System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving an image of a pet; means for receiving an image of pet apparel; means for using a generative AI model to combine the received image of the pet and the image of the pet apparel; and means for displaying the combined image to a 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] In today's world, fashion for pets is on the rise, and choosing clothes for pets can be a time-consuming and labor-intensive process for owners. This is particularly inconvenient for pet owners, as pets often dislike trying on clothes or find it difficult to do so. It's also important to avoid causing stress to pets by trying on clothes. To solve these problems, there's a need for a simple and accurate way for pets to see how clothes will look when trying them on, without actually having to try them on. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following means. The system includes a means for receiving an image of a pet, a means for receiving an image of pet clothing, a means for using a generative AI model that synthesizes the received image of the pet with an image of the pet clothing, and a means for displaying the synthesized image to the user. The generative AI model also includes a means for recognizing the outline and body shape of the pet and adjusting the shape of the pet clothing. The synthesized image also includes a means for adjusting the fitting according to the pet's body color and background, allowing the user to see how the clothing will look when worn in a natural way without actually having to try it on.

[0006] The "means for receiving pet images" is a function used to receive digital photo data of a pet taken by a user.

[0007] The "means for receiving an image of pet clothing" is a function used to receive photographic data of the pet clothing selected by the user in digital form.

[0008] A "generative AI model" is an algorithm or network model that uses machine learning and deep learning technologies to synthesize input images of pets with images of pet clothing, generating natural-looking try-on images.

[0009] The "synthesis means" is a function that uses a generative AI model to overlay an image of a pet on an image of the pet's clothing, making it appear as if the pet is wearing the clothing.

[0010] The "display means" is a function for displaying the synthesized try-on image on the screen of the user's terminal.

[0011] The "means for recognizing the outline and body shape of a pet" is a function for extracting the outline and body shape characteristics from an image of a pet and adjusting the shape of the pet's clothing based on them.

[0012] The "shape adjusting means" is a function that automatically changes the size and shape of pet clothing to fit the pet's body shape.

[0013] The "means for performing fitting adjustment" is a function that automatically performs adjustments to make the synthesized fitting image look natural, according to the pet's body color and background. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

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

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

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

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0029] 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.

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

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] System Overview

[0036] This invention is a system that simulates trying on pet clothes using images of pets and pet clothes. This system receives images of pets and pet clothes, synthesizes them using a generative AI model, and provides the user with a natural try-on image. The system is broadly composed of a server and a user's terminal.

[0037] Program processing flow

[0038] 1. User Input

[0039] Users use their device to upload images of their pets taken with their smartphone or camera, as well as images of the pet clothing they are considering purchasing, to the application. When the user selects the image files and presses the upload button, the device sends the image data to the server.

[0040] 2. Sending images

[0041] The device sends image data to the server using an HTTP POST request. The image data is sent in a multipart form data format to prevent data loss or inconsistent data formats.

[0042] 3. Image Processing and Composition

[0043] The server processes the received images of the pet and pet clothing. First, it preprocesses the images to unify the size and resolution. Next, it uses a generative AI model to recognize the pet's outline and body shape from the pet image and adjusts the shape of the pet clothing accordingly. The generative AI model uses machine learning and deep learning techniques to perform optimal synthesis based on the input images.

[0044] 4. Generating synthetic images

[0045] The server encodes the resulting composite image into the appropriate image format before sending it back to the device, ensuring compatibility when the image is displayed on the user's device.

[0046] 5. Sending the composite image

[0047] The server sends the generated composite image back to the device as an HTTP response. It is recommended to use HTTPS to ensure communication security.

[0048] 6. Display of fitting images

[0049] The device decodes the composite image received from the server and displays it on the application UI. The user can then view the image of their pet wearing the pet clothing on the device screen.

[0050] Specific examples

[0051] User operations

[0052] User A takes a photo of his dog and wants to buy new pet clothes. User A starts the application, selects a photo of his dog and an image of a candidate pet clothes, and presses the upload button. The device sends these images to the server.

[0053] Server Processing

[0054] The server receives the image of User A's dog and the image of the pet clothing, performs preprocessing, and then uses a generative AI model to synthesize the image of the pet and the image of the pet clothing. The synthesized image simulates the dog wearing the pet clothing.

[0055] Displaying the results

[0056] The server sends the composite image to User A's device, which displays the image on the application's UI. User A checks the dog wearing the new pet clothes and considers purchasing them.

[0057] This system allows users to easily and accurately see how pet clothes will look on their pet without actually trying them on, making it easier to select pet clothes while minimizing stress on the pet.

[0058] The processing flow will be explained below.

[0059] Step 1: User Input

[0060] The user opens the application on the device, selects a photo of the pet and a photo of the pet's clothing, and when the user presses the "Upload" button, the device obtains the path of the selected image file.

[0061] Step 2: Sending images

[0062] The terminal sends the selected image data to the server using an HTTP POST request. At this time, the image data is sent in a multipart form data format.

[0063] Step 3: Receiving the image

[0064] The server receives the HTTP request and saves the image files of the pet and the pet clothes. The saved data is placed in a directory for image processing.

[0065] Step 4: Image preprocessing

[0066] The server performs preprocessing on the stored image data, including standardizing image size, adjusting resolution, and removing noise.

[0067] Step 5: Extracting the pet outline

[0068] The server applies an edge detection algorithm to recognize the pet's contours and shape from the pet image, which gives a clearer picture of the pet's shape in the image.

[0069] Step 6: Applying the generative AI model

[0070] The server uses a generative AI model to synthesize an image of the pet with an image of the pet's clothing, and the generative AI model adjusts the shape of the pet's clothing to fit the synthesized image based on the pet's contours and body shape.

[0071] Step 7: Generate a composite image

[0072] The server generates a synthetic image of the pet wearing the pet clothing as a result of the processing by the generative AI model, which reproduces the natural look of the pet and the clothing.

[0073] Step 8: Encode the composite image

[0074] The server encodes the resulting composite image into JPEG or PNG format, ensuring compatibility and display quality of the image.

[0075] Step 9: Submit your composite image

[0076] The server sends the encoded composite image to the terminal as an HTTP response. The image data may be sent again in multipart form data format.

[0077] Step 10: Receiving the composite image

[0078] The device receives the HTTP response sent from the server and acquires the composite image data, which is then temporarily stored in its internal memory.

[0079] Step 11: Displaying the composite image

[0080] The device decodes the synthesized image and displays it on the application's UI, allowing the user to see the image of their pet wearing the pet clothing on the device screen.

[0081] Example 1

[0082] 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."

[0083] Conventional pet clothing fitting systems require pets to actually try on the clothes, which increases stress for the pet and wastes time. Furthermore, when purchasing online, it is difficult to confirm whether the clothes actually fit the pet, and mismatched sizes or designs are often discovered after purchase. To solve these issues, a system is needed that combines images of the pet and the pet clothing to provide users with a realistic fitting experience.

[0084] 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.

[0085] In this invention, the server includes means for receiving pet images, means for receiving pet clothing images, means for sending image data to the server using an HTTP POST request, means for preprocessing the received pet images and pet clothing images and using a generative AI model, means for encoding and sending the preprocessed images, and means for displaying the synthesized image to the user. This allows the user to easily and accurately check how the pet clothing will look on their pet without actually trying it on.

[0086] A "pet image" is visual information in digital form that includes the entire image or part of a pet.

[0087] "Pet apparel image" means visual information in digital form that visually represents the design or shape of pet apparel or accessories.

[0088] An "HTTP POST request" is one of the methods in the HTTP protocol for sending data to a web server, and is a method that is particularly suitable for sending large amounts of data or multiple pieces of data.

[0089] A "generative AI model" is an algorithm or program that uses machine learning or deep learning techniques to analyze and process input image data and generate output tailored to a specific purpose.

[0090] "Preprocessing" refers to a series of processes such as data resizing, resolution adjustment, and noise removal to convert received image data into a format that is easier to process.

[0091] "Encoding" is the process of converting image data into a specific file format (e.g., JPEG, PNG) to make it easier to store and transfer.

[0092] "Decoding" is the process of converting encoded image data into a format that can be displayed or edited.

[0093] This invention is a system that simulates trying on pet clothes using images of pets and pet clothes. The system receives images of pets and pet clothes, synthesizes them using a generative AI model, and provides the user with a natural fitting image. The system is mainly composed of a server and a user's terminal.

[0094] User Input

[0095] The user takes a picture of their pet using a smartphone or digital camera. They also prepare an image of the pet clothing they are considering purchasing. The user launches the application, selects the image of the pet and the image of the pet clothing from the file browser, and clicks the upload button. This causes the device to prepare the image data and proceed to the next step.

[0096] Sending images

[0097] The device sends image data to the server using an HTTP POST request. At this time, the image data is sent in multipart form data format, which prevents data loss and format inconsistencies. Specifically, the device includes the image file in the body of the HTTP request and sends the request to the specified endpoint on the server.

[0098] Image Processing and Compositing

[0099] The server processes the received images of the pet and pet clothing. First, as preprocessing, the images are resized to unify the size and resolution. Then, a generative AI model is used to recognize the pet's outline and body shape from the pet image. This generative AI model is built using deep learning frameworks such as TENSORFLOW (registered trademark) and PyTorch. This generative AI model calculates the optimal shape and placement of the clothing for the pet and synthesizes a realistic image.

[0100] Generate synthetic images

[0101] The server encodes the composite image into an appropriate image format before sending it back to the device, specifically using a library like Pillow or OpenCV to encode the generated image into a format like JPEG or PNG, ensuring compatibility when the image is displayed on the user's device.

[0102] Sending a composite image

[0103] The server returns the generated composite image to the terminal as an HTTP response. To ensure communication security, it is recommended to use HTTPS (HTTP using SSL / TLS). The server sets the appropriate content type (e.g., image / jpeg) in the response header and sends the image data in the response body.

[0104] Display of try-on images

[0105] The device decodes the composite image received from the server and displays it on the application's UI. First, the received image data is loaded into a buffer and decoded using an image display library. The decoded image is then displayed in a specific view of the application. The user can view the image of their pet wearing pet clothing on the device screen.

[0106] Specific examples

[0107] 1. The user opens the application, selects an image of the pet and an image of the pet clothing, and presses the upload button.

[0108] 2. The device sends the image data to the server using an HTTP POST request.

[0109] 3. The server preprocesses the image and synthesizes it using a generative AI model.

[0110] 4. The server encodes the composite image and sends it to the device as an HTTP response.

[0111] 5. The device receives the composite image, decodes it, and displays it in the application UI.

[0112] Example prompts for generative AI models:

[0113] "Generate a composite image using an image of a dog and an image of a dog T-shirt."

[0114] The present invention provides a system that allows users to easily and accurately check how pet clothing will look on their pet without actually trying it on, thereby enabling smooth selection of pet clothing while minimizing stress on the pet.

[0115] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0116] Step 1: User Input

[0117] The user uses a device to upload images of their pet and pet clothing to the application. Specifically, they prepare images of their pet taken with a smartphone or digital camera, as well as images of the pet clothing they are considering purchasing. The user selects these image files from the file browser within the application and clicks the upload button to complete the input. The input here is the image of the pet and the image of the pet clothing, and this data will be used in the next step.

[0118] Step 2: Sending images

[0119] The terminal sends the selected image data to the server using an HTTP POST request. Specifically, the terminal encodes the image data in a multipart form data format and includes it in the body of the HTTP request. The terminal then sends the request to the specified endpoint of the server. The input of this step is the image data selected by the user, and the output is the image data sent to the server.

[0120] Step 3: Image preprocessing

[0121] The server preprocesses the received image data. Specifically, it performs resizing to unify the image size and resolution, noise removal, color correction, etc. The input to this step is the image of the pet and the image of the pet's clothing sent from the terminal, and outputs image data in a unified format.

[0122] Step 4: Image synthesis using a generative AI model

[0123] The server inputs the preprocessed image data into a generative AI model, which recognizes the pet's contours and body shape and adjusts the shape of the pet clothing accordingly. The generative AI model is built using deep learning frameworks such as TensorFlow and PyTorch. The input of this step is the preprocessed image data, and the output is the generated synthetic image.

[0124] Step 5: Encode the composite image

[0125] The server encodes the generated composite image into an appropriate image format, such as JPEG or PNG, using a library like Pillow or OpenCV. The input to this step is the generated composite image, and the output is the encoded image data.

[0126] Step 6: Submit your composite image

[0127] The server returns the encoded composite image to the terminal as an HTTP response, using HTTPS (HTTP using SSL / TLS) to ensure communication security. The server sets the appropriate content type (e.g., image / jpeg) in the response header and sends the image data in the response body. The input to this step is the encoded composite image, and the output is the composite image sent to the terminal.

[0128] Step 7: Displaying fitting images

[0129] The device decodes the received composite image and displays it on the application's UI. Specifically, the device first loads the received image data into a buffer and decodes it using an image display library. The decoded image is then displayed in a specific view of the application. The input to this step is the encoded composite image received from the server, and the output is the try-on image displayed on the user's screen.

[0130] The above is the specific processing flow of this system.

[0131] (Application example 1)

[0132] 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."

[0133] When purchasing pet clothing in the past, it was necessary to actually try it on the pet, which caused stress and trouble for the pet. Also, when purchasing online, there was a risk that the size or design would not fit after purchase because it was not possible to try it on.

[0134] 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.

[0135] In this invention, the server includes means for receiving an image of a pet, means for receiving an image of a pet garment, means for using a generative AI model to synthesize the received image of the pet with an image of the pet garment, means for displaying the synthesized image to a user, and means for transmitting the synthesized image to a user terminal using a communication protocol, thereby enabling a user to check the effect of trying on pet garments online in real time without actually trying them on their pet.

[0136] The "means for receiving pet images" is a function that allows a user to send a photo of their pet from the terminal to the server.

[0137] The "means for receiving images of pet clothes" is a function for transmitting images of the pet clothes that the user wishes to try on from the terminal to the server.

[0138] "Means for using a generative AI model to synthesize received images of pets and images of pet clothing" refers to AI technology used to combine images of pets and images of pet clothing to generate natural-looking images for trying on.

[0139] The "means for displaying the synthesized image to the user" is a function for displaying the generated try-on image on the user's terminal.

[0140] The "means for transmitting the synthesized image to the user terminal using a communication protocol" refers to a communication technology used to securely transmit the generated try-on image to the user terminal.

[0141] "Means for recognizing the pet's contours and body shape and adjusting the shape of the pet's clothing" is a function that enables the generative AI model to optimize the shape of the clothing to match the shape of the pet.

[0142] "Means for adjusting fitting according to the pet's body color and background" is a function that enables the generative AI model to adjust the fit of the synthetic image according to the pet's body color and background.

[0143] The present invention is a system for simulating trying on pet clothes using images of a pet and pet clothes. Detailed explanations of the implementation of the system are given below.

[0144] System Configuration

[0145] This system mainly consists of a server and a user device. The user device can be a smartphone or tablet, and the server is a cloud server.

[0146] Hardware and software used

[0147] Server: Cloud Server

[0148] User devices: smartphones, tablets

[0149] Generative AI models: VQ-VAE and GAN models trained using TensorFlow or PyTorch

[0150] Image processing library: OpenCV

[0151] Communication protocol: HTTPS protocol

[0152] Program processing

[0153] User operations

[0154] Using the application, users first take a photo of their pet and then upload an image of the pet clothing they want to try on. This process is very intuitive and can be easily done on the application screen.

[0155] Sending images

[0156] The user device sends image data to the server using an HTTP POST request. The image data is sent in a multipart form data format to prevent data loss or format inconsistencies.

[0157] Image Processing and Compositing

[0158] The server performs the following processes on the received pet images and pet costume images:

[0159] 1. First, preprocess the images to unify their size and resolution.

[0160] 2. Next, a generative AI model (e.g., VQ-VAE or GAN) is used to synthesize an image of the pet with an image of the pet costume. The generative AI model recognizes the pet's contours and body shape and adjusts the pet costume based on that shape.

[0161] Generate and transmit synthetic images

[0162] The server encodes the resulting composite image into the appropriate image format (JPEG or PNG) and then sends it back to the user's device using HTTPS, ensuring secure communication.

[0163] Display of try-on images

[0164] The user device decodes the received composite image and displays it on the application UI, allowing the user to see how their pet will actually look wearing the pet costume.

[0165] Specific examples

[0166] For example, if a user uploads a photo of their dog (e.g., a Shiba Inu) and selects an image of a blue sweater, the generative AI model will combine these images to create an image of the dog wearing the blue sweater, which the user can view and consider purchasing.

[0167] Prompt Sentence Examples

[0168] Using a picture of a pet and a picture of a pet costume, simulate a pet wearing the pet costume. The pet is a picture of a dog, and the costume is an image of a blue sweater.

[0169] This allows users to check the effects of trying on pet clothes online in real time without actually trying them on their pets.

[0170] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0171] Step 1:

[0172] The user launches the application and uploads images of their pet and pet costume by selecting images from their smartphone's camera or photo gallery. The input is the image files of the pet and pet costume, and the output is the image data of these.

[0173] Step 2:

[0174] The terminal sends the pet image and pet costume image uploaded by the user to the server. The communication protocol is HTTP POST request, and the image data is sent in multipart form data format. The input is the image file, and the output is the image data sent to the server.

[0175] Step 3:

[0176] The server preprocesses the received pet images and pet costume images, including image resizing, resolution unification, noise removal, etc. The input is the received image data, and the output is the preprocessed image data.

[0177] Step 4:

[0178] The server uses a generative AI model (e.g., VQ-VAE or GAN) to synthesize an image of the pet and an image of the pet costume. The generative AI model recognizes the pet's contours and body shape and adjusts the pet costume based on that shape. The input is the preprocessed image of the pet and the pet costume, and the output is a synthesized try-on image.

[0179] Step 5:

[0180] The server encodes the composite try-on image into the appropriate image format (JPEG or PNG) to display the image correctly on the user's device. The input is the composite try-on image, and the output is the encoded image file.

[0181] Step 6:

[0182] The server sends the encoded image file to the user terminal using HTTPS, which ensures communication security. The input is the encoded image file, and the output is the image data sent to the user terminal.

[0183] Step 7:

[0184] The device decodes the composite image received from the server and displays it on the application UI. The user can see the image of their pet wearing the pet costume through the decoded image. The input is the received image data, and the output is the try-on image displayed to the user.

[0185] 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.

[0186] System Overview

[0187] This invention is a system that simulates trying on pet clothes using images of pets and pet clothes, and also combines it with an emotion engine that recognizes the user's emotions. This system receives images of pets and pet clothes, synthesizes them using a generative AI model, and provides the user with a natural trying-on image. It also has the ability to recognize the user's emotions and provide feedback and suggestions based on those emotions. The main components of the system are a server and a user's terminal.

[0188] Program processing flow

[0189] 1. User Input

[0190] Users use their device to upload images of their pets taken with their smartphone or camera, as well as images of the pet clothing they are considering purchasing, to the application. When the user selects the image files and presses the upload button, the device sends the image data to the server.

[0191] 2. Sending images

[0192] The device sends image data to the server using an HTTP POST request. The image data is sent in a multipart form data format to prevent data loss or inconsistent data formats.

[0193] 3. Image Processing and Composition

[0194] The server processes the received images of the pet and pet clothing. First, it preprocesses the images to unify the size and resolution. Next, it uses a generative AI model to recognize the pet's outline and body shape from the pet image and adjusts the shape of the pet clothing accordingly. The generative AI model uses machine learning and deep learning techniques to perform optimal synthesis based on the input images.

[0195] 4. Generating synthetic images

[0196] The server encodes the resulting composite image into the appropriate image format before sending it back to the device, ensuring compatibility when the image is displayed on the user's device.

[0197] 5. Sending the composite image

[0198] The server sends the generated composite image back to the device as an HTTP response. It is recommended to use HTTPS to ensure communication security.

[0199] 6. Display of fitting images

[0200] The device decodes the composite image received from the server and displays it on the application UI. The user can then view the image of their pet wearing the pet clothing on the device screen.

[0201] 7. Emotional Engine Analysis

[0202] The device captures the user's facial expressions with a camera and analyzes them in real time with an emotion engine that detects the user's emotional state (e.g., joy, surprise, dissatisfaction, etc.) when viewing the pet try-on image.

[0203] 8. Emotional Feedback

[0204] The server analyzes the user's emotion data obtained from the emotion engine and provides appropriate feedback. For example, if the user is happy, it will suggest pet clothes with a similar design. If the user is unhappy, it will suggest pet clothes with a different style.

