model's coordinate system, adding appropriate AR markers, and exporting it to a specific format (e.g., USDZ or GLTF).

[1191] Step 7:

[1192] The server sends the generated augmented reality data to the device using HTTP responses or WebSockets.

[1193] Step 8:

[1194] The device then loads the received augmented reality data into a dedicated app, which uses the data to display a 3D model in real space through the device's camera.

[1195] Step 9:

[1196] The user operates the device to check how the 3D model will look in the location where they want to place the product, and then rotates, moves, scales, and performs other operations on the model to simulate the optimal placement.

[1197] Example 1

[1198] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1199] In recent years, many users have begun to purchase products via the Internet, and purchasing activities on e-commerce sites have become increasingly popular. However, it is difficult for users to fully grasp the actual size and appearance of a product from online product images and descriptions alone, which often makes it difficult to make a purchasing decision. In particular, for products such as furniture and decorative items, where it is not clear whether they will fit in a particular space until they are actually placed, it is often discovered after purchase that the product does not meet expectations, resulting in frequent returns and exchanges, which is inefficient for companies. To solve these problems, there is a need for a system that allows users to check the actual placement and appearance of products at home in real time.

[1200] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1201] In this invention, the server includes means for receiving a URL entered by a user, means for acquiring product information based on the received URL, means for analyzing the product information and generating a three-dimensional model based on the analysis result, means for converting the generated three-dimensional model into augmented reality data, means for transmitting the augmented reality data to a user's terminal, and means for displaying the augmented reality data on the user's terminal. This allows users to place products they find on an e-commerce site in their home or other physical space in real time via a dedicated application, allowing them to intuitively check the size and appearance of the products and making it easier for them to make a purchasing decision.

[1202] The "URL receiving means" is a means for receiving a URL entered by a user.

[1203] The "product information acquisition means" is a means for accessing the EC site based on the received URL and acquiring information about the product.

[1204] The "product information analysis means" is a means for analyzing the acquired product information and extracting shape, color, and texture information.

[1205] The "three-dimensional model generating means" is a means for generating a three-dimensional model of a product based on the analysis results.

[1206] The "augmented reality data conversion means" is a means for converting the generated three-dimensional model into augmented reality data.

[1207] The "data transmission means" is a means for transmitting the converted augmented reality data to the user's terminal.

[1208] "Data display means" refers to means for displaying augmented reality data received by a user's terminal.

[1209] An "image analysis algorithm" is an algorithm for analyzing image data from product information and extracting shape, color, and texture information.

[1210] A "prompt statement" is an instruction statement to be input into a generative AI model, and includes information for generating a three-dimensional model based on the analysis results.

[1211] Overall system configuration

[1212] The system of this invention uses generative AI to automatically generate 3D models based on product information found by users on an e-commerce site, enabling real-time augmented reality (AR) display. It mainly consists of the following elements:

[1213] URL receiving method

[1214] Product information acquisition means

[1215] Product information analysis means

[1216] 3D model generation means

[1217] Augmented reality data conversion means

[1218] Data transmission method

[1219] Data display means

[1220] Details of each element

[1221] URL receiving method

[1222] This is a means of receiving a URL entered by the user into a dedicated application. For example, the user enters the URL of a sofa they found on an e-commerce site. This identifies the specific product to be displayed in AR.

[1223] Product information acquisition means

[1224] The device sends the received URL to the server. The server accesses the e-commerce site based on that URL and retrieves product information. Specifically, it uses a scraping tool (e.g., BeautifulSoup, Selenium) or API to collect image data from the product page, as well as specifications such as dimensions and materials.

[1225] Product information analysis means

[1226] The server analyzes the acquired product information. In this process, image analysis libraries (e.g., OpenCV, TensorFlow) are used to extract shape, color, and texture information from the image data. Specifications (dimensions and materials) are also analyzed at the same time, and the data necessary to generate a 3D model is prepared.

[1227] 3D model generation means

[1228] Based on the analyzed data, a generative AI model generates a 3D model of the product. Examples of generative AI models used include DALL-E and GAN (Generative Adversarial Network). The generated 3D model applies color and texture to the shape data, allowing it to be displayed as a realistic model.

[1229] Specific examples of prompts are as follows:

[1230] "Create a realistic 3D model using the images and specifications of the following products.

[1231] Image URL: [Image URL]

[1232] Specification information:

[1233] Dimensions: Width [xx] cm, Height [xx] cm, Depth [xx] cm

[1234] Material: [Material information]

[1235] Color: [Color information]

[1236] Please use USDZ format for the output format.

[1237] Augmented reality data conversion means

[1238] The generated 3D model is converted into augmented reality data. This conversion process involves setting the coordinates of the model, adding AR markers, and exporting it to a specific format (e.g., USDZ, GLTF). This can be done using a 3D modeling tool (e.g., Blender, Unity) or a conversion library.

[1239] Data transmission method

[1240] The converted augmented reality data is sent to the device using HTTP responses or WebSockets. The server properly packets the data and sends it to the device.

[1241] Data display means

[1242] The device reads the received augmented reality data using a dedicated application, which allows the device to display a three-dimensional model in real space through the camera. AR display uses ARKit (iOS) or ARCore (Android).

[1243] Example of operation

[1244] Furniture purchase example

[1245] A user enters the URL of a sofa they find interesting on an e-commerce site into a dedicated app. The device then sends the URL as an HTTP request to the server. The server then accesses the e-commerce site using this URL and collects the sofa's image data and dimensions. The collected data is analyzed using an image analysis library to extract shape, color, and texture information. Based on the analysis results, a generative AI model generates a 3D model, which the server then converts into augmented reality data in USDZ format. The server then sends the converted data to the device, which then displays the AR image, allowing the user to see in real time how the sofa will look in their living room.

[1246] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1247] Step 1:

[1248] The user launches the dedicated application and enters the URL of the product they want to create in AR. This operation allows the user to provide specific information about the product. The entered URL becomes the input for the next processing step.

[1249] Step 2:

[1250] The terminal sends the URL entered by the user to the server. The transmission is done via an HTTP request. This request contains the URL entered by the user. The output of the terminal is the URL transmission data to the server.

[1251] Step 3:

[1252] The server accesses the e-commerce site based on the received URL. The server uses a scraping tool (e.g., BeautifulSoup or Selenium) or an API to collect product information. Specifically, it obtains image data and specification information (dimensions, material, color, etc.). The input for this step is the sent URL, and the output is the collected product information.

[1253] Step 4:

[1254] The server analyzes the collected product information. It extracts shape, color, and texture information from image data, and analyzes dimensions and materials from spec information. This process uses an image analysis library (e.g., OpenCV or TensorFlow). The input is the collected product information, and the output is the analyzed product information.

[1255] Step 5:

[1256] The server then inputs prompts into the generative AI model based on the analyzed data to generate a 3D model of the product. The generative AI models used include DALL-E and GAN. Specific examples of prompts are as follows:

[1257] "Create a realistic 3D model using the images and specifications of the following products.

[1258] Image URL: [Image URL]

[1259] Specification information:

[1260] Dimensions: Width [xx] cm, Height [xx] cm, Depth [xx] cm

[1261] Material: [Material information]

[1262] Color: [Color information]

[1263] Please use USDZ format for the output format.

[1264] The input is analyzed product information, and the output is generated 3D model data.

[1265] Step 6:

[1266] The server converts the generated 3D model into augmented reality data (e.g., USDZ format). This conversion involves setting the coordinates of the model, adding AR markers, and exporting it to a specific format. The input is the 3D model data generated by the generative AI model, and the output is the converted augmented reality data.

[1267] Step 7:

[1268] The server then sends the converted augmented reality data to the device, using HTTP responses or WebSockets. The server's output is packets of augmented reality data sent to the user's device.

[1269] Step 8:

[1270] The device reads the received augmented reality data using a dedicated application. A three-dimensional model is displayed in real space through the device's camera. This allows the user to see the product as if it were actually placed in that location. The input is the augmented reality data sent from the server, and the output is the displayed three-dimensional model.

[1271] Specific examples

[1272] For example, a user enters the URL of a sofa they found on an e-commerce site, and their device sends the URL to a server. The server collects product information based on the URL and analyzes image data and dimensions. A generative AI model generates a 3D model and converts it into USDZ format. The data is then sent to the device and loaded into a dedicated application, allowing the user to see how the sofa would look in their living room.

[1273] (Application example 1)

[1274] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1275] With conventional food delivery services, it was difficult for users to check in advance what the food they were ordering would actually look like. This created a gap between the actual food and the photos on the delivery site, which led to a decrease in user satisfaction. Furthermore, there were cases where users hesitated to order because they lacked the visual information necessary to decide whether to order or not.

[1276] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1277] In this invention, the server includes means for receiving a URL entered by a user, means for acquiring product information based on the received URL, means for analyzing the product information and generating a three-dimensional model based on the analysis results, means for converting the generated three-dimensional model into augmented reality data, means for transmitting the augmented reality data to a user's terminal, means for displaying the augmented reality data on the user's terminal, and means for generating a three-dimensional model based on food information collected from a food delivery site and displaying it in augmented reality, thereby enabling users to check the actual appearance of food in augmented reality before delivery.

[1278] "URL receiving means" refers to a device or method that has the function of receiving a URL entered by a user.

[1279] The "product information acquisition means" refers to a device or method that has the function of collecting data about products based on the received URL.

[1280] "Product information analysis means" refers to a device or method that has the function of analyzing acquired product information and extracting necessary data.

[1281] The "three-dimensional model generating means" refers to a device or method that has the function of generating a three-dimensional model of a product based on the analysis results.

[1282] The "augmented reality data conversion means" refers to a device or method that has the function of converting the generated three-dimensional model into a data format that can be used as augmented reality content.

[1283] "Data transmission means" refers to a device or method that has the function of transmitting the converted augmented reality data to the user's terminal.

[1284] "Data display means" refers to a device or method that has the function of displaying augmented reality data on a user's terminal.

[1285] A "food delivery site" is a website or application that allows users to order food online.

[1286] "Food information" refers to data such as images and descriptions of dishes posted on food delivery sites.

[1287] "Augmented reality display means" refers to a device or method that has the function of displaying three-dimensionally modeled food information superimposed on the real world.

[1288] This invention relates to a system that uses augmented reality (AR) to display the actual food a user is considering ordering when using a food delivery service. Specifically, when a user inputs the URL of a food item, the system acquires and analyzes food information based on the URL, generates a three-dimensional model of the food, and converts it into AR data for display.

[1289] System configuration

[1290] The system mainly consists of the following elements:

[1291] URL receiving method

[1292] Product information acquisition means

[1293] Product information analysis means

[1294] 3D model generation means

[1295] Augmented reality data conversion means

[1296] Data transmission method

[1297] Data display means

[1298] Food delivery site

[1299] Food Information

[1300] Augmented reality display means

[1301] Program processing explanation

[1302] User operations

[1303] 1. Enter the URL

[1304] The user launches the dedicated application and enters the URL of the dish they are considering ordering. By doing this, the user arranges to check the appearance of the dish in detail.

