System

Abstract

A system is provided.SOLUTION: A system, comprising: means for a user to input an image of the user; means for the user to select a transformation option to be applied to the image; means for the user to transmit the image and the selected transformation option to a server; means for the server to process the image using a deep-learning model to generate a new image; means for the server to return the generated new image to a terminal of the user; and means for the user to confirm and share the new image.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] The present invention relates to an image processing system that allows users to easily transform their own images into specific people or animals without requiring special technical knowledge or skills, and share the results via social networking sites or messaging applications. Conventional image processing technologies require specialized software and skills, making them difficult for many users to use. The challenge is to solve this problem and enable more users to easily enjoy high-quality image processing. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by the following means. This system includes a means for a user to input their own image, a means for selecting conversion options to be applied to the image, a means for transmitting the image and the selected conversion options to a server, a means for the server to process the image using a deep learning model to generate a new image, a means for returning the generated new image to the user's device, and a means for the user to review and share the new image. This allows users to easily edit images and share the results without technical knowledge. The system also includes a means for the server to apply a specific model from multiple deep learning models to the received image based on the selected conversion options, thereby providing a wide range of conversion options. Furthermore, the device includes a means for sharing the new image via multiple social networking services or messaging applications in accordance with the user's sharing selection, allowing users to easily utilize the generated image in communication.

[0006] "User" refers to an individual or organization that uses the image processing system.

[0007] "Image" refers to photographs and illustration data entered or uploaded by the user.

[0008] "Transformation options" refer to styles or themes such as specific people, animals, characters, etc. that are applied to an image.

[0009] "Server" refers to a computer system that processes and converts data sent from a user's device and returns the results.

[0010] "Deep learning model" refers to an algorithm developed based on deep learning technology that is used to convert an input image into a specific style.

[0011] "Processing" refers to a series of operations in which the server uses a deep learning model to regenerate the image based on the specified transformation options.

[0012] "New Image" refers to the image data after it has been processed and transformed by the server.

[0013] "Terminal" refers to a user's device (such as a smartphone, tablet, or PC) that runs the image processing system and sends and receives images to the server.

[0014] "Sharing means" refers to the ability for users to share the newly generated image with others via social networking sites, messaging applications, etc.

[0015] "Social Networking Service (SNS)" refers to an online platform that enables users to share new images they have created with other users.

[0016] "Messaging Application" means an application that enables a User to communicate and share new images that the User has created with others. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] This invention is a system that allows users to upload their own images, convert the images into specific people, animals, characters, etc., and share the generated images. An embodiment of this system will be described in detail below.

[0039] System Configuration

[0040] The system of the present invention mainly comprises the following components:

[0041] 1. User device: A device on which a user inputs and selects an image, specifies conversion options, sends it to the server, and receives, displays, and shares the processed image. This includes smartphones, tablets, and PCs.

[0042] 2. Server: Receives the image and conversion options sent from the user device, processes the image using a deep learning model, generates a new image, and sends it back to the user device.

[0043] 3. Network: The Internet or other communications network that allows data communication between user terminals and the server.

[0044] Program processing

[0045] User terminal processing

[0046] When a user wants to edit their own image, they launch the application on their device. The user clicks the "Upload Photo" button in the application and selects a photo from their gallery. After the user selects an image, the device displays a preview of the image and asks the user for confirmation. For the confirmed image, the application presents the user with transformation options (e.g., "Anime Character," "Celebrity," "Dog," "Cat," etc.). After the user selects the desired transformation option, the device temporarily saves the selected image and transformation option and sends this data to the server.

[0047] Server Processing

[0048] The server receives the image and conversion options sent from the user device. It decodes the received data and separates the image from the conversion options. The server then selects a deep learning model based on the specified conversion options. The selected model inputs the image data and converts the image into a specific style. It then generates new processed image data, encodes it, and sends it back to the user device.

[0049] Specific examples

[0050] For example, if a user wants to convert their selfie into an anime character style, the process would be as follows:

[0051] 1. The user uploads a selfie to the application and selects the option to convert it into an anime character.

[0052] 2. The device sends the selfie and conversion options to the server.

[0053] 3. The server receives the selfie and selects an anime character generation model.

[0054] 4. The server uses the model to transform the selfie into an anime character.

[0055] 5. The server returns the newly generated anime character-style image to the device.

[0056] 6. The device displays the returned image and asks the user to confirm it.

[0057] 7. The user reviews the image and shares it via social media or messaging apps.

[0058] In this way, the system of the present invention allows users to easily enjoy high-quality image processing even if they do not have special technical skills, and the results can be easily shared with others.

[0059] The processing flow will be explained below.

[0060] Step 1:

[0061] The user launches a photo editing app on their device.

[0062] Step 2:

[0063] The user clicks the "Upload Photo" button within the app and selects the photo they want to edit from their gallery.

[0064] Step 3:

[0065] The device displays a preview of the selected photo for the user to confirm, and also presents conversion options (e.g., "celebrity," "anime character," "dog," "cat," etc.) to the user.

[0066] Step 4:

[0067] The user selects the desired conversion options.

[0068] Step 5:

[0069] Your device will temporarily save the photo and conversion options you selected.

[0070] Step 6:

[0071] The device encodes the photo data and conversion options into JSON format and prepares an HTTP request to send to the server.

[0072] Step 7:

[0073] The device sends an HTTP request containing the encoded data to the server.

[0074] Step 8:

[0075] The server receives the HTTP request sent from the terminal and decodes the JSON data.

[0076] Step 9:

[0077] The server separates the decoded photo data and the transformation options, and selects the required deep learning model based on the transformation options.

[0078] Step 10:

[0079] The server inputs the photo data into a deep learning model and converts the image into the specified style.

[0080] Step 11:

[0081] The server generates new converted image data and encodes it in JPEG format or the like.

[0082] Step 12:

[0083] The server prepares and sends an HTTP response to return the new encoded image data to the user's terminal.

[0084] Step 13:

[0085] The terminal receives the HTTP response sent back from the server and decodes the encoded image data.

[0086] Step 14:

[0087] The device will then display the new decoded image in the app for the user to review.

[0088] Step 15:

[0089] The user reviews the new image and chooses to share it via social media or messaging applications.

[0090] Step 16:

[0091] The device will provide sharing options based on the user's selection, launching the specified social networking site or messaging application to share the new image.

[0092] Example 1

[0093] 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."

[0094] With conventional image conversion systems, it is difficult to achieve high-quality image conversion unless the user has special technical skills, and there are limited ways to easily share the results with others. It is also difficult to select the appropriate deep learning model for a specific conversion option and perform the optimal conversion. This limits the user experience and makes the system less convenient and versatile.

[0095] 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.

[0096] In this invention, the server includes means for applying a specific model from among a plurality of deep learning models to the received image based on a selected conversion option, means for generating a new image after the conversion process, and means for returning the generated new image to the user terminal, thereby enabling users to easily achieve high-quality image conversion without requiring special technical skills and quickly share the results with others.

[0097] A "User" is an individual or entity who provides input and selections to transform and share their images using the system.

[0098] "Terminal" refers to a device that allows a user to input or select an image, specify conversion options, and send the image to the server, and includes smartphones, tablets, and PCs.

[0099] "Server" means a centralized computer system that receives images and transformation options sent from a user device, transforms the images using a deep learning model, and generates a new image that is sent back to the user device.

[0100] "Images" are visual data such as photographs and illustrations uploaded by users.

[0101] "Conversion options" are settings that represent a particular style or theme (e.g., "Anime Characters," "Celebrities," "Animals," etc.) that is applied to an image.

[0102] A "deep learning model" is a machine learning model that has been trained to transform images into a specific style using deep learning algorithms.

[0103] A "new generated image" is another visual data generated by transforming the original image using a deep learning model.

[0104] "Sharing" refers to the act of a user sending and publishing a newly generated image to others via social networking sites, messaging applications, etc.

[0105] The present invention provides a system that allows users to upload their own images, convert the images into a specific style, and share the generated images with others. An embodiment of this system will be described in detail below.

[0106] System Configuration

[0107] The system of the present invention mainly comprises the following components:

[0108] 1. User device: A device on which a user inputs and selects an image, specifies conversion options, sends it to the server, and receives, displays, and shares the processed image. This includes smartphones, tablets, PCs, etc.

[0109] 2. Server: Receives the image and conversion options sent from the user device, converts the image using a deep learning model, generates a new image, and sends it back to the user device.

[0110] 3. Network: The Internet or other communication network that allows data communication between user terminals and the server.

[0111] Program processing

[0112] When a user wants to edit their own image, they first launch the application on their device. The user clicks the "Upload Photo" button and selects a photo from their gallery. After the user selects an image, the device displays a preview of the image and asks the user for confirmation. For the confirmed image, the application presents the user with transformation options (e.g., "Anime Character," "Celebrity," "Dog," "Cat," etc.). After the user selects the desired transformation option, the device temporarily saves the selected image and transformation option and sends this data to the server.

[0113] Specific processing flow

[0114] 1. User uploads an image

[0115] The user launches the application on their device, clicks the "Upload Photos" button, and the gallery is displayed. They can then select the image they want to upload. The selected image is then displayed on the preview screen.

[0116] 2. The user selects conversion options

[0117] After viewing the image in the preview screen, the user selects a conversion option (e.g., "Anime Character," "Celebrity," "Dog," "Cat," etc.) from a menu within the application. A dialog displays the selection and asks the user for confirmation.

[0118] 3. The device sends the data to the server

[0119] Once the user has selected the conversion options, the device temporarily stores the selected image and conversion options, and then sends the image data and conversion options to the server using an HTTP request.

[0120] 4. The server receives and analyzes the data

[0121] The server parses the received HTTP request and separates the image data and conversion options. The image data is saved in temporary storage, and the conversion options are stored in variables.

[0122] 5. The server converts the image

[0123] The server selects an appropriate deep learning model based on the conversion options. The selected model may use TensorFlow or PyTorch. The server inputs the image data into the deep learning model and converts it into the specified style. New converted image data is generated.

[0124] 6. The server sends the converted image back to the device.

[0125] The server encodes the converted image data and returns it to the user device. The HTTP response is used again for the return. The server records the processing results in a log and performs error handling as necessary.

[0126] 7. User reviews and shares the image

[0127] The user's device decodes the converted image data received from the server and displays it on the screen. The user can then view the image and easily share it via social media or messaging apps by clicking the share button within the application.

[0128] Specific examples

[0129] For example, if a user wants to transform their selfie into a cartoon character, the process would look like this:

[0130] 1. The user uploads a selfie to the application and selects the option to convert it as an "anime character."

[0131] 2. The device sends the selfie and conversion options to the server.

[0132] 3. The server receives the selfie and selects an anime character generation model.

[0133] 4. The server uses the model to transform the selfie into an anime character.

[0134] 5. The server returns the newly generated anime character-style image to the device.

[0135] 6. The device displays the returned image and asks the user to confirm it.

[0136] 7. The user reviews the image and shares it via social media or messaging apps.

[0137] Prompt Sentence Examples

[0138] To adjust the quality and style of the resulting image, you can provide prompts to the generative AI model, such as:

[0139] "Transform your selfie into an anime character-style image."

[0140] This prompt will guide the AI ​​model through the process of transforming the selfie into an "anime character" image. Additional prompts can be used to specify more specific styles and characteristics, if desired.

[0141] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0142] Processing flow

[0143] Step 1:

[0144] The user uploads an image

[0145] Specific operation: The user launches the application on their device and clicks the "Upload Photo" button. The gallery will be displayed, and they can select the image they want to upload. The selected image will be displayed on the preview screen.

[0146] Input: An image file selected by the user.

[0147] Output: Preview image displayed on the device

[0148] Step 2:

[0149] The user selects conversion options

[0150] What it does: After viewing an image in the preview screen, the user selects a conversion option from a menu within the application (e.g., "Anime Character," "Celebrity," "Dog," "Cat," etc.) A dialog appears displaying the selection and asking the user for confirmation.

[0151] Input: User selected conversion options

[0152] Output: A confirmation dialog displayed on the terminal

[0153] Step 3:

[0154] The device sends the data to the server

[0155] Specific operation: After the user has selected the conversion options, the device temporarily saves the selected image and conversion options, and then sends the image data and conversion options to the server using an HTTP request.

[0156] Input: Selected image data and conversion options

[0157] Output: HTTP request sent to the server

[0158] Step 4:

[0159] The server receives and analyzes the data

[0160] Specific operation: The server parses the received HTTP request and separates the image data and conversion options. The image data is saved in temporary storage, and the conversion options are stored in variables.

[0161] Input: Image data and conversion options sent as an HTTP request

[0162] Output: Parsed image data and conversion options

[0163] Step 5:

[0164] The server converts the image

[0165] Specific operation: The server selects an appropriate deep learning model based on the conversion options. The selected model may use TensorFlow or PyTorch. The server inputs the image data into the deep learning model and converts it into the specified style. New converted image data is generated.

[0166] Input: Parsed image data and transformation options

[0167] Output: New image data after conversion processing

[0168] Step 6:

[0169] The server sends the converted image back to the device.

[0170] Specific operation: The server encodes the converted image data and returns it to the user device. The HTTP response is used again for the return. The server records the processing result in a log and performs error handling as necessary.

[0171] Input: New image data after conversion processing

[0172] Output: The HTTP response sent back to the device

[0173] Step 7:

[0174] Users review and share images

[0175] Specific operation: The user device decodes the converted image data received from the server and displays it on the screen. The user can then view the image and easily share it via social media or messaging apps by clicking the share button in the application.

[0176] Input: The converted image data sent back to the device

[0177] Output: The converted image displayed on the device and the shared image

[0178] (Application example 1)

[0179] 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."

[0180] Conventional image conversion technologies simply convert images statically, limiting their use as content. Furthermore, there are limited ways to generate and share more diverse content using the converted images. Therefore, there is a need for technology that improves the user experience and enhances the scalability of generated content.

[0181] 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.

[0182] In this invention, the server includes a means for processing user-entered images using a generative artificial intelligence model to generate new images, a means for generating custom videos or moving images using the generated new images, and a means for sharing the generated content via multiple information distribution services or messaging applications, thereby enabling users to not only enjoy high-quality image conversion but also easily generate and share a variety of content based on the generated images.

[0183] "User" refers to the person using the system who inputs their image, selects conversion options, and reviews and shares the generated content.

[0184] "Conversion options" refer to specific styles and settings that users can select when converting images using a deep learning model.

[0185] "Server" refers to a device or system that receives images and conversion options sent from a user terminal, processes the images using a generative artificial intelligence model, generates new images or video, and returns them to the user terminal.

[0186] A "generative artificial intelligence model" is a deep learning-based model used for image transformation, which refers to a technique for transforming an input image according to a specific style.

[0187] "Custom video" or "motion picture" refers to a moving image or animation created from newly generated images.

[0188] An "information distribution service" is an online platform for sharing user-generated content with others, including social networking services and messaging applications.

[0189] "Sharing" refers to the act of sending generated content to other users or platforms where it can be accessed or viewed.

[0190] The present invention provides a system that allows users to upload their own images, convert those images into specific people, animals, characters, etc., and share the generated images and videos. Specific embodiments of this system are described below.