[0205] 9. Accumulation of Emotional Data and Historical Use

[0206] The server accumulates the user's emotional data and makes personalized suggestions based on their past emotional history. This allows the server to learn the user's preferences and tendencies, and provide more appropriate fitting images and clothing suggestions.

[0207] Specific examples

[0208] User operations

[0209] User B takes a photo of his cat and wants to buy new pet clothes. User B starts the application, selects a photo of the cat and an image of the candidate pet clothes, and presses the upload button. The device sends these images to the server.

[0210] Server Processing

[0211] The server receives the image of User B's cat and the image of the pet clothing, performs preprocessing, and then uses a generative AI model to synthesize the image of the pet and the image of the pet clothing. The synthesized image simulates the cat wearing the pet clothing.

[0212] Results display and sentiment analysis

[0213] The server sends the synthesized image to User B's device, which displays the image on the application's UI. User B checks that the cat is wearing the new pet clothes, and its facial expressions are captured through the camera. The emotion engine analyzes User B's emotional state, and the server provides feedback and additional suggestions based on this.

[0214] This system allows users to easily and accurately check how pet clothes will look on their pets without actually trying them on. Feedback that takes the user's emotions into account also enables more appropriate clothing selection, improving the user experience.

[0215] The processing flow will be explained below.

[0216] Step 1: User Input

[0217] The user opens the application on the device, selects a photo of the pet and a photo of the pet's clothing, and when the user presses the "Upload" button, the device obtains the path of the selected image file and prepares the image data.

[0218] Step 2: Sending images

[0219] The terminal sends the prepared pet image and pet clothing image to the server using an HTTP POST request, where the image data is sent in a multipart form data format.

[0220] Step 3: Receiving the image

[0221] The server receives the HTTP POST request and saves the submitted pet image and pet clothing image files in a specific directory for processing.

[0222] Step 4: Image preprocessing

[0223] The server performs preprocessing on the images of the pet and pet clothing stored in the storage. This preprocessing includes resizing the images, adjusting the resolution, and removing noise. This process converts both images into a format that is easy for the generative AI model to process.

[0224] Step 5: Extracting the pet outline

[0225] The server applies a contour extraction algorithm to the pre-processed pet image, which clearly identifies the pet's contours and body shape, providing the data needed for subsequent image synthesis.

[0226] Step 6: Applying the generative AI model

[0227] The server uses a generative AI model to synthesize an image of the pet and an image of the pet's clothing. The generative AI model adjusts the shape of the pet's clothing appropriately based on the pet's outline information, resulting in a natural-looking composition.

[0228] Step 7: Generate a composite image

[0229] The server generates a composite image of the pet wearing the pet clothing as a result of the generative AI model processing, and the composite image is encoded in JPEG or PNG format to ensure display compatibility.

[0230] Step 8: Submit your composite image

[0231] The server sends the encoded composite image to the terminal as an HTTP response. Image data must be sent in an appropriate format, and it is recommended to use HTTPS for communication security.

[0232] Step 9: Receiving the composite image

[0233] The device receives the HTTP response sent from the server and acquires the composite image data, which is then temporarily stored in the device's internal memory.

[0234] Step 10: Displaying the composite image

[0235] The device decodes the temporarily stored composite image and displays it on the application's UI, allowing the user to see the image of their pet wearing the pet clothing on the device screen.

[0236] Step 11: Activating the Emotion Engine

[0237] The device captures the user's facial expressions with a camera and activates the emotion engine, which analyzes the user's emotional state in real time and sends the data to the server.

[0238] Step 12: Analyze the sentiment data

[0239] The server analyzes the user's emotion data sent from the emotion engine, using facial recognition algorithms and machine learning models to detect the user's emotional state, such as joy, surprise, or dissatisfaction.

[0240] Step 13: Emotional Feedback

[0241] The server then provides appropriate feedback to the user based on the analyzed emotional data. For example, if the user is happy, it will automatically suggest pet clothes with a similar design. If the user is unhappy, it will suggest pet clothes with a different style.

[0242] Step 14: Accumulating Emotional Data and Using History

[0243] The server accumulates the user's emotional data and makes personalized suggestions based on their past emotional history. This allows the system to learn the user's preferences and tendencies, and provide more appropriate fitting images and pet clothing suggestions.

[0244] Example 2

[0245] 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."

[0246] Conventional pet clothing fitting systems require users to actually try on clothes, which places a heavy burden on the user. Furthermore, they do not provide feedback that takes into account the user's reactions and emotions, making it difficult to select appropriate pet clothing. Furthermore, when shopping online, there is a high risk of purchasing products that do not fit the pet's size or shape.

[0247] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving a pet image, means for receiving an image of a pet clothing, means for using a generative AI model to synthesize the received pet image with an image of the pet clothing, means for displaying the synthesized image to the user, means for using an emotion engine to recognize the user's emotional state, and means for providing feedback and suggestions based on emotion data obtained from the emotion engine. This allows the user to naturally check how pet clothing will look on their pet without actually trying it on their pet, and feedback that takes the user's emotions into consideration enables more appropriate clothing selection.

[0248] The "means for receiving pet images" refers to an interface and communication mechanism that allows a user to use a terminal to upload pet photo data to the system.

[0249] The "means for receiving images of pet clothing" refers to an interface and communication mechanism that allows users to upload photographic data of candidate pet clothing to the system.

[0250] "Means for using generative AI models" refers to algorithms and software that utilize machine learning and deep learning techniques to synthesize images of pets and images of pet clothing.

[0251] The "means for displaying a synthesized image to a user" refers to an interface and communication mechanism for transferring the synthesized image created by the generative AI model to a user's terminal and displaying it.

[0252] The "means for using an emotion engine" is an algorithm and software for capturing a user's facial expressions using a camera and analyzing the expression data to extract an emotional state.

[0253] The "means for providing feedback and suggestions based on emotional data" refers to algorithms and software that analyze the user's emotional data obtained from the emotion engine and provide the user with appropriate feedback and suggestions for pet clothing based on the results.

[0254] System Overview

[0255] This invention is a system that simulates trying on pet clothes using images of pets and pet clothes, and also combines it with an emotion engine that recognizes the user's emotions. This system receives images of pets and pet clothes, synthesizes them using a generative AI model, and provides the user with a natural trying-on image. It also has the ability to recognize the user's emotions and provide feedback and suggestions based on those emotions. The main components of the system are a server and a user's terminal.

[0256] Hardware and software used

[0257] Devices: smartphones, tablets, personal computers, etc.

[0258] Server: Cloud server or on-premise server

[0259] Generative AI models: Deep learning models such as StyleGAN2 and VGG-19

[0260] Emotion engine: Microsoft® Azure® Emotional API, Google® Cloud Vision API, etc.

[0261] Specific processing outline of the program

[0262] 1. User Input

[0263] The user uses the device to upload images of their pet and the pet clothing they are considering purchasing to the application. The user selects the image files and presses the "Upload" button. At this point, the device temporarily stores these image files.

[0264] Examples:

[0265] User A takes a photo of the dog with their smartphone, selects an image of the pet clothing from the device's gallery, and presses the "Upload" button in the application.

[0266] 2. Sending images

[0267] The device sends image data to the server using an HTTP POST request, in a multipart form data format, using the HTTPS protocol to prevent data loss or formatting inconsistencies.

[0268] Examples:

[0269] The device divides the image of the dog and the image of the pet clothing into packets and sends them to the server along with an HTTP POST request.

[0270] 3. Image Preprocessing

[0271] The server receives the image data and checks its format and size. It then performs preprocessing to standardize the resolution and size, facilitating smooth processing in the generative AI model.

[0272] Examples:

[0273] The server resizes the dog image and pet clothing image to a resolution of 1920x1080 and converts the format from JPEG to PNG.

[0274] 4. Image synthesis using generative AI models

[0275] The server inputs the preprocessed image data into a generative AI model. This generative AI model (e.g., StyleGAN2) recognizes the dog's outline and body shape and adjusts the shape of the pet clothing based on that. It then synthesizes the image of the dog with the image of the pet clothing to generate a fitting image.

[0276] Examples:

[0277] The server extracts the outline from the image of the dog, transforms the image of the pet clothing into a shape that fits the outline, and generates a composite image.

[0278] 5. Encoding and transmitting the composite image

[0279] The server encodes the generated composite image into an appropriate format (e.g. PNG) and sends it to the terminal as an HTTP response.

[0280] Examples:

[0281] The server encodes the composite image into PNG format and sends it.

[0282] 6. Displaying the composite image

[0283] The device decodes the synthesized image received from the server and displays it on the application UI. The user can see the image of their pet wearing the pet clothing on the device screen.

[0284] Examples:

[0285] The terminal decodes the received composite image and displays it full screen on the application screen.

[0286] 7. Emotional Engine Analysis

[0287] The device captures the user's facial expressions with a camera and analyzes them in real time using an emotion engine (e.g., Microsoft Azure Emotional API), which detects the user's emotional state (e.g., joy, surprise, dissatisfaction, etc.).

[0288] Examples:

[0289] The device's front camera captures the user's face and transmits the facial expression data to the emotion engine.

[0290] The emotion engine detects when the user is smiling and reports it to the server.

[0291] 8. Emotional Feedback

[0292] The server analyzes the emotion data obtained from the emotion engine and provides appropriate feedback. For example, if the user is happy, it will suggest pet clothes with a similar design. If the user is unhappy, it will suggest pet clothes with a different style.

[0293] Examples:

[0294] The server determines that the user is satisfied and displays options for pet clothing with similar designs in the UI.

[0295] 9. Accumulation of Emotional Data and Historical Use

[0296] The server accumulates user emotional data and makes personalized suggestions based on past emotional history, allowing it to learn the user's preferences and tendencies and provide more appropriate fitting images and pet clothing suggestions.

[0297] Examples:

[0298] The server stores past emotion data in a database and uses it when making new suggestions.

[0299] Prompt Sentence Examples

[0300] Example prompts to be input to the generative AI model:

[0301] Using a "cat image" and an "image of pet clothing," create a composite image of a cat wearing the clothing.

[0302] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0303] Step 1:

[0304] The user uploads images of their pet and pet clothing to the application using their device. Specifically, the user selects an image from the device's gallery and presses the "Upload" button in the application. This temporarily saves the image to the device's local storage.

[0305] Input: User-selected pet image file and pet clothing image file

[0306] Output: Image data temporarily stored in the device's local storage

[0307] Step 2:

[0308] The device sends the image data to the server using an HTTP POST request. Specifically, the selected image file is attached to the POST request and sent to the specified URL on the server. During the sending process, the image data is converted to a multipart form data format.

[0309] Input: Image data of the pet and image data of the pet's clothes stored on the device

[0310] Output: Image data sent to the server in an HTTP POST request

[0311] Step 3:

[0312] The server validates the received image data, checking its format and size, and then preprocesses the image to unify its size and resolution. Specifically, it resizes the image while maintaining its aspect ratio, and converts JPEG images to PNG format.

[0313] Input: Pet image data and pet clothing image data sent via HTTP POST request

[0314] Output: Pre-processed image data in a unified size and format

[0315] Step 4:

[0316] The server inputs the preprocessed image data into a generative AI model. The generative AI model (e.g., StyleGAN2) recognizes the pet's outline and body shape and adjusts the shape of the pet's clothing based on that. Specifically, it extracts the outline from the pet's image and transforms the image of the pet's clothing into an appropriate shape.

[0317] Input: Preprocessed pet image data and pet clothing image data

[0318] Output: Composite image of pet wearing clothes

[0319] Step 5:

[0320] The server encodes the generated composite image and converts it into an appropriate image format (e.g. PNG). It then returns it to the terminal as an HTTP response. Specifically, it performs the encoding process, adds the necessary information to the response header, and then sends the image.

[0321] Input: Generated synthetic image

[0322] Output: The encoded image sent in the HTTP response.

[0323] Step 6:

[0324] The device decodes the composite image received from the server and displays it on the application UI. Specifically, it decodes the received image data and applies CSS and JavaScript (registered trademark) to display it appropriately on the user's screen.

[0325] Input: Synthetic image data sent from the server

[0326] Output: Composite image displayed in the application UI

[0327] Step 7:

[0328] The device captures the user's facial expressions with a camera and transmits them to the emotion engine in real time. Specifically, it captures the camera image and communicates to send the data to the emotion engine in real time.

[0329] Input: User's facial expression data captured by a camera

[0330] Output: Facial expression data sent to the emotion engine

[0331] Step 8:

[0332] The emotion engine analyzes the user's facial expression data and extracts their emotional state. The server provides feedback and suggestions based on the obtained emotional data. Specifically, the emotion engine analyzes the facial expression data in real time and outputs the emotional state as a number or category.

[0333] Input: Facial expression data sent to the emotion engine

[0334] Output: Analysis results regarding emotional state

[0335] Step 9:

[0336] The server accumulates emotional data and makes personalized suggestions based on the user's past emotional history. Specifically, it stores the emotional data in a database and uses a suggestion algorithm to generate optimal feedback and product suggestions.

[0337] Input: Emotional state data output from the emotion engine

[0338] Output: Personalized feedback and suggestions provided to the user

[0339] (Application example 2)

[0340] 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."

[0341] Conventional pet clothing fitting systems have the problem that simply combining an image of the pet with an image of the pet clothing does not adequately convey to the user what it will actually be like trying on the pet. Furthermore, since no feedback or suggestions are provided based on the user's reactions or emotions, the user experience is not improved.

[0342] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving an image of a pet, means for receiving an image of pet clothing, and means for using a generative AI model to synthesize the received image of the pet with an image of the pet clothing. This makes it possible to provide a try-on image in which the image of the pet and the image of the pet clothing are naturally synthesized. In addition, by including means for acquiring emotion data using an emotion engine that recognizes the user's emotions and means for providing feedback based on the emotion data, personalized feedback and suggestions according to the user's emotions become possible, significantly improving the user experience.

[0343] The "means for receiving a pet image" is a device or interface for importing a photo of a pet taken or selected by a user into the system.

[0344] The "means for receiving an image of pet clothing" is a device or interface for importing a photo of the pet clothing selected by the user into the system.

[0345] A "means for using a generative AI model" is a device or software that runs an AI model using machine learning or deep learning to synthesize an image of a pet with an image of the pet's clothing.

[0346] "Means for displaying a synthesized image to a user" refers to a device or interface for displaying an image synthesized by a generative AI model on a user's device.

[0347] "Means for acquiring emotional data using an emotion engine that recognizes the user's emotions" refers to software or algorithms that determine the user's emotions in real time from their facial expressions, voice, etc.

[0348] The "means for providing feedback based on emotional data" refers to a device or software that analyzes the acquired emotional data of the user and provides appropriate feedback or suggestions to the user based on the results.

[0349] "Means for recognizing the pet's outline and body shape and adjusting the shape of the pet's clothing" refers to a function in which an AI model detects the pet's outline and body shape from a photo of the pet and automatically changes the shape of the pet's clothing accordingly.

[0350] "Means for making personalized suggestions based on emotional data" refers to software or algorithms that suggest optimal pet clothing and related items based on the user's past emotional data and current emotional state.

[0351] The "means for performing fitting adjustment according to the pet's body color and background" is a function that automatically adjusts the color tone and position of the composite image according to the pet's body color and background.

[0352] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described in detail below with reference to the accompanying drawings.

[0353] System Overview

[0354] The system synthesizes an image of the pet taken by the user with an image of the pet clothing the user is considering purchasing, and uses a generative AI model to generate a natural fitting image. It also incorporates an emotion engine that recognizes the user's emotions in real time, allowing it to provide feedback and suggestions based on the user's emotions.

[0355] Hardware and software used

[0356] Hardware

[0357] 1. Smartphone: Take and upload images of your pet and pet clothing, and display a composite image of the clothing to try on. The camera also captures the user's facial expression.

[0358] 2. Cloud server: Receives image data, preprocesses images, synthesizes images using a generative AI model, and analyzes emotional data.

[0359] software

[0360] 1. Requests library: Sends image data via HTTP POST requests.

[0361] 2. Pillow (PIL): Image preprocessing and compositing.

[0362] 3. Generative AI model: An AI model for synthesizing images of pets and pet costumes. It uses machine learning and deep learning techniques.

[0363] 4. FER (Facial Expression Recognition): A facial expression recognition engine that determines the user's emotions in real time.

[0364] 5. Keras library: Supports AI models for emotion recognition.

[0365] What the program does

[0366] Sending images

[0367] The user device sends the photographed or selected image of the pet and the image of the pet's clothing to the server. The transmission is performed using an HTTP POST request, and the image data is sent in multipart form data format, which prevents data loss and format inconsistencies.

[0368] Image Processing and Compositing

[0369] The server preprocesses the received images to standardize the size and resolution, then uses a generative AI model to recognize the pet's contours and body shape, adjust the shape of the pet's clothing, and synthesize it. The synthesized image simulates how the pet will look wearing the clothing and is encoded into the appropriate image format.

[0370] Emotional Recognition and Feedback

[0371] The user device displays the synthesized image and captures the user's facial expression with a camera. The emotion engine analyzes the user's emotional state in real time and sends the data to the server. The server then provides feedback and additional suggestions based on this emotional data, helping the user to purchase the pet clothing they are most satisfied with.

[0372] Specific examples

[0373] User A takes a photo of his dog and wants to buy new pet clothing. User A starts the application, selects a photo of the dog and an image of a candidate pet clothing item, and presses the upload button. The device sends these images to the server. The server processes the received dog image and clothing image and synthesizes them using a generative AI model. A composite image is generated and sent to User A's device. User A checks the composite image, and his facial expression is captured through the camera. The emotion engine analyzes User A's emotions, and additional pet clothing items are suggested accordingly.

[0374] Prompt Sentence Examples

[0375] Combine the "pet image" and the "pet costume image" to create a natural-looking image of the pet wearing the costume.

[0376] By implementing this mode, the user can easily check the image of the pet trying on the clothes, and can select a more appropriate item while receiving feedback that takes emotions into consideration.

[0377] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0378] Step 1:

[0379] The user uses a smartphone to take or select an image of the pet and an image of the pet's clothes and upload them to the application. When the user presses the upload button, the application obtains the image data of the pet and the image data of the pet's clothes and sends both of these image data to the server. The input here is the image of the pet and the image of the pet's clothes, and the output is that these data are sent to the server.

[0380] Step 2:

[0381] The terminal uses an HTTP POST request to send pet image data and pet clothing image data to the server. Here, the image data is sent in multipart form data format to prevent data loss and format inconsistencies. The input is the pet image data and pet clothing image data, and the output is the data being received by the server.

[0382] Step 3:

[0383] The server preprocesses the received images of the pet and pet clothing. Specifically, it standardizes the image size and resolution, removes noise, etc. The input here is the received images of the pet and pet clothing, and the output is the preprocessed image data.

[0384] Step 4:

[0385] The server uses a generative AI model to recognize the pet's contours and body shape, and adjusts the shape of the pet's clothing accordingly. Using the generative AI model, the image of the pet and the image of the pet's clothing are naturally synthesized. The input here is the preprocessed image of the pet and the image of the pet's clothing, and the output is the synthesized image.

[0386] Step 5:

[0387] The server encodes the generated composite image into an appropriate image format and prepares it for transmission to the user's device, where it is encoded into an appropriate format such as JPEG or PNG to ensure compatibility and display quality. The input is the composite image, and the output is the encoded image data.

[0388] Step 6:

[0389] The server sends the encoded composite image to the terminal as an HTTP response. To ensure security, it is recommended to use HTTPS. The input is the encoded image data, and the output is the image data sent to the user's terminal.

[0390] Step 7:

[0391] The user's device decodes the composite image received from the server and displays it on the application's UI. The user can then view the image of their pet wearing the pet clothing. The input is the composite image data received from the server, and the output is the composite image displayed on the application's UI.

[0392] Step 8:

[0393] The user's device uses a camera to capture the user's facial expressions, which are then analyzed in real time by the emotion engine. The emotion engine recognizes the user's emotional state when viewing the pet try-on image. The input is the user's facial expression image, and the output is emotion data.

[0394] Step 9:

[0395] The server analyzes the user's emotional data obtained from the emotion engine and generates appropriate feedback and suggestions based on the emotional data. For example, if the user is happy, it will suggest pet clothes with a similar design, and if the user is unhappy, it will suggest pet clothes with a different style. The input is the user's emotional data, and the output is feedback and suggestions.