[1305] Device behavior

[1306] 2. Sending the URL

[1307] The device sends the URL entered by the user to the server, usually via an HTTP request.

[1308] Server Operation

[1309] 3. Collecting product information

[1310] The server accesses the food delivery site based on the URL and collects image data and specifications of the corresponding dishes using scraping technology or API.

[1311] 4. Product information analysis

[1312] The server analyzes the collected food information, analyzing shape, color, and texture information from image data, and extracting dimensions and ingredient information from spec information.

[1313] 5. 3D Model Generation

[1314] Based on the analyzed data, the generative AI generates a 3D model of the dish, which applies color and texture to the geometric data to create a realistic model.

[1315] 6. Augmented Reality Data Conversion

[1316] The server converts the generated 3D model into augmented reality data, a process that includes setting the coordinates of the model, adding AR markers, and exporting it to a specific format (e.g., USDZ or GLTF).

[1317] 7. Data transmission

[1318] The server sends the converted augmented reality data to the device using HTTP responses or WebSockets.

[1319] Device behavior

[1320] 8. Displaying Data

[1321] The device reads the received augmented reality data using a dedicated application and displays a 3D model in real space through the device's camera, allowing the user to see the food as if it were actually placed in that location.

[1322] Examples of concrete examples and prompts

[1323] Sushi plate ordering example

[1324] 1. User Operation

[1325] Users enter the URL of a sushi plate they are interested in on a food delivery site into a dedicated app.

[1326] 2. Send URL

[1327] The device sends this URL to the server.

[1328] 3. Information gathering

[1329] The server accesses the food delivery site based on this URL and collects images and specifications of the sushi plates.

[1330] 4. Data Analysis

[1331] The server analyzes the shape, color, and texture information of the sushi plate from the image and extracts information about its dimensions and ingredients.

[1332] 5. Model Generation

[1333] The 3D model generation AI uses this data to generate a realistic 3D model of the sushi plate.

[1334] 6. Data Conversion

[1335] The server converts the generated model into augmented reality data (e.g., USDZ format).

[1336] 7. Data Transmission

[1337] The server transmits this augmented reality data to the terminal.

[1338] 8. Data Display

[1339] The device loads the augmented reality data into the app, which uses the camera to show what the sushi plate will look like at the user's table.

[1340] Example prompt sentence:

[1341] text

[1342] Generate a 3D model of a sushi plate. Get the image data and dimensions from the following URL: http: / / example.com / sushi-plate

[1343] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1344] Step 1:

[1345] The user launches the dedicated application and enters the URL of the dish they are considering ordering. The entered URL is saved in an input field in the application. This URL becomes the key to obtain detailed information about the dish.

[1346] Step 2:

[1347] The terminal sends the URL entered by the user to the server. This process is done through an HTTP request. The input is the URL entered by the user, and the output is the request sent to the server.

[1348] Step 3:

[1349] The server receives the URL and accesses the food delivery site based on that URL. The server uses this URL to collect image data and specifications for the corresponding dish using scraping technology or an API. The input is the received URL, and the output is image data and specifications for the dish.

[1350] Step 4:

[1351] The server analyzes the collected food information. In this analysis, the shape, color, and texture information of the food is extracted from the image data, and data such as dimensions and ingredients is extracted from the specification information. The input is the image data and specification information, and the output is the analysis results: shape data, color data, texture data, and dimension data.

[1352] Step 5:

[1353] The server generates a 3D model of the dish based on the analysis results. This process involves using a generative AI model to create a realistic 3D model. The input is shape data, color data, texture data, and dimension data, and the output is a 3D model.

[1354] Step 6:

[1355] The server converts the generated 3D model into augmented reality data. This conversion process includes setting the coordinates of the model, adding AR markers, and exporting it to a specific format (e.g., USDZ or GLTF). The input is the 3D model, and the output is the augmented reality data.

[1356] Step 7:

[1357] The server sends the augmented reality data to the device. This transmission process uses HTTP responses and WebSockets. The input is the augmented reality data, and the output is the data transmission to the device.

[1358] Step 8:

[1359] The device reads the received augmented reality data with a dedicated application and uses that data to display a 3D model in real space through the camera. The input is the augmented reality data, and the output is an augmented reality view of the food displayed on the user's display. The user can see the food as if it were actually placed in that location, which helps them make ordering decisions.

[1360] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1361] This invention relates to a system that uses generative AI to automatically generate 3D models based on product information found by a user on an e-commerce site, and combines this with an emotion engine to provide optimal augmented reality (AR) display and product recommendations based on the user's emotions. The program processing of this system is explained below.

[1362] System configuration

[1363] The system mainly consists of the following elements:

[1364] URL receiving method

[1365] Product information acquisition means

[1366] Product information analysis means

[1367] 3D model generation means

[1368] Augmented reality data conversion means

[1369] Data transmission method

[1370] Data display means

[1371] Emotion Engine

[1372] Program processing

[1373] User operations

[1374] 1. Enter the URL

[1375] The user launches the dedicated application and enters the URL of the product they want to convert into AR, which is then inserted into an input field within the application.

[1376] Device behavior

[1377] 2. Sending the URL

[1378] The device sends the entered URL to the server using an HTTP request.

[1379] Server Operation

[1380] 3. Collecting product information

[1381] The server accesses the e-commerce site based on the URL and retrieves product image data and specifications. This information is collected using scraping technology or API calls.

[1382] 4. Product information analysis

[1383] The server analyzes the acquired product information, extracting shape, color, and texture information from the image data, and analyzing and extracting dimensions and material information from the specification information.

[1384] 5. 3D Model Generation

[1385] The server-based generative AI generates a 3D model of the product based on the analyzed data, applying color and texture to the shape data to create a realistic model.

[1386] 6. Augmented Reality Data Conversion

[1387] The server converts the generated 3D model into augmented reality data, a process that includes setting the coordinate system of the model, adding AR markers, and exporting it to a specific format (e.g., USDZ or GLTF).

[1388] 7. Data transmission

[1389] The server sends the converted augmented reality data to the device using HTTP responses or WebSockets.

[1390] Device behavior

[1391] 8. Displaying Data

[1392] The device reads the received augmented reality data using a dedicated application and displays a three-dimensional model in real space through the device's camera, making the product appear as if it were actually placed in that location.

[1393] Emotion Engine Operation

[1394] 9. Emotional Recognition

[1395] The device captures the user's facial expressions, voice, gestures, etc. through cameras, microphones, and other sensors, and recognizes the user's emotions in real time from this data.

[1396] 10. Emotion-Based Display Adjustment

[1397] The emotion engine adjusts the display of the 3D model based on the user's emotions. For example, if the user is satisfied, the display will continue as is, but if the user is anxious, a different perspective or information will be added.

[1398] 11. Emotion-Based Product Recommendations

[1399] The emotion engine recommends related products based on the user's emotional data. For example, if a user is interested in and enjoys a particular product, it will recommend other products in the same category.

[1400] Specific examples

[1401] Furniture purchase example

[1402] 1. User Operation

[1403] The user enters the URL of a sofa that interests them on an e-commerce site into a dedicated app.

[1404] 2. Send URL

[1405] The terminal sends this URL to the server in an HTTP request.

[1406] 3. Information gathering

[1407] The server accesses the e-commerce site based on this URL and collects images and dimensions of the sofa.

[1408] 4. Data Analysis

[1409] The server analyzes the sofa's shape, color, and texture information from the image and extracts its dimensions and material information.

[1410] 5. Model Generation

[1411] The 3D model generation AI uses this data to generate a realistic 3D model of the sofa.

[1412] 6. Data Conversion

[1413] The server converts the generated model into augmented reality data (e.g., USDZ format).

[1414] 7. Data Transmission

[1415] The server transmits this augmented reality data to the terminal.

[1416] 8. Data Display

[1417] The device loads the augmented reality data into the app and displays, via the camera, what the sofa would look like in the user's living room.

[1418] 9. Emotional Recognition

[1419] The device acquires emotional data from the user's facial expressions and voice, and the emotion engine analyzes this to recognize the user's emotions.

[1420] 10. Display adjustment

[1421] The emotion engine adjusts the display of the 3D model based on the user's emotions: if the user is feeling anxious, it will show more details or a different perspective.

[1422] 11. Product Recommendations

[1423] The emotion engine will recommend other products in similar categories based on the user's emotional data, for example, if they are having fun, it will show other related sofas and furniture.

[1424] In this way, users can view realistic models of products at home and receive optimal information and recommendations based on their own emotions, which will facilitate purchasing decisions and contribute to increased sales on e-commerce sites.

[1425] The processing flow will be explained below.

[1426] Step 1:

[1427] The user launches the app and enters the URL of the product they are considering purchasing, which is then inserted into an input field within the app.

[1428] Step 2:

[1429] The terminal sends the input URL to the server using an HTTP request, and the server receives the URL.

[1430] Step 3:

[1431] The server accesses the corresponding e-commerce site based on the received URL and collects product information. Specifically, it obtains product image data and specifications (e.g., dimensions, material, price, etc.). This is done using scraping technology or API calls.

[1432] Step 4:

[1433] The server analyzes the acquired product information. Specifically, it analyzes shape, color, and texture information from the image data, and extracts dimensions and material information from the specification information. This analysis provides the basic data for generating a 3D model.

[1434] Step 5:

[1435] The server-based generative AI generates a 3D model of the product based on the analyzed data, first creating a 3D mesh based on the shape information, and then applying color and texture information to the model.

[1436] Step 6:

[1437] The server converts the generated 3D model into augmented reality data by setting the model's coordinate system, adding appropriate AR markers, and exporting it to a specific format (e.g., USDZ or GLTF).

[1438] Step 7:

[1439] The server sends the generated augmented reality data to the device using an HTTP response or WebSocket, and the device receives the augmented reality data.

[1440] Step 8:

[1441] The device then loads the received augmented reality data into a dedicated app, and the user can use the device's camera to display a 3D model in real space and check how the product will look when installed.

[1442] Step 9:

[1443] The device captures the user's facial expressions, voice, gestures, etc. through cameras, microphones, and other sensors, and sends this data to an emotion engine to recognize the user's emotions in real time.

[1444] Step 10:

[1445] The emotion engine analyzes the acquired data and recognizes the user's emotional state, for example, determining whether the user is surprised or feeling happy.

[1446] Step 11:

[1447] The emotion engine adjusts the display of the 3D model based on the user's perceived emotions, for example, providing more information or different perspectives to reassure the user if they are feeling anxious.

[1448] Step 12:

[1449] The emotion engine recommends related products based on emotion data. For example, if a user shows a strong interest in a particular product, it will also display and recommend other products in the same category or similar.

[1450] Step 13:

[1451] The user operates the device to check the provided information and recommended products and consider purchasing them. The user can rotate, scale, move, and perform other operations to simulate the optimal arrangement.