[0191] System Overview

[0192] The system mainly consists of the following components:

[0193] 1. User terminal: A device that allows users to input and select images, specify conversion options, send them to the server, and receive, display, and share processed images, custom videos, and moving images. This includes smartphones, tablets, and PCs.

[0194] 2. Server: Receives images and conversion options sent from the user terminal, processes the images using a generative artificial intelligence model, generates new images and videos, and sends them back to the user terminal.

[0195] 3. Network: The Internet or other communication network that allows data communication between user terminals and the server.

[0196] Program processing

[0197] User terminal processing

[0198] When a user wants to edit their own image, they launch the application on their device. Within the application, the user clicks the "Upload Photo" button and selects a photo from their gallery. Once the user selects an image, the device displays a preview of the image and asks the user for confirmation. For the confirmed image, the application presents the user with transformation options (e.g., "Anime Character," "Celebrity," "Dog," "Cat," etc.). Once the user selects the desired transformation option, the device temporarily saves the selected image and transformation option and sends this data to the server.

[0199] Server Processing

[0200] The server receives the images and conversion options sent from the user device. It decodes the received data and separates the images from the conversion options. Next, the server selects a generative artificial intelligence (AI) model based on the specified conversion options. The image data is input into the selected model and converted into a specific style. PyTorch is used as the deep learning library. The generated images are then used to generate custom videos and moving images. At this stage, PIL (Python Imaging Library) and the generative artificial intelligence model are used. New processed image data and moving images are generated, encoded, and sent back to the user device.

[0201] An example

[0202] For example, if a user wants to transform their selfie into a cartoon character and create a short video from it to share with friends, here's what happens:

[0203] 1. The user uploads a selfie to the application and selects the option to convert it into an "anime character."

[0204] 2. The device sends the selfie and conversion options to the server.

[0205] 3. The server receives the selfie and selects an anime character generation model.

[0206] 4. The server uses a generative artificial intelligence model to transform the selfie into an anime character.

[0207] 5. The server creates a short video or animation using the newly generated anime character-style image.

[0208] 6. The server returns the generated content to the device.

[0209] 7. The device displays the returned images and videos for the user to review.

[0210] 8. The user reviews the images and videos and shares them via social media or messaging apps.

[0211] Prompt Sentence Examples

[0212] For example, by entering a prompt such as "Please convert this selfie into an anime character style," the user can easily obtain the desired conversion result.

[0213] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0214] Step 1:

[0215] The user launches the application and clicks the "Upload Photo" button.

[0216] Specifically, the user selects a photo from their gallery. The input is the image file selected by the user, and the device displays a preview of the image. The output is the image displayed on the preview screen.

[0217] Step 2:

[0218] The terminal asks the user for confirmation, and then presents the user with conversion options (e.g., "anime character," "celebrity," "dog," "cat," etc.) for the confirmed image.

[0219] The input is the conversion options selected by the user, which the terminal temporarily stores, and the output is the data for the selected conversion options.

[0220] Step 3:

[0221] The terminal sends the selected image and conversion options to the server.

[0222] The input is the image and conversion options selected by the user, and the terminal sends this data to the server via the network. The output is the image data and conversion options sent to the server.

[0223] Step 4:

[0224] The server receives the image and conversion options sent from the user terminal.

[0225] The input is image data and conversion options sent from the terminal, which the server decodes and separates into the image and conversion options, and the output is the separated image data and conversion options.

[0226] Step 5:

[0227] The server selects a generative artificial intelligence model based on the specified transformation options.

[0228] The input is a set of isolated transformation options, and the server selects an appropriate model from among multiple generative artificial intelligence models. The output is the selected generative artificial intelligence model.

[0229] Step 6:

[0230] The server inputs the image data into the selected model and transforms the image into a particular style.

[0231] The input is image data and a selected generative artificial intelligence model, the server uses the model to transform the image, and the output is the new transformed image data.

[0232] Step 7:

[0233] The server uses the new images to generate custom video or animation.

[0234] The input is the new transformed image data that the server uses to generate the video or animation, and the output is the custom video or animation that is generated.

[0235] Step 8:

[0236] The server encodes the generated custom video or animation and sends it back to the user's device.

[0237] The input is the generated custom video or animation that the server encodes and sends back to the user's device over the network, and the output is the custom video or animation sent to the user's device.

[0238] Step 9:

[0239] The user terminal displays the returned custom video or moving image for the user to review.

[0240] The input is a custom video or animation returned from the server, which the terminal displays and asks the user for confirmation. The output is the displayed custom video or animation.

[0241] Step 10:

[0242] Users can view images and videos and share them via social media or messaging applications.

[0243] The input is a verified custom video or moving image, and the user selects the platform to share it on. The output is content shared to social media or messaging applications.

[0244] 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.

[0245] This invention relates to a system that allows users to upload their own images, convert them into specific people, animals, characters, etc., and share the generated images. In addition, the invention aims to provide more appropriate and personalized conversion options by combining an emotion engine that recognizes the user's emotions.

[0246] System Configuration

[0247] The system of the present invention mainly comprises the following components:

[0248] 1. User device: A device on which a user inputs and selects an image, specifies conversion options, sends the image to the server, and receives, displays, and shares the processed image. This includes smartphones, tablets, and PCs. It also has the function of sending the user's facial expression and voice data to the emotion engine.

[0249] 2. Server: Receives the image and conversion options sent from the user device, processes the image using a deep learning model, generates a new image, and sends it back to the user device. Furthermore, it utilizes data from the emotion engine to suggest and apply appropriate conversion options.

[0250] 3. Emotion Engine: A component that includes algorithms for estimating emotions based on the user's facial recognition data and voice data, and proposing and selecting the optimal conversion options.

[0251] 4. Network: The Internet or other communications network that allows data communication between user terminals and the server.

[0252] Program processing

[0253] User terminal processing

[0254] When a user wants to edit their own image, they launch the application on their device. Within the application, the user clicks the "Upload Photo" button and selects a photo from their gallery. Once the user selects an image, the device displays a preview of the image and asks the user for confirmation. For the confirmed image, the application presents the user with transformation options (e.g., "Anime Character," "Celebrity," "Dog," "Cat," etc.).

[0255] Furthermore, the device sends the user's facial recognition data and voice data to the emotion engine to estimate their emotions. The emotion engine then suggests optimal conversion options based on the estimated emotions. When the user accepts the optimal suggestion or selects another option, the device temporarily stores the selected image and conversion options and transmits this data to the server.

[0256] Server Processing

[0257] The server receives the image and conversion options sent from the user device. It decodes the received data and separates the image from the conversion options. The server then selects the required deep learning model based on the specified conversion options, inputs the image data into the model, and generates a new image. The generated image data is then encoded and sent back to the user device.

[0258] Specific examples

[0259] For example, if a user wants to convert their selfie into an anime character style, the process would be as follows:

[0260] 1. The user uploads a selfie to the application and selects the desired conversion options.

[0261] 2. The device displays a preview of the selfie image and also sends the user's facial recognition data to the emotion engine.

[0262] 3. The emotion engine estimates the user's emotion (e.g., joy, surprise, etc.) and suggests "anime character" as the optimal conversion option.

[0263] 4. If the user accepts the suggestion, the device sends the selected selfie and the "Anime Character" conversion option to the server.

[0264] 5. The server receives the selfie and selects an anime character generation model.

[0265] 6. The server uses the model to transform the selfie into an anime character image and sends the resulting image back to the device.

[0266] 7. The device displays the returned image and asks the user to confirm it.

[0267] 8. The user reviews the image and selects the option to share it via social media or messaging apps.

[0268] This system allows users to easily enjoy personalized image processing based on emotions, even without any special technical skills, and easily share the results with others.

[0269] The processing flow will be explained below.

[0270] Step 1:

[0271] The user launches a photo editing app on their device.

[0272] Step 2:

[0273] The user clicks the "Upload Photo" button within the app and selects the photo they want to edit from their gallery.

[0274] Step 3:

[0275] The device displays a preview of the selected photo for the user to confirm, and also presents conversion options (e.g., "celebrity," "anime character," "dog," "cat," etc.) to the user.

[0276] Step 4:

[0277] The terminal collects the user's facial recognition data and voice data and sends them to the emotion engine.

[0278] Step 5:

[0279] The emotion engine analyzes the received facial recognition data and voice data to estimate the user's emotion.

[0280] Step 6:

[0281] The emotion engine suggests optimal conversion options based on the estimated emotion.

[0282] Step 7:

[0283] The user accepts the proposed conversion options or selects other conversion options.

[0284] Step 8:

[0285] The device temporarily saves the selected photo and the confirmed conversion options.

[0286] Step 9:

[0287] The device encodes the photo data and conversion options into JSON format and prepares an HTTP request to send to the server.

[0288] Step 10:

[0289] The device sends an HTTP request containing the encoded data to the server.

[0290] Step 11:

[0291] The server receives the HTTP request sent from the terminal and decodes the JSON data.

[0292] Step 12:

[0293] The server separates the decoded photo data and the transformation options, and selects the required deep learning model based on the transformation options.

[0294] Step 13:

[0295] The server inputs the photo data into a deep learning model and converts the image into the specified style.

[0296] Step 14:

[0297] The server generates new converted image data and encodes it in JPEG format or the like.

[0298] Step 15:

[0299] The server prepares and sends an HTTP response to return the new encoded image data to the user's terminal.

[0300] Step 16:

[0301] The terminal receives the HTTP response sent back from the server and decodes the encoded image data.

[0302] Step 17:

[0303] The device will then display the new decoded image in the app for the user to review.

[0304] Step 18:

[0305] The user reviews the new image and chooses to share it via social media or messaging applications.

[0306] Step 19:

[0307] The device will provide sharing options based on the user's selection, launching the specified social networking site or messaging application to share the new image.

[0308] Example 2

[0309] 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."

[0310] In recent years, advances in image editing technology have made it possible for individuals to easily process and edit images. However, existing systems have difficulty in providing personalized editing that takes user emotions into account, and this poses a high hurdle for general users without special technical skills. To solve this problem, there is a need for a simple and intuitive image conversion system that can recognize user emotions and suggest optimal conversion options.

[0311] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0312] In this invention, the server includes a means for processing an image using a deep learning model to generate a new image, a means for returning the generated new image to the user's terminal, and a means including an emotion engine for recognizing the user's emotion and suggesting conversion options based on the emotion, thereby enabling the user to easily perform personalized image conversion based on their own emotion.

[0313] A "user" is an individual or entity that inputs an image, selects conversion options, and reviews and shares the resulting image.

[0314] "User terminal" refers to a device on which a user inputs and selects an image, specifies conversion options, sends the image to the server, and receives, displays, and shares the processed image. This includes smartphones, tablets, PCs, etc.

[0315] A "server" is a device or system that receives an image and conversion options sent from a user terminal, processes the image using a deep learning model, generates a new image, and returns it to the user terminal.

[0316] "Image" refers to data containing visual information such as a photograph or picture entered by the user.

[0317] "Conversion options" are options for how the user can process or edit an image. Examples include "anime characters," "celebrities," "dogs," and "cats."

[0318] A "deep learning model" is a model that uses advanced machine learning algorithms to process input data, learn and recognize specific patterns, and generate images.

[0319] The "emotion engine" is a component that includes algorithms for estimating emotions based on the user's facial recognition data and voice data, and proposing and selecting optimal conversion options.

[0320] A "preview" is a temporary display that allows the user to check the image selected and the editing operations performed.

[0321] "Encoding" is the process of converting data into a particular format.

[0322] "Decoding" is the process of restoring encoded data to its original form.

[0323] This invention relates to a system that allows users to convert their own images into specific people, animals, characters, etc., and share the generated images. Furthermore, the invention aims to combine an emotion engine that recognizes the user's emotions to provide more appropriate and personalized conversion options. Specific embodiments for implementing this system are described below.

[0324] System Configuration

[0325] The system of the present invention mainly comprises the following components:

[0326] 1. User device: A device on which users input and select images, specify conversion options, send them to the server, and receive, display, and share the processed images. This includes smartphones, tablets, PCs, etc., and also has the function of sending the user's facial expression data and voice data to the emotion engine.

[0327] 2. Server: Receives the image and conversion options sent from the user device, processes the image using a deep learning model, generates a new image, and sends it back to the user device. It also uses data from the emotion engine to suggest and apply appropriate conversion options.

[0328] 3. Emotion Engine: This component includes algorithms for estimating emotions based on the user's facial recognition data and voice data, and for suggesting and selecting optimal conversion options.

[0329] 4. Network: The Internet or other communications network that allows data communication between user terminals and the server.

[0330] System Operation

[0331] When a user wants to edit their own image, they launch the application on their device. The user clicks the "Upload Photo" button in the application and selects a photo from their gallery. After the user selects an image, the device displays a preview of the image and asks the user for confirmation. For the confirmed image, the application presents the user with transformation options (e.g., "Anime Character," "Celebrity," "Dog," "Cat," etc.). In addition, the device sends the user's facial recognition data and voice data to an emotion engine to estimate their emotion. The emotion engine suggests the optimal transformation option based on the estimated emotion. If the user accepts the optimal suggestion or selects another option, the device temporarily saves the selected image and transformation option and sends this data to the server.

[0332] The server receives the image and conversion options sent from the user device. It decodes the received data and separates the image from the conversion options. The server then selects the required deep learning model based on the specified conversion options, inputs the image data into the model, and generates a new image. The generated image data is then encoded and sent back to the user device.

[0333] Specific examples

[0334] For example, if a user wants to convert their selfie into an anime character style, the process would be as follows:

[0335] 1. The user uploads a selfie to the application and selects the desired conversion options.

[0336] 2. The device displays a preview of the selfie image and also sends the user's facial recognition data to the emotion engine.

[0337] 3. The emotion engine estimates the user's emotion (e.g., joy, surprise, etc.) and suggests "anime character" as the optimal conversion option.

[0338] 4. If the user accepts the suggestion, the device sends the selected selfie and the "Anime Character" conversion option to the server.

[0339] 5. The server receives the selfie and selects an anime character generation model.

[0340] 6. The server uses the model to transform the selfie into an anime character image and sends the resulting image back to the device.

[0341] 7. The device displays the returned image and asks the user to confirm it.

[0342] 8. The user reviews the image and selects the option to share it via social media or messaging apps.

[0343] Example of input prompt for generative AI model

[0344] "A user uploaded a selfie and selected the 'Anime Character' conversion option. Please convert this selfie to look like an anime character."

[0345] This system allows users to easily enjoy personalized image processing based on emotions, even without any special technical skills, and easily share the results with others.

[0346] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0347] Step 1:

[0348] The user launches an application on the device.

[0349] Input: The user taps on an app on their smartphone.

[0350] Output: The main screen of the application is displayed.

[0351] Specific behavior: The user taps the icon to launch the app, and the app displays the main screen.

[0352] Step 2:

[0353] A user uploads an image.

[0354] Input: User presses the "Upload Photo" button and selects a photo from the gallery.

[0355] Output: The selected image is displayed in the application.

[0356] Specific operation: The user presses a button, moves to an image selection screen, and selects an image such as a selfie from the gallery.

[0357] Step 3:

[0358] Your device will display a preview of the image and ask for confirmation.

[0359] Input: An image selected by the user.