[0396] Step 10:

[0397] The server accumulates the user's emotional data and stores it as an emotional history. This allows personalized suggestions to be made in the future based on the past emotional history. The input is the emotional data and feedback history, and the output is the accumulated emotional data.

[0398] 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.

[0399] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0400] 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.

[0401] [Second embodiment]

[0402] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0403] 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.

[0404] 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).

[0405] 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.

[0406] 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.

[0407] 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).

[0408] 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. 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.

[0409] 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.

[0410] 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.

[0411] 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.

[0412] 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.

[0413] 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."

[0414] System Overview

[0415] This invention is a system that simulates trying on pet clothes using images of pets and pet clothes. This system receives images of pets and pet clothes, synthesizes them using a generative AI model, and provides the user with a natural try-on image. The system is broadly composed of a server and a user's terminal.

[0416] Program processing flow

[0417] 1. User Input

[0418] Users use their device to upload images of their pets taken with their smartphone or camera, as well as images of the pet clothing they are considering purchasing, to the application. When the user selects the image files and presses the upload button, the device sends the image data to the server.

[0419] 2. Sending images

[0420] The device sends image data to the server using an HTTP POST request. The image data is sent in a multipart form data format to prevent data loss or inconsistent data formats.

[0421] 3. Image Processing and Composition

[0422] The server processes the received images of the pet and pet clothing. First, it preprocesses the images to unify the size and resolution. Next, it uses a generative AI model to recognize the pet's outline and body shape from the pet image and adjusts the shape of the pet clothing accordingly. The generative AI model uses machine learning and deep learning techniques to perform optimal synthesis based on the input images.

[0423] 4. Generating synthetic images

[0424] The server encodes the resulting composite image into the appropriate image format before sending it back to the device, ensuring compatibility when the image is displayed on the user's device.

[0425] 5. Sending the composite image

[0426] The server sends the generated composite image back to the device as an HTTP response. It is recommended to use HTTPS to ensure communication security.

[0427] 6. Display of fitting images

[0428] The device decodes the composite image received from the server and displays it on the application UI. The user can then view the image of their pet wearing the pet clothing on the device screen.

[0429] Specific examples

[0430] User operations

[0431] User A takes a photo of his dog and wants to buy new pet clothes. User A starts the application, selects a photo of his dog and an image of a candidate pet clothes, and presses the upload button. The device sends these images to the server.

[0432] Server Processing

[0433] The server receives the image of User A's dog and the image of the pet clothing, performs preprocessing, and then uses a generative AI model to synthesize the image of the pet and the image of the pet clothing. The synthesized image simulates the dog wearing the pet clothing.

[0434] Displaying the results

[0435] The server sends the composite image to User A's device, which displays the image on the application's UI. User A checks the dog wearing the new pet clothes and considers purchasing them.

[0436] This system allows users to easily and accurately see how pet clothes will look on their pet without actually trying them on, making it easier to select pet clothes while minimizing stress on the pet.

[0437] The processing flow will be explained below.

[0438] Step 1: User Input

[0439] The user opens the application on the device, selects a photo of the pet and a photo of the pet's clothing, and when the user presses the "Upload" button, the device obtains the path of the selected image file.

[0440] Step 2: Sending images

[0441] The terminal sends the selected image data to the server using an HTTP POST request. At this time, the image data is sent in a multipart form data format.

[0442] Step 3: Receiving the image

[0443] The server receives the HTTP request and saves the image files of the pet and the pet clothes. The saved data is placed in a directory for image processing.

[0444] Step 4: Image preprocessing

[0445] The server performs preprocessing on the stored image data, including standardizing image size, adjusting resolution, and removing noise.

[0446] Step 5: Extracting the pet outline

[0447] The server applies an edge detection algorithm to recognize the pet's contours and shape from the pet image, which gives a clearer picture of the pet's shape in the image.

[0448] Step 6: Applying the generative AI model

[0449] The server uses a generative AI model to synthesize an image of the pet with an image of the pet's clothing, and the generative AI model adjusts the shape of the pet's clothing to fit the synthesized image based on the pet's contours and body shape.

[0450] Step 7: Generate a composite image

[0451] The server generates a synthetic image of the pet wearing the pet clothing as a result of the processing by the generative AI model, which reproduces the natural look of the pet and the clothing.

[0452] Step 8: Encode the composite image

[0453] The server encodes the resulting composite image into JPEG or PNG format, ensuring compatibility and display quality of the image.

[0454] Step 9: Submit your composite image

[0455] The server sends the encoded composite image to the terminal as an HTTP response. The image data may be sent again in multipart form data format.

[0456] Step 10: Receiving the composite image

[0457] The device receives the HTTP response sent from the server and acquires the composite image data, which is then temporarily stored in its internal memory.

[0458] Step 11: Displaying the composite image

[0459] The device decodes the synthesized image and displays it on the application's UI, allowing the user to see the image of their pet wearing the pet clothing on the device screen.

[0460] Example 1

[0461] 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."

[0462] Conventional pet clothing fitting systems require pets to actually try on the clothes, which increases stress for the pet and wastes time. Furthermore, when purchasing online, it is difficult to confirm whether the clothes actually fit the pet, and mismatched sizes or designs are often discovered after purchase. To solve these issues, a system is needed that combines images of the pet and the pet clothing to provide users with a realistic fitting experience.

[0463] 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.

[0464] In this invention, the server includes means for receiving pet images, means for receiving pet clothing images, means for sending image data to the server using an HTTP POST request, means for preprocessing the received pet images and pet clothing images and using a generative AI model, means for encoding and sending the preprocessed images, and means for displaying the synthesized image to the user. This allows the user to easily and accurately check how the pet clothing will look on their pet without actually trying it on.

[0465] A "pet image" is visual information in digital form that includes the entire image or part of a pet.

[0466] "Pet apparel image" means visual information in digital form that visually represents the design or shape of pet apparel or accessories.

[0467] An "HTTP POST request" is one of the methods in the HTTP protocol for sending data to a web server, and is a method that is particularly suitable for sending large amounts of data or multiple pieces of data.

[0468] A "generative AI model" is an algorithm or program that uses machine learning or deep learning techniques to analyze and process input image data and generate output tailored to a specific purpose.

[0469] "Preprocessing" refers to a series of processes such as data resizing, resolution adjustment, and noise removal to convert received image data into a format that is easier to process.

[0470] "Encoding" is the process of converting image data into a specific file format (e.g., JPEG, PNG) to make it easier to store and transfer.

[0471] "Decoding" is the process of converting encoded image data into a format that can be displayed or edited.

[0472] This invention is a system that simulates trying on pet clothes using images of pets and pet clothes. The system receives images of pets and pet clothes, synthesizes them using a generative AI model, and provides the user with a natural fitting image. The system is mainly composed of a server and a user's terminal.

[0473] User Input

[0474] The user takes a picture of their pet using a smartphone or digital camera. They also prepare an image of the pet clothing they are considering purchasing. The user launches the application, selects the image of the pet and the image of the pet clothing from the file browser, and clicks the upload button. This causes the device to prepare the image data and proceed to the next step.

[0475] Sending images

[0476] The device sends image data to the server using an HTTP POST request. At this time, the image data is sent in multipart form data format, which prevents data loss and format inconsistencies. Specifically, the device includes the image file in the body of the HTTP request and sends the request to the specified endpoint on the server.

[0477] Image Processing and Compositing

[0478] The server processes the received images of the pet and pet clothing. First, as a pre-processing step, the images are resized to unify the size and resolution. Then, a generative AI model is used to recognize the pet's outline and body shape from the pet image. This generative AI model is built using deep learning frameworks such as TensorFlow and PyTorch. This generative AI model calculates the optimal shape and placement of the clothing for the pet and synthesizes a realistic image.

[0479] Generate synthetic images

[0480] The server encodes the composite image into an appropriate image format before sending it back to the device, specifically using a library like Pillow or OpenCV to encode the generated image into a format like JPEG or PNG, ensuring compatibility when the image is displayed on the user's device.

[0481] Sending a composite image

[0482] The server returns the generated composite image to the terminal as an HTTP response. To ensure communication security, it is recommended to use HTTPS (HTTP using SSL / TLS). The server sets the appropriate content type (e.g., image / jpeg) in the response header and sends the image data in the response body.

[0483] Display of try-on images

[0484] The device decodes the composite image received from the server and displays it on the application's UI. First, the received image data is loaded into a buffer and decoded using an image display library. The decoded image is then displayed in a specific view of the application. The user can view the image of their pet wearing pet clothing on the device screen.

[0485] Specific examples

[0486] 1. The user opens the application, selects an image of the pet and an image of the pet clothing, and presses the upload button.

[0487] 2. The device sends the image data to the server using an HTTP POST request.

[0488] 3. The server preprocesses the image and synthesizes it using a generative AI model.

[0489] 4. The server encodes the composite image and sends it to the device as an HTTP response.

[0490] 5. The device receives the composite image, decodes it, and displays it in the application UI.

[0491] Example prompts for generative AI models:

[0492] "Generate a composite image using an image of a dog and an image of a dog T-shirt."

[0493] The present invention provides a system that allows users to easily and accurately check how pet clothing will look on their pet without actually trying it on, thereby enabling smooth selection of pet clothing while minimizing stress on the pet.

[0494] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0495] Step 1: User Input

[0496] The user uses a device to upload images of their pet and pet clothing to the application. Specifically, they prepare images of their pet taken with a smartphone or digital camera, as well as images of the pet clothing they are considering purchasing. The user selects these image files from the file browser within the application and clicks the upload button to complete the input. The input here is the image of the pet and the image of the pet clothing, and this data will be used in the next step.

[0497] Step 2: Sending images

[0498] The terminal sends the selected image data to the server using an HTTP POST request. Specifically, the terminal encodes the image data in a multipart form data format and includes it in the body of the HTTP request. The terminal then sends the request to the specified endpoint of the server. The input of this step is the image data selected by the user, and the output is the image data sent to the server.

[0499] Step 3: Image preprocessing

[0500] The server preprocesses the received image data. Specifically, it performs resizing to unify the image size and resolution, noise removal, color correction, etc. The input to this step is the image of the pet and the image of the pet's clothing sent from the terminal, and outputs image data in a unified format.

[0501] Step 4: Image synthesis using a generative AI model

[0502] The server inputs the preprocessed image data into a generative AI model, which recognizes the pet's contours and body shape and adjusts the shape of the pet clothing accordingly. The generative AI model is built using deep learning frameworks such as TensorFlow and PyTorch. The input of this step is the preprocessed image data, and the output is the generated synthetic image.

[0503] Step 5: Encode the composite image

[0504] The server encodes the generated composite image into an appropriate image format, such as JPEG or PNG, using a library like Pillow or OpenCV. The input to this step is the generated composite image, and the output is the encoded image data.

[0505] Step 6: Submit your composite image

[0506] The server returns the encoded composite image to the terminal as an HTTP response, using HTTPS (HTTP using SSL / TLS) to ensure communication security. The server sets the appropriate content type (e.g., image / jpeg) in the response header and sends the image data in the response body. The input to this step is the encoded composite image, and the output is the composite image sent to the terminal.

[0507] Step 7: Displaying fitting images

[0508] The device decodes the received composite image and displays it on the application's UI. Specifically, the device first loads the received image data into a buffer and decodes it using an image display library. The decoded image is then displayed in a specific view of the application. The input to this step is the encoded composite image received from the server, and the output is the try-on image displayed on the user's screen.

[0509] The above is the specific processing flow of this system.

[0510] (Application example 1)

[0511] 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."

[0512] When purchasing pet clothing in the past, it was necessary to actually try it on the pet, which caused stress and trouble for the pet. Also, when purchasing online, there was a risk that the size or design would not fit after purchase because it was not possible to try it on.

[0513] 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.

[0514] In this invention, the server includes means for receiving an image of a pet, means for receiving an image of a pet garment, means for using a generative AI model to synthesize the received image of the pet with an image of the pet garment, means for displaying the synthesized image to a user, and means for transmitting the synthesized image to a user terminal using a communication protocol, thereby enabling a user to check the effect of trying on pet garments online in real time without actually trying them on their pet.

[0515] The "means for receiving pet images" is a function that allows a user to send a photo of their pet from the terminal to the server.

[0516] The "means for receiving images of pet clothes" is a function for transmitting images of the pet clothes that the user wishes to try on from the terminal to the server.

[0517] "Means for using a generative AI model to synthesize received images of pets and images of pet clothing" refers to AI technology used to combine images of pets and images of pet clothing to generate natural-looking images for trying on.

[0518] The "means for displaying the synthesized image to the user" is a function for displaying the generated try-on image on the user's terminal.

[0519] The "means for transmitting the synthesized image to the user terminal using a communication protocol" refers to a communication technology used to securely transmit the generated try-on image to the user terminal.

[0520] "Means for recognizing the pet's contours and body shape and adjusting the shape of the pet's clothing" is a function that enables the generative AI model to optimize the shape of the clothing to match the shape of the pet.

[0521] "Means for adjusting fitting according to the pet's body color and background" is a function that enables the generative AI model to adjust the fit of the synthetic image according to the pet's body color and background.

[0522] The present invention is a system for simulating trying on pet clothes using images of a pet and pet clothes. Detailed explanations of the implementation of the system are given below.

[0523] System Configuration

[0524] This system mainly consists of a server and a user device. The user device can be a smartphone or tablet, and the server is a cloud server.

[0525] Hardware and software used

[0526] Server: Cloud Server

[0527] User devices: smartphones, tablets

[0528] Generative AI models: VQ-VAE and GAN models trained using TensorFlow or PyTorch

[0529] Image processing library: OpenCV

[0530] Communication protocol: HTTPS protocol

[0531] Program processing

[0532] User operations

[0533] Using the application, users first take a photo of their pet and then upload an image of the pet clothing they want to try on. This process is very intuitive and can be easily done on the application screen.

[0534] Sending images

[0535] The user device sends image data to the server using an HTTP POST request. The image data is sent in a multipart form data format to prevent data loss or format inconsistencies.

[0536] Image Processing and Compositing

[0537] The server performs the following processes on the received pet images and pet costume images:

[0538] 1. First, preprocess the images to unify their size and resolution.

[0539] 2. Next, a generative AI model (e.g., VQ-VAE or GAN) is used to synthesize an image of the pet with an image of the pet costume. The generative AI model recognizes the pet's contours and body shape and adjusts the pet costume based on that shape.

[0540] Generate and transmit synthetic images

[0541] The server encodes the resulting composite image into the appropriate image format (JPEG or PNG) and then sends it back to the user's device using HTTPS, ensuring secure communication.

[0542] Display of try-on images

[0543] The user device decodes the received composite image and displays it on the application UI, allowing the user to see how their pet will actually look wearing the pet costume.

[0544] Specific examples

[0545] For example, if a user uploads a photo of their dog (e.g., a Shiba Inu) and selects an image of a blue sweater, the generative AI model will combine these images to create an image of the dog wearing the blue sweater, which the user can view and consider purchasing.

[0546] Prompt Sentence Examples

[0547] Using a picture of a pet and a picture of a pet costume, simulate a pet wearing the pet costume. The pet is a picture of a dog, and the costume is an image of a blue sweater.

[0548] This allows users to check the effects of trying on pet clothes online in real time without actually trying them on their pets.

[0549] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0550] Step 1:

[0551] The user launches the application and uploads images of their pet and pet costume by selecting images from their smartphone's camera or photo gallery. The input is the image files of the pet and pet costume, and the output is the image data of these.

[0552] Step 2:

[0553] The terminal sends the pet image and pet costume image uploaded by the user to the server. The communication protocol is HTTP POST request, and the image data is sent in multipart form data format. The input is the image file, and the output is the image data sent to the server.

[0554] Step 3:

[0555] The server preprocesses the received pet images and pet costume images, including image resizing, resolution unification, noise removal, etc. The input is the received image data, and the output is the preprocessed image data.

[0556] Step 4:

[0557] The server uses a generative AI model (e.g., VQ-VAE or GAN) to synthesize an image of the pet and an image of the pet costume. The generative AI model recognizes the pet's contours and body shape and adjusts the pet costume based on that shape. The input is the preprocessed image of the pet and the pet costume, and the output is a synthesized try-on image.

[0558] Step 5:

[0559] The server encodes the composite try-on image into the appropriate image format (JPEG or PNG) to display the image correctly on the user's device. The input is the composite try-on image, and the output is the encoded image file.

[0560] Step 6:

[0561] The server sends the encoded image file to the user terminal using HTTPS, which ensures communication security. The input is the encoded image file, and the output is the image data sent to the user terminal.

[0562] Step 7:

[0563] The device decodes the composite image received from the server and displays it on the application UI. The user can see the image of their pet wearing the pet costume through the decoded image. The input is the received image data, and the output is the try-on image displayed to the user.

[0564] 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.

[0565] System Overview

[0566] This invention is a system that simulates trying on pet clothes using images of pets and pet clothes, and also combines it with an emotion engine that recognizes the user's emotions. This system receives images of pets and pet clothes, synthesizes them using a generative AI model, and provides the user with a natural trying-on image. It also has the ability to recognize the user's emotions and provide feedback and suggestions based on those emotions. The main components of the system are a server and a user's terminal.

[0567] Program processing flow

[0568] 1. User Input

[0569] Users use their device to upload images of their pets taken with their smartphone or camera, as well as images of the pet clothing they are considering purchasing, to the application. When the user selects the image files and presses the upload button, the device sends the image data to the server.

[0570] 2. Sending images

[0571] The device sends image data to the server using an HTTP POST request. The image data is sent in a multipart form data format to prevent data loss or inconsistent data formats.

[0572] 3. Image Processing and Composition

[0573] The server processes the received images of the pet and pet clothing. First, it preprocesses the images to unify the size and resolution. Next, it uses a generative AI model to recognize the pet's outline and body shape from the pet image and adjusts the shape of the pet clothing accordingly. The generative AI model uses machine learning and deep learning techniques to perform optimal synthesis based on the input images.

[0574] 4. Generating synthetic images

[0575] The server encodes the resulting composite image into the appropriate image format before sending it back to the device, ensuring compatibility when the image is displayed on the user's device.

[0576] 5. Sending the composite image

[0577] The server sends the generated composite image back to the device as an HTTP response. It is recommended to use HTTPS to ensure communication security.

[0578] 6. Display of fitting images

[0579] The device decodes the composite image received from the server and displays it on the application UI. The user can then view the image of their pet wearing the pet clothing on the device screen.

[0580] 7. Emotional Engine Analysis

[0581] The device captures the user's facial expressions with a camera and analyzes them in real time with an emotion engine that detects the user's emotional state (e.g., joy, surprise, dissatisfaction, etc.) when viewing the pet try-on image.

[0582] 8. Emotional Feedback

[0583] The server analyzes the user's emotion data obtained from the emotion engine and provides appropriate feedback. For example, if the user is happy, it will suggest pet clothes with a similar design. If the user is unhappy, it will suggest pet clothes with a different style.

[0584] 9. Accumulation of Emotional Data and Historical Use

[0585] The server accumulates the user's emotional data and makes personalized suggestions based on their past emotional history. This allows the server to learn the user's preferences and tendencies, and provide more appropriate fitting images and clothing suggestions.

[0586] Specific examples

[0587] User operations

[0588] User B takes a photo of his cat and wants to buy new pet clothes. User B starts the application, selects a photo of the cat and an image of the candidate pet clothes, and presses the upload button. The device sends these images to the server.

[0589] Server Processing

[0590] The server receives the image of User B's cat and the image of the pet clothing, performs preprocessing, and then uses a generative AI model to synthesize the image of the pet and the image of the pet clothing. The synthesized image simulates the cat wearing the pet clothing.

[0591] Results display and sentiment analysis

[0592] The server sends the synthesized image to User B's device, which displays the image on the application's UI. User B checks that the cat is wearing the new pet clothes, and its facial expressions are captured through the camera. The emotion engine analyzes User B's emotional state, and the server provides feedback and additional suggestions based on this.

[0593] This system allows users to easily and accurately check how pet clothes will look on their pets without actually trying them on. Feedback that takes the user's emotions into account also enables more appropriate clothing selection, improving the user experience.

[0594] The processing flow will be explained below.

[0595] Step 1: User Input

[0596] The user opens the application on the device, selects a photo of the pet and a photo of the pet's clothing, and when the user presses the "Upload" button, the device obtains the path of the selected image file and prepares the image data.