[1452] Example 2

[1453] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1454] On conventional e-commerce sites, users cannot see the actual product before purchasing it, which often leads to problems after purchase, such as the product's size or appearance being different from what they expected. Furthermore, conventional systems do not provide services that take user emotions into consideration, which can lead to a poor user experience. This leads to low user satisfaction and makes it difficult to increase sales on e-commerce sites.

[1455] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1456] In this invention, the server includes means for receiving a URL entered by a user, means for acquiring product information, means for analyzing the acquired information to generate a three-dimensional model, means for converting the generated three-dimensional model into augmented reality data, means for transmitting the augmented reality data to a terminal, means for recognizing emotions, means for adjusting the display based on the recognized emotions, and means for recommending related products. This allows the user to see an AR display of the product that is close to the real thing, and further allows the user to receive optimal information and product recommendations based on their emotions.

[1457] "URL" stands for Uniform Resource Locator and is a symbol that indicates the location of a resource on the Web.

[1458] "Product information" refers to information about the characteristics and features of a product, such as product images, specifications, dimensions, materials, and colors.

[1459] A "three-dimensional model" is a three-dimensional digital representation generated based on product information, which realistically reproduces the appearance and shape of the product.

[1460] "Augmented reality data" is data used to overlay a three-dimensional model onto real space, and is usually converted into a specific format (e.g., USDZ format or GLTF format).

[1461] A "server" is a computer system that receives requests from users, processes the necessary data, and sends it to terminals.

[1462] A "terminal" is a device used by a user, including a smartphone, tablet, etc.

[1463] An "emotion engine" is a system that recognizes emotions from a user's facial expressions, voice, gestures, etc., and provides information based on those emotions.

[1464] "Perception" is the use of sensors and algorithms to determine specific information or conditions.

[1465] "Adjusting the display content" means changing the information and layout to be displayed according to the user's emotions and situation.

[1466] "Product recommendation" refers to proposing products that are likely to interest a user based on their past behavior and current emotions.

[1467] This invention relates to a system that uses a generative AI model to automatically generate a three-dimensional model based on product information found by a user on an e-commerce site, and combines it with an emotion engine to provide optimal augmented reality (AR) display and product recommendations based on the user's emotions.

[1468] System configuration

[1469] The system mainly consists of the following elements:

[1470] server

[1471] Device (smartphone, tablet, etc.)

[1472] Emotion Engine

[1473] URL receiving method

[1474] Product information acquisition means

[1475] Product information analysis means

[1476] 3D model generation means

[1477] Augmented reality data conversion means

[1478] Data transmission method

[1479] Data display means

[1480] Hardware and software used

[1481] Hardware:

[1482] A server is a computer with high-performance data processing capabilities.

[1483] The devices are smartphones or tablets equipped with cameras, microphones, and sensors.

[1484] software:

[1485] Python library BeautifulSoup (for scraping product information)

[1486] OpenCV (for analyzing image data)

[1487] Blender Python API (to generate 3D models using generative AI models)

[1488] Three.js (for converting augmented reality data to USDZ or GLTF format)

[1489] Microsoft Azure Emotion API (for emotion recognition)

[1490] ARKit (for displaying AR on devices)

[1491] Specific processing of the program

[1492] The user launches a dedicated application and enters the URL of the product they want to use in AR. The device receives the URL and sends it to the server using an HTTP request. The server then accesses the e-commerce site based on the received URL and obtains the product's image data and specifications using scraping or an API call.

[1493] The acquired product information is analyzed by the server. Format data (shape, color, texture information) is extracted from the image data, and dimensions and material information are analyzed from the spec information. The OpenCV library is used for the analysis.

[1494] Next, a generative AI model (e.g., Blender Python API) generates a 3D model based on the parsed data, which is then converted into a data format for AR display (e.g., USDZ or GLTF) using the Three.js library.

[1495] The converted augmented reality data is sent to the device by the server using HTTP responses or WebSockets. The device reads the received data with a dedicated application and displays the model in real space through the camera. For example, you can use your smartphone camera to see how a sofa would look in your living room.

[1496] The device also uses cameras, microphones, and other sensors to capture the user's facial expressions, voice, and gestures, and the emotion engine uses this data to recognize the user's emotions in real time. The emotion engine analyzes emotions using Microsoft Azure's Emotion API.

[1497] The emotion engine adjusts the display of the 3D model based on the recognized emotion: for example, if the user is anxious, it will show additional details or different perspectives, but if the user is satisfied, it will continue to display the model as is.

[1498] The emotion engine also recommends related products based on the recognized emotion, for example, if the user is enjoying something, it will show other products in the same category.

[1499] Examples of concrete examples and prompts

[1500] Example: Purchasing furniture

[1501] A user enters the URL of a sofa that catches their eye on an e-commerce site into a dedicated app. The device then sends this URL to the server via an HTTP request. The server then accesses the e-commerce site based on this URL and uses BeautifulSoup to collect images and dimensions of the sofa.

[1502] The server then uses OpenCV to analyze the images and extract shape, color, and texture information. A generative AI model (Blender Python API) uses this data to generate a realistic 3D model. The generated model is then converted to USDZ format using Three.js. The server then sends the converted data to the device, which then uses ARKit to overlay the 3D model of the sofa on the camera image.

[1503] Example prompt sentence:

[1504] "Generate a detailed 3D model of a sofa based on the following data:

[1505] Image data: [image_url]

[1506] Product dimensions: Height 80cm, width 200cm, depth 100cm

[1507] Material: Cloth

[1508] Color: Gray

[1509] "

[1510] In this way, users can view models of products that are close to the real thing, while receiving optimal information and product recommendations that correspond to their own emotions.

[1511] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1512] Step 1:

[1513] User operation (URL input)

[1514] The user launches the dedicated application and enters the URL of the product they want to convert into AR. Specifically, they paste the URL of the product page of a sofa they found on a furniture mail-order website into the input field.

[1515] Input: Product URL

[1516] Output: The entered product URL is saved on the device.

[1517] Step 2:

[1518] Device operation (URL sending)

[1519] The device sends the entered URL to the server as an HTTP request. At this time, the device sends a POST request including the URL to the server and delivers the data.

[1520] Input: Product URL entered by the user

[1521] Output: The product URL is sent to the server.

[1522] Step 3:

[1523] Server operation (collection of product information)

[1524] The server accesses the e-commerce site based on the received URL and retrieves the product's image data and specifications. This process can be done by scraping using Python's BeautifulSoup library or by using the API provided by the e-commerce site. Specifically, BeautifulSoup is used to extract the product image URL and dimensional information from the HTML document.

[1525] Input: Product URL

[1526] Output: Product image URL, dimensions, and other specifications

[1527] Step 4:

[1528] Server operation (analysis of product information)

[1529] The server analyzes the shape, color, and texture information from the image data based on the acquired product information, and extracts dimensions and material information from the spec information. This analysis uses the OpenCV library. For example, it performs edge detection on the image to identify the shape.

[1530] Input: URL of product image, dimensions, and other specifications

[1531] Output: Shape data, color data, texture data, dimension information, material information

[1532] Step 5:

[1533] Server operation (generation of 3D models)

[1534] The generative AI model installed on the server generates a 3D model of the product based on the analyzed data. Specifically, Blender's Python API is used to apply color and texture to the shape data to generate a realistic 3D model. The prompt text input to the generative AI is, "Please generate a detailed 3D model of a sofa based on the following data: image data, product size (height 80cm, width 200cm, depth 100cm), material (fabric), and color (gray)."

[1535] Input: Shape data, color data, texture data, dimension information, material information

[1536] Output: 3D model

[1537] Step 6:

[1538] Server operation (augmented reality data conversion)

[1539] The server converts the generated 3D model into augmented reality (AR) data. This process involves setting the coordinate system of the 3D model, adding AR markers, and exporting it to a specific format (USDZ or GLTF). Specifically, the Three.js library is used to export the 3D model into an AR-compatible data format.

[1540] Input: 3D model

[1541] Output: Augmented reality data (USDZ format or GLTF format)

[1542] Step 7:

[1543] Server operation (data transmission)

[1544] The server sends the converted augmented reality data to the device using an HTTP response or WebSocket. Specifically, when the device sends an HTTP request, the server returns the converted augmented reality data as an HTTP response.

[1545] Input: Augmented reality data

[1546] Output: Augmented reality data is sent to the device.

[1547] Step 8:

[1548] Terminal operation (displaying data)

[1549] The device reads the received augmented reality data using a dedicated application and displays a 3D model in real space. Specifically, it displays what the sofa would look like in the user's living room through the device's camera. For example, it uses ARKit to overlay a 3D model of the sofa on the camera image.

[1550] Input: Augmented reality data

[1551] Output: 3D model displayed in real space

[1552] Step 9:

[1553] Emotion engine operation (emotion recognition)

[1554] The device captures the user's facial expressions, voice, gestures, etc. through the camera, microphone, and other sensors, and the emotion engine recognizes the user's emotions in real time from this data. This emotion recognition is done using Microsoft Azure's Emotion API.

[1555] Input: User's facial expression data, voice data, gesture data

[1556] Output: User emotion data

[1557] Step 10:

[1558] Emotion engine operation (adjusting display content)

[1559] The emotion engine adjusts the display of the 3D model based on the user's perceived emotions, for example by adding more detailed information or showing different perspectives if the user is feeling anxious.

[1560] Input: User emotion data

[1561] Output: Adjusted display content

[1562] Step 11:

[1563] Emotion engine operation (product recommendation)

[1564] The emotion engine recommends related products based on the user's emotional data. For example, if the user enjoys a product, it will display other products in the same category. Specifically, it applies a recommendation algorithm based on the user's past preference data.

[1565] Input: User emotion data

[1566] Output: Related product recommendations

[1567] The above is the detailed program processing of this system, which allows users to check the appearance and placement of products in a realistic augmented reality model and receive optimal information and related product recommendations based on their own emotions.

[1568] (Application example 2)

[1569] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1570] Conventional e-commerce sites have the problem that it is difficult for users to form an image of the product they are considering purchasing that is similar to the actual product. Also, because product information is presented uniformly without considering the user's feelings, there are cases where the user experience is not sufficiently improved. In addition, the accuracy of product recommendations does not reflect the user's intentions, which is an issue that does not sufficiently stimulate the desire to purchase.

[1571] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1572] In this invention, the server includes means for receiving a URL entered by a user, means for acquiring product information based on the received URL, means for analyzing the product information and generating a three-dimensional model based on the analysis results, means for converting the generated three-dimensional model into augmented reality data, means for transmitting the augmented reality data to the user's terminal, means for recognizing the user's emotion and adjusting the display content of the three-dimensional model based on the recognized emotion, and means for recommending related products based on the user's emotion. This allows the user to view products in a manner close to the real thing, and enables optimal information presentation and product recommendations based on emotion.

[1573] - "URL receiving means" is a function that receives the URL entered by the user via the network.

[1574] The "product information acquisition means" is a function that acquires the necessary product information from a product database or website based on the received URL.

[1575] The "product information analysis means" is a function that analyzes the acquired product information and extracts the shape, color, texture, and the like.