[0360] Output: A preview of the image and a confirmation message asking "Are you sure this is the image?"

[0361] What happens: The device generates a preview of the image and displays a confirmation dialog.

[0362] Step 4:

[0363] The terminal presents conversion options to the user.

[0364] Input: User sees the image and answers "yes."

[0365] Output: You will see conversion options such as anime characters, celebrities, dogs, cats, etc.

[0366] Specific behavior: The device renders a UI to display the options.

[0367] Step 5:

[0368] The device sends facial recognition data and voice data to the emotion engine.

[0369] Input: User's facial recognition and voice data.

[0370] Output: Data sent to the emotion engine.

[0371] Specific operation: The device captures data using the camera and microphone and sends it to the emotion engine.

[0372] Step 6:

[0373] The device presents suggestions from the emotion engine to the user.

[0374] Input: Transformation option suggestions from the sentiment engine.

[0375] Output: The best conversion options based on the estimated sentiment are displayed to the user.

[0376] Specific operation: The device receives the response from the emotion engine and displays the suggestions.

[0377] Step 7:

[0378] The user selects a conversion option.

[0379] Input: User's choice of conversion options.

[0380] Output: The selected conversion options will be saved to your device.

[0381] What happens: The user taps an option and the device records the selection.

[0382] Step 8:

[0383] The device sends the selected image and conversion options to the server.

[0384] Input: Selected image and conversion options.

[0385] Output: The image and conversion options are sent to the server.

[0386] Specific operation: The terminal forms transmission data and transmits the data to the server through the network.

[0387] Step 9:

[0388] The server receives the image and conversion options.

[0389] Input: Image sent from the device and conversion options.

[0390] Output: Decoded result of received data.

[0391] What it does: The server decodes the received data and separates the image and conversion options.

[0392] Step 10:

[0393] The server selects the required deep learning model.

[0394] Input: Conversion options.

[0395] Output: The selected deep learning model.

[0396] What happens: The server looks up the appropriate model from the database or file system.

[0397] Step 11:

[0398] The server inputs the image into the model and generates a new image.

[0399] Input: Original image data, selected deep learning model.

[0400] Output: The new image generated.

[0401] Specific operation: The server inputs image data into the model, processes it, and generates a new image.

[0402] Step 12:

[0403] The server encodes the generated image and sends it back to the user's terminal.

[0404] Input: The new image generated.

[0405] Output: The encoded image data.

[0406] Specific operation: The server encodes the image in a timely manner and transmits it to the user terminal via the network.

[0407] Step 13:

[0408] The terminal displays the returned image and prompts the user to confirm it.

[0409] Input: The encoded image data returned from the server.

[0410] Output: The new image displayed.

[0411] What happens: The device decodes the image and displays it to the user for confirmation.

[0412] Step 14:

[0413] The user can view the image and share it via social media or messaging applications.

[0414] Input: User confirmation.

[0415] Output: Link or data for sharing.

[0416] What happens: The user clicks the "Share" button and selects the option to send the image to the social networking or messaging application of their choice.

[0417] (Application example 2)

[0418] 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."

[0419] Conventional image processing systems lack a means to provide personalized transformation options based on the user's emotions, making it difficult to create optimal content for the user. Furthermore, when users use images as virtual try-on simulations, they have difficulty selecting appropriate outfits and accessories, resulting in an unsatisfactory try-on experience.

[0420] The specification processing by the specification 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 acquiring the user's facial expression data and voice data and sending them to the emotion engine, means for proposing optimal conversion options based on the emotions estimated by the emotion engine, and means for applying a specific model from among multiple deep learning models based on the selected conversion options and suggestions from the emotion engine. This enables personalized image conversion and virtual try-on simulations that take the user's emotions into consideration.

[0421] A "user" is someone who uses the system to enhance their own images and review and share the transformed images.

[0422] "Images" are visual data such as photographs or illustrations that users upload to the system.

[0423] "Conversion options" refer to image processing styles and themes that users can select, including anime character style, animal style, celebrity style, etc.

[0424] "Facial expression data" is data used to capture the user's facial expressions and estimate their emotions based on that information.

[0425] "Voice data" is data that captures the user's vocalizations and is used to estimate emotions based on that voice information.

[0426] An "emotion engine" is an algorithm or program that analyzes facial expression data and voice data, estimates the user's emotions, and suggests optimal conversion options.

[0427] A "deep learning model" is a neural network that is trained with large amounts of data to transform input images into a specific style.

[0428] The "server" is the central processing unit of the system, a computer that processes images and conversion options sent by users, generates new images, and returns them.

[0429] "Terminal" refers to a device that a user uses to upload images, receive converted images, and view and share them, including smartphones, tablets, and PCs.

[0430] A "preview" is a temporary image that is displayed to allow a user to check the image they have uploaded.

[0431] A "social networking service" is an online platform used by users to share generated images, also known as an SNS.

[0432] A "messaging application" is a communication tool that users use to share generated images.

[0433] A "personalized image" is an image that is customized based on the user's feelings and preferences.

[0434] "Virtual try-on simulation" is a process in which a user virtually tries on outfits and accessories in images uploaded by the user.

[0435] The following describes an embodiment of the present invention. The system allows users to upload their own images, convert them into specific characters, people, animals, etc., and then review and share the generated images. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides more appropriate and personalized conversion options.

[0436] Hardware and Software

[0437] The main components of the system are:

[0438] User device: A smartphone, tablet, PC, etc. This is the device where users input and select images, and receive, display, and share the processed images. React Native and JavaScript are used to upload images and display previews.

[0439] Server: Receives images, processes them using deep learning models, generates new images, and sends them back to the user device. Can use cloud services such as AWS EC2.

[0440] Emotion engine: An algorithm that estimates emotions based on the user's facial expression and voice data and suggests optimal conversion options. Microsoft Azure's Emotion API can be used.

[0441] Deep learning models: Use frameworks such as TensorFlow to perform image transformation.

[0442] Processing flow

[0443] User device operation

[0444] 1. The user launches the application and clicks the "Upload Photo" button to select their own image.

[0445] 2. A preview of the image is displayed and the user confirms it.

[0446] 3. The user device acquires facial expression data and voice data and sends them to the emotion engine.

[0447] 4. The emotion engine estimates the emotion and presents the user with recommended transformation options (e.g., anime character style).

[0448] 5. If the user accepts the offer or selects another option, the data is sent to the server.

[0449] Server Processing

[0450] 1. The server receives the image and conversion options sent by the user.

[0451] 2. Select a deep learning model, input an image, and generate a new image.

[0452] 3. The generated image is sent back to the user's device.

[0453] Displaying the user terminal

[0454] 1. The generated image is displayed and the user confirms it.

[0455] 2. Users have the option to share the image on social media or messaging applications.

[0456] Specific examples

[0457] For example, if a user wants to convert their selfie into an anime character style, the process would be as follows:

[0458] 1. The user uploads a selfie to the application and selects the conversion option.

[0459] 2. The application displays a preview of the selfie image and sends the user's facial recognition data to the emotion engine.

[0460] 3. The emotion engine estimates the user's emotion (e.g., joy, surprise, etc.) and suggests "anime character" as the optimal conversion option.

[0461] 4. If the user accepts the suggestion, the device sends the selected selfie and the "Anime Character" conversion option to the server.

[0462] 5. The server receives the selfie and selects an anime character generation model.

[0463] 6. The server uses the model to transform the selfie into an anime character image and sends the resulting image back to the device.

[0464] 7. The device displays the returned image and asks the user to confirm it.

[0465] 8. The user reviews the image and selects the option to share it via social media or messaging apps.

[0466] Prompt Sentence Examples

[0467] Users upload an image and send facial expression data to an emotion engine API (e.g., EmotionAPI), which then suggests recommended try-on options to the user.

[0468] This allows users to easily enjoy emotion-based personalized image processing and virtual try-on simulations without any special technical skills, and the results can be easily shared with others.

[0469] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0470] Step 1:

[0471] The user launches the application on their device and clicks the "Photo Upload" button to select their own image. The image is picked from the device's gallery and displayed as a preview. The input is the user's image and the output is the preview image.

[0472] Step 2:

[0473] The device acquires the user's facial expression and voice data and sends them to the emotion engine. The facial expression data is captured using a camera, and the voice data is recorded using a microphone. The input is the facial expression data and voice data, and the output is the emotion estimation result.

[0474] Step 3:

[0475] The emotion engine analyzes the received facial expression and voice data to estimate the user's emotion. Based on the estimated emotion, it proposes optimal conversion options. The input is facial expression and voice data, and the output is the estimated emotion and recommended conversion options.

[0476] Step 4:

[0477] The device presents the recommendation from the emotion engine to the user. If the user accepts the recommendation or selects another conversion option, their selection information is temporarily saved. The input is the estimated emotion and the recommended conversion option, and the output is the user's selection information.

[0478] Step 5:

[0479] The terminal sends the selected conversion options and the image to the server. The input is the user's image and conversion options, and the output is the request data to the server.

[0480] Step 6:

[0481] The server receives and decodes the image and conversion options sent from the terminal. The input is the request data, and the output is the decoded image and conversion options.

[0482] Step 7:

[0483] The server selects the optimal deep learning model based on the suggestions from the emotion engine. The inputs are the transformation options and the suggestions from the emotion engine, and the output is the selected deep learning model.

[0484] Step 8:

[0485] The server processes the image using the selected deep learning model to generate a new image. The inputs are the decoded image and the deep learning model, and the output is the generated new image.

[0486] Step 9:

[0487] The server encodes the new image and sends it back to the user terminal. The input is the new image and the output is the encoded image data.

[0488] Step 10:

[0489] The terminal decodes the received image and displays it to the user. The input is the encoded image data and the output is the decoded image.

[0490] Step 11:

[0491] The user can view the new image and select the option to share it on social media or messaging applications. The input is the decoded image and the output is the shared content.

[0492] 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.

[0493] 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.

[0494] 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.

[0495] [Second embodiment]

[0496] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0497] 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.

[0498] 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).

[0499] 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.

[0500] 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.

[0501] 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).

[0502] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0503] 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.

[0504] 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.

[0505] 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.

[0506] 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.

[0507] 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."

[0508] This invention is a system that allows users to upload their own images, convert the images into specific people, animals, characters, etc., and share the generated images. An embodiment of this system will be described in detail below.

[0509] System Configuration

[0510] The system of the present invention mainly comprises the following components:

[0511] 1. User device: A device on which a user inputs and selects an image, specifies conversion options, sends it to the server, and receives, displays, and shares the processed image. This includes smartphones, tablets, and PCs.

[0512] 2. Server: Receives the image and conversion options sent from the user device, processes the image using a deep learning model, generates a new image, and sends it back to the user device.

[0513] 3. Network: The Internet or other communications network that allows data communication between user terminals and the server.

[0514] Program processing

[0515] User terminal processing

[0516] When a user wants to edit their own image, they launch the application on their device. The user clicks the "Upload Photo" button in the application and selects a photo from their gallery. After the user selects an image, the device displays a preview of the image and asks the user for confirmation. For the confirmed image, the application presents the user with transformation options (e.g., "Anime Character," "Celebrity," "Dog," "Cat," etc.). After the user selects the desired transformation option, the device temporarily saves the selected image and transformation option and sends this data to the server.

[0517] Server Processing

[0518] The server receives the image and conversion options sent from the user device. It decodes the received data and separates the image from the conversion options. The server then selects a deep learning model based on the specified conversion options. The selected model inputs the image data and converts the image into a specific style. It then generates new processed image data, encodes it, and sends it back to the user device.

[0519] Specific examples

[0520] For example, if a user wants to convert their selfie into an anime character style, the process would be as follows:

[0521] 1. The user uploads a selfie to the application and selects the option to convert it into an anime character.

[0522] 2. The device sends the selfie and conversion options to the server.

[0523] 3. The server receives the selfie and selects an anime character generation model.

[0524] 4. The server uses the model to transform the selfie into an anime character.

[0525] 5. The server returns the newly generated anime character-style image to the device.

[0526] 6. The device displays the returned image and asks the user to confirm it.

[0527] 7. The user reviews the image and shares it via social media or messaging apps.

[0528] In this way, the system of the present invention allows users to easily enjoy high-quality image processing even if they do not have special technical skills, and the results can be easily shared with others.

[0529] The processing flow will be explained below.

[0530] Step 1:

[0531] The user launches a photo editing app on their device.

[0532] Step 2:

[0533] The user clicks the "Upload Photo" button within the app and selects the photo they want to edit from their gallery.

[0534] Step 3:

[0535] The device displays a preview of the selected photo for the user to confirm, and also presents conversion options (e.g., "celebrity," "anime character," "dog," "cat," etc.) to the user.

[0536] Step 4:

[0537] The user selects the desired conversion options.

[0538] Step 5:

[0539] Your device will temporarily save the photo and conversion options you selected.

[0540] Step 6:

[0541] The device encodes the photo data and conversion options into JSON format and prepares an HTTP request to send to the server.

[0542] Step 7:

[0543] The device sends an HTTP request containing the encoded data to the server.

[0544] Step 8:

[0545] The server receives the HTTP request sent from the terminal and decodes the JSON data.

[0546] Step 9:

[0547] The server separates the decoded photo data and the transformation options, and selects the required deep learning model based on the transformation options.

[0548] Step 10:

[0549] The server inputs the photo data into a deep learning model and converts the image into the specified style.

[0550] Step 11:

[0551] The server generates new converted image data and encodes it in JPEG format or the like.

[0552] Step 12:

[0553] The server prepares and sends an HTTP response to return the new encoded image data to the user's terminal.

[0554] Step 13:

[0555] The terminal receives the HTTP response sent back from the server and decodes the encoded image data.

[0556] Step 14:

[0557] The device will then display the new decoded image in the app for the user to review.

[0558] Step 15:

[0559] The user reviews the new image and chooses to share it via social media or messaging applications.

[0560] Step 16:

[0561] The device will provide sharing options based on the user's selection, launching the specified social networking site or messaging application to share the new image.

[0562] Example 1

[0563] 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."

[0564] With conventional image conversion systems, it is difficult to achieve high-quality image conversion unless the user has special technical skills, and there are limited ways to easily share the results with others. It is also difficult to select the appropriate deep learning model for a specific conversion option and perform the optimal conversion. This limits the user experience and makes the system less convenient and versatile.

[0565] 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.

[0566] In this invention, the server includes means for applying a specific model from among a plurality of deep learning models to the received image based on a selected conversion option, means for generating a new image after the conversion process, and means for returning the generated new image to the user terminal, thereby enabling users to easily achieve high-quality image conversion without requiring special technical skills and quickly share the results with others.

[0567] A "User" is an individual or entity who provides input and selections to transform and share their images using the system.

[0568] "Terminal" refers to a device that allows a user to input or select an image, specify conversion options, and send the image to the server, and includes smartphones, tablets, and PCs.

[0569] "Server" means a centralized computer system that receives images and transformation options sent from a user device, transforms the images using a deep learning model, and generates a new image that is sent back to the user device.

[0570] "Images" are visual data such as photographs and illustrations uploaded by users.

[0571] "Conversion options" are settings that represent a particular style or theme (e.g., "Anime Characters," "Celebrities," "Animals," etc.) that is applied to an image.