[0597] Step 2: Sending images

[0598] The terminal sends the prepared pet image and pet clothing image to the server using an HTTP POST request, where the image data is sent in a multipart form data format.

[0599] Step 3: Receiving the image

[0600] The server receives the HTTP POST request and saves the submitted pet image and pet clothing image files in a specific directory for processing.

[0601] Step 4: Image preprocessing

[0602] The server performs preprocessing on the images of the pet and pet clothing stored in the storage. This preprocessing includes resizing the images, adjusting the resolution, and removing noise. This process converts both images into a format that is easy for the generative AI model to process.

[0603] Step 5: Extracting the pet outline

[0604] The server applies a contour extraction algorithm to the pre-processed pet image, which clearly identifies the pet's contours and body shape, providing the data needed for subsequent image synthesis.

[0605] Step 6: Applying the generative AI model

[0606] The server uses a generative AI model to synthesize an image of the pet and an image of the pet's clothing. The generative AI model adjusts the shape of the pet's clothing appropriately based on the pet's outline information, resulting in a natural-looking composition.

[0607] Step 7: Generate a composite image

[0608] The server generates a composite image of the pet wearing the pet clothing as a result of the generative AI model processing, and the composite image is encoded in JPEG or PNG format to ensure display compatibility.

[0609] Step 8: Submit your composite image

[0610] The server sends the encoded composite image to the terminal as an HTTP response. Image data must be sent in an appropriate format, and it is recommended to use HTTPS for communication security.

[0611] Step 9: Receiving the composite image

[0612] The device receives the HTTP response sent from the server and acquires the composite image data, which is then temporarily stored in the device's internal memory.

[0613] Step 10: Displaying the composite image

[0614] The device decodes the temporarily stored composite image and displays it on the application's UI, allowing the user to see the image of their pet wearing the pet clothing on the device screen.

[0615] Step 11: Activating the Emotion Engine

[0616] The device captures the user's facial expressions with a camera and activates the emotion engine, which analyzes the user's emotional state in real time and sends the data to the server.

[0617] Step 12: Analyze the sentiment data

[0618] The server analyzes the user's emotion data sent from the emotion engine, using facial recognition algorithms and machine learning models to detect the user's emotional state, such as joy, surprise, or dissatisfaction.

[0619] Step 13: Emotional Feedback

[0620] The server then provides appropriate feedback to the user based on the analyzed emotional data. For example, if the user is happy, it will automatically suggest pet clothes with a similar design. If the user is unhappy, it will suggest pet clothes with a different style.

[0621] Step 14: Accumulating Emotional Data and Using History

[0622] The server accumulates the user's emotional data and makes personalized suggestions based on their past emotional history. This allows the system to learn the user's preferences and tendencies, and provide more appropriate fitting images and pet clothing suggestions.

[0623] Example 2

[0624] 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."

[0625] Conventional pet clothing fitting systems require users to actually try on clothes, which places a heavy burden on the user. Furthermore, they do not provide feedback that takes into account the user's reactions and emotions, making it difficult to select appropriate pet clothing. Furthermore, when shopping online, there is a high risk of purchasing products that do not fit the pet's size or shape.

[0626] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving a pet image, means for receiving an image of a pet clothing, means for using a generative AI model to synthesize the received pet image with an image of the pet clothing, means for displaying the synthesized image to the user, means for using an emotion engine to recognize the user's emotional state, and means for providing feedback and suggestions based on emotion data obtained from the emotion engine. This allows the user to naturally check how pet clothing will look on their pet without actually trying it on their pet, and feedback that takes the user's emotions into consideration enables more appropriate clothing selection.

[0627] The "means for receiving pet images" refers to an interface and communication mechanism that allows a user to use a terminal to upload pet photo data to the system.

[0628] The "means for receiving images of pet clothing" refers to an interface and communication mechanism that allows users to upload photographic data of candidate pet clothing to the system.

[0629] "Means for using generative AI models" refers to algorithms and software that utilize machine learning and deep learning techniques to synthesize images of pets and images of pet clothing.

[0630] The "means for displaying a synthesized image to a user" refers to an interface and communication mechanism for transferring the synthesized image created by the generative AI model to a user's terminal and displaying it.

[0631] The "means for using an emotion engine" is an algorithm and software for capturing a user's facial expressions using a camera and analyzing the expression data to extract an emotional state.

[0632] The "means for providing feedback and suggestions based on emotional data" refers to algorithms and software that analyze the user's emotional data obtained from the emotion engine and provide the user with appropriate feedback and suggestions for pet clothing based on the results.

[0633] System Overview

[0634] This invention is a system that simulates trying on pet clothes using images of pets and pet clothes, and also combines it with an emotion engine that recognizes the user's emotions. This system receives images of pets and pet clothes, synthesizes them using a generative AI model, and provides the user with a natural trying-on image. It also has the ability to recognize the user's emotions and provide feedback and suggestions based on those emotions. The main components of the system are a server and a user's terminal.

[0635] Hardware and software used

[0636] Devices: smartphones, tablets, personal computers, etc.

[0637] Server: Cloud server or on-premise server

[0638] Generative AI models: Deep learning models such as StyleGAN2 and VGG-19

[0639] Emotion engine: Microsoft Azure Emotional API, Google Cloud Vision API, etc.

[0640] Specific processing outline of the program

[0641] 1. User Input

[0642] The user uses the device to upload images of their pet and the pet clothing they are considering purchasing to the application. The user selects the image files and presses the "Upload" button. At this point, the device temporarily stores these image files.

[0643] Examples:

[0644] User A takes a photo of the dog with their smartphone, selects an image of the pet clothing from the device's gallery, and presses the "Upload" button in the application.

[0645] 2. Sending images

[0646] The device sends image data to the server using an HTTP POST request, in a multipart form data format, using the HTTPS protocol to prevent data loss or formatting inconsistencies.

[0647] Examples:

[0648] The device divides the image of the dog and the image of the pet clothing into packets and sends them to the server along with an HTTP POST request.

[0649] 3. Image Preprocessing

[0650] The server receives the image data and checks its format and size. It then performs preprocessing to standardize the resolution and size, facilitating smooth processing in the generative AI model.

[0651] Examples:

[0652] The server resizes the dog image and pet clothing image to a resolution of 1920x1080 and converts the format from JPEG to PNG.

[0653] 4. Image synthesis using generative AI models

[0654] The server inputs the preprocessed image data into a generative AI model. This generative AI model (e.g., StyleGAN2) recognizes the dog's outline and body shape and adjusts the shape of the pet clothing based on that. It then synthesizes the image of the dog with the image of the pet clothing to generate a fitting image.

[0655] Examples:

[0656] The server extracts the outline from the image of the dog, transforms the image of the pet clothing into a shape that fits the outline, and generates a composite image.

[0657] 5. Encoding and transmitting the composite image

[0658] The server encodes the generated composite image into an appropriate format (e.g. PNG) and sends it to the terminal as an HTTP response.

[0659] Examples:

[0660] The server encodes the composite image into PNG format and sends it.

[0661] 6. Displaying the composite image

[0662] The device decodes the synthesized image received from the server and displays it on the application UI. The user can see the image of their pet wearing the pet clothing on the device screen.

[0663] Examples:

[0664] The terminal decodes the received composite image and displays it full screen on the application screen.

[0665] 7. Emotional Engine Analysis

[0666] The device captures the user's facial expressions with a camera and analyzes them in real time using an emotion engine (e.g., Microsoft Azure Emotional API), which detects the user's emotional state (e.g., joy, surprise, dissatisfaction, etc.).

[0667] Examples:

[0668] The device's front camera captures the user's face and transmits the facial expression data to the emotion engine.

[0669] The emotion engine detects when the user is smiling and reports it to the server.

[0670] 8. Emotional Feedback

[0671] The server analyzes the emotion data obtained from the emotion engine and provides appropriate feedback. For example, if the user is happy, it will suggest pet clothes with a similar design. If the user is unhappy, it will suggest pet clothes with a different style.

[0672] Examples:

[0673] The server determines that the user is satisfied and displays options for pet clothing with similar designs in the UI.

[0674] 9. Accumulation of Emotional Data and Historical Use

[0675] The server accumulates user emotional data and makes personalized suggestions based on past emotional history, allowing it to learn the user's preferences and tendencies and provide more appropriate fitting images and pet clothing suggestions.

[0676] Examples:

[0677] The server stores past emotion data in a database and uses it when making new suggestions.

[0678] Prompt Sentence Examples

[0679] Example prompts to be input to the generative AI model:

[0680] Using a "cat image" and an "image of pet clothing," create a composite image of a cat wearing the clothing.

[0681] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0682] Step 1:

[0683] The user uploads images of their pet and pet clothing to the application using their device. Specifically, the user selects an image from the device's gallery and presses the "Upload" button in the application. This temporarily saves the image to the device's local storage.

[0684] Input: User-selected pet image file and pet clothing image file

[0685] Output: Image data temporarily stored in the device's local storage

[0686] Step 2:

[0687] The device sends the image data to the server using an HTTP POST request. Specifically, the selected image file is attached to the POST request and sent to the specified URL on the server. During the sending process, the image data is converted to a multipart form data format.

[0688] Input: Image data of the pet and image data of the pet's clothes stored on the device

[0689] Output: Image data sent to the server in an HTTP POST request

[0690] Step 3:

[0691] The server validates the received image data, checking its format and size, and then preprocesses the image to unify its size and resolution. Specifically, it resizes the image while maintaining its aspect ratio, and converts JPEG images to PNG format.

[0692] Input: Pet image data and pet clothing image data sent via HTTP POST request

[0693] Output: Pre-processed image data in a unified size and format

[0694] Step 4:

[0695] The server inputs the preprocessed image data into a generative AI model. The generative AI model (e.g., StyleGAN2) recognizes the pet's outline and body shape and adjusts the shape of the pet's clothing based on that. Specifically, it extracts the outline from the pet's image and transforms the image of the pet's clothing into an appropriate shape.

[0696] Input: Preprocessed pet image data and pet clothing image data

[0697] Output: Composite image of pet wearing clothes

[0698] Step 5:

[0699] The server encodes the generated composite image and converts it into an appropriate image format (e.g. PNG). It then returns it to the terminal as an HTTP response. Specifically, it performs the encoding process, adds the necessary information to the response header, and then sends the image.

[0700] Input: Generated synthetic image

[0701] Output: The encoded image sent in the HTTP response.

[0702] Step 6:

[0703] The device decodes the composite image received from the server and displays it on the application's UI. Specifically, it decodes the received image data and applies CSS and JavaScript to display it appropriately on the user's screen.

[0704] Input: Synthetic image data sent from the server

[0705] Output: Composite image displayed in the application UI

[0706] Step 7:

[0707] The device captures the user's facial expressions with a camera and transmits them to the emotion engine in real time. Specifically, it captures the camera image and communicates to send the data to the emotion engine in real time.

[0708] Input: User's facial expression data captured by a camera

[0709] Output: Facial expression data sent to the emotion engine

[0710] Step 8:

[0711] The emotion engine analyzes the user's facial expression data and extracts their emotional state. The server provides feedback and suggestions based on the obtained emotional data. Specifically, the emotion engine analyzes the facial expression data in real time and outputs the emotional state as a number or category.

[0712] Input: Facial expression data sent to the emotion engine

[0713] Output: Analysis results regarding emotional state

[0714] Step 9:

[0715] The server accumulates emotional data and makes personalized suggestions based on the user's past emotional history. Specifically, it stores the emotional data in a database and uses a suggestion algorithm to generate optimal feedback and product suggestions.

[0716] Input: Emotional state data output from the emotion engine

[0717] Output: Personalized feedback and suggestions provided to the user

[0718] (Application example 2)

[0719] 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."

[0720] Conventional pet clothing fitting systems have the problem that simply combining an image of the pet with an image of the pet clothing does not adequately convey to the user what it will actually be like trying on the pet. Furthermore, since no feedback or suggestions are provided based on the user's reactions or emotions, the user experience is not improved.

[0721] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving an image of a pet, means for receiving an image of pet clothing, and means for using a generative AI model to synthesize the received image of the pet with an image of the pet clothing. This makes it possible to provide a try-on image in which the image of the pet and the image of the pet clothing are naturally synthesized. In addition, by including means for acquiring emotion data using an emotion engine that recognizes the user's emotions and means for providing feedback based on the emotion data, personalized feedback and suggestions according to the user's emotions become possible, significantly improving the user experience.

[0722] The "means for receiving a pet image" is a device or interface for importing a photo of a pet taken or selected by a user into the system.

[0723] The "means for receiving an image of pet clothing" is a device or interface for importing a photo of the pet clothing selected by the user into the system.

[0724] A "means for using a generative AI model" is a device or software that runs an AI model using machine learning or deep learning to synthesize an image of a pet with an image of the pet's clothing.

[0725] "Means for displaying a synthesized image to a user" refers to a device or interface for displaying an image synthesized by a generative AI model on a user's device.

[0726] "Means for acquiring emotional data using an emotion engine that recognizes the user's emotions" refers to software or algorithms that determine the user's emotions in real time from their facial expressions, voice, etc.

[0727] The "means for providing feedback based on emotional data" refers to a device or software that analyzes the acquired emotional data of the user and provides appropriate feedback or suggestions to the user based on the results.

[0728] "Means for recognizing the pet's outline and body shape and adjusting the shape of the pet's clothing" refers to a function in which an AI model detects the pet's outline and body shape from a photo of the pet and automatically changes the shape of the pet's clothing accordingly.

[0729] "Means for making personalized suggestions based on emotional data" refers to software or algorithms that suggest optimal pet clothing and related items based on the user's past emotional data and current emotional state.

[0730] The "means for performing fitting adjustment according to the pet's body color and background" is a function that automatically adjusts the color tone and position of the composite image according to the pet's body color and background.

[0731] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described in detail below with reference to the accompanying drawings.

[0732] System Overview

[0733] The system synthesizes an image of the pet taken by the user with an image of the pet clothing the user is considering purchasing, and uses a generative AI model to generate a natural fitting image. It also incorporates an emotion engine that recognizes the user's emotions in real time, allowing it to provide feedback and suggestions based on the user's emotions.

[0734] Hardware and software used

[0735] Hardware

[0736] 1. Smartphone: Take and upload images of your pet and pet clothing, and display a composite image of the clothing to try on. The camera also captures the user's facial expression.

[0737] 2. Cloud server: Receives image data, preprocesses images, synthesizes images using a generative AI model, and analyzes emotional data.

[0738] software

[0739] 1. Requests library: Sends image data via HTTP POST requests.

[0740] 2. Pillow (PIL): Image preprocessing and compositing.

[0741] 3. Generative AI model: An AI model for synthesizing images of pets and pet costumes. It uses machine learning and deep learning techniques.

[0742] 4. FER (Facial Expression Recognition): A facial expression recognition engine that determines the user's emotions in real time.

[0743] 5. Keras library: Supports AI models for emotion recognition.

[0744] What the program does

[0745] Sending images

[0746] The user device sends the photographed or selected image of the pet and the image of the pet's clothing to the server. The transmission is performed using an HTTP POST request, and the image data is sent in multipart form data format, which prevents data loss and format inconsistencies.

[0747] Image Processing and Compositing

[0748] The server preprocesses the received images to standardize the size and resolution, then uses a generative AI model to recognize the pet's contours and body shape, adjust the shape of the pet's clothing, and synthesize it. The synthesized image simulates how the pet will look wearing the clothing and is encoded into the appropriate image format.

[0749] Emotional Recognition and Feedback

[0750] The user device displays the synthesized image and captures the user's facial expression with a camera. The emotion engine analyzes the user's emotional state in real time and sends the data to the server. The server then provides feedback and additional suggestions based on this emotional data, helping the user to purchase the pet clothing they are most satisfied with.

[0751] Specific examples

[0752] User A takes a photo of his dog and wants to buy new pet clothing. User A starts the application, selects a photo of the dog and an image of a candidate pet clothing item, and presses the upload button. The device sends these images to the server. The server processes the received dog image and clothing image and synthesizes them using a generative AI model. A composite image is generated and sent to User A's device. User A checks the composite image, and his facial expression is captured through the camera. The emotion engine analyzes User A's emotions, and additional pet clothing items are suggested accordingly.

[0753] Prompt Sentence Examples

[0754] Combine the "pet image" and the "pet costume image" to create a natural-looking image of the pet wearing the costume.

[0755] By implementing this mode, the user can easily check the image of the pet trying on the clothes, and can select a more appropriate item while receiving feedback that takes emotions into consideration.

[0756] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0757] Step 1:

[0758] The user uses a smartphone to take or select an image of the pet and an image of the pet's clothes and upload them to the application. When the user presses the upload button, the application obtains the image data of the pet and the image data of the pet's clothes and sends both of these image data to the server. The input here is the image of the pet and the image of the pet's clothes, and the output is that these data are sent to the server.

[0759] Step 2:

[0760] The terminal uses an HTTP POST request to send pet image data and pet clothing image data to the server. Here, the image data is sent in multipart form data format to prevent data loss and format inconsistencies. The input is the pet image data and pet clothing image data, and the output is the data being received by the server.

[0761] Step 3:

[0762] The server preprocesses the received images of the pet and pet clothing. Specifically, it standardizes the image size and resolution, removes noise, etc. The input here is the received images of the pet and pet clothing, and the output is the preprocessed image data.

[0763] Step 4:

[0764] The server uses a generative AI model to recognize the pet's contours and body shape, and adjusts the shape of the pet's clothing accordingly. Using the generative AI model, the image of the pet and the image of the pet's clothing are naturally synthesized. The input here is the preprocessed image of the pet and the image of the pet's clothing, and the output is the synthesized image.

[0765] Step 5:

[0766] The server encodes the generated composite image into an appropriate image format and prepares it for transmission to the user's device, where it is encoded into an appropriate format such as JPEG or PNG to ensure compatibility and display quality. The input is the composite image, and the output is the encoded image data.

[0767] Step 6:

[0768] The server sends the encoded composite image to the terminal as an HTTP response. To ensure security, it is recommended to use HTTPS. The input is the encoded image data, and the output is the image data sent to the user's terminal.

[0769] Step 7:

[0770] The user's device decodes the composite image received from the server and displays it on the application's UI. The user can then view the image of their pet wearing the pet clothing. The input is the composite image data received from the server, and the output is the composite image displayed on the application's UI.

[0771] Step 8:

[0772] The user's device uses a camera to capture the user's facial expressions, which are then analyzed in real time by the emotion engine. The emotion engine recognizes the user's emotional state when viewing the pet try-on image. The input is the user's facial expression image, and the output is emotion data.

[0773] Step 9:

[0774] The server analyzes the user's emotional data obtained from the emotion engine and generates appropriate feedback and suggestions based on the emotional data. For example, if the user is happy, it will suggest pet clothes with a similar design, and if the user is unhappy, it will suggest pet clothes with a different style. The input is the user's emotional data, and the output is feedback and suggestions.

[0775] Step 10:

[0776] The server accumulates the user's emotional data and stores it as an emotional history. This allows personalized suggestions to be made in the future based on the past emotional history. The input is the emotional data and feedback history, and the output is the accumulated emotional data.

[0777] 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.

[0778] 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.

[0779] 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.

[0780] [Third embodiment]

[0781] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0782] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0783] 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).

[0784] 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.

[0785] 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.

[0786] 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).

[0787] 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. 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.

[0788] 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.

[0789] 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.

[0790] 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.

[0791] 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.

[0792] 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."

[0793] System Overview

[0794] This invention is a system that simulates trying on pet clothes using images of pets and pet clothes. This system receives images of pets and pet clothes, synthesizes them using a generative AI model, and provides the user with a natural try-on image. The system is broadly composed of a server and a user's terminal.

[0795] Program processing flow

[0796] 1. User Input

[0797] Users use their device to upload images of their pets taken with their smartphone or camera, as well as images of the pet clothing they are considering purchasing, to the application. When the user selects the image files and presses the upload button, the device sends the image data to the server.

[0798] 2. Sending images

[0799] The device sends image data to the server using an HTTP POST request. The image data is sent in a multipart form data format to prevent data loss or inconsistent data formats.

[0800] 3. Image Processing and Composition

[0801] The server processes the received images of the pet and pet clothing. First, it preprocesses the images to unify the size and resolution. Next, it uses a generative AI model to recognize the pet's outline and body shape from the pet image and adjusts the shape of the pet clothing accordingly. The generative AI model uses machine learning and deep learning techniques to perform optimal synthesis based on the input images.