[1576] The "three-dimensional model generating means" is a function that automatically generates a three-dimensional digital model based on analyzed product information.

[1577] The "augmented reality data conversion means" is a function that converts the generated three-dimensional model into a data format that can be displayed in AR.

[1578] The "data transmission means" is a function that transmits the converted augmented reality data to the user's terminal.

[1579] The "data display means" is a function that displays the received data as augmented reality on the user's terminal.

[1580] The "emotion recognition means" is a function that analyzes the user's facial expressions and voice to recognize the emotion at that time.

[1581] The "display adjustment means" is a function that adjusts the content and viewpoint of the displayed three-dimensional model based on the recognized user's emotions.

[1582] The "product recommendation means" is a function that recommends other related products to the user based on the user's emotional data.

[1583] The system of this invention generates a 3D model based on the product URL entered by the user and displays it in augmented reality (AR).It also has the ability to adjust the display content based on the user's emotions and recommend related products.

[1584] The server processes the URL received from the user and obtains product information based on that URL. The product information obtaining means collects images and specification information related to the product from a database or website. The product information analysis means then analyzes the obtained information and extracts shape, color, and texture information. Based on the results of this analysis, the 3D model generation means generates a digital 3D model of the product.

[1585] The generated three-dimensional model is converted into a format that can be displayed in AR (e.g., USDZ or GLTF format) by the augmented reality data conversion means. This converted data is transmitted to the user's terminal via the data transmission means. The received data is displayed as augmented reality by the user's terminal.

[1586] Furthermore, the emotion recognition means allows the user's device to analyze the user's facial expressions and voice to obtain emotion data. Based on the recognized emotion, the display adjustment means adjusts the display content and viewpoint of the three-dimensional model. For example, if the user is feeling anxious, a different viewpoint or additional information is displayed. Furthermore, based on the user's emotion data, the product recommendation means recommends related products. If the user finds the emotion engine to be fun, other products in the same category are displayed.

[1587] Hardware and software used

[1588] Hardware: Smartphone, smart glasses, head-mounted display (camera, sensor)

[1589] software:

[1590] EmotionRecognizer Library: Recognize user emotions

[1591] ARDisplay library: AR display of 3D models

[1592] HTTP request: Get product information

[1593] Generative AI model: 3D model generation

[1594] Specific examples

[1595] A user opens a smartphone app and enters the URL of a product they found on an e-commerce site. For example, if a user is considering purchasing furniture, they enter the URL of a sofa they are interested in into a dedicated app. The server retrieves product information based on the URL, and the generative AI model generates a 3D model using the following prompt:

[1596] Prompt: "Shape: square, Color: blue, Texture: fabric"

[1597] The generated 3D model is converted and sent to the user's smartphone, where it is displayed in real space through the camera. The user can see how the sofa would look in their living room. Furthermore, if the user looks happy at the camera, the emotion recognition means detects this and the product recommendation means displays other related furniture. For example, cushions or tables of the same color are recommended. This makes it easier for the user to make a purchase decision and allows them to check the product in a way that is close to the real thing in their own home.

[1598] Prompt Sentence Examples

[1599] "Shape: Square, Color: Blue, Texture: Fabric"

[1600] "Shape: Rectangle, Color: White, Texture: Wood Grain"

[1601] In this way, the invention improves the user experience and supports purchasing decisions.

[1602] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1603] Step 1:

[1604] The user launches the application and enters the URL of a product they found on an e-commerce site.

[1605] Input: Product URL

[1606] Output: The URL is saved on the user's device.

[1607] Specific operation: The user enters the product URL into the input field of the dedicated application.

[1608] Step 2:

[1609] The device sends the entered URL to the server.

[1610] Input: The URL entered by the user

[1611] Output: URL sent to server

[1612] Specific operation: The device sends a URL to the server using an HTTP request.

[1613] Step 3:

[1614] The server accesses the e-commerce site based on the URL and retrieves product information.

[1615] Input: User submitted URL

[1616] Output: Product image data and specifications

[1617] Specific operations: The server collects product information (images, shapes, colors, textures, dimensions, material information, etc.) through scraping technology or API calls.

[1618] Step 4:

[1619] The server analyzes the acquired product information and extracts the necessary data.

[1620] Input: Retrieved product information

[1621] Output: Analyzed shape, color, and texture information

[1622] Specific operation: Using product information analysis means, shape, color, and texture information are extracted from image data, and dimension and material information is extracted from specification information.

[1623] Step 5:

[1624] The server generates a three-dimensional model based on the analyzed data.

[1625] Input: Shape, color, texture information

[1626] Output: 3D model

[1627] How it works: Using a generative AI model, generate a 3D model based on the following prompt:

[1628] Prompt: "Shape: square, Color: blue, Texture: fabric"

[1629] Step 6:

[1630] The server converts the generated three-dimensional model into augmented reality data.

[1631] Input: 3D model

[1632] Output: Augmented reality data (e.g. USDZ format)

[1633] Specific operations: Using augmented reality data conversion means, the coordinate system of the model is set, AR markers are added, and export to a specific format.

[1634] Step 7:

[1635] The server transmits the converted augmented reality data to the terminal.

[1636] Input: Augmented reality data

[1637] Output: Augmented reality data sent to the device

[1638] Specific operation: Sends data to the user's device using an HTTP response or WebSocket.

[1639] Step 8:

[1640] The device displays the received augmented reality data.

[1641] Input: Augmented reality data

[1642] Output: 3D model displayed in real space

[1643] Specific operation: The device application displays augmented reality data in real space through the camera.

[1644] Step 9:

[1645] The device recognizes the user's emotions.

[1646] Input: User's facial expressions and voice data

[1647] Output: Recognized emotion data

[1648] Specific operation: Analyzes the user's emotions using the EmotionRecognizer library through the device's camera and microphone.

[1649] Step 10:

[1650] The server adjusts the display content of the three-dimensional model based on the emotion.

[1651] Input: Recognized emotion data

[1652] Output: Adjusted display content

[1653] Specific operation: Based on the emotion data, the display adjustment means adjusts the display viewpoint and detailed information of the three-dimensional model.

[1654] Step 11:

[1655] The server recommends related products based on the user's emotions.

[1656] Input: Recognized emotion data

[1657] Output: Recommended related products

[1658] Specific operation: Using the emotion engine, other related products are selected and displayed based on the user's emotion data.

[1659] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1660] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1661] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1662] [Fourth embodiment]

[1663] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1664] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1665] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1666] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1667] 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.

[1668] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1669] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1670] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1671] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1672] 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.

[1673] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1674] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1675] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1676] This invention relates to a system that uses generative AI to automatically generate 3D models based on product information found by users on an e-commerce site, enabling real-time augmented reality (AR) display. The program processing of this system is explained below.

[1677] System configuration

[1678] The system mainly consists of the following elements:

[1679] URL receiving method

[1680] Product information acquisition means

[1681] Product information analysis means

[1682] 3D model generation means

[1683] Augmented reality data conversion means

[1684] Data transmission method

[1685] Data display means

[1686] Program processing

[1687] User operations

[1688] 1. Enter the URL

[1689] The user launches the dedicated application and enters the URL of the product they want to convert into AR. By doing this, the user prepares to view the product in detail at home.

[1690] Device behavior

[1691] 2. Sending the URL

[1692] The device sends the URL entered by the user to the server, usually via an HTTP request.

[1693] Server Operation

[1694] 3. Collecting product information

[1695] The server accesses the e-commerce site based on the URL and collects image data and specifications of the relevant product. This collection can be done using scraping technology or API.

[1696] 4. Product information analysis

[1697] The server analyzes the collected product information, analyzing shape, color, and texture information from image data, and extracting dimensions and material information from spec information.

[1698] 5. 3D Model Generation

[1699] Based on the analyzed data, generative AI generates a 3D model of the product, which applies color and texture to the geometric data to create a realistic model.

[1700] 6. Augmented Reality Data Conversion

[1701] The server converts the generated 3D model into augmented reality data, a process that includes setting the coordinates of the model, adding AR markers, and exporting it to a specific format (e.g., USDZ or GLTF).

[1702] 7. Data transmission

[1703] The server sends the converted augmented reality data to the device using HTTP responses or WebSockets.

[1704] Device behavior

[1705] 8. Displaying Data

[1706] The device reads the received augmented reality data using a dedicated application and displays a 3D model in real space through the device's camera, allowing the user to see the product as if it were actually placed in that location.

[1707] Specific examples

[1708] Furniture purchase example

[1709] 1. User Operation

[1710] The user enters the URL of a sofa that catches their eye on an e-commerce site into a dedicated app.

[1711] 2. Send URL

[1712] The device sends this URL to the server.

[1713] 3. Information gathering

[1714] The server accesses the e-commerce site based on this URL and collects images and dimensions of the sofa.

[1715] 4. Data Analysis

[1716] The server analyzes the sofa's shape, color, and texture information from the image and extracts its dimensions and material information.

[1717] 5. Model Generation

[1718] The 3D model generation AI uses this data to generate a realistic 3D model of the sofa.

[1719] 6. Data Conversion

[1720] The server converts the generated model into augmented reality data (e.g., USDZ format).

[1721] 7. Data Transmission

[1722] The server transmits this augmented reality data to the terminal.

[1723] 8. Data Display

[1724] The device loads the augmented reality data into the app and displays, via the camera, what the sofa would look like in the user's living room.

[1725] In this way, users can see exactly how the sofa will look and feel in their home, which will make purchasing decisions easier and is expected to lead to increased sales on e-commerce sites.

[1726] The processing flow will be explained below.

[1727] Step 1:

[1728] The user launches the dedicated app and enters the URL of the product they want to convert into AR, which inserts the URL into the input field within the app.

[1729] Step 2:

[1730] The device sends the entered URL to the server using an HTTP request.

[1731] Step 3:

[1732] The server accesses the e-commerce site based on the received URL and obtains product image data and specifications using scraping technology or API calls.

[1733] Step 4:

[1734] The server analyzes the acquired product information, extracting shape, color, and texture information from the image data, and analyzing and extracting dimensions and material information from the specification information.

[1735] Step 5:

[1736] The server-based generative AI generates a 3D model of the product based on the analyzed data. First, it creates a 3D mesh based on the shape information, and then applies color and texture information to the model.

[1737] Step 6:

[1738] The server converts the generated 3D model into augmented reality data by setting the model's coordinate system, adding appropriate AR markers, and exporting it to a specific format (e.g., USDZ or GLTF).

[1739] Step 7:

[1740] The server sends the generated augmented reality data to the device using HTTP responses or WebSockets.

[1741] Step 8:

[1742] The device then loads the received augmented reality data into a dedicated app, which uses the data to display a 3D model in real space through the device's camera.

[1743] Step 9:

[1744] The user operates the device to check how the 3D model will look in the location where they want to place the product, and then rotates, moves, scales, and performs other operations on the model to simulate the optimal placement.