[0572] A "deep learning model" is a machine learning model that has been trained to transform images into a specific style using deep learning algorithms.

[0573] A "new generated image" is another visual data generated by transforming the original image using a deep learning model.

[0574] "Sharing" refers to the act of a user sending and publishing a newly generated image to others via social networking sites, messaging applications, etc.

[0575] The present invention provides a system that allows users to upload their own images, convert the images into a specific style, and share the generated images with others. An embodiment of this system will be described in detail below.

[0576] System Configuration

[0577] The system of the present invention mainly comprises the following components:

[0578] 1. User device: A device on which a user inputs and selects an image, specifies conversion options, sends it to the server, and receives, displays, and shares the processed image. This includes smartphones, tablets, PCs, etc.

[0579] 2. Server: Receives the image and conversion options sent from the user device, converts the image using a deep learning model, generates a new image, and sends it back to the user device.

[0580] 3. Network: The Internet or other communication network that allows data communication between user terminals and the server.

[0581] Program processing

[0582] When a user wants to edit their own image, they first launch the application on their device. The user clicks the "Upload Photo" button and selects a photo from their gallery. After the user selects an image, the device displays a preview of the image and asks the user for confirmation. For the confirmed image, the application presents the user with transformation options (e.g., "Anime Character," "Celebrity," "Dog," "Cat," etc.). After the user selects the desired transformation option, the device temporarily saves the selected image and transformation option and sends this data to the server.

[0583] Specific processing flow

[0584] 1. User uploads an image

[0585] The user launches the application on their device, clicks the "Upload Photos" button, and the gallery is displayed. They can then select the image they want to upload. The selected image is then displayed on the preview screen.

[0586] 2. The user selects conversion options

[0587] After viewing the image in the preview screen, the user selects a conversion option (e.g., "Anime Character," "Celebrity," "Dog," "Cat," etc.) from a menu within the application. A dialog displays the selection and asks the user for confirmation.

[0588] 3. The device sends the data to the server

[0589] Once the user has selected the conversion options, the device temporarily stores the selected image and conversion options, and then sends the image data and conversion options to the server using an HTTP request.

[0590] 4. The server receives and analyzes the data

[0591] The server parses the received HTTP request and separates the image data and conversion options. The image data is saved in temporary storage, and the conversion options are stored in variables.

[0592] 5. The server converts the image

[0593] The server selects an appropriate deep learning model based on the conversion options. The selected model may use TensorFlow or PyTorch. The server inputs the image data into the deep learning model and converts it into the specified style. New converted image data is generated.

[0594] 6. The server sends the converted image back to the device.

[0595] The server encodes the converted image data and returns it to the user device. The HTTP response is used again for the return. The server records the processing results in a log and performs error handling as necessary.

[0596] 7. User reviews and shares the image

[0597] The user's device decodes the converted image data received from the server and displays it on the screen. The user can then view the image and easily share it via social media or messaging apps by clicking the share button within the application.

[0598] Specific examples

[0599] For example, if a user wants to transform their selfie into a cartoon character, the process would look like this:

[0600] 1. The user uploads a selfie to the application and selects the option to convert it as an "anime character."

[0601] 2. The device sends the selfie and conversion options to the server.

[0602] 3. The server receives the selfie and selects an anime character generation model.

[0603] 4. The server uses the model to transform the selfie into an anime character.

[0604] 5. The server returns the newly generated anime character-style image to the device.

[0605] 6. The device displays the returned image and asks the user to confirm it.

[0606] 7. The user reviews the image and shares it via social media or messaging apps.

[0607] Prompt Sentence Examples

[0608] To adjust the quality and style of the resulting image, you can provide prompts to the generative AI model, such as:

[0609] "Transform your selfie into an anime character-style image."

[0610] This prompt will guide the AI ​​model through the process of transforming the selfie into an "anime character" image. Additional prompts can be used to specify more specific styles and characteristics, if desired.

[0611] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0612] Processing flow

[0613] Step 1:

[0614] The user uploads an image

[0615] Specific operation: The user launches the application on their device and clicks the "Upload Photo" button. The gallery will be displayed, and they can select the image they want to upload. The selected image will be displayed on the preview screen.

[0616] Input: An image file selected by the user.

[0617] Output: Preview image displayed on the device

[0618] Step 2:

[0619] The user selects conversion options

[0620] What it does: After viewing an image in the preview screen, the user selects a conversion option from a menu within the application (e.g., "Anime Character," "Celebrity," "Dog," "Cat," etc.) A dialog appears displaying the selection and asking the user for confirmation.

[0621] Input: User selected conversion options

[0622] Output: A confirmation dialog displayed on the terminal

[0623] Step 3:

[0624] The device sends the data to the server

[0625] Specific operation: After the user has selected the conversion options, the device temporarily saves the selected image and conversion options, and then sends the image data and conversion options to the server using an HTTP request.

[0626] Input: Selected image data and conversion options

[0627] Output: HTTP request sent to the server

[0628] Step 4:

[0629] The server receives and analyzes the data

[0630] Specific operation: The server parses the received HTTP request and separates the image data and conversion options. The image data is saved in temporary storage, and the conversion options are stored in variables.

[0631] Input: Image data and conversion options sent as an HTTP request

[0632] Output: Parsed image data and conversion options

[0633] Step 5:

[0634] The server converts the image

[0635] Specific operation: The server selects an appropriate deep learning model based on the conversion options. The selected model may use TensorFlow or PyTorch. The server inputs the image data into the deep learning model and converts it into the specified style. New converted image data is generated.

[0636] Input: Parsed image data and transformation options

[0637] Output: New image data after conversion processing

[0638] Step 6:

[0639] The server sends the converted image back to the device.

[0640] Specific operation: The server encodes the converted image data and returns it to the user device. The HTTP response is used again for the return. The server records the processing result in a log and performs error handling as necessary.

[0641] Input: New image data after conversion processing

[0642] Output: The HTTP response sent back to the device

[0643] Step 7:

[0644] Users review and share images

[0645] Specific operation: The user device decodes the converted image data received from the server and displays it on the screen. The user can then view the image and easily share it via social media or messaging apps by clicking the share button in the application.

[0646] Input: The converted image data sent back to the device

[0647] Output: The converted image displayed on the device and the shared image

[0648] (Application example 1)

[0649] 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."

[0650] Conventional image conversion technologies simply convert images statically, limiting their use as content. Furthermore, there are limited ways to generate and share more diverse content using the converted images. Therefore, there is a need for technology that improves the user experience and enhances the scalability of generated content.

[0651] 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.

[0652] In this invention, the server includes a means for processing user-entered images using a generative artificial intelligence model to generate new images, a means for generating custom videos or moving images using the generated new images, and a means for sharing the generated content via multiple information distribution services or messaging applications, thereby enabling users to not only enjoy high-quality image conversion but also easily generate and share a variety of content based on the generated images.

[0653] "User" refers to the person using the system who inputs their image, selects conversion options, and reviews and shares the generated content.

[0654] "Conversion options" refer to specific styles and settings that users can select when converting images using a deep learning model.

[0655] "Server" refers to a device or system that receives images and conversion options sent from a user terminal, processes the images using a generative artificial intelligence model, generates new images or video, and returns them to the user terminal.

[0656] A "generative artificial intelligence model" is a deep learning-based model used for image transformation, which refers to a technique for transforming an input image according to a specific style.

[0657] "Custom video" or "motion picture" refers to a moving image or animation created from newly generated images.

[0658] An "information distribution service" is an online platform for sharing user-generated content with others, including social networking services and messaging applications.

[0659] "Sharing" refers to the act of sending generated content to other users or platforms where it can be accessed or viewed.

[0660] The present invention provides a system that allows users to upload their own images, convert those images into specific people, animals, characters, etc., and share the generated images and videos. Specific embodiments of this system are described below.

[0661] System Overview

[0662] The system mainly consists of the following components:

[0663] 1. User terminal: A device that allows users to input and select images, specify conversion options, send them to the server, and receive, display, and share processed images, custom videos, and moving images. This includes smartphones, tablets, and PCs.

[0664] 2. Server: Receives images and conversion options sent from the user terminal, processes the images using a generative artificial intelligence model, generates new images and videos, and sends them back to the user terminal.

[0665] 3. Network: The Internet or other communication network that allows data communication between user terminals and the server.

[0666] Program processing

[0667] User terminal processing

[0668] When a user wants to edit their own image, they launch the application on their device. Within the application, the user clicks the "Upload Photo" button and selects a photo from their gallery. Once the user selects an image, the device displays a preview of the image and asks the user for confirmation. For the confirmed image, the application presents the user with transformation options (e.g., "Anime Character," "Celebrity," "Dog," "Cat," etc.). Once the user selects the desired transformation option, the device temporarily saves the selected image and transformation option and sends this data to the server.

[0669] Server Processing

[0670] The server receives the images and conversion options sent from the user device. It decodes the received data and separates the images from the conversion options. Next, the server selects a generative artificial intelligence (AI) model based on the specified conversion options. The image data is input into the selected model and converted into a specific style. PyTorch is used as the deep learning library. The generated images are then used to generate custom videos and moving images. At this stage, PIL (Python Imaging Library) and the generative artificial intelligence model are used. New processed image data and moving images are generated, encoded, and sent back to the user device.

[0671] An example

[0672] For example, if a user wants to transform their selfie into a cartoon character and create a short video from it to share with friends, here's what happens:

[0673] 1. The user uploads a selfie to the application and selects the option to convert it into an "anime character."

[0674] 2. The device sends the selfie and conversion options to the server.

[0675] 3. The server receives the selfie and selects an anime character generation model.

[0676] 4. The server uses a generative artificial intelligence model to transform the selfie into an anime character.

[0677] 5. The server creates a short video or animation using the newly generated anime character-style image.

[0678] 6. The server returns the generated content to the device.

[0679] 7. The device displays the returned images and videos for the user to review.

[0680] 8. The user reviews the images and videos and shares them via social media or messaging apps.

[0681] Prompt Sentence Examples

[0682] For example, by entering a prompt such as "Please convert this selfie into an anime character style," the user can easily obtain the desired conversion result.

[0683] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0684] Step 1:

[0685] The user launches the application and clicks the "Upload Photo" button.

[0686] Specifically, the user selects a photo from their gallery. The input is the image file selected by the user, and the device displays a preview of the image. The output is the image displayed on the preview screen.

[0687] Step 2:

[0688] The terminal asks the user for confirmation, and then presents the user with conversion options (e.g., "anime character," "celebrity," "dog," "cat," etc.) for the confirmed image.

[0689] The input is the conversion options selected by the user, which the terminal temporarily stores, and the output is the data for the selected conversion options.

[0690] Step 3:

[0691] The terminal sends the selected image and conversion options to the server.

[0692] The input is the image and conversion options selected by the user, and the terminal sends this data to the server via the network. The output is the image data and conversion options sent to the server.

[0693] Step 4:

[0694] The server receives the image and conversion options sent from the user terminal.

[0695] The input is image data and conversion options sent from the terminal, which the server decodes and separates into the image and conversion options, and the output is the separated image data and conversion options.

[0696] Step 5:

[0697] The server selects a generative artificial intelligence model based on the specified transformation options.

[0698] The input is a set of isolated transformation options, and the server selects an appropriate model from among multiple generative artificial intelligence models. The output is the selected generative artificial intelligence model.

[0699] Step 6:

[0700] The server inputs the image data into the selected model and transforms the image into a particular style.

[0701] The input is image data and a selected generative artificial intelligence model, the server uses the model to transform the image, and the output is the new transformed image data.

[0702] Step 7:

[0703] The server uses the new images to generate custom video or animation.

[0704] The input is the new transformed image data that the server uses to generate the video or animation, and the output is the custom video or animation that is generated.

[0705] Step 8:

[0706] The server encodes the generated custom video or animation and sends it back to the user's device.

[0707] The input is the generated custom video or animation that the server encodes and sends back to the user's device over the network, and the output is the custom video or animation sent to the user's device.

[0708] Step 9:

[0709] The user terminal displays the returned custom video or moving image for the user to review.

[0710] The input is a custom video or animation returned from the server, which the terminal displays and asks the user for confirmation. The output is the displayed custom video or animation.

[0711] Step 10:

[0712] Users can view images and videos and share them via social media or messaging applications.

[0713] The input is a verified custom video or moving image, and the user selects the platform to share it on. The output is content shared to social media or messaging applications.

[0714] 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.

[0715] This invention relates to a system that allows users to upload their own images, convert them into specific people, animals, characters, etc., and share the generated images. In addition, the invention aims to provide more appropriate and personalized conversion options by combining an emotion engine that recognizes the user's emotions.

[0716] System Configuration

[0717] The system of the present invention mainly comprises the following components:

[0718] 1. User device: A device on which a user inputs and selects an image, specifies conversion options, sends the image to the server, and receives, displays, and shares the processed image. This includes smartphones, tablets, and PCs. It also has the function of sending the user's facial expression and voice data to the emotion engine.

[0719] 2. Server: Receives the image and conversion options sent from the user device, processes the image using a deep learning model, generates a new image, and sends it back to the user device. Furthermore, it utilizes data from the emotion engine to suggest and apply appropriate conversion options.

[0720] 3. Emotion Engine: A component that includes algorithms for estimating emotions based on the user's facial recognition data and voice data, and proposing and selecting the optimal conversion options.

[0721] 4. Network: The Internet or other communications network that allows data communication between user terminals and the server.

[0722] Program processing

[0723] User terminal processing

[0724] When a user wants to edit their own image, they launch the application on their device. Within the application, the user clicks the "Upload Photo" button and selects a photo from their gallery. Once the user selects an image, the device displays a preview of the image and asks the user for confirmation. For the confirmed image, the application presents the user with transformation options (e.g., "Anime Character," "Celebrity," "Dog," "Cat," etc.).

[0725] Furthermore, the device sends the user's facial recognition data and voice data to the emotion engine to estimate their emotions. The emotion engine then suggests optimal conversion options based on the estimated emotions. When the user accepts the optimal suggestion or selects another option, the device temporarily stores the selected image and conversion options and transmits this data to the server.

[0726] Server Processing

[0727] The server receives the image and conversion options sent from the user device. It decodes the received data and separates the image from the conversion options. The server then selects the required deep learning model based on the specified conversion options, inputs the image data into the model, and generates a new image. The generated image data is then encoded and sent back to the user device.

[0728] Specific examples

[0729] For example, if a user wants to convert their selfie into an anime character style, the process would be as follows:

[0730] 1. The user uploads a selfie to the application and selects the desired conversion options.

[0731] 2. The device displays a preview of the selfie image and also sends the user's facial recognition data to the emotion engine.

[0732] 3. The emotion engine estimates the user's emotion (e.g., joy, surprise, etc.) and suggests "anime character" as the optimal conversion option.

[0733] 4. If the user accepts the suggestion, the device sends the selected selfie and the "Anime Character" conversion option to the server.

[0734] 5. The server receives the selfie and selects an anime character generation model.

[0735] 6. The server uses the model to transform the selfie into an anime character image and sends the resulting image back to the device.

[0736] 7. The device displays the returned image and asks the user to confirm it.

[0737] 8. The user reviews the image and selects the option to share it via social media or messaging apps.