[0802] 4. Generating synthetic images

[0803] The server encodes the resulting composite image into the appropriate image format before sending it back to the device, ensuring compatibility when the image is displayed on the user's device.

[0804] 5. Sending the composite image

[0805] The server sends the generated composite image back to the device as an HTTP response. It is recommended to use HTTPS to ensure communication security.

[0806] 6. Display of fitting images

[0807] The device decodes the composite image received from the server and displays it on the application UI. The user can then view the image of their pet wearing the pet clothing on the device screen.

[0808] Specific examples

[0809] User operations

[0810] User A takes a photo of his dog and wants to buy new pet clothes. User A starts the application, selects a photo of his dog and an image of a candidate pet clothes, and presses the upload button. The device sends these images to the server.

[0811] Server Processing

[0812] The server receives the image of User A's dog and the image of the pet clothing, performs preprocessing, and then uses a generative AI model to synthesize the image of the pet and the image of the pet clothing. The synthesized image simulates the dog wearing the pet clothing.

[0813] Displaying the results

[0814] The server sends the composite image to User A's device, which displays the image on the application's UI. User A checks the dog wearing the new pet clothes and considers purchasing them.

[0815] This system allows users to easily and accurately see how pet clothes will look on their pet without actually trying them on, making it easier to select pet clothes while minimizing stress on the pet.

[0816] The processing flow will be explained below.

[0817] Step 1: User Input

[0818] The user opens the application on the device, selects a photo of the pet and a photo of the pet's clothing, and when the user presses the "Upload" button, the device obtains the path of the selected image file.

[0819] Step 2: Sending images

[0820] The terminal sends the selected image data to the server using an HTTP POST request. At this time, the image data is sent in a multipart form data format.

[0821] Step 3: Receiving the image

[0822] The server receives the HTTP request and saves the image files of the pet and the pet clothes. The saved data is placed in a directory for image processing.

[0823] Step 4: Image preprocessing

[0824] The server performs preprocessing on the stored image data, including standardizing image size, adjusting resolution, and removing noise.

[0825] Step 5: Extracting the pet outline

[0826] The server applies an edge detection algorithm to recognize the pet's contours and shape from the pet image, which gives a clearer picture of the pet's shape in the image.

[0827] Step 6: Applying the generative AI model

[0828] The server uses a generative AI model to synthesize an image of the pet with an image of the pet's clothing, and the generative AI model adjusts the shape of the pet's clothing to fit the synthesized image based on the pet's contours and body shape.

[0829] Step 7: Generate a composite image

[0830] The server generates a synthetic image of the pet wearing the pet clothing as a result of the processing by the generative AI model, which reproduces the natural look of the pet and the clothing.

[0831] Step 8: Encode the composite image

[0832] The server encodes the resulting composite image into JPEG or PNG format, ensuring compatibility and display quality of the image.

[0833] Step 9: Submit your composite image

[0834] The server sends the encoded composite image to the terminal as an HTTP response. The image data may be sent again in multipart form data format.

[0835] Step 10: Receiving the composite image

[0836] The device receives the HTTP response sent from the server and acquires the composite image data, which is then temporarily stored in its internal memory.

[0837] Step 11: Displaying the composite image

[0838] The device decodes the synthesized image and displays it on the application's UI, allowing the user to see the image of their pet wearing the pet clothing on the device screen.

[0839] Example 1

[0840] 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."

[0841] Conventional pet clothing fitting systems require pets to actually try on the clothes, which increases stress for the pet and wastes time. Furthermore, when purchasing online, it is difficult to confirm whether the clothes actually fit the pet, and mismatched sizes or designs are often discovered after purchase. To solve these issues, a system is needed that combines images of the pet and the pet clothing to provide users with a realistic fitting experience.

[0842] 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.

[0843] In this invention, the server includes means for receiving pet images, means for receiving pet clothing images, means for sending image data to the server using an HTTP POST request, means for preprocessing the received pet images and pet clothing images and using a generative AI model, means for encoding and sending the preprocessed images, and means for displaying the synthesized image to the user. This allows the user to easily and accurately check how the pet clothing will look on their pet without actually trying it on.

[0844] A "pet image" is visual information in digital form that includes the entire image or part of a pet.

[0845] "Pet apparel image" means visual information in digital form that visually represents the design or shape of pet apparel or accessories.

[0846] An "HTTP POST request" is one of the methods in the HTTP protocol for sending data to a web server, and is a method that is particularly suitable for sending large amounts of data or multiple pieces of data.

[0847] A "generative AI model" is an algorithm or program that uses machine learning or deep learning techniques to analyze and process input image data and generate output tailored to a specific purpose.

[0848] "Preprocessing" refers to a series of processes such as data resizing, resolution adjustment, and noise removal to convert received image data into a format that is easier to process.

[0849] "Encoding" is the process of converting image data into a specific file format (e.g., JPEG, PNG) to make it easier to store and transfer.

[0850] "Decoding" is the process of converting encoded image data into a format that can be displayed or edited.

[0851] This invention is a system that simulates trying on pet clothes using images of pets and pet clothes. The system receives images of pets and pet clothes, synthesizes them using a generative AI model, and provides the user with a natural fitting image. The system is mainly composed of a server and a user's terminal.

[0852] User Input

[0853] The user takes a picture of their pet using a smartphone or digital camera. They also prepare an image of the pet clothing they are considering purchasing. The user launches the application, selects the image of the pet and the image of the pet clothing from the file browser, and clicks the upload button. This causes the device to prepare the image data and proceed to the next step.

[0854] Sending images

[0855] The device sends image data to the server using an HTTP POST request. At this time, the image data is sent in multipart form data format, which prevents data loss and format inconsistencies. Specifically, the device includes the image file in the body of the HTTP request and sends the request to the specified endpoint on the server.

[0856] Image Processing and Compositing

[0857] The server processes the received images of the pet and pet clothing. First, as a pre-processing step, the images are resized to unify the size and resolution. Then, a generative AI model is used to recognize the pet's outline and body shape from the pet image. This generative AI model is built using deep learning frameworks such as TensorFlow and PyTorch. This generative AI model calculates the optimal shape and placement of the clothing for the pet and synthesizes a realistic image.

[0858] Generate synthetic images

[0859] The server encodes the composite image into an appropriate image format before sending it back to the device, specifically using a library like Pillow or OpenCV to encode the generated image into a format like JPEG or PNG, ensuring compatibility when the image is displayed on the user's device.

[0860] Sending a composite image

[0861] The server returns the generated composite image to the terminal as an HTTP response. To ensure communication security, it is recommended to use HTTPS (HTTP using SSL / TLS). The server sets the appropriate content type (e.g., image / jpeg) in the response header and sends the image data in the response body.

[0862] Display of try-on images

[0863] The device decodes the composite image received from the server and displays it on the application's UI. First, the received image data is loaded into a buffer and decoded using an image display library. The decoded image is then displayed in a specific view of the application. The user can view the image of their pet wearing pet clothing on the device screen.

[0864] Specific examples

[0865] 1. The user opens the application, selects an image of the pet and an image of the pet clothing, and presses the upload button.

[0866] 2. The device sends the image data to the server using an HTTP POST request.

[0867] 3. The server preprocesses the image and synthesizes it using a generative AI model.

[0868] 4. The server encodes the composite image and sends it to the device as an HTTP response.

[0869] 5. The device receives the composite image, decodes it, and displays it in the application UI.

[0870] Example prompts for generative AI models:

[0871] "Generate a composite image using an image of a dog and an image of a dog T-shirt."

[0872] The present invention provides a system that allows users to easily and accurately check how pet clothing will look on their pet without actually trying it on, thereby enabling smooth selection of pet clothing while minimizing stress on the pet.

[0873] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0874] Step 1: User Input

[0875] The user uses a device to upload images of their pet and pet clothing to the application. Specifically, they prepare images of their pet taken with a smartphone or digital camera, as well as images of the pet clothing they are considering purchasing. The user selects these image files from the file browser within the application and clicks the upload button to complete the input. The input here is the image of the pet and the image of the pet clothing, and this data will be used in the next step.

[0876] Step 2: Sending images

[0877] The terminal sends the selected image data to the server using an HTTP POST request. Specifically, the terminal encodes the image data in a multipart form data format and includes it in the body of the HTTP request. The terminal then sends the request to the specified endpoint of the server. The input of this step is the image data selected by the user, and the output is the image data sent to the server.

[0878] Step 3: Image preprocessing

[0879] The server preprocesses the received image data. Specifically, it performs resizing to unify the image size and resolution, noise removal, color correction, etc. The input to this step is the image of the pet and the image of the pet's clothing sent from the terminal, and outputs image data in a unified format.

[0880] Step 4: Image synthesis using a generative AI model

[0881] The server inputs the preprocessed image data into a generative AI model, which recognizes the pet's contours and body shape and adjusts the shape of the pet clothing accordingly. The generative AI model is built using deep learning frameworks such as TensorFlow and PyTorch. The input of this step is the preprocessed image data, and the output is the generated synthetic image.

[0882] Step 5: Encode the composite image

[0883] The server encodes the generated composite image into an appropriate image format, such as JPEG or PNG, using a library like Pillow or OpenCV. The input to this step is the generated composite image, and the output is the encoded image data.

[0884] Step 6: Submit your composite image

[0885] The server returns the encoded composite image to the terminal as an HTTP response, using HTTPS (HTTP using SSL / TLS) to ensure communication security. The server sets the appropriate content type (e.g., image / jpeg) in the response header and sends the image data in the response body. The input to this step is the encoded composite image, and the output is the composite image sent to the terminal.

[0886] Step 7: Displaying fitting images

[0887] The device decodes the received composite image and displays it on the application's UI. Specifically, the device first loads the received image data into a buffer and decodes it using an image display library. The decoded image is then displayed in a specific view of the application. The input to this step is the encoded composite image received from the server, and the output is the try-on image displayed on the user's screen.

[0888] The above is the specific processing flow of this system.

[0889] (Application example 1)

[0890] 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."

[0891] When purchasing pet clothing in the past, it was necessary to actually try it on the pet, which caused stress and trouble for the pet. Also, when purchasing online, there was a risk that the size or design would not fit after purchase because it was not possible to try it on.

[0892] 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.

[0893] In this invention, the server includes means for receiving an image of a pet, means for receiving an image of a pet garment, means for using a generative AI model to synthesize the received image of the pet with an image of the pet garment, means for displaying the synthesized image to a user, and means for transmitting the synthesized image to a user terminal using a communication protocol, thereby enabling a user to check the effect of trying on pet garments online in real time without actually trying them on their pet.

[0894] The "means for receiving pet images" is a function that allows a user to send a photo of their pet from the terminal to the server.

[0895] The "means for receiving images of pet clothes" is a function for transmitting images of the pet clothes that the user wishes to try on from the terminal to the server.

[0896] "Means for using a generative AI model to synthesize received images of pets and images of pet clothing" refers to AI technology used to combine images of pets and images of pet clothing to generate natural-looking try-on images.

[0897] The "means for displaying the synthesized image to the user" is a function for displaying the generated try-on image on the user's terminal.

[0898] The "means for transmitting the synthesized image to the user terminal using a communication protocol" refers to a communication technology used to securely transmit the generated try-on image to the user terminal.

[0899] "Means for recognizing the pet's contours and body shape and adjusting the shape of the pet's clothing" is a function that enables the generative AI model to optimize the shape of the clothing to match the shape of the pet.

[0900] "Means for adjusting fitting according to the pet's body color and background" is a function that enables the generative AI model to adjust the fit of the synthetic image according to the pet's body color and background.

[0901] The present invention is a system for simulating trying on pet clothes using images of a pet and pet clothes. Detailed explanations of the implementation of the system are given below.

[0902] System Configuration

[0903] This system mainly consists of a server and a user device. The user device can be a smartphone or tablet, and the server is a cloud server.

[0904] Hardware and software used

[0905] Server: Cloud Server

[0906] User devices: smartphones, tablets

[0907] Generative AI models: VQ-VAE and GAN models trained using TensorFlow or PyTorch

[0908] Image processing library: OpenCV

[0909] Communication protocol: HTTPS protocol

[0910] Program processing

[0911] User operations

[0912] Using the application, users first take a photo of their pet and then upload an image of the pet clothing they want to try on. This process is very intuitive and can be easily done on the application screen.

[0913] Sending images

[0914] The user device sends image data to the server using an HTTP POST request. The image data is sent in a multipart form data format to prevent data loss or format inconsistencies.

[0915] Image Processing and Compositing

[0916] The server performs the following processes on the received pet images and pet costume images:

[0917] 1. First, preprocess the images to unify their size and resolution.

[0918] 2. Next, a generative AI model (e.g., VQ-VAE or GAN) is used to synthesize an image of the pet with an image of the pet costume. The generative AI model recognizes the pet's contours and body shape and adjusts the pet costume based on that shape.

[0919] Generate and transmit synthetic images

[0920] The server encodes the resulting composite image into the appropriate image format (JPEG or PNG) and then sends it back to the user's device using HTTPS, ensuring secure communication.

[0921] Display of try-on images

[0922] The user device decodes the received composite image and displays it on the application UI, allowing the user to see how their pet will actually look wearing the pet costume.

[0923] Specific examples

[0924] For example, if a user uploads a photo of their dog (e.g., a Shiba Inu) and selects an image of a blue sweater, the generative AI model will combine these images to create an image of the dog wearing the blue sweater, which the user can view and consider purchasing.

[0925] Prompt Sentence Examples

[0926] Using a picture of a pet and a picture of a pet costume, simulate a pet wearing the pet costume. The pet is a picture of a dog, and the costume is an image of a blue sweater.

[0927] This allows users to check the effects of trying on pet clothes online in real time without actually trying them on their pets.

[0928] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0929] Step 1:

[0930] The user launches the application and uploads images of their pet and pet costume by selecting images from their smartphone's camera or photo gallery. The input is the image files of the pet and pet costume, and the output is the image data of these.

[0931] Step 2:

[0932] The terminal sends the pet image and pet costume image uploaded by the user to the server. The communication protocol is HTTP POST request, and the image data is sent in multipart form data format. The input is the image file, and the output is the image data sent to the server.

[0933] Step 3:

[0934] The server preprocesses the received pet images and pet costume images, including image resizing, resolution unification, noise removal, etc. The input is the received image data, and the output is the preprocessed image data.

[0935] Step 4:

[0936] The server uses a generative AI model (e.g., VQ-VAE or GAN) to synthesize an image of the pet and an image of the pet costume. The generative AI model recognizes the pet's contours and body shape and adjusts the pet costume based on that shape. The input is the preprocessed image of the pet and the pet costume, and the output is a synthesized try-on image.

[0937] Step 5:

[0938] The server encodes the composite try-on image into the appropriate image format (JPEG or PNG) to display the image correctly on the user's device. The input is the composite try-on image, and the output is the encoded image file.

[0939] Step 6:

[0940] The server sends the encoded image file to the user terminal using HTTPS, which ensures communication security. The input is the encoded image file, and the output is the image data sent to the user terminal.

[0941] Step 7:

[0942] The device decodes the composite image received from the server and displays it on the application UI. The user can see the image of their pet wearing the pet costume through the decoded image. The input is the received image data, and the output is the try-on image displayed to the user.

[0943] 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.

[0944] System Overview

[0945] This invention is a system that simulates trying on pet clothes using images of pets and pet clothes, and also combines it with an emotion engine that recognizes the user's emotions. This system receives images of pets and pet clothes, synthesizes them using a generative AI model, and provides the user with a natural trying-on image. It also has the ability to recognize the user's emotions and provide feedback and suggestions based on those emotions. The main components of the system are a server and a user's terminal.

[0946] Program processing flow

[0947] 1. User Input

[0948] Users use their device to upload images of their pets taken with their smartphone or camera, as well as images of the pet clothing they are considering purchasing, to the application. When the user selects the image files and presses the upload button, the device sends the image data to the server.

[0949] 2. Sending images

[0950] The device sends image data to the server using an HTTP POST request. The image data is sent in a multipart form data format to prevent data loss or inconsistent data formats.

[0951] 3. Image Processing and Composition

[0952] The server processes the received images of the pet and pet clothing. First, it preprocesses the images to unify the size and resolution. Next, it uses a generative AI model to recognize the pet's outline and body shape from the pet image and adjusts the shape of the pet clothing accordingly. The generative AI model uses machine learning and deep learning techniques to perform optimal synthesis based on the input images.

[0953] 4. Generating synthetic images

[0954] The server encodes the resulting composite image into the appropriate image format before sending it back to the device, ensuring compatibility when the image is displayed on the user's device.

[0955] 5. Sending the composite image

[0956] The server sends the generated composite image back to the device as an HTTP response. It is recommended to use HTTPS to ensure communication security.

[0957] 6. Display of fitting images

[0958] The device decodes the composite image received from the server and displays it on the application UI. The user can then view the image of their pet wearing the pet clothing on the device screen.

[0959] 7. Emotional Engine Analysis

[0960] The device captures the user's facial expressions with a camera and analyzes them in real time with an emotion engine that detects the user's emotional state (e.g., joy, surprise, dissatisfaction, etc.) when viewing the pet try-on image.

[0961] 8. Emotional Feedback

[0962] The server analyzes the user's emotion data obtained from the emotion engine and provides appropriate feedback. For example, if the user is happy, it will suggest pet clothes with a similar design. If the user is unhappy, it will suggest pet clothes with a different style.

[0963] 9. Accumulation of Emotional Data and Historical Use

[0964] The server accumulates the user's emotional data and makes personalized suggestions based on their past emotional history. This allows the server to learn the user's preferences and tendencies, and provide more appropriate fitting images and clothing suggestions.

[0965] Specific examples

[0966] User operations

[0967] User B takes a photo of his cat and wants to buy new pet clothes. User B starts the application, selects a photo of the cat and an image of the candidate pet clothes, and presses the upload button. The device sends these images to the server.

[0968] Server Processing

[0969] The server receives the image of User B's cat and the image of the pet clothing, performs preprocessing, and then uses a generative AI model to synthesize the image of the pet and the image of the pet clothing. The synthesized image simulates the cat wearing the pet clothing.

[0970] Results display and sentiment analysis

[0971] The server sends the synthesized image to User B's device, which displays the image on the application's UI. User B checks that the cat is wearing the new pet clothes, and its facial expressions are captured through the camera. The emotion engine analyzes User B's emotional state, and the server provides feedback and additional suggestions based on this.

[0972] This system allows users to easily and accurately check how pet clothes will look on their pets without actually trying them on. Feedback that takes the user's emotions into account also enables more appropriate clothing selection, improving the user experience.

[0973] The processing flow will be explained below.

[0974] Step 1: User Input

[0975] The user opens the application on the device, selects a photo of the pet and a photo of the pet's clothing, and when the user presses the "Upload" button, the device obtains the path of the selected image file and prepares the image data.

[0976] Step 2: Sending images

[0977] The terminal sends the prepared pet image and pet clothing image to the server using an HTTP POST request, where the image data is sent in a multipart form data format.

[0978] Step 3: Receiving the image

[0979] The server receives the HTTP POST request and saves the submitted pet image and pet clothing image files in a specific directory for processing.

[0980] Step 4: Image preprocessing

[0981] The server performs preprocessing on the images of the pet and pet clothing stored in the storage. This preprocessing includes resizing the images, adjusting the resolution, and removing noise. This process converts both images into a format that is easy for the generative AI model to process.

[0982] Step 5: Extracting the pet outline

[0983] The server applies a contour extraction algorithm to the pre-processed pet image, which clearly identifies the pet's contours and body shape, providing the data needed for subsequent image synthesis.

[0984] Step 6: Applying the generative AI model

[0985] The server uses a generative AI model to synthesize an image of the pet and an image of the pet's clothing. The generative AI model adjusts the shape of the pet's clothing appropriately based on the pet's outline information, resulting in a natural-looking composition.

[0986] Step 7: Generate a composite image

[0987] The server generates a composite image of the pet wearing the pet clothing as a result of the generative AI model processing, and the composite image is encoded in JPEG or PNG format to ensure display compatibility.

[0988] Step 8: Submit your composite image

[0989] The server sends the encoded composite image to the terminal as an HTTP response. Image data must be sent in an appropriate format, and it is recommended to use HTTPS for communication security.

[0990] Step 9: Receiving the composite image

[0991] The device receives the HTTP response sent from the server and acquires the composite image data, which is then temporarily stored in the device's internal memory.