[1745] Example 1

[1746] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1747] In recent years, many users have begun to purchase products via the Internet, and purchasing activities on e-commerce sites have become increasingly popular. However, it is difficult for users to fully grasp the actual size and appearance of a product from online product images and descriptions alone, which often makes it difficult to make a purchasing decision. In particular, for products such as furniture and decorative items, where it is not clear whether they will fit in a particular space until they are actually placed, it is often discovered after purchase that the product does not meet expectations, resulting in frequent returns and exchanges, which is inefficient for companies. To solve these problems, there is a need for a system that allows users to check the actual placement and appearance of products at home in real time.

[1748] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1749] In this invention, the server includes means for receiving a URL entered by a user, means for acquiring product information based on the received URL, means for analyzing the product information and generating a three-dimensional model based on the analysis result, means for converting the generated three-dimensional model into augmented reality data, means for transmitting the augmented reality data to a user's terminal, and means for displaying the augmented reality data on the user's terminal. This allows users to place products they find on an e-commerce site in their home or other physical space in real time via a dedicated application, allowing them to intuitively check the size and appearance of the products and making it easier for them to make a purchasing decision.

[1750] The "URL receiving means" is a means for receiving a URL entered by a user.

[1751] The "product information acquisition means" is a means for accessing the EC site based on the received URL and acquiring information about the product.

[1752] The "product information analysis means" is a means for analyzing the acquired product information and extracting shape, color, and texture information.

[1753] The "three-dimensional model generating means" is a means for generating a three-dimensional model of a product based on the analysis results.

[1754] The "augmented reality data conversion means" is a means for converting the generated three-dimensional model into augmented reality data.

[1755] The "data transmission means" is a means for transmitting the converted augmented reality data to the user's terminal.

[1756] "Data display means" refers to means for displaying augmented reality data received by a user's terminal.

[1757] An "image analysis algorithm" is an algorithm for analyzing image data from product information and extracting shape, color, and texture information.

[1758] A "prompt statement" is an instruction statement to be input into a generative AI model, and includes information for generating a three-dimensional model based on the analysis results.

[1759] Overall system configuration

[1760] The system of this invention uses generative AI to automatically generate 3D models based on product information found by users on an e-commerce site, enabling real-time augmented reality (AR) display. It mainly consists of the following elements:

[1761] URL receiving method

[1762] Product information acquisition means

[1763] Product information analysis means

[1764] 3D model generation means

[1765] Augmented reality data conversion means

[1766] Data transmission method

[1767] Data display means

[1768] Details of each element

[1769] URL receiving method

[1770] This is a means of receiving a URL entered by the user into a dedicated application. For example, the user enters the URL of a sofa they found on an e-commerce site. This identifies the specific product to be displayed in AR.

[1771] Product information acquisition means

[1772] The device sends the received URL to the server. The server accesses the e-commerce site based on that URL and retrieves product information. Specifically, it uses a scraping tool (e.g., BeautifulSoup, Selenium) or API to collect image data from the product page, as well as specifications such as dimensions and materials.

[1773] Product information analysis means

[1774] The server analyzes the acquired product information. In this process, image analysis libraries (e.g., OpenCV, TensorFlow) are used to extract shape, color, and texture information from the image data. Specifications (dimensions and materials) are also analyzed at the same time, and the data necessary to generate a 3D model is prepared.

[1775] 3D model generation means

[1776] Based on the analyzed data, a generative AI model generates a 3D model of the product. Examples of generative AI models used include DALL-E and GAN (Generative Adversarial Network). The generated 3D model applies color and texture to the shape data, allowing it to be displayed as a realistic model.

[1777] Specific examples of prompts are as follows:

[1778] "Create a realistic 3D model using the images and specifications of the following products.

[1779] Image URL: [Image URL]

[1780] Specification information:

[1781] Dimensions: Width [xx] cm, Height [xx] cm, Depth [xx] cm

[1782] Material: [Material information]

[1783] Color: [Color information]

[1784] Please use USDZ format for the output format.

[1785] Augmented reality data conversion means

[1786] The generated 3D model is converted into augmented reality data. This conversion process involves setting the coordinates of the model, adding AR markers, and exporting it to a specific format (e.g., USDZ, GLTF). This can be done using a 3D modeling tool (e.g., Blender, Unity) or a conversion library.

[1787] Data transmission method

[1788] The converted augmented reality data is sent to the device using HTTP responses or WebSockets. The server properly packets the data and sends it to the device.

[1789] Data display means

[1790] The device reads the received augmented reality data using a dedicated application, which allows the device to display a three-dimensional model in real space through the camera. AR display uses ARKit (iOS) or ARCore (Android).

[1791] Example of operation

[1792] Furniture purchase example

[1793] A user enters the URL of a sofa they find interesting on an e-commerce site into a dedicated app. The device then sends the URL as an HTTP request to the server. The server then accesses the e-commerce site using this URL and collects the sofa's image data and dimensions. The collected data is analyzed using an image analysis library to extract shape, color, and texture information. Based on the analysis results, a generative AI model generates a 3D model, which the server then converts into augmented reality data in USDZ format. The server then sends the converted data to the device, which then displays the AR image, allowing the user to see in real time how the sofa will look in their living room.

[1794] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1795] Step 1:

[1796] The user launches the dedicated application and enters the URL of the product they want to create in AR. This operation allows the user to provide specific information about the product. The entered URL becomes the input for the next processing step.

[1797] Step 2:

[1798] The terminal sends the URL entered by the user to the server. The transmission is done via an HTTP request. This request contains the URL entered by the user. The output of the terminal is the URL transmission data to the server.

[1799] Step 3:

[1800] The server accesses the e-commerce site based on the received URL. The server uses a scraping tool (e.g., BeautifulSoup or Selenium) or an API to collect product information. Specifically, it obtains image data and specification information (dimensions, material, color, etc.). The input for this step is the sent URL, and the output is the collected product information.

[1801] Step 4:

[1802] The server analyzes the collected product information. It extracts shape, color, and texture information from image data, and analyzes dimensions and materials from spec information. This process uses an image analysis library (e.g., OpenCV or TensorFlow). The input is the collected product information, and the output is the analyzed product information.

[1803] Step 5:

[1804] The server then inputs prompts into the generative AI model based on the analyzed data to generate a 3D model of the product. The generative AI models used include DALL-E and GAN. Specific examples of prompts are as follows:

[1805] "Create a realistic 3D model using the images and specifications of the following products.

[1806] Image URL: [Image URL]

[1807] Specification information:

[1808] Dimensions: Width [xx] cm, Height [xx] cm, Depth [xx] cm

[1809] Material: [Material information]

[1810] Color: [Color information]

[1811] Please use USDZ format for the output format.

[1812] The input is analyzed product information, and the output is generated 3D model data.

[1813] Step 6:

[1814] The server converts the generated 3D model into augmented reality data (e.g., USDZ format). This conversion involves setting the coordinates of the model, adding AR markers, and exporting it to a specific format. The input is the 3D model data generated by the generative AI model, and the output is the converted augmented reality data.

[1815] Step 7:

[1816] The server then sends the converted augmented reality data to the device, using HTTP responses or WebSockets. The server's output is packets of augmented reality data sent to the user's device.

[1817] Step 8:

[1818] The device reads the received augmented reality data using a dedicated application. A three-dimensional model is displayed in real space through the device's camera. This allows the user to see the product as if it were actually placed in that location. The input is the augmented reality data sent from the server, and the output is the displayed three-dimensional model.

[1819] Specific examples

[1820] For example, a user enters the URL of a sofa they found on an e-commerce site, and their device sends the URL to a server. The server collects product information based on the URL and analyzes image data and dimensions. A generative AI model generates a 3D model and converts it into USDZ format. The data is then sent to the device and loaded into a dedicated application, allowing the user to see how the sofa would look in their living room.

[1821] (Application example 1)

[1822] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1823] With conventional food delivery services, it was difficult for users to check in advance what the food they were ordering would actually look like. This created a gap between the actual food and the photos on the delivery site, which led to a decrease in user satisfaction. Furthermore, there were cases where users hesitated to order because they lacked the visual information necessary to decide whether to order or not.

[1824] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1825] In this invention, the server includes means for receiving a URL entered by a user, means for acquiring product information based on the received URL, means for analyzing the product information and generating a three-dimensional model based on the analysis results, means for converting the generated three-dimensional model into augmented reality data, means for transmitting the augmented reality data to a user's terminal, means for displaying the augmented reality data on the user's terminal, and means for generating a three-dimensional model based on food information collected from a food delivery site and displaying it in augmented reality, thereby enabling users to check the actual appearance of food in augmented reality before delivery.

[1826] "URL receiving means" refers to a device or method that has the function of receiving a URL entered by a user.

[1827] The "product information acquisition means" refers to a device or method that has the function of collecting data about products based on the received URL.

[1828] "Product information analysis means" refers to a device or method that has the function of analyzing acquired product information and extracting necessary data.

[1829] The "three-dimensional model generating means" refers to a device or method that has the function of generating a three-dimensional model of a product based on the analysis results.

[1830] The "augmented reality data conversion means" refers to a device or method that has the function of converting the generated three-dimensional model into a data format that can be used as augmented reality content.

[1831] "Data transmission means" refers to a device or method that has the function of transmitting the converted augmented reality data to the user's terminal.

[1832] "Data display means" refers to a device or method that has the function of displaying augmented reality data on a user's terminal.

[1833] A "food delivery site" is a website or application that allows users to order food online.

[1834] "Food information" refers to data such as images and descriptions of dishes posted on food delivery sites.

[1835] "Augmented reality display means" refers to a device or method that has the function of displaying three-dimensionally modeled food information superimposed on the real world.

[1836] This invention relates to a system that uses augmented reality (AR) to display the actual food a user is considering ordering when using a food delivery service. Specifically, when a user inputs the URL of a food item, the system acquires and analyzes food information based on the URL, generates a three-dimensional model of the food, and converts it into AR data for display.

[1837] System configuration

[1838] The system mainly consists of the following elements:

[1839] URL receiving method

[1840] Product information acquisition means

[1841] Product information analysis means

[1842] 3D model generation means

[1843] Augmented reality data conversion means

[1844] Data transmission method

[1845] Data display means

[1846] Food delivery site

[1847] Food Information

[1848] Augmented reality display means

[1849] Program processing explanation

[1850] User operations

[1851] 1. Enter the URL

[1852] The user launches the dedicated application and enters the URL of the dish they are considering ordering. By doing this, the user arranges to check the appearance of the dish in detail.

[1853] Device behavior

[1854] 2. Sending the URL

[1855] The device sends the URL entered by the user to the server, usually via an HTTP request.

[1856] Server Operation

[1857] 3. Collecting product information

[1858] The server accesses the food delivery site based on the URL and collects image data and specifications of the corresponding dishes using scraping technology or API.

[1859] 4. Product information analysis

[1860] The server analyzes the collected food information, analyzing shape, color, and texture information from image data, and extracting dimensions and ingredient information from spec information.

[1861] 5. 3D Model Generation

[1862] Based on the analyzed data, the generative AI generates a 3D model of the dish, which applies color and texture to the geometric data to create a realistic model.