[0738] This system allows users to easily enjoy personalized image processing based on emotions, even without any special technical skills, and easily share the results with others.

[0739] The processing flow will be explained below.

[0740] Step 1:

[0741] The user launches a photo editing app on their device.

[0742] Step 2:

[0743] The user clicks the "Upload Photo" button within the app and selects the photo they want to edit from their gallery.

[0744] Step 3:

[0745] The device displays a preview of the selected photo for the user to confirm, and also presents conversion options (e.g., "celebrity," "anime character," "dog," "cat," etc.) to the user.

[0746] Step 4:

[0747] The terminal collects the user's facial recognition data and voice data and sends them to the emotion engine.

[0748] Step 5:

[0749] The emotion engine analyzes the received facial recognition data and voice data to estimate the user's emotion.

[0750] Step 6:

[0751] The emotion engine suggests optimal conversion options based on the estimated emotion.

[0752] Step 7:

[0753] The user accepts the proposed conversion options or selects other conversion options.

[0754] Step 8:

[0755] The device temporarily saves the selected photo and the confirmed conversion options.

[0756] Step 9:

[0757] The device encodes the photo data and conversion options into JSON format and prepares an HTTP request to send to the server.

[0758] Step 10:

[0759] The device sends an HTTP request containing the encoded data to the server.

[0760] Step 11:

[0761] The server receives the HTTP request sent from the terminal and decodes the JSON data.

[0762] Step 12:

[0763] The server separates the decoded photo data and the transformation options, and selects the required deep learning model based on the transformation options.

[0764] Step 13:

[0765] The server inputs the photo data into a deep learning model and converts the image into the specified style.

[0766] Step 14:

[0767] The server generates new converted image data and encodes it in JPEG format or the like.

[0768] Step 15:

[0769] The server prepares and sends an HTTP response to return the new encoded image data to the user's terminal.

[0770] Step 16:

[0771] The terminal receives the HTTP response sent back from the server and decodes the encoded image data.

[0772] Step 17:

[0773] The device will then display the new decoded image in the app for the user to review.

[0774] Step 18:

[0775] The user reviews the new image and chooses to share it via social media or messaging applications.

[0776] Step 19:

[0777] The device will provide sharing options based on the user's selection, launching the specified social networking site or messaging application to share the new image.

[0778] Example 2

[0779] 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."

[0780] In recent years, advances in image editing technology have made it possible for individuals to easily process and edit images. However, existing systems have difficulty in providing personalized editing that takes user emotions into account, and this poses a high hurdle for general users without special technical skills. To solve this problem, there is a need for a simple and intuitive image conversion system that can recognize user emotions and suggest optimal conversion options.

[0781] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0782] In this invention, the server includes a means for processing an image using a deep learning model to generate a new image, a means for returning the generated new image to the user's terminal, and a means including an emotion engine for recognizing the user's emotion and suggesting conversion options based on the emotion, thereby enabling the user to easily perform personalized image conversion based on their own emotion.

[0783] A "user" is an individual or entity that inputs an image, selects conversion options, and reviews and shares the resulting image.

[0784] "User terminal" refers to a device on which a user inputs and selects an image, specifies conversion options, sends the image to the server, and receives, displays, and shares the processed image. This includes smartphones, tablets, PCs, etc.

[0785] A "server" is a device or system that receives an image and conversion options sent from a user terminal, processes the image using a deep learning model, generates a new image, and returns it to the user terminal.

[0786] "Image" refers to data containing visual information such as a photograph or picture entered by the user.

[0787] "Conversion options" are options for how the user can process or edit an image. Examples include "anime characters," "celebrities," "dogs," and "cats."

[0788] A "deep learning model" is a model that uses advanced machine learning algorithms to process input data, learn and recognize specific patterns, and generate images.

[0789] The "emotion engine" is a component that includes algorithms for estimating emotions based on the user's facial recognition data and voice data, and proposing and selecting optimal conversion options.

[0790] A "preview" is a temporary display that allows the user to check the image selected and the editing operations performed.

[0791] "Encoding" is the process of converting data into a particular format.

[0792] "Decoding" is the process of restoring encoded data to its original form.

[0793] This invention relates to a system that allows users to convert their own images into specific people, animals, characters, etc., and share the generated images. Furthermore, the invention aims to combine an emotion engine that recognizes the user's emotions to provide more appropriate and personalized conversion options. Specific embodiments for implementing this system are described below.

[0794] System Configuration

[0795] The system of the present invention mainly comprises the following components:

[0796] 1. User device: A device on which users input and select images, specify conversion options, send them to the server, and receive, display, and share the processed images. This includes smartphones, tablets, PCs, etc., and also has the function of sending the user's facial expression data and voice data to the emotion engine.

[0797] 2. Server: Receives the image and conversion options sent from the user device, processes the image using a deep learning model, generates a new image, and sends it back to the user device. It also uses data from the emotion engine to suggest and apply appropriate conversion options.

[0798] 3. Emotion Engine: This component includes algorithms for estimating emotions based on the user's facial recognition data and voice data, and for suggesting and selecting optimal conversion options.

[0799] 4. Network: The Internet or other communications network that allows data communication between user terminals and the server.

[0800] System Operation

[0801] When a user wants to edit their own image, they launch the application on their device. The user clicks the "Upload Photo" button in the application and selects a photo from their gallery. After the user selects an image, the device displays a preview of the image and asks the user for confirmation. For the confirmed image, the application presents the user with transformation options (e.g., "Anime Character," "Celebrity," "Dog," "Cat," etc.). In addition, the device sends the user's facial recognition data and voice data to an emotion engine to estimate their emotion. The emotion engine suggests the optimal transformation option based on the estimated emotion. If the user accepts the optimal suggestion or selects another option, the device temporarily saves the selected image and transformation option and sends this data to the server.

[0802] The server receives the image and conversion options sent from the user device. It decodes the received data and separates the image from the conversion options. The server then selects the required deep learning model based on the specified conversion options, inputs the image data into the model, and generates a new image. The generated image data is then encoded and sent back to the user device.

[0803] Specific examples

[0804] For example, if a user wants to convert their selfie into an anime character style, the process would be as follows:

[0805] 1. The user uploads a selfie to the application and selects the desired conversion options.

[0806] 2. The device displays a preview of the selfie image and also sends the user's facial recognition data to the emotion engine.

[0807] 3. The emotion engine estimates the user's emotion (e.g., joy, surprise, etc.) and suggests "anime character" as the optimal conversion option.

[0808] 4. If the user accepts the suggestion, the device sends the selected selfie and the "Anime Character" conversion option to the server.

[0809] 5. The server receives the selfie and selects an anime character generation model.

[0810] 6. The server uses the model to transform the selfie into an anime character image and sends the resulting image back to the device.

[0811] 7. The device displays the returned image and asks the user to confirm it.

[0812] 8. The user reviews the image and selects the option to share it via social media or messaging apps.

[0813] Example of input prompt for generative AI model

[0814] "A user uploaded a selfie and selected the 'Anime Character' conversion option. Please convert this selfie to look like an anime character."

[0815] This system allows users to easily enjoy personalized image processing based on emotions, even without any special technical skills, and easily share the results with others.

[0816] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0817] Step 1:

[0818] The user launches an application on the device.

[0819] Input: The user taps on an app on their smartphone.

[0820] Output: The main screen of the application is displayed.

[0821] Specific behavior: The user taps the icon to launch the app, and the app displays the main screen.

[0822] Step 2:

[0823] A user uploads an image.

[0824] Input: User presses the "Upload Photo" button and selects a photo from the gallery.

[0825] Output: The selected image is displayed in the application.

[0826] Specific operation: The user presses a button, moves to an image selection screen, and selects an image such as a selfie from the gallery.

[0827] Step 3:

[0828] Your device will display a preview of the image and ask for confirmation.

[0829] Input: An image selected by the user.

[0830] Output: A preview of the image and a confirmation message asking "Are you sure this is the image?"

[0831] What happens: The device generates a preview of the image and displays a confirmation dialog.

[0832] Step 4:

[0833] The terminal presents conversion options to the user.

[0834] Input: User sees the image and answers "yes."

[0835] Output: You will see conversion options such as anime characters, celebrities, dogs, cats, etc.

[0836] Specific behavior: The device renders a UI to display the options.

[0837] Step 5:

[0838] The device sends facial recognition data and voice data to the emotion engine.

[0839] Input: User's facial recognition and voice data.

[0840] Output: Data sent to the emotion engine.

[0841] Specific operation: The device captures data using the camera and microphone and sends it to the emotion engine.

[0842] Step 6:

[0843] The device presents suggestions from the emotion engine to the user.

[0844] Input: Transformation option suggestions from the sentiment engine.

[0845] Output: The best conversion options based on the estimated sentiment are displayed to the user.

[0846] Specific operation: The device receives the response from the emotion engine and displays the suggestions.

[0847] Step 7:

[0848] The user selects a conversion option.

[0849] Input: User's choice of conversion options.

[0850] Output: The selected conversion options will be saved to your device.

[0851] What happens: The user taps an option and the device records the selection.

[0852] Step 8:

[0853] The device sends the selected image and conversion options to the server.

[0854] Input: Selected image and conversion options.

[0855] Output: The image and conversion options are sent to the server.

[0856] Specific operation: The terminal forms transmission data and transmits the data to the server through the network.

[0857] Step 9:

[0858] The server receives the image and conversion options.

[0859] Input: Image sent from the device and conversion options.

[0860] Output: Decoded result of received data.

[0861] What it does: The server decodes the received data and separates the image and conversion options.

[0862] Step 10:

[0863] The server selects the required deep learning model.

[0864] Input: Conversion options.

[0865] Output: The selected deep learning model.

[0866] What happens: The server looks up the appropriate model from the database or file system.

[0867] Step 11:

[0868] The server inputs the image into the model and generates a new image.

[0869] Input: Original image data, selected deep learning model.

[0870] Output: The new image generated.

[0871] Specific operation: The server inputs image data into the model, processes it, and generates a new image.

[0872] Step 12:

[0873] The server encodes the generated image and sends it back to the user's terminal.

[0874] Input: The new image generated.

[0875] Output: The encoded image data.

[0876] Specific operation: The server encodes the image in a timely manner and transmits it to the user terminal via the network.

[0877] Step 13:

[0878] The terminal displays the returned image and prompts the user to confirm it.

[0879] Input: The encoded image data returned from the server.

[0880] Output: The new image displayed.

[0881] What happens: The device decodes the image and displays it to the user for confirmation.

[0882] Step 14:

[0883] The user can view the image and share it via social media or messaging applications.

[0884] Input: User confirmation.

[0885] Output: Link or data for sharing.

[0886] What happens: The user clicks the "Share" button and selects the option to send the image to the social networking or messaging application of their choice.

[0887] (Application example 2)

[0888] 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."

[0889] Conventional image processing systems lack a means to provide personalized transformation options based on the user's emotions, making it difficult to create optimal content for the user. Furthermore, when users use images as virtual try-on simulations, they have difficulty selecting appropriate outfits and accessories, resulting in an unsatisfactory try-on experience.

[0890] The specification processing by the specification 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 acquiring the user's facial expression data and voice data and sending them to the emotion engine, means for proposing optimal conversion options based on the emotions estimated by the emotion engine, and means for applying a specific model from among multiple deep learning models based on the selected conversion options and suggestions from the emotion engine. This enables personalized image conversion and virtual try-on simulations that take the user's emotions into consideration.

[0891] A "user" is someone who uses the system to enhance their own images and review and share the transformed images.

[0892] "Images" are visual data such as photographs or illustrations that users upload to the system.

[0893] "Conversion options" refer to image processing styles and themes that users can select, including anime character style, animal style, celebrity style, etc.

[0894] "Facial expression data" is data used to capture the user's facial expressions and estimate their emotions based on that information.

[0895] "Voice data" is data that captures the user's vocalizations and is used to estimate emotions based on that voice information.

[0896] An "emotion engine" is an algorithm or program that analyzes facial expression data and voice data, estimates the user's emotions, and suggests optimal conversion options.

[0897] A "deep learning model" is a neural network that is trained with large amounts of data to transform input images into a specific style.

[0898] The "server" is the central processing unit of the system, a computer that processes images and conversion options sent by users, generates new images, and returns them.

[0899] "Terminal" refers to a device that a user uses to upload images, receive converted images, and view and share them, including smartphones, tablets, and PCs.

[0900] A "preview" is a temporary image that is displayed to allow a user to check the image they have uploaded.

[0901] A "social networking service" is an online platform used by users to share generated images, also known as an SNS.

[0902] A "messaging application" is a communication tool that users use to share generated images.

[0903] A "personalized image" is an image that is customized based on the user's feelings and preferences.

[0904] "Virtual try-on simulation" is a process in which a user virtually tries on outfits and accessories in images uploaded by the user.

[0905] The following describes an embodiment of the present invention. The system allows users to upload their own images, convert them into specific characters, people, animals, etc., and then review and share the generated images. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides more appropriate and personalized conversion options.

[0906] Hardware and Software

[0907] The main components of the system are:

[0908] User device: A smartphone, tablet, PC, etc. This is the device where users input and select images, and receive, display, and share the processed images. React Native and JavaScript are used to upload images and display previews.

[0909] Server: Receives images, processes them using deep learning models, generates new images, and sends them back to the user device. Can use cloud services such as AWS EC2.

[0910] Emotion engine: An algorithm that estimates emotions based on the user's facial expression and voice data and suggests optimal conversion options. Microsoft Azure's Emotion API can be used.

[0911] Deep learning models: Use frameworks such as TensorFlow to perform image transformation.

[0912] Processing flow

[0913] User device operation

[0914] 1. The user launches the application and clicks the "Upload Photo" button to select their own image.

[0915] 2. A preview of the image is displayed and the user confirms it.

[0916] 3. The user device acquires facial expression data and voice data and sends them to the emotion engine.

[0917] 4. The emotion engine estimates the emotion and presents the user with recommended transformation options (e.g., anime character style).

[0918] 5. If the user accepts the offer or selects another option, the data is sent to the server.

[0919] Server Processing

[0920] 1. The server receives the image and conversion options sent by the user.

[0921] 2. Select a deep learning model, input an image, and generate a new image.

[0922] 3. The generated image is sent back to the user's device.

[0923] Displaying the user terminal

[0924] 1. The generated image is displayed and the user confirms it.

[0925] 2. Users have the option to share the image on social media or messaging applications.

[0926] Specific examples

[0927] For example, if a user wants to convert their selfie into an anime character style, the process would be as follows:

[0928] 1. The user uploads a selfie to the application and selects the conversion option.

[0929] 2. The application displays a preview of the selfie image and sends the user's facial recognition data to the emotion engine.

[0930] 3. The emotion engine estimates the user's emotion (e.g., joy, surprise, etc.) and suggests "anime character" as the optimal conversion option.

[0931] 4. If the user accepts the suggestion, the device sends the selected selfie and the "Anime Character" conversion option to the server.

[0932] 5. The server receives the selfie and selects an anime character generation model.

[0933] 6. The server uses the model to transform the selfie into an anime character image and sends the resulting image back to the device.

[0934] 7. The device displays the returned image and asks the user to confirm it.