[0992] Step 10: Displaying the composite image

[0993] The device decodes the temporarily stored composite image and displays it on the application's UI, allowing the user to see the image of their pet wearing the pet clothing on the device screen.

[0994] Step 11: Activating the Emotion Engine

[0995] The device captures the user's facial expressions with a camera and activates the emotion engine, which analyzes the user's emotional state in real time and sends the data to the server.

[0996] Step 12: Analyze the sentiment data

[0997] The server analyzes the user's emotion data sent from the emotion engine, using facial recognition algorithms and machine learning models to detect the user's emotional state, such as joy, surprise, or dissatisfaction.

[0998] Step 13: Emotional Feedback

[0999] The server then provides appropriate feedback to the user based on the analyzed emotional data. For example, if the user is happy, it will automatically suggest pet clothes with a similar design. If the user is unhappy, it will suggest pet clothes with a different style.

[1000] Step 14: Accumulating Emotional Data and Using History

[1001] The server accumulates the user's emotional data and makes personalized suggestions based on their past emotional history. This allows the system to learn the user's preferences and tendencies, and provide more appropriate fitting images and pet clothing suggestions.

[1002] Example 2

[1003] 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."

[1004] Conventional pet clothing fitting systems require users to actually try on clothes, which places a heavy burden on the user. Furthermore, they do not provide feedback that takes into account the user's reactions and emotions, making it difficult to select appropriate pet clothing. Furthermore, when shopping online, there is a high risk of purchasing products that do not fit the pet's size or shape.

[1005] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving a pet image, means for receiving an image of a pet clothing, means for using a generative AI model to synthesize the received pet image with an image of the pet clothing, means for displaying the synthesized image to the user, means for using an emotion engine to recognize the user's emotional state, and means for providing feedback and suggestions based on emotion data obtained from the emotion engine. This allows the user to naturally check how pet clothing will look on their pet without actually trying it on their pet, and feedback that takes the user's emotions into consideration enables more appropriate clothing selection.

[1006] The "means for receiving pet images" refers to an interface and communication mechanism that allows a user to use a terminal to upload pet photo data to the system.

[1007] The "means for receiving images of pet clothing" refers to an interface and communication mechanism that allows users to upload photographic data of candidate pet clothing to the system.

[1008] "Means for using generative AI models" refers to algorithms and software that utilize machine learning and deep learning techniques to synthesize images of pets and images of pet clothing.

[1009] The "means for displaying a synthesized image to a user" refers to an interface and communication mechanism for transferring the synthesized image created by the generative AI model to a user's terminal and displaying it.

[1010] The "means for using an emotion engine" is an algorithm and software for capturing a user's facial expressions using a camera and analyzing the expression data to extract an emotional state.

[1011] The "means for providing feedback and suggestions based on emotional data" refers to algorithms and software that analyze the user's emotional data obtained from the emotion engine and provide the user with appropriate feedback and suggestions for pet clothing based on the results.

[1012] System Overview

[1013] This invention is a system that simulates trying on pet clothes using images of pets and pet clothes, and also combines it with an emotion engine that recognizes the user's emotions. This system receives images of pets and pet clothes, synthesizes them using a generative AI model, and provides the user with a natural trying-on image. It also has the ability to recognize the user's emotions and provide feedback and suggestions based on those emotions. The main components of the system are a server and a user's terminal.

[1014] Hardware and software used

[1015] Devices: smartphones, tablets, personal computers, etc.

[1016] Server: Cloud server or on-premise server

[1017] Generative AI models: Deep learning models such as StyleGAN2 and VGG-19

[1018] Emotion engine: Microsoft Azure Emotional API, Google Cloud Vision API, etc.

[1019] Specific processing outline of the program

[1020] 1. User Input

[1021] The user uses the device to upload images of their pet and the pet clothing they are considering purchasing to the application. The user selects the image files and presses the "Upload" button. At this point, the device temporarily stores these image files.

[1022] Examples:

[1023] User A takes a photo of the dog with their smartphone, selects an image of the pet clothing from the device's gallery, and presses the "Upload" button in the application.

[1024] 2. Sending images

[1025] The device sends image data to the server using an HTTP POST request, in a multipart form data format, using the HTTPS protocol to prevent data loss or formatting inconsistencies.

[1026] Examples:

[1027] The device divides the image of the dog and the image of the pet clothing into packets and sends them to the server along with an HTTP POST request.

[1028] 3. Image Preprocessing

[1029] The server receives the image data and checks its format and size. It then performs preprocessing to standardize the resolution and size, facilitating smooth processing in the generative AI model.

[1030] Examples:

[1031] The server resizes the dog image and pet clothing image to a resolution of 1920x1080 and converts the format from JPEG to PNG.

[1032] 4. Image synthesis using generative AI models

[1033] The server inputs the preprocessed image data into a generative AI model. This generative AI model (e.g., StyleGAN2) recognizes the dog's outline and body shape and adjusts the shape of the pet clothing based on that. It then synthesizes the image of the dog with the image of the pet clothing to generate a fitting image.

[1034] Examples:

[1035] The server extracts the outline from the image of the dog, transforms the image of the pet clothing into a shape that fits the outline, and generates a composite image.

[1036] 5. Encoding and transmitting the composite image

[1037] The server encodes the generated composite image into an appropriate format (e.g. PNG) and sends it to the terminal as an HTTP response.

[1038] Examples:

[1039] The server encodes the composite image into PNG format and sends it.

[1040] 6. Displaying the composite image

[1041] The device decodes the synthesized image received from the server and displays it on the application UI. The user can see the image of their pet wearing the pet clothing on the device screen.

[1042] Examples:

[1043] The terminal decodes the received composite image and displays it full screen on the application screen.

[1044] 7. Emotional Engine Analysis

[1045] The device captures the user's facial expressions with a camera and analyzes them in real time using an emotion engine (e.g., Microsoft Azure Emotional API), which detects the user's emotional state (e.g., joy, surprise, dissatisfaction, etc.).

[1046] Examples:

[1047] The device's front camera captures the user's face and transmits the facial expression data to the emotion engine.

[1048] The emotion engine detects when the user is smiling and reports it to the server.

[1049] 8. Emotional Feedback

[1050] The server analyzes the emotion data obtained from the emotion engine and provides appropriate feedback. For example, if the user is happy, it will suggest pet clothes with a similar design. If the user is unhappy, it will suggest pet clothes with a different style.

[1051] Examples:

[1052] The server determines that the user is satisfied and displays options for pet clothing with similar designs in the UI.

[1053] 9. Accumulation of Emotional Data and Historical Use

[1054] The server accumulates user emotional data and makes personalized suggestions based on past emotional history, allowing it to learn the user's preferences and tendencies and provide more appropriate fitting images and pet clothing suggestions.

[1055] Examples:

[1056] The server stores past emotion data in a database and uses it when making new suggestions.

[1057] Prompt Sentence Examples

[1058] Example prompts to be input to the generative AI model:

[1059] Using a "cat image" and an "image of pet clothing," create a composite image of a cat wearing the clothing.

[1060] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1061] Step 1:

[1062] The user uploads images of their pet and pet clothing to the application using their device. Specifically, the user selects an image from the device's gallery and presses the "Upload" button in the application. This temporarily saves the image to the device's local storage.

[1063] Input: User-selected pet image file and pet clothing image file

[1064] Output: Image data temporarily stored in the device's local storage

[1065] Step 2:

[1066] The device sends the image data to the server using an HTTP POST request. Specifically, the selected image file is attached to the POST request and sent to the specified URL on the server. During the sending process, the image data is converted to a multipart form data format.

[1067] Input: Image data of the pet and image data of the pet's clothes stored on the device

[1068] Output: Image data sent to the server in an HTTP POST request

[1069] Step 3:

[1070] The server validates the received image data, checking its format and size, and then preprocesses the image to unify its size and resolution. Specifically, it resizes the image while maintaining its aspect ratio, and converts JPEG images to PNG format.

[1071] Input: Pet image data and pet clothing image data sent via HTTP POST request

[1072] Output: Pre-processed image data in a unified size and format

[1073] Step 4:

[1074] The server inputs the preprocessed image data into a generative AI model. The generative AI model (e.g., StyleGAN2) recognizes the pet's outline and body shape and adjusts the shape of the pet's clothing based on that. Specifically, it extracts the outline from the pet's image and transforms the image of the pet's clothing into an appropriate shape.

[1075] Input: Preprocessed pet image data and pet clothing image data

[1076] Output: Composite image of pet wearing clothes

[1077] Step 5:

[1078] The server encodes the generated composite image and converts it into an appropriate image format (e.g. PNG). It then returns it to the terminal as an HTTP response. Specifically, it performs the encoding process, adds the necessary information to the response header, and then sends the image.

[1079] Input: Generated synthetic image

[1080] Output: The encoded image sent in the HTTP response.

[1081] Step 6:

[1082] The device decodes the composite image received from the server and displays it on the application's UI. Specifically, it decodes the received image data and applies CSS and JavaScript to display it appropriately on the user's screen.

[1083] Input: Synthetic image data sent from the server

[1084] Output: Composite image displayed in the application UI

[1085] Step 7:

[1086] The device captures the user's facial expressions with a camera and transmits them to the emotion engine in real time. Specifically, it captures the camera image and communicates to send the data to the emotion engine in real time.

[1087] Input: User's facial expression data captured by a camera

[1088] Output: Facial expression data sent to the emotion engine

[1089] Step 8:

[1090] The emotion engine analyzes the user's facial expression data and extracts their emotional state. The server provides feedback and suggestions based on the obtained emotional data. Specifically, the emotion engine analyzes the facial expression data in real time and outputs the emotional state as a number or category.

[1091] Input: Facial expression data sent to the emotion engine

[1092] Output: Analysis results regarding emotional state

[1093] Step 9:

[1094] The server accumulates emotional data and makes personalized suggestions based on the user's past emotional history. Specifically, it stores the emotional data in a database and uses a suggestion algorithm to generate optimal feedback and product suggestions.

[1095] Input: Emotional state data output from the emotion engine

[1096] Output: Personalized feedback and suggestions provided to the user

[1097] (Application example 2)

[1098] 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."

[1099] Conventional pet clothing fitting systems have the problem that simply combining an image of the pet with an image of the pet clothing does not adequately convey to the user what it will actually be like trying on the pet. Furthermore, since no feedback or suggestions are provided based on the user's reactions or emotions, the user experience is not improved.

[1100] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving an image of a pet, means for receiving an image of pet clothing, and means for using a generative AI model to synthesize the received image of the pet with an image of the pet clothing. This makes it possible to provide a try-on image in which the image of the pet and the image of the pet clothing are naturally synthesized. In addition, by including means for acquiring emotion data using an emotion engine that recognizes the user's emotions and means for providing feedback based on the emotion data, personalized feedback and suggestions according to the user's emotions become possible, significantly improving the user experience.

[1101] The "means for receiving a pet image" is a device or interface for importing a photo of a pet taken or selected by a user into the system.

[1102] The "means for receiving an image of pet clothing" is a device or interface for importing a photo of the pet clothing selected by the user into the system.

[1103] A "means for using a generative AI model" is a device or software that runs an AI model using machine learning or deep learning to synthesize an image of a pet with an image of the pet's clothing.

[1104] "Means for displaying a synthesized image to a user" refers to a device or interface for displaying an image synthesized by a generative AI model on a user's device.

[1105] "Means for acquiring emotional data using an emotion engine that recognizes the user's emotions" refers to software or algorithms that determine the user's emotions in real time from their facial expressions, voice, etc.

[1106] The "means for providing feedback based on emotional data" refers to a device or software that analyzes the acquired emotional data of the user and provides appropriate feedback or suggestions to the user based on the results.

[1107] "Means for recognizing the pet's outline and body shape and adjusting the shape of the pet's clothing" refers to a function in which an AI model detects the pet's outline and body shape from a photo of the pet and automatically changes the shape of the pet's clothing accordingly.

[1108] "Means for making personalized suggestions based on emotional data" refers to software or algorithms that suggest optimal pet clothing and related items based on the user's past emotional data and current emotional state.

[1109] The "means for performing fitting adjustment according to the pet's body color and background" is a function that automatically adjusts the color tone and position of the composite image according to the pet's body color and background.

[1110] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described in detail below with reference to the accompanying drawings.

[1111] System Overview

[1112] The system synthesizes an image of the pet taken by the user with an image of the pet clothing the user is considering purchasing, and uses a generative AI model to generate a natural fitting image. It also incorporates an emotion engine that recognizes the user's emotions in real time, allowing it to provide feedback and suggestions based on the user's emotions.

[1113] Hardware and software used

[1114] Hardware

[1115] 1. Smartphone: Take and upload images of your pet and pet clothing, and display a composite image of the clothing to try on. The camera also captures the user's facial expression.

[1116] 2. Cloud server: Receives image data, preprocesses images, synthesizes images using a generative AI model, and analyzes emotional data.

[1117] software

[1118] 1. Requests library: Sends image data via HTTP POST requests.

[1119] 2. Pillow (PIL): Image preprocessing and compositing.

[1120] 3. Generative AI model: An AI model for synthesizing images of pets and pet costumes. It uses machine learning and deep learning techniques.

[1121] 4. FER (Facial Expression Recognition): A facial expression recognition engine that determines the user's emotions in real time.

[1122] 5. Keras library: Supports AI models for emotion recognition.

[1123] What the program does

[1124] Sending images

[1125] The user device sends the photographed or selected image of the pet and the image of the pet's clothing to the server. The transmission is performed using an HTTP POST request, and the image data is sent in multipart form data format, which prevents data loss and format inconsistencies.

[1126] Image Processing and Compositing

[1127] The server preprocesses the received images to standardize the size and resolution, then uses a generative AI model to recognize the pet's contours and body shape, adjust the shape of the pet's clothing, and synthesize it. The synthesized image simulates how the pet will look wearing the clothing and is encoded into the appropriate image format.

[1128] Emotional Recognition and Feedback

[1129] The user device displays the synthesized image and captures the user's facial expression with a camera. The emotion engine analyzes the user's emotional state in real time and sends the data to the server. The server then provides feedback and additional suggestions based on this emotional data, helping the user to purchase the pet clothing they are most satisfied with.

[1130] Specific examples

[1131] User A takes a photo of his dog and wants to buy new pet clothing. User A starts the application, selects a photo of the dog and an image of a candidate pet clothing item, and presses the upload button. The device sends these images to the server. The server processes the received dog image and clothing image and synthesizes them using a generative AI model. A composite image is generated and sent to User A's device. User A checks the composite image, and his facial expression is captured through the camera. The emotion engine analyzes User A's emotions, and additional pet clothing items are suggested accordingly.

[1132] Prompt Sentence Examples

[1133] Combine the "pet image" and the "pet costume image" to create a natural-looking image of the pet wearing the costume.

[1134] By implementing this mode, the user can easily check the image of the pet trying on the clothes, and can select a more appropriate item while receiving feedback that takes emotions into consideration.

[1135] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1136] Step 1:

[1137] The user uses a smartphone to take or select an image of the pet and an image of the pet's clothes and upload them to the application. When the user presses the upload button, the application obtains the image data of the pet and the image data of the pet's clothes and sends both of these image data to the server. The input here is the image of the pet and the image of the pet's clothes, and the output is that these data are sent to the server.

[1138] Step 2:

[1139] The terminal uses an HTTP POST request to send pet image data and pet clothing image data to the server. Here, the image data is sent in multipart form data format to prevent data loss and format inconsistencies. The input is the pet image data and pet clothing image data, and the output is the data being received by the server.

[1140] Step 3:

[1141] The server preprocesses the received images of the pet and pet clothing. Specifically, it standardizes the image size and resolution, removes noise, etc. The input here is the received images of the pet and pet clothing, and the output is the preprocessed image data.

[1142] Step 4:

[1143] The server uses a generative AI model to recognize the pet's contours and body shape, and adjusts the shape of the pet's clothing accordingly. Using the generative AI model, the image of the pet and the image of the pet's clothing are naturally synthesized. The input here is the preprocessed image of the pet and the image of the pet's clothing, and the output is the synthesized image.

[1144] Step 5:

[1145] The server encodes the generated composite image into an appropriate image format and prepares it for transmission to the user's device, where it is encoded into an appropriate format such as JPEG or PNG to ensure compatibility and display quality. The input is the composite image, and the output is the encoded image data.

[1146] Step 6:

[1147] The server sends the encoded composite image to the terminal as an HTTP response. To ensure security, it is recommended to use HTTPS. The input is the encoded image data, and the output is the image data sent to the user's terminal.

[1148] Step 7:

[1149] The user's device decodes the composite image received from the server and displays it on the application's UI. The user can then view the image of their pet wearing the pet clothing. The input is the composite image data received from the server, and the output is the composite image displayed on the application's UI.

[1150] Step 8:

[1151] The user's device uses a camera to capture the user's facial expressions, which are then analyzed in real time by the emotion engine. The emotion engine recognizes the user's emotional state when viewing the pet try-on image. The input is the user's facial expression image, and the output is emotion data.

[1152] Step 9:

[1153] The server analyzes the user's emotional data obtained from the emotion engine and generates appropriate feedback and suggestions based on the emotional data. For example, if the user is happy, it will suggest pet clothes with a similar design, and if the user is unhappy, it will suggest pet clothes with a different style. The input is the user's emotional data, and the output is feedback and suggestions.

[1154] Step 10:

[1155] The server accumulates the user's emotional data and stores it as an emotional history. This allows personalized suggestions to be made in the future based on the past emotional history. The input is the emotional data and feedback history, and the output is the accumulated emotional data.

[1156] 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.

[1157] 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.

[1158] 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.

[1159] [Fourth embodiment]

[1160] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1161] 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.

[1162] 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).

[1163] 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.

[1164] 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.

[1165] 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).

[1166] 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. 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.

[1167] 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.

[1168] 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.

[1169] 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.

[1170] 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.

[1171] 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.

[1172] 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."

[1173] System Overview

[1174] This invention is a system that simulates trying on pet clothes using images of pets and pet clothes. This system receives images of pets and pet clothes, synthesizes them using a generative AI model, and provides the user with a natural try-on image. The system is broadly composed of a server and a user's terminal.

[1175] Program processing flow

[1176] 1. User Input

[1177] Users use their device to upload images of their pets taken with their smartphone or camera, as well as images of the pet clothing they are considering purchasing, to the application. When the user selects the image files and presses the upload button, the device sends the image data to the server.

[1178] 2. Sending images

[1179] The device sends image data to the server using an HTTP POST request. The image data is sent in a multipart form data format to prevent data loss or inconsistent data formats.

[1180] 3. Image Processing and Composition

[1181] The server processes the received images of the pet and pet clothing. First, it preprocesses the images to unify the size and resolution. Next, it uses a generative AI model to recognize the pet's outline and body shape from the pet image and adjusts the shape of the pet clothing accordingly. The generative AI model uses machine learning and deep learning techniques to perform optimal synthesis based on the input images.

[1182] 4. Generating synthetic images

[1183] The server encodes the resulting composite image into the appropriate image format before sending it back to the device, ensuring compatibility when the image is displayed on the user's device.

[1184] 5. Sending the composite image

[1185] The server sends the generated composite image back to the device as an HTTP response. It is recommended to use HTTPS to ensure communication security.

[1186] 6. Display of fitting images

[1187] The device decodes the composite image received from the server and displays it on the application UI. The user can then view the image of their pet wearing the pet clothing on the device screen.

[1188] Specific examples

[1189] User operations

[1190] User A takes a photo of his dog and wants to buy new pet clothes. User A starts the application, selects a photo of his dog and an image of a candidate pet clothes, and presses the upload button. The device sends these images to the server.

[1191] Server Processing

[1192] The server receives the image of User A's dog and the image of the pet clothing, performs preprocessing, and then uses a generative AI model to synthesize the image of the pet and the image of the pet clothing. The synthesized image simulates the dog wearing the pet clothing.

[1193] Displaying the results

[1194] The server sends the composite image to User A's device, which displays the image on the application's UI. User A checks the dog wearing the new pet clothes and considers purchasing them.

[1195] This system allows users to easily and accurately see how pet clothes will look on their pet without actually trying them on, making it easier to select pet clothes while minimizing stress on the pet.

[1196] The processing flow will be explained below.

[1197] Step 1: User Input

[1198] The user opens the application on the device, selects a photo of the pet and a photo of the pet's clothing, and when the user presses the "Upload" button, the device obtains the path of the selected image file.