[1863] 6. Augmented Reality Data Conversion

[1864] The server converts the generated 3D model into augmented reality data, a process that includes setting the coordinates of the model, adding AR markers, and exporting it to a specific format (e.g., USDZ or GLTF).

[1865] 7. Data transmission

[1866] The server sends the converted augmented reality data to the device using HTTP responses or WebSockets.

[1867] Device behavior

[1868] 8. Displaying Data

[1869] The device reads the received augmented reality data using a dedicated application and displays a 3D model in real space through the device's camera, allowing the user to see the food as if it were actually placed in that location.

[1870] Examples of concrete examples and prompts

[1871] Sushi plate ordering example

[1872] 1. User Operation

[1873] Users enter the URL of a sushi plate they are interested in on a food delivery site into a dedicated app.

[1874] 2. Send URL

[1875] The device sends this URL to the server.

[1876] 3. Information gathering

[1877] The server accesses the food delivery site based on this URL and collects images and specifications of the sushi plates.

[1878] 4. Data Analysis

[1879] The server analyzes the shape, color, and texture information of the sushi plate from the image and extracts information about its dimensions and ingredients.

[1880] 5. Model Generation

[1881] The 3D model generation AI uses this data to generate a realistic 3D model of the sushi plate.

[1882] 6. Data Conversion

[1883] The server converts the generated model into augmented reality data (e.g., USDZ format).

[1884] 7. Data Transmission

[1885] The server transmits this augmented reality data to the terminal.

[1886] 8. Data Display

[1887] The device loads the augmented reality data into the app, which uses the camera to show what the sushi plate will look like at the user's table.

[1888] Example prompt sentence:

[1889] text

[1890] Generate a 3D model of a sushi plate. Get the image data and dimensions from the following URL: http: / / example.com / sushi-plate

[1891] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1892] Step 1:

[1893] The user launches the dedicated application and enters the URL of the dish they are considering ordering. The entered URL is saved in an input field in the application. This URL becomes the key to obtain detailed information about the dish.

[1894] Step 2:

[1895] The terminal sends the URL entered by the user to the server. This process is done through an HTTP request. The input is the URL entered by the user, and the output is the request sent to the server.

[1896] Step 3:

[1897] The server receives the URL and accesses the food delivery site based on that URL. The server uses this URL to collect image data and specifications for the corresponding dish using scraping technology or an API. The input is the received URL, and the output is image data and specifications for the dish.

[1898] Step 4:

[1899] The server analyzes the collected food information. In this analysis, the shape, color, and texture information of the food is extracted from the image data, and data such as dimensions and ingredients is extracted from the specification information. The input is the image data and specification information, and the output is the analysis results: shape data, color data, texture data, and dimension data.

[1900] Step 5:

[1901] The server generates a 3D model of the dish based on the analysis results. This process involves using a generative AI model to create a realistic 3D model. The input is shape data, color data, texture data, and dimension data, and the output is a 3D model.

[1902] Step 6:

[1903] The server converts the generated 3D model into augmented reality data. This conversion process includes setting the coordinates of the model, adding AR markers, and exporting it to a specific format (e.g., USDZ or GLTF). The input is the 3D model, and the output is the augmented reality data.

[1904] Step 7:

[1905] The server sends the augmented reality data to the device. This transmission process uses HTTP responses and WebSockets. The input is the augmented reality data, and the output is the data transmission to the device.

[1906] Step 8:

[1907] The device reads the received augmented reality data with a dedicated application and uses that data to display a 3D model in real space through the camera. The input is the augmented reality data, and the output is an augmented reality view of the food displayed on the user's display. The user can see the food as if it were actually placed in that location, which helps them make ordering decisions.

[1908] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1909] This invention relates to a system that uses generative AI to automatically generate 3D models based on product information found by a user on an e-commerce site, and combines this with an emotion engine to provide optimal augmented reality (AR) display and product recommendations based on the user's emotions. The program processing of this system is explained below.

[1910] System configuration

[1911] The system mainly consists of the following elements:

[1912] URL receiving method

[1913] Product information acquisition means

[1914] Product information analysis means

[1915] 3D model generation means

[1916] Augmented reality data conversion means

[1917] Data transmission method

[1918] Data display means

[1919] Emotion Engine

[1920] Program processing

[1921] User operations

[1922] 1. Enter the URL

[1923] The user launches the dedicated application and enters the URL of the product they want to convert into AR, which is then inserted into an input field within the application.

[1924] Device behavior

[1925] 2. Sending the URL

[1926] The device sends the entered URL to the server using an HTTP request.

[1927] Server Operation

[1928] 3. Collecting product information

[1929] The server accesses the e-commerce site based on the URL and retrieves product image data and specifications. This information is collected using scraping technology or API calls.

[1930] 4. Product information analysis

[1931] The server analyzes the acquired product information, extracting shape, color, and texture information from the image data, and analyzing and extracting dimensions and material information from the specification information.

[1932] 5. 3D Model Generation

[1933] The server-based generative AI generates a 3D model of the product based on the analyzed data, applying color and texture to the shape data to create a realistic model.

[1934] 6. Augmented Reality Data Conversion

[1935] The server converts the generated 3D model into augmented reality data, a process that includes setting the coordinate system of the model, adding AR markers, and exporting it to a specific format (e.g., USDZ or GLTF).

[1936] 7. Data transmission

[1937] The server sends the converted augmented reality data to the device using HTTP responses or WebSockets.

[1938] Device behavior

[1939] 8. Displaying Data

[1940] The device reads the received augmented reality data using a dedicated application and displays a three-dimensional model in real space through the device's camera, making the product appear as if it were actually placed in that location.

[1941] Emotion Engine Operation

[1942] 9. Emotional Recognition

[1943] The device captures the user's facial expressions, voice, gestures, etc. through cameras, microphones, and other sensors, and recognizes the user's emotions in real time from this data.

[1944] 10. Emotion-Based Display Adjustment

[1945] The emotion engine adjusts the display of the 3D model based on the user's emotions. For example, if the user is satisfied, the display will continue as is, but if the user is anxious, a different perspective or information will be added.

[1946] 11. Emotion-Based Product Recommendations

[1947] The emotion engine recommends related products based on the user's emotional data. For example, if a user is interested in and enjoys a particular product, it will recommend other products in the same category.

[1948] Specific examples

[1949] Furniture purchase example

[1950] 1. User Operation

[1951] The user enters the URL of a sofa that interests them on an e-commerce site into a dedicated app.

[1952] 2. Send URL

[1953] The terminal sends this URL to the server in an HTTP request.

[1954] 3. Information gathering

[1955] The server accesses the e-commerce site based on this URL and collects images and dimensions of the sofa.

[1956] 4. Data Analysis

[1957] The server analyzes the sofa's shape, color, and texture information from the image and extracts its dimensions and material information.

[1958] 5. Model Generation

[1959] The 3D model generation AI uses this data to generate a realistic 3D model of the sofa.

[1960] 6. Data Conversion

[1961] The server converts the generated model into augmented reality data (e.g., USDZ format).

[1962] 7. Data Transmission

[1963] The server transmits this augmented reality data to the terminal.

[1964] 8. Data Display

[1965] The device loads the augmented reality data into the app and displays, via the camera, what the sofa would look like in the user's living room.

[1966] 9. Emotional Recognition

[1967] The device acquires emotional data from the user's facial expressions and voice, and the emotion engine analyzes this to recognize the user's emotions.

[1968] 10. Display adjustment

[1969] The emotion engine adjusts the display of the 3D model based on the user's emotions: if the user is feeling anxious, it will show more details or a different perspective.

[1970] 11. Product Recommendations

[1971] The emotion engine will recommend other products in similar categories based on the user's emotional data, for example, if they are having fun, it will show other related sofas and furniture.

[1972] In this way, users can view realistic models of products at home and receive optimal information and recommendations based on their own emotions, which will facilitate purchasing decisions and contribute to increased sales on e-commerce sites.

[1973] The processing flow will be explained below.

[1974] Step 1:

[1975] The user launches the app and enters the URL of the product they are considering purchasing, which is then inserted into an input field within the app.

[1976] Step 2:

[1977] The terminal sends the input URL to the server using an HTTP request, and the server receives the URL.

[1978] Step 3:

[1979] The server accesses the corresponding e-commerce site based on the received URL and collects product information. Specifically, it obtains product image data and specifications (e.g., dimensions, material, price, etc.). This is done using scraping technology or API calls.

[1980] Step 4:

[1981] The server analyzes the acquired product information. Specifically, it analyzes shape, color, and texture information from the image data, and extracts dimensions and material information from the specification information. This analysis provides the basic data for generating a 3D model.

[1982] Step 5:

[1983] The server-based generative AI generates a 3D model of the product based on the analyzed data, first creating a 3D mesh based on the shape information, and then applying color and texture information to the model.

[1984] Step 6:

[1985] The server converts the generated 3D model into augmented reality data by setting the model's coordinate system, adding appropriate AR markers, and exporting it to a specific format (e.g., USDZ or GLTF).

[1986] Step 7:

[1987] The server sends the generated augmented reality data to the device using an HTTP response or WebSocket, and the device receives the augmented reality data.

[1988] Step 8:

[1989] The device then loads the received augmented reality data into a dedicated app, and the user can use the device's camera to display a 3D model in real space and check how the product will look when installed.

[1990] Step 9:

[1991] The device captures the user's facial expressions, voice, gestures, etc. through cameras, microphones, and other sensors, and sends this data to an emotion engine to recognize the user's emotions in real time.

[1992] Step 10:

[1993] The emotion engine analyzes the acquired data and recognizes the user's emotional state, for example, determining whether the user is surprised or feeling happy.

[1994] Step 11:

[1995] The emotion engine adjusts the display of the 3D model based on the user's perceived emotions, for example, providing more information or different perspectives to reassure the user if they are feeling anxious.

[1996] Step 12:

[1997] The emotion engine recommends related products based on emotion data. For example, if a user shows a strong interest in a particular product, it will also display and recommend other products in the same category or similar.

[1998] Step 13:

[1999] The user operates the device to check the provided information and recommended products and consider purchasing them. The user can rotate, scale, move, and perform other operations to simulate the optimal arrangement.

[2000] Example 2

[2001] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2002] On conventional e-commerce sites, users cannot see the actual product before purchasing it, which often leads to problems after purchase, such as the product's size or appearance being different from what they expected. Furthermore, conventional systems do not provide services that take user emotions into consideration, which can lead to a poor user experience. This leads to low user satisfaction and makes it difficult to increase sales on e-commerce sites.

[2003] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[2004] In this invention, the server includes means for receiving a URL entered by a user, means for acquiring product information, means for analyzing the acquired information to generate a three-dimensional model, means for converting the generated three-dimensional model into augmented reality data, means for transmitting the augmented reality data to a terminal, means for recognizing emotions, means for adjusting the display based on the recognized emotions, and means for recommending related products. This allows the user to see an AR display of the product that is close to the real thing, and further allows the user to receive optimal information and product recommendations based on their emotions.