[0935] 8. The user reviews the image and selects the option to share it via social media or messaging apps.

[0936] Prompt Sentence Examples

[0937] Users upload an image and send facial expression data to an emotion engine API (e.g., EmotionAPI), which then suggests recommended try-on options to the user.

[0938] This allows users to easily enjoy emotion-based personalized image processing and virtual try-on simulations without any special technical skills, and the results can be easily shared with others.

[0939] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0940] Step 1:

[0941] The user launches the application on their device and clicks the "Photo Upload" button to select their own image. The image is picked from the device's gallery and displayed as a preview. The input is the user's image and the output is the preview image.

[0942] Step 2:

[0943] The device acquires the user's facial expression and voice data and sends them to the emotion engine. The facial expression data is captured using a camera, and the voice data is recorded using a microphone. The input is the facial expression data and voice data, and the output is the emotion estimation result.

[0944] Step 3:

[0945] The emotion engine analyzes the received facial expression and voice data to estimate the user's emotion. Based on the estimated emotion, it proposes optimal conversion options. The input is facial expression and voice data, and the output is the estimated emotion and recommended conversion options.

[0946] Step 4:

[0947] The device presents the recommendation from the emotion engine to the user. If the user accepts the recommendation or selects another conversion option, their selection information is temporarily saved. The input is the estimated emotion and the recommended conversion option, and the output is the user's selection information.

[0948] Step 5:

[0949] The terminal sends the selected conversion options and the image to the server. The input is the user's image and conversion options, and the output is the request data to the server.

[0950] Step 6:

[0951] The server receives and decodes the image and conversion options sent from the terminal. The input is the request data, and the output is the decoded image and conversion options.

[0952] Step 7:

[0953] The server selects the optimal deep learning model based on the suggestions from the emotion engine. The inputs are the transformation options and the suggestions from the emotion engine, and the output is the selected deep learning model.

[0954] Step 8:

[0955] The server processes the image using the selected deep learning model to generate a new image. The inputs are the decoded image and the deep learning model, and the output is the generated new image.

[0956] Step 9:

[0957] The server encodes the new image and sends it back to the user terminal. The input is the new image and the output is the encoded image data.

[0958] Step 10:

[0959] The terminal decodes the received image and displays it to the user. The input is the encoded image data and the output is the decoded image.

[0960] Step 11:

[0961] The user can view the new image and select the option to share it on social media or messaging applications. The input is the decoded image and the output is the shared content.

[0962] 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.

[0963] 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.

[0964] 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.

[0965] [Third embodiment]

[0966] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0967] 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.

[0968] 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).

[0969] 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.

[0970] 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.

[0971] 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).

[0972] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0973] 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.

[0974] 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.

[0975] 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.

[0976] 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.

[0977] 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."

[0978] This invention is a system that allows users to upload their own images, convert the images into specific people, animals, characters, etc., and share the generated images. An embodiment of this system will be described in detail below.

[0979] System Configuration

[0980] The system of the present invention mainly comprises the following components:

[0981] 1. User device: A device on which a user inputs and selects an image, specifies conversion options, sends it to the server, and receives, displays, and shares the processed image. This includes smartphones, tablets, and PCs.

[0982] 2. Server: Receives the image and conversion options sent from the user device, processes the image using a deep learning model, generates a new image, and sends it back to the user device.

[0983] 3. Network: The Internet or other communications network that allows data communication between user terminals and the server.

[0984] Program processing

[0985] User terminal processing

[0986] When a user wants to edit their own image, they launch the application on their device. The user clicks the "Upload Photo" button in the application and selects a photo from their gallery. After the user selects an image, the device displays a preview of the image and asks the user for confirmation. For the confirmed image, the application presents the user with transformation options (e.g., "Anime Character," "Celebrity," "Dog," "Cat," etc.). After the user selects the desired transformation option, the device temporarily saves the selected image and transformation option and sends this data to the server.

[0987] Server Processing

[0988] The server receives the image and conversion options sent from the user device. It decodes the received data and separates the image from the conversion options. The server then selects a deep learning model based on the specified conversion options. The selected model inputs the image data and converts the image into a specific style. It then generates new processed image data, encodes it, and sends it back to the user device.

[0989] Specific examples

[0990] For example, if a user wants to convert their selfie into an anime character style, the process would be as follows:

[0991] 1. The user uploads a selfie to the application and selects the option to convert it into an anime character.

[0992] 2. The device sends the selfie and conversion options to the server.

[0993] 3. The server receives the selfie and selects an anime character generation model.

[0994] 4. The server uses the model to transform the selfie into an anime character.

[0995] 5. The server returns the newly generated anime character-style image to the device.

[0996] 6. The device displays the returned image and asks the user to confirm it.

[0997] 7. The user reviews the image and shares it via social media or messaging apps.

[0998] In this way, the system of the present invention allows users to easily enjoy high-quality image processing even if they do not have special technical skills, and the results can be easily shared with others.

[0999] The processing flow will be explained below.

[1000] Step 1:

[1001] The user launches a photo editing app on their device.

[1002] Step 2:

[1003] The user clicks the "Upload Photo" button within the app and selects the photo they want to edit from their gallery.

[1004] Step 3:

[1005] The device displays a preview of the selected photo for the user to confirm, and also presents conversion options (e.g., "celebrity," "anime character," "dog," "cat," etc.) to the user.

[1006] Step 4:

[1007] The user selects the desired conversion options.

[1008] Step 5:

[1009] Your device will temporarily save the photo and conversion options you selected.

[1010] Step 6:

[1011] The device encodes the photo data and conversion options into JSON format and prepares an HTTP request to send to the server.

[1012] Step 7:

[1013] The device sends an HTTP request containing the encoded data to the server.

[1014] Step 8:

[1015] The server receives the HTTP request sent from the terminal and decodes the JSON data.

[1016] Step 9:

[1017] The server separates the decoded photo data and the transformation options, and selects the required deep learning model based on the transformation options.

[1018] Step 10:

[1019] The server inputs the photo data into a deep learning model and converts the image into the specified style.

[1020] Step 11:

[1021] The server generates new converted image data and encodes it in JPEG format or the like.

[1022] Step 12:

[1023] The server prepares and sends an HTTP response to return the new encoded image data to the user's terminal.

[1024] Step 13:

[1025] The terminal receives the HTTP response sent back from the server and decodes the encoded image data.

[1026] Step 14:

[1027] The device will then display the new decoded image in the app for the user to review.

[1028] Step 15:

[1029] The user reviews the new image and chooses to share it via social media or messaging applications.

[1030] Step 16:

[1031] The device will provide sharing options based on the user's selection, launching the specified social networking site or messaging application to share the new image.

[1032] Example 1

[1033] 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."

[1034] With conventional image conversion systems, it is difficult to achieve high-quality image conversion unless the user has special technical skills, and there are limited ways to easily share the results with others. It is also difficult to select the appropriate deep learning model for a specific conversion option and perform the optimal conversion. This limits the user experience and makes the system less convenient and versatile.

[1035] 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.

[1036] In this invention, the server includes means for applying a specific model from among a plurality of deep learning models to the received image based on a selected conversion option, means for generating a new image after the conversion process, and means for returning the generated new image to the user terminal, thereby enabling users to easily achieve high-quality image conversion without requiring special technical skills and quickly share the results with others.

[1037] A "User" is an individual or entity who provides input and selections to transform and share their images using the system.

[1038] "Terminal" refers to a device that allows a user to input or select an image, specify conversion options, and send the image to the server, and includes smartphones, tablets, and PCs.

[1039] "Server" means a centralized computer system that receives images and transformation options sent from a user device, transforms the images using a deep learning model, and generates a new image that is sent back to the user device.

[1040] "Images" are visual data such as photographs and illustrations uploaded by users.

[1041] "Conversion options" are settings that represent a particular style or theme (e.g., "Anime Characters," "Celebrities," "Animals," etc.) that is applied to an image.

[1042] A "deep learning model" is a machine learning model that has been trained to transform images into a specific style using deep learning algorithms.

[1043] A "new generated image" is another visual data generated by transforming the original image using a deep learning model.

[1044] "Sharing" refers to the act of a user sending and publishing a newly generated image to others via social networking sites, messaging applications, etc.

[1045] The present invention provides a system that allows users to upload their own images, convert the images into a specific style, and share the generated images with others. An embodiment of this system will be described in detail below.

[1046] System Configuration

[1047] The system of the present invention mainly comprises the following components:

[1048] 1. User device: A device on which a user inputs and selects an image, specifies conversion options, sends it to the server, and receives, displays, and shares the processed image. This includes smartphones, tablets, PCs, etc.

[1049] 2. Server: Receives the image and conversion options sent from the user device, converts the image using a deep learning model, generates a new image, and sends it back to the user device.

[1050] 3. Network: The Internet or other communication network that allows data communication between user terminals and the server.

[1051] Program processing

[1052] When a user wants to edit their own image, they first launch the application on their device. The user clicks the "Upload Photo" button and selects a photo from their gallery. After the user selects an image, the device displays a preview of the image and asks the user for confirmation. For the confirmed image, the application presents the user with transformation options (e.g., "Anime Character," "Celebrity," "Dog," "Cat," etc.). After the user selects the desired transformation option, the device temporarily saves the selected image and transformation option and sends this data to the server.

[1053] Specific processing flow

[1054] 1. User uploads an image

[1055] The user launches the application on their device, clicks the "Upload Photos" button, and the gallery is displayed. They can then select the image they want to upload. The selected image is then displayed on the preview screen.

[1056] 2. The user selects conversion options

[1057] After viewing the image in the preview screen, the user selects a conversion option (e.g., "Anime Character," "Celebrity," "Dog," "Cat," etc.) from a menu within the application. A dialog displays the selection and asks the user for confirmation.

[1058] 3. The device sends the data to the server

[1059] Once the user has selected the conversion options, the device temporarily stores the selected image and conversion options, and then sends the image data and conversion options to the server using an HTTP request.

[1060] 4. The server receives and analyzes the data

[1061] The server parses the received HTTP request and separates the image data and conversion options. The image data is saved in temporary storage, and the conversion options are stored in variables.

[1062] 5. The server converts the image

[1063] The server selects an appropriate deep learning model based on the conversion options. The selected model may use TensorFlow or PyTorch. The server inputs the image data into the deep learning model and converts it into the specified style. New converted image data is generated.

[1064] 6. The server sends the converted image back to the device.

[1065] The server encodes the converted image data and returns it to the user device. The HTTP response is used again for the return. The server records the processing results in a log and performs error handling as necessary.

[1066] 7. User reviews and shares the image

[1067] The user's device decodes the converted image data received from the server and displays it on the screen. The user can then view the image and easily share it via social media or messaging apps by clicking the share button within the application.

[1068] Specific examples

[1069] For example, if a user wants to transform their selfie into a cartoon character, the process would look like this:

[1070] 1. The user uploads a selfie to the application and selects the option to convert it as an "anime character."

[1071] 2. The device sends the selfie and conversion options to the server.

[1072] 3. The server receives the selfie and selects an anime character generation model.

[1073] 4. The server uses the model to transform the selfie into an anime character.

[1074] 5. The server returns the newly generated anime character-style image to the device.

[1075] 6. The device displays the returned image and asks the user to confirm it.

[1076] 7. The user reviews the image and shares it via social media or messaging apps.

[1077] Prompt Sentence Examples

[1078] To adjust the quality and style of the resulting image, you can provide prompts to the generative AI model, such as:

[1079] "Transform your selfie into an anime character-style image."

[1080] This prompt will guide the AI ​​model through the process of transforming the selfie into an "anime character" image. Additional prompts can be used to specify more specific styles and characteristics, if desired.

[1081] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1082] Processing flow

[1083] Step 1:

[1084] The user uploads an image

[1085] Specific operation: The user launches the application on their device and clicks the "Upload Photo" button. The gallery will be displayed, and they can select the image they want to upload. The selected image will be displayed on the preview screen.

[1086] Input: An image file selected by the user.

[1087] Output: Preview image displayed on the device

[1088] Step 2:

[1089] The user selects conversion options

[1090] What it does: After viewing an image in the preview screen, the user selects a conversion option from a menu within the application (e.g., "Anime Character," "Celebrity," "Dog," "Cat," etc.) A dialog appears displaying the selection and asking the user for confirmation.

[1091] Input: User selected conversion options

[1092] Output: A confirmation dialog displayed on the terminal

[1093] Step 3:

[1094] The device sends the data to the server

[1095] Specific operation: After the user has selected the conversion options, the device temporarily saves the selected image and conversion options, and then sends the image data and conversion options to the server using an HTTP request.

[1096] Input: Selected image data and conversion options

[1097] Output: HTTP request sent to the server

[1098] Step 4:

[1099] The server receives and analyzes the data

[1100] Specific operation: The server parses the received HTTP request and separates the image data and conversion options. The image data is saved in temporary storage, and the conversion options are stored in variables.

[1101] Input: Image data and conversion options sent as an HTTP request

[1102] Output: Parsed image data and conversion options

[1103] Step 5:

[1104] The server converts the image

[1105] Specific operation: The server selects an appropriate deep learning model based on the conversion options. The selected model may use TensorFlow or PyTorch. The server inputs the image data into the deep learning model and converts it into the specified style. New converted image data is generated.

[1106] Input: Parsed image data and transformation options

[1107] Output: New image data after conversion processing

[1108] Step 6:

[1109] The server sends the converted image back to the device.

[1110] Specific operation: The server encodes the converted image data and returns it to the user device. The HTTP response is used again for the return. The server records the processing result in a log and performs error handling as necessary.

[1111] Input: New image data after conversion processing

[1112] Output: The HTTP response sent back to the device

[1113] Step 7:

[1114] Users review and share images

[1115] Specific operation: The user device decodes the converted image data received from the server and displays it on the screen. The user can then view the image and easily share it via social media or messaging apps by clicking the share button in the application.

[1116] Input: The converted image data sent back to the device

[1117] Output: The converted image displayed on the device and the shared image

[1118] (Application example 1)

[1119] 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."

[1120] Conventional image conversion technologies simply convert images statically, limiting their use as content. Furthermore, there are limited ways to generate and share more diverse content using the converted images. Therefore, there is a need for technology that improves the user experience and enhances the scalability of generated content.

[1121] 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.

[1122] In this invention, the server includes a means for processing user-entered images using a generative artificial intelligence model to generate new images, a means for generating custom videos or moving images using the generated new images, and a means for sharing the generated content via multiple information distribution services or messaging applications, thereby enabling users to not only enjoy high-quality image conversion but also easily generate and share a variety of content based on the generated images.

[1123] "User" refers to the person using the system who inputs their image, selects conversion options, and reviews and shares the generated content.

[1124] "Conversion options" refer to specific styles and settings that users can select when converting images using a deep learning model.

[1125] "Server" refers to a device or system that receives images and conversion options sent from a user terminal, processes the images using a generative artificial intelligence model, generates new images or video, and returns them to the user terminal.

[1126] A "generative artificial intelligence model" is a deep learning-based model used for image transformation, which refers to a technique for transforming an input image according to a specific style.

[1127] "Custom video" or "motion picture" refers to a moving image or animation created from newly generated images.

[1128] An "information distribution service" is an online platform for sharing user-generated content with others, including social networking services and messaging applications.