[1199] Step 2: Sending images

[1200] The terminal sends the selected image data to the server using an HTTP POST request. At this time, the image data is sent in a multipart form data format.

[1201] Step 3: Receiving the image

[1202] The server receives the HTTP request and saves the image files of the pet and the pet clothes. The saved data is placed in a directory for image processing.

[1203] Step 4: Image preprocessing

[1204] The server performs preprocessing on the stored image data, including standardizing image size, adjusting resolution, and removing noise.

[1205] Step 5: Extracting the pet outline

[1206] The server applies an edge detection algorithm to recognize the pet's contours and shape from the pet image, which gives a clearer picture of the pet's shape in the image.

[1207] Step 6: Applying the generative AI model

[1208] The server uses a generative AI model to synthesize an image of the pet with an image of the pet's clothing, and the generative AI model adjusts the shape of the pet's clothing to fit the synthesized image based on the pet's contours and body shape.

[1209] Step 7: Generate a composite image

[1210] The server generates a synthetic image of the pet wearing the pet clothing as a result of the processing by the generative AI model, which reproduces the natural look of the pet and the clothing.

[1211] Step 8: Encode the composite image

[1212] The server encodes the resulting composite image into JPEG or PNG format, ensuring compatibility and display quality of the image.

[1213] Step 9: Submit your composite image

[1214] The server sends the encoded composite image to the terminal as an HTTP response. The image data may be sent again in multipart form data format.

[1215] Step 10: Receiving the composite image

[1216] The device receives the HTTP response sent from the server and acquires the composite image data, which is then temporarily stored in its internal memory.

[1217] Step 11: Displaying the composite image

[1218] The device decodes the synthesized image and displays it on the application's UI, allowing the user to see the image of their pet wearing the pet clothing on the device screen.

[1219] Example 1

[1220] 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."

[1221] Conventional pet clothing fitting systems require pets to actually try on the clothes, which increases stress for the pet and wastes time. Furthermore, when purchasing online, it is difficult to confirm whether the clothes actually fit the pet, and mismatched sizes or designs are often discovered after purchase. To solve these issues, a system is needed that combines images of the pet and the pet clothing to provide users with a realistic fitting experience.

[1222] 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.

[1223] In this invention, the server includes means for receiving pet images, means for receiving pet clothing images, means for sending image data to the server using an HTTP POST request, means for preprocessing the received pet images and pet clothing images and using a generative AI model, means for encoding and sending the preprocessed images, and means for displaying the synthesized image to the user. This allows the user to easily and accurately check how the pet clothing will look on their pet without actually trying it on.

[1224] A "pet image" is visual information in digital form that includes the entire image or part of a pet.

[1225] "Pet apparel image" means visual information in digital form that visually represents the design or shape of pet apparel or accessories.

[1226] An "HTTP POST request" is one of the methods in the HTTP protocol for sending data to a web server, and is a method that is particularly suitable for sending large amounts of data or multiple pieces of data.

[1227] A "generative AI model" is an algorithm or program that uses machine learning or deep learning techniques to analyze and process input image data and generate output tailored to a specific purpose.

[1228] "Preprocessing" refers to a series of processes such as data resizing, resolution adjustment, and noise removal to convert received image data into a format that is easier to process.

[1229] "Encoding" is the process of converting image data into a specific file format (e.g., JPEG, PNG) to make it easier to store and transfer.

[1230] "Decoding" is the process of converting encoded image data into a format that can be displayed or edited.

[1231] This invention is a system that simulates trying on pet clothes using images of pets and pet clothes. The system receives images of pets and pet clothes, synthesizes them using a generative AI model, and provides the user with a natural fitting image. The system is mainly composed of a server and a user's terminal.

[1232] User Input

[1233] The user takes a picture of their pet using a smartphone or digital camera. They also prepare an image of the pet clothing they are considering purchasing. The user launches the application, selects the image of the pet and the image of the pet clothing from the file browser, and clicks the upload button. This causes the device to prepare the image data and proceed to the next step.

[1234] Sending images

[1235] The device sends image data to the server using an HTTP POST request. At this time, the image data is sent in multipart form data format, which prevents data loss and format inconsistencies. Specifically, the device includes the image file in the body of the HTTP request and sends the request to the specified endpoint on the server.

[1236] Image Processing and Compositing

[1237] The server processes the received images of the pet and pet clothing. First, as a pre-processing step, the images are resized to unify the size and resolution. Then, a generative AI model is used to recognize the pet's outline and body shape from the pet image. This generative AI model is built using deep learning frameworks such as TensorFlow and PyTorch. This generative AI model calculates the optimal shape and placement of the clothing for the pet and synthesizes a realistic image.

[1238] Generate synthetic images

[1239] The server encodes the composite image into an appropriate image format before sending it back to the device, specifically using a library like Pillow or OpenCV to encode the generated image into a format like JPEG or PNG, ensuring compatibility when the image is displayed on the user's device.

[1240] Sending a composite image

[1241] The server returns the generated composite image to the terminal as an HTTP response. To ensure communication security, it is recommended to use HTTPS (HTTP using SSL / TLS). The server sets the appropriate content type (e.g., image / jpeg) in the response header and sends the image data in the response body.

[1242] Display of try-on images

[1243] The device decodes the composite image received from the server and displays it on the application's UI. First, the received image data is loaded into a buffer and decoded using an image display library. The decoded image is then displayed in a specific view of the application. The user can view the image of their pet wearing pet clothing on the device screen.

[1244] Specific examples

[1245] 1. The user opens the application, selects an image of the pet and an image of the pet clothing, and presses the upload button.

[1246] 2. The device sends the image data to the server using an HTTP POST request.

[1247] 3. The server preprocesses the image and synthesizes it using a generative AI model.

[1248] 4. The server encodes the composite image and sends it to the device as an HTTP response.

[1249] 5. The device receives the composite image, decodes it, and displays it in the application UI.

[1250] Example prompts for generative AI models:

[1251] "Generate a composite image using an image of a dog and an image of a dog T-shirt."

[1252] The present invention provides a system that allows users to easily and accurately check how pet clothing will look on their pet without actually trying it on, thereby enabling smooth selection of pet clothing while minimizing stress on the pet.

[1253] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1254] Step 1: User Input

[1255] The user uses a device to upload images of their pet and pet clothing to the application. Specifically, they prepare images of their pet taken with a smartphone or digital camera, as well as images of the pet clothing they are considering purchasing. The user selects these image files from the file browser within the application and clicks the upload button to complete the input. The input here is the image of the pet and the image of the pet clothing, and this data will be used in the next step.

[1256] Step 2: Sending images

[1257] The terminal sends the selected image data to the server using an HTTP POST request. Specifically, the terminal encodes the image data in a multipart form data format and includes it in the body of the HTTP request. The terminal then sends the request to the specified endpoint of the server. The input of this step is the image data selected by the user, and the output is the image data sent to the server.

[1258] Step 3: Image preprocessing

[1259] The server preprocesses the received image data. Specifically, it performs resizing to unify the image size and resolution, noise removal, color correction, etc. The input to this step is the image of the pet and the image of the pet's clothing sent from the terminal, and outputs image data in a unified format.

[1260] Step 4: Image synthesis using a generative AI model

[1261] The server inputs the preprocessed image data into a generative AI model, which recognizes the pet's contours and body shape and adjusts the shape of the pet clothing accordingly. The generative AI model is built using deep learning frameworks such as TensorFlow and PyTorch. The input of this step is the preprocessed image data, and the output is the generated synthetic image.

[1262] Step 5: Encode the composite image

[1263] The server encodes the generated composite image into an appropriate image format, such as JPEG or PNG, using a library like Pillow or OpenCV. The input to this step is the generated composite image, and the output is the encoded image data.

[1264] Step 6: Submit your composite image

[1265] The server returns the encoded composite image to the terminal as an HTTP response, using HTTPS (HTTP using SSL / TLS) to ensure communication security. The server sets the appropriate content type (e.g., image / jpeg) in the response header and sends the image data in the response body. The input to this step is the encoded composite image, and the output is the composite image sent to the terminal.

[1266] Step 7: Displaying fitting images

[1267] The device decodes the received composite image and displays it on the application's UI. Specifically, the device first loads the received image data into a buffer and decodes it using an image display library. The decoded image is then displayed in a specific view of the application. The input to this step is the encoded composite image received from the server, and the output is the try-on image displayed on the user's screen.

[1268] The above is the specific processing flow of this system.

[1269] (Application example 1)

[1270] 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."

[1271] When purchasing pet clothing in the past, it was necessary to actually try it on the pet, which caused stress and trouble for the pet. Also, when purchasing online, there was a risk that the size or design would not fit after purchase because it was not possible to try it on.

[1272] 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.

[1273] In this invention, the server includes means for receiving an image of a pet, means for receiving an image of a pet garment, means for using a generative AI model to synthesize the received image of the pet with an image of the pet garment, means for displaying the synthesized image to a user, and means for transmitting the synthesized image to a user terminal using a communication protocol, thereby enabling a user to check the effect of trying on pet garments online in real time without actually trying them on their pet.

[1274] The "means for receiving pet images" is a function that allows a user to send a photo of their pet from the terminal to the server.

[1275] The "means for receiving images of pet clothes" is a function for transmitting images of the pet clothes that the user wishes to try on from the terminal to the server.

[1276] "Means for using a generative AI model to synthesize received images of pets and images of pet clothing" refers to AI technology used to combine images of pets and images of pet clothing to generate natural-looking images for trying on.

[1277] The "means for displaying the synthesized image to the user" is a function for displaying the generated try-on image on the user's terminal.

[1278] The "means for transmitting the synthesized image to the user terminal using a communication protocol" refers to a communication technology used to securely transmit the generated try-on image to the user terminal.

[1279] "Means for recognizing the pet's contours and body shape and adjusting the shape of the pet's clothing" is a function that enables the generative AI model to optimize the shape of the clothing to match the shape of the pet.

[1280] "Means for adjusting fitting according to the pet's body color and background" is a function that enables the generative AI model to adjust the fit of the synthetic image according to the pet's body color and background.

[1281] The present invention is a system for simulating trying on pet clothes using images of a pet and pet clothes. Detailed explanations of the implementation of the system are given below.

[1282] System Configuration

[1283] This system mainly consists of a server and a user device. The user device can be a smartphone or tablet, and the server is a cloud server.

[1284] Hardware and software used

[1285] Server: Cloud Server

[1286] User devices: smartphones, tablets

[1287] Generative AI models: VQ-VAE and GAN models trained using TensorFlow or PyTorch

[1288] Image processing library: OpenCV

[1289] Communication protocol: HTTPS protocol

[1290] Program processing

[1291] User operations

[1292] Using the application, users first take a photo of their pet and then upload an image of the pet clothing they want to try on. This process is very intuitive and can be easily done on the application screen.

[1293] Sending images

[1294] The user device sends image data to the server using an HTTP POST request. The image data is sent in a multipart form data format to prevent data loss or format inconsistencies.

[1295] Image Processing and Compositing

[1296] The server performs the following processes on the received pet images and pet costume images:

[1297] 1. First, preprocess the images to unify their size and resolution.

[1298] 2. Next, a generative AI model (e.g., VQ-VAE or GAN) is used to synthesize an image of the pet with an image of the pet costume. The generative AI model recognizes the pet's contours and body shape and adjusts the pet costume based on that shape.

[1299] Generate and transmit synthetic images

[1300] The server encodes the resulting composite image into the appropriate image format (JPEG or PNG) and then sends it back to the user's device using HTTPS, ensuring secure communication.

[1301] Display of try-on images

[1302] The user device decodes the received composite image and displays it on the application UI, allowing the user to see how their pet will actually look wearing the pet costume.

[1303] Specific examples

[1304] For example, if a user uploads a photo of their dog (e.g., a Shiba Inu) and selects an image of a blue sweater, the generative AI model will combine these images to create an image of the dog wearing the blue sweater, which the user can view and consider purchasing.

[1305] Prompt Sentence Examples

[1306] Using a picture of a pet and a picture of a pet costume, simulate a pet wearing the pet costume. The pet is a picture of a dog, and the costume is an image of a blue sweater.

[1307] This allows users to check the effects of trying on pet clothes online in real time without actually trying them on their pets.

[1308] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1309] Step 1:

[1310] The user launches the application and uploads images of their pet and pet costume by selecting images from their smartphone's camera or photo gallery. The input is the image files of the pet and pet costume, and the output is the image data of these.

[1311] Step 2:

[1312] The terminal sends the pet image and pet costume image uploaded by the user to the server. The communication protocol is HTTP POST request, and the image data is sent in multipart form data format. The input is the image file, and the output is the image data sent to the server.

[1313] Step 3:

[1314] The server preprocesses the received pet images and pet costume images, including image resizing, resolution unification, noise removal, etc. The input is the received image data, and the output is the preprocessed image data.

[1315] Step 4:

[1316] The server uses a generative AI model (e.g., VQ-VAE or GAN) to synthesize an image of the pet and an image of the pet costume. The generative AI model recognizes the pet's contours and body shape and adjusts the pet costume based on that shape. The input is the preprocessed image of the pet and the pet costume, and the output is a synthesized try-on image.

[1317] Step 5:

[1318] The server encodes the composite try-on image into the appropriate image format (JPEG or PNG) to display the image correctly on the user's device. The input is the composite try-on image, and the output is the encoded image file.

[1319] Step 6:

[1320] The server sends the encoded image file to the user terminal using HTTPS, which ensures communication security. The input is the encoded image file, and the output is the image data sent to the user terminal.

[1321] Step 7:

[1322] The device decodes the composite image received from the server and displays it on the application UI. The user can see the image of their pet wearing the pet costume through the decoded image. The input is the received image data, and the output is the try-on image displayed to the user.

[1323] 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.

[1324] System Overview

[1325] This invention is a system that simulates trying on pet clothes using images of pets and pet clothes, and also combines it with an emotion engine that recognizes the user's emotions. This system receives images of pets and pet clothes, synthesizes them using a generative AI model, and provides the user with a natural trying-on image. It also has the ability to recognize the user's emotions and provide feedback and suggestions based on those emotions. The main components of the system are a server and a user's terminal.

[1326] Program processing flow

[1327] 1. User Input

[1328] Users use their device to upload images of their pets taken with their smartphone or camera, as well as images of the pet clothing they are considering purchasing, to the application. When the user selects the image files and presses the upload button, the device sends the image data to the server.

[1329] 2. Sending images

[1330] The device sends image data to the server using an HTTP POST request. The image data is sent in a multipart form data format to prevent data loss or inconsistent data formats.

[1331] 3. Image Processing and Composition

[1332] The server processes the received images of the pet and pet clothing. First, it preprocesses the images to unify the size and resolution. Next, it uses a generative AI model to recognize the pet's outline and body shape from the pet image and adjusts the shape of the pet clothing accordingly. The generative AI model uses machine learning and deep learning techniques to perform optimal synthesis based on the input images.

[1333] 4. Generating synthetic images

[1334] The server encodes the resulting composite image into the appropriate image format before sending it back to the device, ensuring compatibility when the image is displayed on the user's device.

[1335] 5. Sending the composite image

[1336] The server sends the generated composite image back to the device as an HTTP response. It is recommended to use HTTPS to ensure communication security.

[1337] 6. Display of fitting images

[1338] The device decodes the composite image received from the server and displays it on the application UI. The user can then view the image of their pet wearing the pet clothing on the device screen.

[1339] 7. Emotional Engine Analysis

[1340] The device captures the user's facial expressions with a camera and analyzes them in real time with an emotion engine that detects the user's emotional state (e.g., joy, surprise, dissatisfaction, etc.) when viewing the pet try-on image.

[1341] 8. Emotional Feedback

[1342] The server analyzes the user's emotion data obtained from the emotion engine and provides appropriate feedback. For example, if the user is happy, it will suggest pet clothes with a similar design. If the user is unhappy, it will suggest pet clothes with a different style.

[1343] 9. Accumulation of Emotional Data and Historical Use

[1344] The server accumulates the user's emotional data and makes personalized suggestions based on their past emotional history. This allows the server to learn the user's preferences and tendencies, and provide more appropriate fitting images and clothing suggestions.

[1345] Specific examples

[1346] User operations

[1347] User B takes a photo of his cat and wants to buy new pet clothes. User B starts the application, selects a photo of the cat and an image of the candidate pet clothes, and presses the upload button. The device sends these images to the server.

[1348] Server Processing

[1349] The server receives the image of User B's cat and the image of the pet clothing, performs preprocessing, and then uses a generative AI model to synthesize the image of the pet and the image of the pet clothing. The synthesized image simulates the cat wearing the pet clothing.

[1350] Results display and sentiment analysis

[1351] The server sends the synthesized image to User B's device, which displays the image on the application's UI. User B checks that the cat is wearing the new pet clothes, and its facial expressions are captured through the camera. The emotion engine analyzes User B's emotional state, and the server provides feedback and additional suggestions based on this.

[1352] This system allows users to easily and accurately check how pet clothes will look on their pets without actually trying them on. Feedback that takes the user's emotions into account also enables more appropriate clothing selection, improving the user experience.

[1353] The processing flow will be explained below.

[1354] Step 1: User Input

[1355] The user opens the application on the device, selects a photo of the pet and a photo of the pet's clothing, and when the user presses the "Upload" button, the device obtains the path of the selected image file and prepares the image data.

[1356] Step 2: Sending images

[1357] The terminal sends the prepared pet image and pet clothing image to the server using an HTTP POST request, where the image data is sent in a multipart form data format.

[1358] Step 3: Receiving the image

[1359] The server receives the HTTP POST request and saves the submitted pet image and pet clothing image files in a specific directory for processing.

[1360] Step 4: Image preprocessing

[1361] The server performs preprocessing on the images of the pet and pet clothing stored in the storage. This preprocessing includes resizing the images, adjusting the resolution, and removing noise. This process converts both images into a format that is easy for the generative AI model to process.

[1362] Step 5: Extracting the pet outline

[1363] The server applies a contour extraction algorithm to the pre-processed pet image, which clearly identifies the pet's contours and body shape, providing the data needed for subsequent image synthesis.

[1364] Step 6: Applying the generative AI model

[1365] The server uses a generative AI model to synthesize an image of the pet and an image of the pet's clothing. The generative AI model adjusts the shape of the pet's clothing appropriately based on the pet's outline information, resulting in a natural-looking composition.

[1366] Step 7: Generate a composite image

[1367] The server generates a composite image of the pet wearing the pet clothing as a result of the generative AI model processing, and the composite image is encoded in JPEG or PNG format to ensure display compatibility.

[1368] Step 8: Submit your composite image

[1369] The server sends the encoded composite image to the terminal as an HTTP response. Image data must be sent in an appropriate format, and it is recommended to use HTTPS for communication security.

[1370] Step 9: Receiving the composite image

[1371] The device receives the HTTP response sent from the server and acquires the composite image data, which is then temporarily stored in the device's internal memory.

[1372] Step 10: Displaying the composite image

[1373] The device decodes the temporarily stored composite image and displays it on the application's UI, allowing the user to see the image of their pet wearing the pet clothing on the device screen.

[1374] Step 11: Activating the Emotion Engine

[1375] The device captures the user's facial expressions with a camera and activates the emotion engine, which analyzes the user's emotional state in real time and sends the data to the server.

[1376] Step 12: Analyze the sentiment data

[1377] The server analyzes the user's emotion data sent from the emotion engine, using facial recognition algorithms and machine learning models to detect the user's emotional state, such as joy, surprise, or dissatisfaction.

[1378] Step 13: Emotional Feedback

[1379] The server then provides appropriate feedback to the user based on the analyzed emotional data. For example, if the user is happy, it will automatically suggest pet clothes with a similar design. If the user is unhappy, it will suggest pet clothes with a different style.

[1380] Step 14: Accumulating Emotional Data and Using History

[1381] The server accumulates the user's emotional data and makes personalized suggestions based on their past emotional history. This allows the system to learn the user's preferences and tendencies, and provide more appropriate fitting images and pet clothing suggestions.

[1382] Example 2

[1383] 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."

[1384] Conventional pet clothing fitting systems require users to actually try on clothes, which places a heavy burden on the user. Furthermore, they do not provide feedback that takes into account the user's reactions and emotions, making it difficult to select appropriate pet clothing. Furthermore, when shopping online, there is a high risk of purchasing products that do not fit the pet's size or shape.