[2005] "URL" stands for Uniform Resource Locator and is a symbol that indicates the location of a resource on the Web.

[2006] "Product information" refers to information about the characteristics and features of a product, such as product images, specifications, dimensions, materials, and colors.

[2007] A "three-dimensional model" is a three-dimensional digital representation generated based on product information, which realistically reproduces the appearance and shape of the product.

[2008] "Augmented reality data" is data used to overlay a three-dimensional model onto real space, and is usually converted into a specific format (e.g., USDZ format or GLTF format).

[2009] A "server" is a computer system that receives requests from users, processes the necessary data, and sends it to terminals.

[2010] A "terminal" is a device used by a user, including a smartphone, tablet, etc.

[2011] An "emotion engine" is a system that recognizes emotions from a user's facial expressions, voice, gestures, etc., and provides information based on those emotions.

[2012] "Perception" is the use of sensors and algorithms to determine specific information or conditions.

[2013] "Adjusting the display content" means changing the information and layout to be displayed according to the user's emotions and situation.

[2014] "Product recommendation" refers to proposing products that are likely to interest a user based on their past behavior and current emotions.

[2015] This invention relates to a system that uses a generative AI model to automatically generate a three-dimensional model based on product information found by a user on an e-commerce site, and combines it with an emotion engine to provide optimal augmented reality (AR) display and product recommendations based on the user's emotions.

[2016] System configuration

[2017] The system mainly consists of the following elements:

[2018] server

[2019] Device (smartphone, tablet, etc.)

[2020] Emotion Engine

[2021] URL receiving method

[2022] Product information acquisition means

[2023] Product information analysis means

[2024] 3D model generation means

[2025] Augmented reality data conversion means

[2026] Data transmission method

[2027] Data display means

[2028] Hardware and software used

[2029] Hardware:

[2030] A server is a computer with high-performance data processing capabilities.

[2031] The devices are smartphones or tablets equipped with cameras, microphones, and sensors.

[2032] software:

[2033] Python library BeautifulSoup (for scraping product information)

[2034] OpenCV (for analyzing image data)

[2035] Blender Python API (to generate 3D models using generative AI models)

[2036] Three.js (for converting augmented reality data to USDZ or GLTF format)

[2037] Microsoft Azure Emotion API (for emotion recognition)

[2038] ARKit (for displaying AR on devices)

[2039] Specific processing of the program

[2040] The user launches a dedicated application and enters the URL of the product they want to use in AR. The device receives the URL and sends it to the server using an HTTP request. The server then accesses the e-commerce site based on the received URL and obtains the product's image data and specifications using scraping or an API call.

[2041] The acquired product information is analyzed by the server. Format data (shape, color, texture information) is extracted from the image data, and dimensions and material information are analyzed from the spec information. The OpenCV library is used for the analysis.

[2042] Next, a generative AI model (e.g., Blender Python API) generates a 3D model based on the parsed data, which is then converted into a data format for AR display (e.g., USDZ or GLTF) using the Three.js library.

[2043] The converted augmented reality data is sent to the device by the server using HTTP responses or WebSockets. The device reads the received data with a dedicated application and displays the model in real space through the camera. For example, you can use your smartphone camera to see how a sofa would look in your living room.

[2044] The device also uses cameras, microphones, and other sensors to capture the user's facial expressions, voice, and gestures, and the emotion engine uses this data to recognize the user's emotions in real time. The emotion engine analyzes emotions using Microsoft Azure's Emotion API.

[2045] The emotion engine adjusts the display of the 3D model based on the recognized emotion: for example, if the user is anxious, it will show additional details or different perspectives, but if the user is satisfied, it will continue to display the model as is.

[2046] The emotion engine also recommends related products based on the recognized emotion, for example, if the user is enjoying something, it will show other products in the same category.

[2047] Examples of concrete examples and prompts

[2048] Example: Purchasing furniture

[2049] A user enters the URL of a sofa that catches their eye on an e-commerce site into a dedicated app. The device then sends this URL to the server via an HTTP request. The server then accesses the e-commerce site based on this URL and uses BeautifulSoup to collect images and dimensions of the sofa.

[2050] The server then uses OpenCV to analyze the images and extract shape, color, and texture information. A generative AI model (Blender Python API) uses this data to generate a realistic 3D model. The generated model is then converted to USDZ format using Three.js. The server then sends the converted data to the device, which then uses ARKit to overlay the 3D model of the sofa on the camera image.

[2051] Example prompt sentence:

[2052] "Generate a detailed 3D model of a sofa based on the following data:

[2053] Image data: [image_url]

[2054] Product dimensions: Height 80cm, width 200cm, depth 100cm

[2055] Material: Cloth

[2056] Color: Gray

[2057] "

[2058] In this way, users can view models of products that are close to the real thing, while receiving optimal information and product recommendations that correspond to their own emotions.

[2059] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2060] Step 1:

[2061] User operation (URL input)

[2062] The user launches the dedicated application and enters the URL of the product they want to convert into AR. Specifically, they paste the URL of the product page of a sofa they found on a furniture mail-order website into the input field.

[2063] Input: Product URL

[2064] Output: The entered product URL is saved on the device.

[2065] Step 2:

[2066] Device operation (URL sending)

[2067] The device sends the entered URL to the server as an HTTP request. At this time, the device sends a POST request including the URL to the server and delivers the data.

[2068] Input: Product URL entered by the user

[2069] Output: The product URL is sent to the server.

[2070] Step 3:

[2071] Server operation (collection of product information)

[2072] The server accesses the e-commerce site based on the received URL and retrieves the product's image data and specifications. This process can be done by scraping using Python's BeautifulSoup library or by using the API provided by the e-commerce site. Specifically, BeautifulSoup is used to extract the product image URL and dimensional information from the HTML document.

[2073] Input: Product URL

[2074] Output: Product image URL, dimensions, and other specifications

[2075] Step 4:

[2076] Server operation (analysis of product information)

[2077] The server analyzes the shape, color, and texture information from the image data based on the acquired product information, and extracts dimensions and material information from the spec information. This analysis uses the OpenCV library. For example, it performs edge detection on the image to identify the shape.

[2078] Input: URL of product image, dimensions, and other specifications

[2079] Output: Shape data, color data, texture data, dimension information, material information

[2080] Step 5:

[2081] Server operation (generation of 3D models)

[2082] The generative AI model installed on the server generates a 3D model of the product based on the analyzed data. Specifically, Blender's Python API is used to apply color and texture to the shape data to generate a realistic 3D model. The prompt text input to the generative AI is, "Please generate a detailed 3D model of a sofa based on the following data: image data, product size (height 80cm, width 200cm, depth 100cm), material (fabric), and color (gray)."

[2083] Input: Shape data, color data, texture data, dimension information, material information

[2084] Output: 3D model

[2085] Step 6:

[2086] Server operation (augmented reality data conversion)

[2087] The server converts the generated 3D model into augmented reality (AR) data. This process involves setting the coordinate system of the 3D model, adding AR markers, and exporting it to a specific format (USDZ or GLTF). Specifically, the Three.js library is used to export the 3D model into an AR-compatible data format.

[2088] Input: 3D model

[2089] Output: Augmented reality data (USDZ format or GLTF format)

[2090] Step 7:

[2091] Server operation (data transmission)

[2092] The server sends the converted augmented reality data to the device using an HTTP response or WebSocket. Specifically, when the device sends an HTTP request, the server returns the converted augmented reality data as an HTTP response.

[2093] Input: Augmented reality data

[2094] Output: Augmented reality data is sent to the device.

[2095] Step 8:

[2096] Terminal operation (displaying data)

[2097] The device reads the received augmented reality data using a dedicated application and displays a 3D model in real space. Specifically, it displays what the sofa would look like in the user's living room through the device's camera. For example, it uses ARKit to overlay a 3D model of the sofa on the camera image.

[2098] Input: Augmented reality data

[2099] Output: 3D model displayed in real space

[2100] Step 9:

[2101] Emotion engine operation (emotion recognition)

[2102] The device captures the user's facial expressions, voice, gestures, etc. through the camera, microphone, and other sensors, and the emotion engine recognizes the user's emotions in real time from this data. This emotion recognition is done using Microsoft Azure's Emotion API.

[2103] Input: User's facial expression data, voice data, gesture data

[2104] Output: User emotion data

[2105] Step 10:

[2106] Emotion engine operation (adjusting display content)

[2107] The emotion engine adjusts the display of the 3D model based on the user's perceived emotions, for example by adding more detailed information or showing different perspectives if the user is feeling anxious.

[2108] Input: User emotion data

[2109] Output: Adjusted display content

[2110] Step 11:

[2111] Emotion engine operation (product recommendation)

[2112] The emotion engine recommends related products based on the user's emotional data. For example, if the user enjoys a product, it will display other products in the same category. Specifically, it applies a recommendation algorithm based on the user's past preference data.

[2113] Input: User emotion data

[2114] Output: Related product recommendations

[2115] The above is the detailed program processing of this system, which allows users to check the appearance and placement of products in a realistic augmented reality model and receive optimal information and related product recommendations based on their own emotions.

[2116] (Application example 2)

[2117] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2118] Conventional e-commerce sites have the problem that it is difficult for users to form an image of the product they are considering purchasing that is similar to the actual product. Also, because product information is presented uniformly without considering the user's feelings, there are cases where the user experience is not sufficiently improved. In addition, the accuracy of product recommendations does not reflect the user's intentions, which is an issue that does not sufficiently stimulate the desire to purchase.

[2119] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[2120] In this invention, the server includes means for receiving a URL entered by a user, means for acquiring product information based on the received URL, means for analyzing the product information and generating a three-dimensional model based on the analysis results, means for converting the generated three-dimensional model into augmented reality data, means for transmitting the augmented reality data to the user's terminal, means for recognizing the user's emotion and adjusting the display content of the three-dimensional model based on the recognized emotion, and means for recommending related products based on the user's emotion. This allows the user to view products in a manner close to the real thing, and enables optimal information presentation and product recommendations based on emotion.

[2121] - "URL receiving means" is a function that receives the URL entered by the user via the network.

[2122] The "product information acquisition means" is a function that acquires the necessary product information from a product database or website based on the received URL.

[2123] The "product information analysis means" is a function that analyzes the acquired product information and extracts the shape, color, texture, and the like.

[2124] The "three-dimensional model generating means" is a function that automatically generates a three-dimensional digital model based on analyzed product information.

[2125] The "augmented reality data conversion means" is a function that converts the generated three-dimensional model into a data format that can be displayed in AR.

[2126] The "data transmission means" is a function that transmits the converted augmented reality data to the user's terminal.

[2127] The "data display means" is a function that displays the received data as augmented reality on the user's terminal.

[2128] The "emotion recognition means" is a function that analyzes the user's facial expressions and voice to recognize the emotion at that time.

[2129] The "display adjustment means" is a function that adjusts the content and viewpoint of the displayed three-dimensional model based on the recognized user's emotions.

[2130] The "product recommendation means" is a function that recommends other related products to the user based on the user's emotional data.