[1129] "Sharing" refers to the act of sending generated content to other users or platforms where it can be accessed or viewed.

[1130] The present invention provides a system that allows users to upload their own images, convert those images into specific people, animals, characters, etc., and share the generated images and videos. Specific embodiments of this system are described below.

[1131] System Overview

[1132] The system mainly consists of the following components:

[1133] 1. User terminal: A device that allows users to input and select images, specify conversion options, send them to the server, and receive, display, and share processed images, custom videos, and moving images. This includes smartphones, tablets, and PCs.

[1134] 2. Server: Receives images and conversion options sent from the user terminal, processes the images using a generative artificial intelligence model, generates new images and videos, and sends them back to the user terminal.

[1135] 3. Network: The Internet or other communication network that allows data communication between user terminals and the server.

[1136] Program processing

[1137] User terminal processing

[1138] When a user wants to edit their own image, they launch the application on their device. Within the application, the user clicks the "Upload Photo" button and selects a photo from their gallery. Once the user selects an image, the device displays a preview of the image and asks the user for confirmation. For the confirmed image, the application presents the user with transformation options (e.g., "Anime Character," "Celebrity," "Dog," "Cat," etc.). Once the user selects the desired transformation option, the device temporarily saves the selected image and transformation option and sends this data to the server.

[1139] Server Processing

[1140] The server receives the images and conversion options sent from the user device. It decodes the received data and separates the images from the conversion options. Next, the server selects a generative artificial intelligence (AI) model based on the specified conversion options. The image data is input into the selected model and converted into a specific style. PyTorch is used as the deep learning library. The generated images are then used to generate custom videos and moving images. At this stage, PIL (Python Imaging Library) and the generative artificial intelligence model are used. New processed image data and moving images are generated, encoded, and sent back to the user device.

[1141] An example

[1142] For example, if a user wants to transform their selfie into a cartoon character and create a short video from it to share with friends, here's what happens:

[1143] 1. The user uploads a selfie to the application and selects the option to convert it into an "anime character."

[1144] 2. The device sends the selfie and conversion options to the server.

[1145] 3. The server receives the selfie and selects an anime character generation model.

[1146] 4. The server uses a generative artificial intelligence model to transform the selfie into an anime character.

[1147] 5. The server creates a short video or animation using the newly generated anime character-style image.

[1148] 6. The server returns the generated content to the device.

[1149] 7. The device displays the returned images and videos for the user to review.

[1150] 8. The user reviews the images and videos and shares them via social media or messaging apps.

[1151] Prompt Sentence Examples

[1152] For example, by entering a prompt such as "Please convert this selfie into an anime character style," the user can easily obtain the desired conversion result.

[1153] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1154] Step 1:

[1155] The user launches the application and clicks the "Upload Photo" button.

[1156] Specifically, the user selects a photo from their gallery. The input is the image file selected by the user, and the device displays a preview of the image. The output is the image displayed on the preview screen.

[1157] Step 2:

[1158] The terminal asks the user for confirmation, and then presents the user with conversion options (e.g., "anime character," "celebrity," "dog," "cat," etc.) for the confirmed image.

[1159] The input is the conversion options selected by the user, which the terminal temporarily stores, and the output is the data for the selected conversion options.

[1160] Step 3:

[1161] The terminal sends the selected image and conversion options to the server.

[1162] The input is the image and conversion options selected by the user, and the terminal sends this data to the server via the network. The output is the image data and conversion options sent to the server.

[1163] Step 4:

[1164] The server receives the image and conversion options sent from the user terminal.

[1165] The input is image data and conversion options sent from the terminal, which the server decodes and separates into the image and conversion options, and the output is the separated image data and conversion options.

[1166] Step 5:

[1167] The server selects a generative artificial intelligence model based on the specified transformation options.

[1168] The input is a set of isolated transformation options, and the server selects an appropriate model from among multiple generative artificial intelligence models. The output is the selected generative artificial intelligence model.

[1169] Step 6:

[1170] The server inputs the image data into the selected model and transforms the image into a particular style.

[1171] The input is image data and a selected generative artificial intelligence model, the server uses the model to transform the image, and the output is the new transformed image data.

[1172] Step 7:

[1173] The server uses the new images to generate custom video or animation.

[1174] The input is the new transformed image data that the server uses to generate the video or animation, and the output is the custom video or animation that is generated.

[1175] Step 8:

[1176] The server encodes the generated custom video or animation and sends it back to the user's device.

[1177] The input is the generated custom video or animation that the server encodes and sends back to the user's device over the network, and the output is the custom video or animation sent to the user's device.

[1178] Step 9:

[1179] The user terminal displays the returned custom video or moving image for the user to review.

[1180] The input is a custom video or animation returned from the server, which the terminal displays and asks the user for confirmation. The output is the displayed custom video or animation.

[1181] Step 10:

[1182] Users can view images and videos and share them via social media or messaging applications.

[1183] The input is a verified custom video or moving image, and the user selects the platform to share it on. The output is content shared to social media or messaging applications.

[1184] 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.

[1185] This invention relates to a system that allows users to upload their own images, convert them into specific people, animals, characters, etc., and share the generated images. In addition, the invention aims to provide more appropriate and personalized conversion options by combining an emotion engine that recognizes the user's emotions.

[1186] System Configuration

[1187] The system of the present invention mainly comprises the following components:

[1188] 1. User device: A device on which a user inputs and selects an image, specifies conversion options, sends the image to the server, and receives, displays, and shares the processed image. This includes smartphones, tablets, and PCs. It also has the function of sending the user's facial expression and voice data to the emotion engine.

[1189] 2. Server: Receives the image and conversion options sent from the user device, processes the image using a deep learning model, generates a new image, and sends it back to the user device. Furthermore, it utilizes data from the emotion engine to suggest and apply appropriate conversion options.

[1190] 3. Emotion Engine: A component that includes algorithms for estimating emotions based on the user's facial recognition data and voice data, and proposing and selecting the optimal conversion options.

[1191] 4. Network: The Internet or other communications network that allows data communication between user terminals and the server.

[1192] Program processing

[1193] User terminal processing

[1194] When a user wants to edit their own image, they launch the application on their device. Within the application, the user clicks the "Upload Photo" button and selects a photo from their gallery. Once the user selects an image, the device displays a preview of the image and asks the user for confirmation. For the confirmed image, the application presents the user with transformation options (e.g., "Anime Character," "Celebrity," "Dog," "Cat," etc.).

[1195] Furthermore, the device sends the user's facial recognition data and voice data to the emotion engine to estimate their emotions. The emotion engine then suggests optimal conversion options based on the estimated emotions. When the user accepts the optimal suggestion or selects another option, the device temporarily stores the selected image and conversion options and transmits this data to the server.

[1196] Server Processing

[1197] The server receives the image and conversion options sent from the user device. It decodes the received data and separates the image from the conversion options. The server then selects the required deep learning model based on the specified conversion options, inputs the image data into the model, and generates a new image. The generated image data is then encoded and sent back to the user device.

[1198] Specific examples

[1199] For example, if a user wants to convert their selfie into an anime character style, the process would be as follows:

[1200] 1. The user uploads a selfie to the application and selects the desired conversion options.

[1201] 2. The device displays a preview of the selfie image and also sends the user's facial recognition data to the emotion engine.

[1202] 3. The emotion engine estimates the user's emotion (e.g., joy, surprise, etc.) and suggests "anime character" as the optimal conversion option.

[1203] 4. If the user accepts the suggestion, the device sends the selected selfie and the "Anime Character" conversion option to the server.

[1204] 5. The server receives the selfie and selects an anime character generation model.

[1205] 6. The server uses the model to transform the selfie into an anime character image and sends the resulting image back to the device.

[1206] 7. The device displays the returned image and asks the user to confirm it.

[1207] 8. The user reviews the image and selects the option to share it via social media or messaging apps.

[1208] This system allows users to easily enjoy personalized image processing based on emotions, even without any special technical skills, and easily share the results with others.

[1209] The processing flow will be explained below.

[1210] Step 1:

[1211] The user launches a photo editing app on their device.

[1212] Step 2:

[1213] The user clicks the "Upload Photo" button within the app and selects the photo they want to edit from their gallery.

[1214] Step 3:

[1215] The device displays a preview of the selected photo for the user to confirm, and also presents conversion options (e.g., "celebrity," "anime character," "dog," "cat," etc.) to the user.

[1216] Step 4:

[1217] The terminal collects the user's facial recognition data and voice data and sends them to the emotion engine.

[1218] Step 5:

[1219] The emotion engine analyzes the received facial recognition data and voice data to estimate the user's emotion.

[1220] Step 6:

[1221] The emotion engine suggests optimal conversion options based on the estimated emotion.

[1222] Step 7:

[1223] The user accepts the proposed conversion options or selects other conversion options.

[1224] Step 8:

[1225] The device temporarily saves the selected photo and the confirmed conversion options.

[1226] Step 9:

[1227] The device encodes the photo data and conversion options into JSON format and prepares an HTTP request to send to the server.

[1228] Step 10:

[1229] The device sends an HTTP request containing the encoded data to the server.

[1230] Step 11:

[1231] The server receives the HTTP request sent from the terminal and decodes the JSON data.

[1232] Step 12:

[1233] The server separates the decoded photo data and the transformation options, and selects the required deep learning model based on the transformation options.

[1234] Step 13:

[1235] The server inputs the photo data into a deep learning model and converts the image into the specified style.

[1236] Step 14:

[1237] The server generates new converted image data and encodes it in JPEG format or the like.

[1238] Step 15:

[1239] The server prepares and sends an HTTP response to return the new encoded image data to the user's terminal.

[1240] Step 16:

[1241] The terminal receives the HTTP response sent back from the server and decodes the encoded image data.

[1242] Step 17:

[1243] The device will then display the new decoded image in the app for the user to review.

[1244] Step 18:

[1245] The user reviews the new image and chooses to share it via social media or messaging applications.

[1246] Step 19:

[1247] The device will provide sharing options based on the user's selection, launching the specified social networking site or messaging application to share the new image.

[1248] Example 2

[1249] 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."

[1250] In recent years, advances in image editing technology have made it possible for individuals to easily process and edit images. However, existing systems have difficulty in providing personalized editing that takes user emotions into account, and this poses a high hurdle for general users without special technical skills. To solve this problem, there is a need for a simple and intuitive image conversion system that can recognize user emotions and suggest optimal conversion options.

[1251] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1252] In this invention, the server includes a means for processing an image using a deep learning model to generate a new image, a means for returning the generated new image to the user's terminal, and a means including an emotion engine for recognizing the user's emotion and suggesting conversion options based on the emotion, thereby enabling the user to easily perform personalized image conversion based on their own emotion.

[1253] A "user" is an individual or entity that inputs an image, selects conversion options, and reviews and shares the resulting image.

[1254] "User terminal" refers to a device on which a user inputs and selects an image, specifies conversion options, sends the image to the server, and receives, displays, and shares the processed image. This includes smartphones, tablets, PCs, etc.

[1255] A "server" is a device or system that receives an image and conversion options sent from a user terminal, processes the image using a deep learning model, generates a new image, and returns it to the user terminal.

[1256] "Image" refers to data containing visual information such as a photograph or picture entered by the user.

[1257] "Conversion options" are options for how the user can process or edit an image. Examples include "anime characters," "celebrities," "dogs," and "cats."

[1258] A "deep learning model" is a model that uses advanced machine learning algorithms to process input data, learn and recognize specific patterns, and generate images.

[1259] The "emotion engine" is a component that includes algorithms for estimating emotions based on the user's facial recognition data and voice data, and proposing and selecting optimal conversion options.

[1260] A "preview" is a temporary display that allows the user to check the image selected and the editing operations performed.

[1261] "Encoding" is the process of converting data into a particular format.

[1262] "Decoding" is the process of restoring encoded data to its original form.

[1263] This invention relates to a system that allows users to convert their own images into specific people, animals, characters, etc., and share the generated images. Furthermore, the invention aims to combine an emotion engine that recognizes the user's emotions to provide more appropriate and personalized conversion options. Specific embodiments for implementing this system are described below.

[1264] System Configuration

[1265] The system of the present invention mainly comprises the following components:

[1266] 1. User device: A device on which users input and select images, specify conversion options, send them to the server, and receive, display, and share the processed images. This includes smartphones, tablets, PCs, etc., and also has the function of sending the user's facial expression data and voice data to the emotion engine.

[1267] 2. Server: Receives the image and conversion options sent from the user device, processes the image using a deep learning model, generates a new image, and sends it back to the user device. It also uses data from the emotion engine to suggest and apply appropriate conversion options.

[1268] 3. Emotion Engine: This component includes algorithms for estimating emotions based on the user's facial recognition data and voice data, and for suggesting and selecting optimal conversion options.

[1269] 4. Network: The Internet or other communications network that allows data communication between user terminals and the server.

[1270] System Operation

[1271] When a user wants to edit their own image, they launch the application on their device. The user clicks the "Upload Photo" button in the application and selects a photo from their gallery. After the user selects an image, the device displays a preview of the image and asks the user for confirmation. For the confirmed image, the application presents the user with transformation options (e.g., "Anime Character," "Celebrity," "Dog," "Cat," etc.). In addition, the device sends the user's facial recognition data and voice data to an emotion engine to estimate their emotion. The emotion engine suggests the optimal transformation option based on the estimated emotion. If the user accepts the optimal suggestion or selects another option, the device temporarily saves the selected image and transformation option and sends this data to the server.

[1272] The server receives the image and conversion options sent from the user device. It decodes the received data and separates the image from the conversion options. The server then selects the required deep learning model based on the specified conversion options, inputs the image data into the model, and generates a new image. The generated image data is then encoded and sent back to the user device.

[1273] Specific examples

[1274] For example, if a user wants to convert their selfie into an anime character style, the process would be as follows:

[1275] 1. The user uploads a selfie to the application and selects the desired conversion options.

[1276] 2. The device displays a preview of the selfie image and also sends the user's facial recognition data to the emotion engine.

[1277] 3. The emotion engine estimates the user's emotion (e.g., joy, surprise, etc.) and suggests "anime character" as the optimal conversion option.

[1278] 4. If the user accepts the suggestion, the device sends the selected selfie and the "Anime Character" conversion option to the server.

[1279] 5. The server receives the selfie and selects an anime character generation model.

[1280] 6. The server uses the model to transform the selfie into an anime character image and sends the resulting image back to the device.

[1281] 7. The device displays the returned image and asks the user to confirm it.

[1282] 8. The user reviews the image and selects the option to share it via social media or messaging apps.

[1283] Example of input prompt for generative AI model

[1284] "A user uploaded a selfie and selected the 'Anime Character' conversion option. Please convert this selfie to look like an anime character."

[1285] This system allows users to easily enjoy personalized image processing based on emotions, even without any special technical skills, and easily share the results with others.

[1286] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1287] Step 1:

[1288] The user launches an application on the device.

[1289] Input: The user taps on an app on their smartphone.

[1290] Output: The main screen of the application is displayed.

[1291] Specific behavior: The user taps the icon to launch the app, and the app displays the main screen.

[1292] Step 2:

[1293] A user uploads an image.