[1385] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving a pet image, means for receiving an image of a pet clothing, means for using a generative AI model to synthesize the received pet image with an image of the pet clothing, means for displaying the synthesized image to the user, means for using an emotion engine to recognize the user's emotional state, and means for providing feedback and suggestions based on emotion data obtained from the emotion engine. This allows the user to naturally check how pet clothing will look on their pet without actually trying it on their pet, and feedback that takes the user's emotions into consideration enables more appropriate clothing selection.

[1386] The "means for receiving pet images" refers to an interface and communication mechanism that allows a user to use a terminal to upload pet photo data to the system.

[1387] The "means for receiving images of pet clothing" refers to an interface and communication mechanism that allows users to upload photographic data of candidate pet clothing to the system.

[1388] "Means for using generative AI models" refers to algorithms and software that utilize machine learning and deep learning techniques to synthesize images of pets and images of pet clothing.

[1389] The "means for displaying a synthesized image to a user" refers to an interface and communication mechanism for transferring the synthesized image created by the generative AI model to a user's terminal and displaying it.

[1390] The "means for using an emotion engine" is an algorithm and software for capturing a user's facial expressions using a camera and analyzing the expression data to extract an emotional state.

[1391] The "means for providing feedback and suggestions based on emotional data" refers to algorithms and software that analyze the user's emotional data obtained from the emotion engine and provide the user with appropriate feedback and suggestions for pet clothing based on the results.

[1392] System Overview

[1393] This invention is a system that simulates trying on pet clothes using images of pets and pet clothes, and also combines it with an emotion engine that recognizes the user's emotions. This system receives images of pets and pet clothes, synthesizes them using a generative AI model, and provides the user with a natural trying-on image. It also has the ability to recognize the user's emotions and provide feedback and suggestions based on those emotions. The main components of the system are a server and a user's terminal.

[1394] Hardware and software used

[1395] Devices: smartphones, tablets, personal computers, etc.

[1396] Server: Cloud server or on-premise server

[1397] Generative AI models: Deep learning models such as StyleGAN2 and VGG-19

[1398] Emotion engine: Microsoft Azure Emotional API, Google Cloud Vision API, etc.

[1399] Specific processing outline of the program

[1400] 1. User Input

[1401] The user uses the device to upload images of their pet and the pet clothing they are considering purchasing to the application. The user selects the image files and presses the "Upload" button. At this point, the device temporarily stores these image files.

[1402] Examples:

[1403] User A takes a photo of the dog with their smartphone, selects an image of the pet clothing from the device's gallery, and presses the "Upload" button in the application.

[1404] 2. Sending images

[1405] The device sends image data to the server using an HTTP POST request, in a multipart form data format, using the HTTPS protocol to prevent data loss or formatting inconsistencies.

[1406] Examples:

[1407] The device divides the image of the dog and the image of the pet clothing into packets and sends them to the server along with an HTTP POST request.

[1408] 3. Image Preprocessing

[1409] The server receives the image data and checks its format and size. It then performs preprocessing to standardize the resolution and size, facilitating smooth processing in the generative AI model.

[1410] Examples:

[1411] The server resizes the dog image and pet clothing image to a resolution of 1920x1080 and converts the format from JPEG to PNG.

[1412] 4. Image synthesis using generative AI models

[1413] The server inputs the preprocessed image data into a generative AI model. This generative AI model (e.g., StyleGAN2) recognizes the dog's outline and body shape and adjusts the shape of the pet clothing based on that. It then synthesizes the image of the dog with the image of the pet clothing to generate a fitting image.

[1414] Examples:

[1415] The server extracts the outline from the image of the dog, transforms the image of the pet clothing into a shape that fits the outline, and generates a composite image.

[1416] 5. Encoding and transmitting the composite image

[1417] The server encodes the generated composite image into an appropriate format (e.g. PNG) and sends it to the terminal as an HTTP response.

[1418] Examples:

[1419] The server encodes the composite image into PNG format and sends it.

[1420] 6. Displaying the composite image

[1421] The device decodes the synthesized image received from the server and displays it on the application UI. The user can see the image of their pet wearing the pet clothing on the device screen.

[1422] Examples:

[1423] The terminal decodes the received composite image and displays it full screen on the application screen.

[1424] 7. Emotional Engine Analysis

[1425] The device captures the user's facial expressions with a camera and analyzes them in real time using an emotion engine (e.g., Microsoft Azure Emotional API), which detects the user's emotional state (e.g., joy, surprise, dissatisfaction, etc.).

[1426] Examples:

[1427] The device's front camera captures the user's face and transmits the facial expression data to the emotion engine.

[1428] The emotion engine detects when the user is smiling and reports it to the server.

[1429] 8. Emotional Feedback

[1430] The server analyzes the emotion data obtained from the emotion engine and provides appropriate feedback. For example, if the user is happy, it will suggest pet clothes with a similar design. If the user is unhappy, it will suggest pet clothes with a different style.

[1431] Examples:

[1432] The server determines that the user is satisfied and displays options for pet clothing with similar designs in the UI.

[1433] 9. Accumulation of Emotional Data and Historical Use

[1434] The server accumulates user emotional data and makes personalized suggestions based on past emotional history, allowing it to learn the user's preferences and tendencies and provide more appropriate fitting images and pet clothing suggestions.

[1435] Examples:

[1436] The server stores past emotion data in a database and uses it when making new suggestions.

[1437] Prompt Sentence Examples

[1438] Example prompts to be input to the generative AI model:

[1439] Using a "cat image" and an "image of pet clothing," create a composite image of a cat wearing the clothing.

[1440] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1441] Step 1:

[1442] The user uploads images of their pet and pet clothing to the application using their device. Specifically, the user selects an image from the device's gallery and presses the "Upload" button in the application. This temporarily saves the image to the device's local storage.

[1443] Input: User-selected pet image file and pet clothing image file

[1444] Output: Image data temporarily stored in the device's local storage

[1445] Step 2:

[1446] The device sends the image data to the server using an HTTP POST request. Specifically, the selected image file is attached to the POST request and sent to the specified URL on the server. During the sending process, the image data is converted to a multipart form data format.

[1447] Input: Image data of the pet and image data of the pet's clothes stored on the device

[1448] Output: Image data sent to the server in an HTTP POST request

[1449] Step 3:

[1450] The server validates the received image data, checking its format and size, and then preprocesses the image to unify its size and resolution. Specifically, it resizes the image while maintaining its aspect ratio, and converts JPEG images to PNG format.

[1451] Input: Pet image data and pet clothing image data sent via HTTP POST request

[1452] Output: Pre-processed image data in a unified size and format

[1453] Step 4:

[1454] The server inputs the preprocessed image data into a generative AI model. The generative AI model (e.g., StyleGAN2) recognizes the pet's outline and body shape and adjusts the shape of the pet's clothing based on that. Specifically, it extracts the outline from the pet's image and transforms the image of the pet's clothing into an appropriate shape.

[1455] Input: Preprocessed pet image data and pet clothing image data

[1456] Output: Composite image of pet wearing clothes

[1457] Step 5:

[1458] The server encodes the generated composite image and converts it into an appropriate image format (e.g. PNG). It then returns it to the terminal as an HTTP response. Specifically, it performs the encoding process, adds the necessary information to the response header, and then sends the image.

[1459] Input: Generated synthetic image

[1460] Output: The encoded image sent in the HTTP response.

[1461] Step 6:

[1462] The device decodes the composite image received from the server and displays it on the application's UI. Specifically, it decodes the received image data and applies CSS and JavaScript to display it appropriately on the user's screen.

[1463] Input: Synthetic image data sent from the server

[1464] Output: Composite image displayed in the application UI

[1465] Step 7:

[1466] The device captures the user's facial expressions with a camera and transmits them to the emotion engine in real time. Specifically, it captures the camera image and communicates to send the data to the emotion engine in real time.

[1467] Input: User's facial expression data captured by a camera

[1468] Output: Facial expression data sent to the emotion engine

[1469] Step 8:

[1470] The emotion engine analyzes the user's facial expression data and extracts their emotional state. The server provides feedback and suggestions based on the obtained emotional data. Specifically, the emotion engine analyzes the facial expression data in real time and outputs the emotional state as a number or category.

[1471] Input: Facial expression data sent to the emotion engine

[1472] Output: Analysis results regarding emotional state

[1473] Step 9:

[1474] The server accumulates emotional data and makes personalized suggestions based on the user's past emotional history. Specifically, it stores the emotional data in a database and uses a suggestion algorithm to generate optimal feedback and product suggestions.

[1475] Input: Emotional state data output from the emotion engine

[1476] Output: Personalized feedback and suggestions provided to the user

[1477] (Application example 2)

[1478] 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."

[1479] Conventional pet clothing fitting systems have the problem that simply combining an image of the pet with an image of the pet clothing does not adequately convey to the user what it will actually be like trying on the pet. Furthermore, since no feedback or suggestions are provided based on the user's reactions or emotions, the user experience is not improved.

[1480] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving an image of a pet, means for receiving an image of pet clothing, and means for using a generative AI model to synthesize the received image of the pet with an image of the pet clothing. This makes it possible to provide a try-on image in which the image of the pet and the image of the pet clothing are naturally synthesized. In addition, by including means for acquiring emotion data using an emotion engine that recognizes the user's emotions and means for providing feedback based on the emotion data, personalized feedback and suggestions according to the user's emotions become possible, significantly improving the user experience.

[1481] The "means for receiving a pet image" is a device or interface for importing a photo of a pet taken or selected by a user into the system.

[1482] The "means for receiving an image of pet clothing" is a device or interface for importing a photo of the pet clothing selected by the user into the system.

[1483] A "means for using a generative AI model" is a device or software that runs an AI model using machine learning or deep learning to synthesize an image of a pet with an image of the pet's clothing.

[1484] "Means for displaying a synthesized image to a user" refers to a device or interface for displaying an image synthesized by a generative AI model on a user's device.

[1485] "Means for acquiring emotional data using an emotion engine that recognizes the user's emotions" refers to software or algorithms that determine the user's emotions in real time from their facial expressions, voice, etc.

[1486] The "means for providing feedback based on emotional data" refers to a device or software that analyzes the acquired emotional data of the user and provides appropriate feedback or suggestions to the user based on the results.

[1487] "Means for recognizing the pet's outline and body shape and adjusting the shape of the pet's clothing" refers to a function in which an AI model detects the pet's outline and body shape from a photo of the pet and automatically changes the shape of the pet's clothing accordingly.

[1488] "Means for making personalized suggestions based on emotional data" refers to software or algorithms that suggest optimal pet clothing and related items based on the user's past emotional data and current emotional state.

[1489] The "means for performing fitting adjustment according to the pet's body color and background" is a function that automatically adjusts the color tone and position of the composite image according to the pet's body color and background.

[1490] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described in detail below with reference to the accompanying drawings.

[1491] System Overview

[1492] The system synthesizes an image of the pet taken by the user with an image of the pet clothing the user is considering purchasing, and uses a generative AI model to generate a natural fitting image. It also incorporates an emotion engine that recognizes the user's emotions in real time, allowing it to provide feedback and suggestions based on the user's emotions.

[1493] Hardware and software used

[1494] Hardware

[1495] 1. Smartphone: Take and upload images of your pet and pet clothing, and display a composite image of the clothing to try on. The camera also captures the user's facial expression.

[1496] 2. Cloud server: Receives image data, preprocesses images, synthesizes images using a generative AI model, and analyzes emotional data.

[1497] software

[1498] 1. Requests library: Sends image data via HTTP POST requests.

[1499] 2. Pillow (PIL): Image preprocessing and compositing.

[1500] 3. Generative AI model: An AI model for synthesizing images of pets and pet costumes. It uses machine learning and deep learning techniques.

[1501] 4. FER (Facial Expression Recognition): A facial expression recognition engine that determines the user's emotions in real time.

[1502] 5. Keras library: Supports AI models for emotion recognition.

[1503] What the program does

[1504] Sending images

[1505] The user device sends the photographed or selected image of the pet and the image of the pet's clothing to the server. The transmission is performed using an HTTP POST request, and the image data is sent in multipart form data format, which prevents data loss and format inconsistencies.

[1506] Image Processing and Compositing

[1507] The server preprocesses the received images to standardize the size and resolution, then uses a generative AI model to recognize the pet's contours and body shape, adjust the shape of the pet's clothing, and synthesize it. The synthesized image simulates how the pet will look wearing the clothing and is encoded into the appropriate image format.

[1508] Emotional Recognition and Feedback

[1509] The user device displays the synthesized image and captures the user's facial expression with a camera. The emotion engine analyzes the user's emotional state in real time and sends the data to the server. The server then provides feedback and additional suggestions based on this emotional data, helping the user to purchase the pet clothing they are most satisfied with.

[1510] Specific examples

[1511] User A takes a photo of his dog and wants to buy new pet clothing. User A starts the application, selects a photo of the dog and an image of a candidate pet clothing item, and presses the upload button. The device sends these images to the server. The server processes the received dog image and clothing image and synthesizes them using a generative AI model. A composite image is generated and sent to User A's device. User A checks the composite image, and his facial expression is captured through the camera. The emotion engine analyzes User A's emotions, and additional pet clothing items are suggested accordingly.

[1512] Prompt Sentence Examples

[1513] Combine the "pet image" and the "pet costume image" to create a natural-looking image of the pet wearing the costume.

[1514] By implementing this mode, the user can easily check the image of the pet trying on the clothes, and can select a more appropriate item while receiving feedback that takes emotions into consideration.

[1515] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1516] Step 1:

[1517] The user uses a smartphone to take or select an image of the pet and an image of the pet's clothes and upload them to the application. When the user presses the upload button, the application obtains the image data of the pet and the image data of the pet's clothes and sends both of these image data to the server. The input here is the image of the pet and the image of the pet's clothes, and the output is that these data are sent to the server.

[1518] Step 2:

[1519] The terminal uses an HTTP POST request to send pet image data and pet clothing image data to the server. Here, the image data is sent in multipart form data format to prevent data loss and format inconsistencies. The input is the pet image data and pet clothing image data, and the output is the data being received by the server.

[1520] Step 3:

[1521] The server preprocesses the received images of the pet and pet clothing. Specifically, it standardizes the image size and resolution, removes noise, etc. The input here is the received images of the pet and pet clothing, and the output is the preprocessed image data.

[1522] Step 4:

[1523] The server uses a generative AI model to recognize the pet's contours and body shape, and adjusts the shape of the pet's clothing accordingly. Using the generative AI model, the image of the pet and the image of the pet's clothing are naturally synthesized. The input here is the preprocessed image of the pet and the image of the pet's clothing, and the output is the synthesized image.

[1524] Step 5:

[1525] The server encodes the generated composite image into an appropriate image format and prepares it for transmission to the user's device, where it is encoded into an appropriate format such as JPEG or PNG to ensure compatibility and display quality. The input is the composite image, and the output is the encoded image data.

[1526] Step 6:

[1527] The server sends the encoded composite image to the terminal as an HTTP response. To ensure security, it is recommended to use HTTPS. The input is the encoded image data, and the output is the image data sent to the user's terminal.

[1528] Step 7:

[1529] The user's device decodes the composite image received from the server and displays it on the application's UI. The user can then view the image of their pet wearing the pet clothing. The input is the composite image data received from the server, and the output is the composite image displayed on the application's UI.

[1530] Step 8:

[1531] The user's device uses a camera to capture the user's facial expressions, which are then analyzed in real time by the emotion engine. The emotion engine recognizes the user's emotional state when viewing the pet try-on image. The input is the user's facial expression image, and the output is emotion data.

[1532] Step 9:

[1533] The server analyzes the user's emotional data obtained from the emotion engine and generates appropriate feedback and suggestions based on the emotional data. For example, if the user is happy, it will suggest pet clothes with a similar design, and if the user is unhappy, it will suggest pet clothes with a different style. The input is the user's emotional data, and the output is feedback and suggestions.

[1534] Step 10:

[1535] The server accumulates the user's emotional data and stores it as an emotional history. This allows personalized suggestions to be made in the future based on the past emotional history. The input is the emotional data and feedback history, and the output is the accumulated emotional data.

[1536] 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.

[1537] 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.

[1538] 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.

[1539] 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.

[1540] 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.

[1541] 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.

[1542] 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).

[1543] 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.

[1544] 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."

[1545] 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.

[1546] 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).

[1547] 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.

[1548] 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.

[1549] 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.

[1550] 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.

[1551] 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.

[1552] 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.

[1553] 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.

[1554] 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.

[1555] 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.

[1556] 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.

[1557] The following is further disclosed regarding the above embodiment.

[1558] (Claim 1)

[1559] means for receiving an image of the pet;

[1560] means for receiving an image of the pet clothing;

[1561] a means for using a generative AI model to synthesize the received image of the pet with an image of the pet clothing;

[1562] means for displaying the combined image to a user;

[1563] A system including:

[1564] (Claim 2)

[1565] The system of claim 1, wherein the generative AI model has a means for recognizing the outline and shape of the pet and adjusting the shape of the pet's clothing.

[1566] (Claim 3)

[1567] 2. The system according to claim 1, further comprising means for adjusting the composite image to fit the pet's body color and the background.

[1568] "Example 1"

[1569] (Claim 1)

[1570] means for receiving an image of the pet;

[1571] means for receiving an image of the pet clothing;

[1572] a means for sending image data to a server using an HTTP POST request;

[1573] means for preprocessing the received pet images and pet clothing images to use a generative AI model;

[1574] means for encoding and transmitting the preprocessed image;

[1575] means for displaying the combined image to a user;

[1576] A system including:

[1577] (Claim 2)

[1578] The system of claim 1, wherein the generative AI model has a means for recognizing the pet's contours and body shape and adjusting the shape of the pet's clothing.

[1579] (Claim 3)

[1580] 2. The system according to claim 1, further comprising means for adjusting the composite image to fit the pet's body color and the background.

[1581] "Application Example 1"

[1582] (Claim 1)

[1583] means for receiving an image of the pet;

[1584] means for receiving an image of the pet clothing;

[1585] a means for using a generative AI model to synthesize the received image of the pet with an image of the pet clothing;

[1586] means for displaying the combined image to a user;

[1587] means for transmitting the synthesized image to a user terminal using a communication protocol;

[1588] A system including:

[1589] (Claim 2)

[1590] The system of claim 1, wherein the generative AI model has a means for recognizing the outline and shape of the pet and adjusting the shape of the pet's clothing.

[1591] (Claim 3)

[1592] 2. The system according to claim 1, further comprising means for adjusting the composite image to fit the pet's body color and the background.

[1593] "Example 2: Combining Emotion Engines"

[1594] (Claim 1)

[1595] means for receiving an image of the pet;

[1596] means for receiving an image of the pet clothing;

[1597] a means for using a generative AI model to synthesize the received image of the pet with an image of the pet clothing;

[1598] means for displaying the combined image to a user;

[1599] means for using an emotion engine to recognize the emotional state of a user;

[1600] means for providing feedback and suggestions based on emotion data obtained from the emotion engine;

[1601] A system including:

[1602] (Claim 2)

[1603] The system of claim 1, wherein the generative AI model has a means for recognizing the outline and shape of the pet and adjusting the shape of the pet's clothing.

[1604] (Claim 3)

[1605] 2. The system according to claim 1, further comprising means for adjusting the composite image to fit the pet's body color and the background.

[1606] "Application example 2 when combining emotion engines"

[1607] (Claim 1)

[1608] means for receiving an image of the pet;

[1609] means for receiving an image of the pet clothing;

[1610] a means for using a generative AI model to synthesize the received image of the pet with an image of the pet clothing;

[1611] means for displaying the combined image to a user;

[1612] means for acquiring emotion data using an emotion engine that recognizes the emotion of a user;

[1613] a means for providing feedback based on the emotion data;

[1614] A system including:

[1615] (Claim 2)

[1616] The system of claim 1, wherein the generative AI model has a means for recognizing the outline and shape of the pet and adjusting the shape of the pet's clothing.

[1617] (Claim 3)

[1618] The system according to claim 1, further comprising means for adjusting the composite image to fit the pet's body color and background, and means for making personalized suggestions based on the emotion data. [Explanation of symbols]

[1619] 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 an image of the pet; means for receiving an image of the pet clothing; a means for using a generative AI model to synthesize the received image of the pet with an image of the pet clothing; means for displaying the combined image to a user; A system including:

2. The system of claim 1, wherein the generative AI model has a means for recognizing the outline and shape of the pet and adjusting the shape of the pet's clothing.

3. 2. The system according to claim 1, further comprising means for adjusting the composite image to fit the pet's body color and the background.

Images