[2131] The system of this invention generates a 3D model based on the product URL entered by the user and displays it in augmented reality (AR).It also has the ability to adjust the display content based on the user's emotions and recommend related products.

[2132] The server processes the URL received from the user and obtains product information based on that URL. The product information obtaining means collects images and specification information related to the product from a database or website. The product information analysis means then analyzes the obtained information and extracts shape, color, and texture information. Based on the results of this analysis, the 3D model generation means generates a digital 3D model of the product.

[2133] The generated three-dimensional model is converted into a format that can be displayed in AR (e.g., USDZ or GLTF format) by the augmented reality data conversion means. This converted data is transmitted to the user's terminal via the data transmission means. The received data is displayed as augmented reality by the user's terminal.

[2134] Furthermore, the emotion recognition means allows the user's device to analyze the user's facial expressions and voice to obtain emotion data. Based on the recognized emotion, the display adjustment means adjusts the display content and viewpoint of the three-dimensional model. For example, if the user is feeling anxious, a different viewpoint or additional information is displayed. Furthermore, based on the user's emotion data, the product recommendation means recommends related products. If the user finds the emotion engine to be fun, other products in the same category are displayed.

[2135] Hardware and software used

[2136] Hardware: Smartphone, smart glasses, head-mounted display (camera, sensor)

[2137] software:

[2138] EmotionRecognizer Library: Recognize user emotions

[2139] ARDisplay library: AR display of 3D models

[2140] HTTP request: Get product information

[2141] Generative AI model: 3D model generation

[2142] Specific examples

[2143] A user opens a smartphone app and enters the URL of a product they found on an e-commerce site. For example, if a user is considering purchasing furniture, they enter the URL of a sofa they are interested in into a dedicated app. The server retrieves product information based on the URL, and the generative AI model generates a 3D model using the following prompt:

[2144] Prompt: "Shape: square, Color: blue, Texture: fabric"

[2145] The generated 3D model is converted and sent to the user's smartphone, where it is displayed in real space through the camera. The user can see how the sofa would look in their living room. Furthermore, if the user looks happy at the camera, the emotion recognition means detects this and the product recommendation means displays other related furniture. For example, cushions or tables of the same color are recommended. This makes it easier for the user to make a purchase decision and allows them to check the product in a way that is close to the real thing in their own home.

[2146] Prompt Sentence Examples

[2147] "Shape: Square, Color: Blue, Texture: Fabric"

[2148] "Shape: Rectangle, Color: White, Texture: Wood Grain"

[2149] In this way, the invention improves the user experience and supports purchasing decisions.

[2150] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2151] Step 1:

[2152] The user launches the application and enters the URL of a product they found on an e-commerce site.

[2153] Input: Product URL

[2154] Output: The URL is saved on the user's device.

[2155] Specific operation: The user enters the product URL into the input field of the dedicated application.

[2156] Step 2:

[2157] The device sends the entered URL to the server.

[2158] Input: The URL entered by the user

[2159] Output: URL sent to server

[2160] Specific operation: The device sends a URL to the server using an HTTP request.

[2161] Step 3:

[2162] The server accesses the e-commerce site based on the URL and retrieves product information.

[2163] Input: User submitted URL

[2164] Output: Product image data and specifications

[2165] Specific operations: The server collects product information (images, shapes, colors, textures, dimensions, material information, etc.) through scraping technology or API calls.

[2166] Step 4:

[2167] The server analyzes the acquired product information and extracts the necessary data.

[2168] Input: Retrieved product information

[2169] Output: Analyzed shape, color, and texture information

[2170] Specific operation: Using product information analysis means, shape, color, and texture information are extracted from image data, and dimension and material information is extracted from specification information.

[2171] Step 5:

[2172] The server generates a three-dimensional model based on the analyzed data.

[2173] Input: Shape, color, texture information

[2174] Output: 3D model

[2175] How it works: Using a generative AI model, generate a 3D model based on the following prompt:

[2176] Prompt: "Shape: square, Color: blue, Texture: fabric"

[2177] Step 6:

[2178] The server converts the generated three-dimensional model into augmented reality data.

[2179] Input: 3D model

[2180] Output: Augmented reality data (e.g. USDZ format)

[2181] Specific operations: Using augmented reality data conversion means, the coordinate system of the model is set, AR markers are added, and export to a specific format.

[2182] Step 7:

[2183] The server transmits the converted augmented reality data to the terminal.

[2184] Input: Augmented reality data

[2185] Output: Augmented reality data sent to the device

[2186] Specific operation: Sends data to the user's device using an HTTP response or WebSocket.

[2187] Step 8:

[2188] The device displays the received augmented reality data.

[2189] Input: Augmented reality data

[2190] Output: 3D model displayed in real space

[2191] Specific operation: The device application displays augmented reality data in real space through the camera.

[2192] Step 9:

[2193] The device recognizes the user's emotions.

[2194] Input: User's facial expressions and voice data

[2195] Output: Recognized emotion data

[2196] Specific operation: Analyzes the user's emotions using the EmotionRecognizer library through the device's camera and microphone.

[2197] Step 10:

[2198] The server adjusts the display content of the three-dimensional model based on the emotion.

[2199] Input: Recognized emotion data

[2200] Output: Adjusted display content

[2201] Specific operation: Based on the emotion data, the display adjustment means adjusts the display viewpoint and detailed information of the three-dimensional model.

[2202] Step 11:

[2203] The server recommends related products based on the user's emotions.

[2204] Input: Recognized emotion data

[2205] Output: Recommended related products

[2206] Specific operation: Using the emotion engine, other related products are selected and displayed based on the user's emotion data.

[2207] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[2208] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2209] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[2210] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2211] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[2212] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[2213] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[2214] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[2215] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[2216] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[2217] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[2218] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[2219] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[2220] 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.

[2221] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[2222] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[2223] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[2224] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[2225] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[2226] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[2227] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[2228] The following is further disclosed regarding the above embodiment.

[2229] (Claim 1)

[2230] means for receiving a URL entered by a user;

[2231] A means for obtaining product information based on the received URL;

[2232] means for analyzing product information and generating a three-dimensional model based on the analysis results;

[2233] means for converting the generated three-dimensional model into augmented reality data;

[2234] means for transmitting the augmented reality data to a user terminal;

[2235] means for displaying the augmented reality data by a user terminal;

[2236] A system including:

[2237] (Claim 2)

[2238] The system according to claim 1, further comprising an algorithm for extracting images and specification information from product information and analyzing shape, color, and texture information in generating a three-dimensional model.

[2239] (Claim 3)

[2240] 10. The system of claim 1, wherein converting the augmented reality data includes setting a coordinate system for the model, adding appropriate augmented reality markers, and exporting to a specific format.

[2241] "Example 1"

[2242] (Claim 1)

[2243] means for receiving a URL entered by a user;

[2244] A means for obtaining product information based on the received URL;

[2245] means for analyzing product information and generating a three-dimensional model based on the analysis results;

[2246] means for converting the generated three-dimensional model into augmented reality data;

[2247] means for transmitting the augmented reality data to a user terminal;

[2248] means for displaying the augmented reality data by a user terminal;

[2249] A system including:

[2250] (Claim 2)

[2251] The system according to claim 1, further comprising an algorithm for extracting images and specification information from product information and analyzing shape, color, and texture information in generating a three-dimensional model.

[2252] (Claim 3)

[2253] 10. The system of claim 1, wherein converting the augmented reality data includes setting a coordinate system for the model, adding appropriate augmented reality markers, and exporting to a specific format.

[2254] "Application Example 1"

[2255] (Claim 1)

[2256] means for receiving a URL entered by a user;

[2257] A means for obtaining product information based on the received URL;

[2258] means for analyzing product information and generating a three-dimensional model based on the analysis results;

[2259] means for converting the generated three-dimensional model into augmented reality data;

[2260] means for transmitting the augmented reality data to a user terminal;

[2261] means for displaying the augmented reality data by a user terminal;

[2262] A means for generating a three-dimensional model based on food information collected from food delivery sites and displaying it in augmented reality;

[2263] A system including:

[2264] (Claim 2)

[2265] The system according to claim 1, further comprising an algorithm for extracting images and specification information from product information and analyzing shape, color, and texture information in generating a three-dimensional model.

[2266] (Claim 3)

[2267] 10. The system of claim 1, wherein converting the augmented reality data includes setting a coordinate system for the model, adding appropriate augmented reality markers, and exporting to a specific format.

[2268] "Example 2: Combining Emotion Engines"

[2269] (Claim 1)

[2270] means for receiving a URL entered by a user;

[2271] A means for obtaining product information based on the received URL;

[2272] means for analyzing product information and generating a three-dimensional model based on the analysis results;

[2273] means for converting the generated three-dimensional model into augmented reality data;

[2274] means for transmitting the augmented reality data to a user terminal;

[2275] means for displaying the augmented reality data by a user terminal;

[2276] means for recognizing a user's emotion;

[2277] means for adjusting the display content and recommending related products based on the recognized emotion;

[2278] A system including:

[2279] (Claim 2)

[2280] The system according to claim 1, further comprising an algorithm for extracting images and specification information from product information and analyzing shape, color, and texture information in generating a three-dimensional model.

[2281] (Claim 3)

[2282] 10. The system of claim 1, wherein converting the augmented reality data includes setting a coordinate system for the model, adding appropriate augmented reality markers, and exporting to a specific format.

[2283] "Application example 2 when combining emotion engines"

[2284] (Claim 1)

[2285] means for receiving a URL entered by a user;

[2286] A means for obtaining product information based on the received URL;

[2287] means for analyzing product information and generating a three-dimensional model based on the analysis results;

[2288] means for converting the generated three-dimensional model into augmented reality data;

[2289] means for transmitting the augmented reality data to a user terminal;

[2290] means for displaying the augmented reality data by a user terminal;

[2291] means for recognizing a user's emotion and adjusting the display content of the three-dimensional model based on the recognized emotion;

[2292] means for recommending related products based on user sentiment;

[2293] A system including:

[2294] (Claim 2)

[2295] The system according to claim 1, further comprising an algorithm for extracting images and specification information from product information and analyzing shape, color, and texture information in generating a three-dimensional model.

[2296] (Claim 3)

[2297] 10. The system of claim 1, wherein converting the augmented reality data includes setting a coordinate system for the model, adding appropriate augmented reality markers, and exporting to a specific format. [Explanation of symbols]

[2298] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving a URL entered by a user; A means for obtaining product information based on the received URL; means for analyzing product information and generating a three-dimensional model based on the analysis results; means for converting the generated three-dimensional model into augmented reality data; means for transmitting the augmented reality data to a user terminal; means for displaying the augmented reality data by a user terminal; A system including:

2. 2. The system according to claim 1, further comprising an algorithm for extracting images and specification information from product information and analyzing shape, color, and texture information in generating a three-dimensional model.

3. The system of claim 1 , wherein converting the augmented reality data includes setting a coordinate system for the model, adding appropriate augmented reality markers, and exporting to a specific format.

Images