[1294] Input: User presses the "Upload Photo" button and selects a photo from the gallery.

[1295] Output: The selected image is displayed in the application.

[1296] Specific operation: The user presses a button, moves to an image selection screen, and selects an image such as a selfie from the gallery.

[1297] Step 3:

[1298] Your device will display a preview of the image and ask for confirmation.

[1299] Input: An image selected by the user.

[1300] Output: A preview of the image and a confirmation message asking "Are you sure this is the image?"

[1301] What happens: The device generates a preview of the image and displays a confirmation dialog.

[1302] Step 4:

[1303] The terminal presents conversion options to the user.

[1304] Input: User sees the image and answers "yes."

[1305] Output: You will see conversion options such as anime characters, celebrities, dogs, cats, etc.

[1306] Specific behavior: The device renders a UI to display the options.

[1307] Step 5:

[1308] The device sends facial recognition data and voice data to the emotion engine.

[1309] Input: User's facial recognition and voice data.

[1310] Output: Data sent to the emotion engine.

[1311] Specific operation: The device captures data using the camera and microphone and sends it to the emotion engine.

[1312] Step 6:

[1313] The device presents suggestions from the emotion engine to the user.

[1314] Input: Transformation option suggestions from the sentiment engine.

[1315] Output: The best conversion options based on the estimated sentiment are displayed to the user.

[1316] Specific operation: The device receives the response from the emotion engine and displays the suggestions.

[1317] Step 7:

[1318] The user selects a conversion option.

[1319] Input: User's choice of conversion options.

[1320] Output: The selected conversion options will be saved to your device.

[1321] What happens: The user taps an option and the device records the selection.

[1322] Step 8:

[1323] The device sends the selected image and conversion options to the server.

[1324] Input: Selected image and conversion options.

[1325] Output: The image and conversion options are sent to the server.

[1326] Specific operation: The terminal forms transmission data and transmits the data to the server through the network.

[1327] Step 9:

[1328] The server receives the image and conversion options.

[1329] Input: Image sent from the device and conversion options.

[1330] Output: Decoded result of received data.

[1331] What it does: The server decodes the received data and separates the image and conversion options.

[1332] Step 10:

[1333] The server selects the required deep learning model.

[1334] Input: Conversion options.

[1335] Output: The selected deep learning model.

[1336] What happens: The server looks up the appropriate model from the database or file system.

[1337] Step 11:

[1338] The server inputs the image into the model and generates a new image.

[1339] Input: Original image data, selected deep learning model.

[1340] Output: The new image generated.

[1341] Specific operation: The server inputs image data into the model, processes it, and generates a new image.

[1342] Step 12:

[1343] The server encodes the generated image and sends it back to the user's terminal.

[1344] Input: The new image generated.

[1345] Output: The encoded image data.

[1346] Specific operation: The server encodes the image in a timely manner and transmits it to the user terminal via the network.

[1347] Step 13:

[1348] The terminal displays the returned image and prompts the user to confirm it.

[1349] Input: The encoded image data returned from the server.

[1350] Output: The new image displayed.

[1351] What happens: The device decodes the image and displays it to the user for confirmation.

[1352] Step 14:

[1353] The user can view the image and share it via social media or messaging applications.

[1354] Input: User confirmation.

[1355] Output: Link or data for sharing.

[1356] What happens: The user clicks the "Share" button and selects the option to send the image to the social networking or messaging application of their choice.

[1357] (Application example 2)

[1358] 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."

[1359] Conventional image processing systems lack a means to provide personalized transformation options based on the user's emotions, making it difficult to create optimal content for the user. Furthermore, when users use images as virtual try-on simulations, they have difficulty selecting appropriate outfits and accessories, resulting in an unsatisfactory try-on experience.

[1360] The specification processing by the specification 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 acquiring the user's facial expression data and voice data and sending them to the emotion engine, means for proposing optimal conversion options based on the emotions estimated by the emotion engine, and means for applying a specific model from among multiple deep learning models based on the selected conversion options and suggestions from the emotion engine. This enables personalized image conversion and virtual try-on simulations that take the user's emotions into consideration.

[1361] A "user" is someone who uses the system to enhance their own images and review and share the transformed images.

[1362] "Images" are visual data such as photographs or illustrations that users upload to the system.

[1363] "Conversion options" refer to image processing styles and themes that users can select, including anime character style, animal style, celebrity style, etc.

[1364] "Facial expression data" is data used to capture the user's facial expressions and estimate their emotions based on that information.

[1365] "Voice data" is data that captures the user's vocalizations and is used to estimate emotions based on that voice information.

[1366] An "emotion engine" is an algorithm or program that analyzes facial expression data and voice data, estimates the user's emotions, and suggests optimal conversion options.

[1367] A "deep learning model" is a neural network that is trained with large amounts of data to transform input images into a specific style.

[1368] The "server" is the central processing unit of the system, a computer that processes images and conversion options sent by users, generates new images, and returns them.

[1369] "Terminal" refers to a device that a user uses to upload images, receive converted images, and view and share them, including smartphones, tablets, and PCs.

[1370] A "preview" is a temporary image that is displayed to allow a user to check the image they have uploaded.

[1371] A "social networking service" is an online platform used by users to share generated images, also known as an SNS.

[1372] A "messaging application" is a communication tool that users use to share generated images.

[1373] A "personalized image" is an image that is customized based on the user's feelings and preferences.

[1374] "Virtual try-on simulation" is a process in which a user virtually tries on outfits and accessories in images uploaded by the user.

[1375] The following describes an embodiment of the present invention. The system allows users to upload their own images, convert them into specific characters, people, animals, etc., and then review and share the generated images. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides more appropriate and personalized conversion options.

[1376] Hardware and Software

[1377] The main components of the system are:

[1378] User device: A smartphone, tablet, PC, etc. This is the device where users input and select images, and receive, display, and share the processed images. React Native and JavaScript are used to upload images and display previews.

[1379] Server: Receives images, processes them using deep learning models, generates new images, and sends them back to the user device. Can use cloud services such as AWS EC2.

[1380] Emotion engine: An algorithm that estimates emotions based on the user's facial expression and voice data and suggests optimal conversion options. Microsoft Azure's Emotion API can be used.

[1381] Deep learning models: Use frameworks such as TensorFlow to perform image transformation.

[1382] Processing flow

[1383] User device operation

[1384] 1. The user launches the application and clicks the "Upload Photo" button to select their own image.

[1385] 2. A preview of the image is displayed and the user confirms it.

[1386] 3. The user device acquires facial expression data and voice data and sends them to the emotion engine.

[1387] 4. The emotion engine estimates the emotion and presents the user with recommended transformation options (e.g., anime character style).

[1388] 5. If the user accepts the offer or selects another option, the data is sent to the server.

[1389] Server Processing

[1390] 1. The server receives the image and conversion options sent by the user.

[1391] 2. Select a deep learning model, input an image, and generate a new image.

[1392] 3. The generated image is sent back to the user's device.

[1393] Displaying the user terminal

[1394] 1. The generated image is displayed and the user confirms it.

[1395] 2. Users have the option to share the image on social media or messaging applications.

[1396] Specific examples

[1397] For example, if a user wants to convert their selfie into an anime character style, the process would be as follows:

[1398] 1. The user uploads a selfie to the application and selects the conversion option.

[1399] 2. The application displays a preview of the selfie image and sends the user's facial recognition data to the emotion engine.

[1400] 3. The emotion engine estimates the user's emotion (e.g., joy, surprise, etc.) and suggests "anime character" as the optimal conversion option.

[1401] 4. If the user accepts the suggestion, the device sends the selected selfie and the "Anime Character" conversion option to the server.

[1402] 5. The server receives the selfie and selects an anime character generation model.

[1403] 6. The server uses the model to transform the selfie into an anime character image and sends the resulting image back to the device.

[1404] 7. The device displays the returned image and asks the user to confirm it.

[1405] 8. The user reviews the image and selects the option to share it via social media or messaging apps.

[1406] Prompt Sentence Examples

[1407] Users upload an image and send facial expression data to an emotion engine API (e.g., EmotionAPI), which then suggests recommended try-on options to the user.

[1408] This allows users to easily enjoy emotion-based personalized image processing and virtual try-on simulations without any special technical skills, and the results can be easily shared with others.

[1409] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1410] Step 1:

[1411] The user launches the application on their device and clicks the "Photo Upload" button to select their own image. The image is picked from the device's gallery and displayed as a preview. The input is the user's image and the output is the preview image.

[1412] Step 2:

[1413] The device acquires the user's facial expression and voice data and sends them to the emotion engine. The facial expression data is captured using a camera, and the voice data is recorded using a microphone. The input is the facial expression data and voice data, and the output is the emotion estimation result.

[1414] Step 3:

[1415] The emotion engine analyzes the received facial expression and voice data to estimate the user's emotion. Based on the estimated emotion, it proposes optimal conversion options. The input is facial expression and voice data, and the output is the estimated emotion and recommended conversion options.

[1416] Step 4:

[1417] The device presents the recommendation from the emotion engine to the user. If the user accepts the recommendation or selects another conversion option, their selection information is temporarily saved. The input is the estimated emotion and the recommended conversion option, and the output is the user's selection information.

[1418] Step 5:

[1419] The terminal sends the selected conversion options and the image to the server. The input is the user's image and conversion options, and the output is the request data to the server.

[1420] Step 6:

[1421] The server receives and decodes the image and conversion options sent from the terminal. The input is the request data, and the output is the decoded image and conversion options.

[1422] Step 7:

[1423] The server selects the optimal deep learning model based on the suggestions from the emotion engine. The inputs are the transformation options and the suggestions from the emotion engine, and the output is the selected deep learning model.

[1424] Step 8:

[1425] The server processes the image using the selected deep learning model to generate a new image. The inputs are the decoded image and the deep learning model, and the output is the generated new image.

[1426] Step 9:

[1427] The server encodes the new image and sends it back to the user terminal. The input is the new image and the output is the encoded image data.

[1428] Step 10:

[1429] The terminal decodes the received image and displays it to the user. The input is the encoded image data and the output is the decoded image.

[1430] Step 11:

[1431] The user can view the new image and select the option to share it on social media or messaging applications. The input is the decoded image and the output is the shared content.

[1432] 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.

[1433] 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.

[1434] 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.

[1435] [Fourth embodiment]

[1436] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1437] 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.

[1438] 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).

[1439] 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.

[1440] 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.

[1441] 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).

[1442] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1443] 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.

[1444] 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.

[1445] 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.

[1446] 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.

[1447] 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.

[1448] 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."

[1449] This invention is a system that allows users to upload their own images, convert the images into specific people, animals, characters, etc., and share the generated images. An embodiment of this system will be described in detail below.

[1450] System Configuration

[1451] The system of the present invention mainly comprises the following components:

[1452] 1. User device: A device on which a user inputs and selects an image, specifies conversion options, sends it to the server, and receives, displays, and shares the processed image. This includes smartphones, tablets, and PCs.

[1453] 2. Server: Receives the image and conversion options sent from the user device, processes the image using a deep learning model, generates a new image, and sends it back to the user device.

[1454] 3. Network: The Internet or other communications network that allows data communication between user terminals and the server.

[1455] Program processing

[1456] User terminal processing

[1457] When a user wants to edit their own image, they launch the application on their device. The user clicks the "Upload Photo" button in the application and selects a photo from their gallery. After the user selects an image, the device displays a preview of the image and asks the user for confirmation. For the confirmed image, the application presents the user with transformation options (e.g., "Anime Character," "Celebrity," "Dog," "Cat," etc.). After the user selects the desired transformation option, the device temporarily saves the selected image and transformation option and sends this data to the server.

[1458] Server Processing

[1459] The server receives the image and conversion options sent from the user device. It decodes the received data and separates the image from the conversion options. The server then selects a deep learning model based on the specified conversion options. The selected model inputs the image data and converts the image into a specific style. It then generates new processed image data, encodes it, and sends it back to the user device.

[1460] Specific examples

[1461] For example, if a user wants to convert their selfie into an anime character style, the process would be as follows:

[1462] 1. The user uploads a selfie to the application and selects the option to convert it into an anime character.

[1463] 2. The device sends the selfie and conversion options to the server.

[1464] 3. The server receives the selfie and selects an anime character generation model.

[1465] 4. The server uses the model to transform the selfie into an anime character.

[1466] 5. The server returns the newly generated anime character-style image to the device.

[1467] 6. The device displays the returned image and asks the user to confirm it.

[1468] 7. The user reviews the image and shares it via social media or messaging apps.

[1469] In this way, the system of the present invention allows users to easily enjoy high-quality image processing even if they do not have special technical skills, and the results can be easily shared with others.

[1470] The processing flow will be explained below.

[1471] Step 1:

[1472] The user launches a photo editing app on their device.

[1473] Step 2:

[1474] The user clicks the "Upload Photo" button within the app and selects the photo they want to edit from their gallery.

[1475] Step 3:

[1476] The device displays a preview of the selected photo for the user to confirm, and also presents conversion options (e.g., "celebrity," "anime character," "dog," "cat," etc.) to the user.

[1477] Step 4:

[1478] The user selects the desired conversion options.

[1479] Step 5:

[1480] Your device will temporarily save the photo and conversion options you selected.

[1481] Step 6:

[1482] The device encodes the photo data and conversion options into JSON format and prepares an HTTP request to send to the server.

[1483] Step 7:

[1484] The device sends an HTTP request containing the encoded data to the server.

[1485] Step 8:

[1486] The server receives the HTTP request sent from the terminal and decodes the JSON data.

[1487] Step 9:

[1488] The server separates the decoded photo data and the transformation options, and selects the required deep learning model based on the transformation options.

[1489] Step 10:

[1490] The server inputs the photo data into a deep learning model and converts the image into the specified style.

[1491] Step 11:

[1492] The server generates new converted image data and encodes it in JPEG format or the like.

[1493] Step 12:

[1494] The server prepares and sends an HTTP response to return the new encoded image data to the user's terminal.

[1495] Step 13:

[1496] The terminal receives the HTTP response sent back from the server and decodes the encoded image data.

[1497] Step 14:

[1498] The device will then display the new decoded image in the app for the user to review.

[1499] Step 15:

[1500] The user reviews the new image and chooses to share it via social media or messaging applications.

[1501] Step 16:

[1502] The device will provide sharing options based on the user's selection, launching the specified social networking site or messaging application to share the new image.

[1503] Example 1

[1504] 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."

[1505] With conventional image conversion systems, it is difficult to achieve high-quality image conversion unless the user has special technical skills, and there are limited ways to easily share the results with others. It is also difficult to select the appropriate deep learning model for a specific conversion option and perform the optimal conversion. This limits the user experience and makes the system less convenient and versatile.

[1506] 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.

[1507] In this invention, the server includes means for applying a specific model from among a plurality of deep learning models to the received image based on a selected conversion option, means for generating a new image after the conversion process, and means for returning the generated new image to the user terminal, thereby enabling users to easily achieve high-quality image conversion without requiring special technical skills and quickly share the results with others.

[1508] A "User" is an individual or entity who provides input and selections to transform and share their images using the system.

[1509] "Terminal" refers to a device that allows a user to input or select an image, specify conversion options, and send the image to the server, and includes smartphones, tablets, and PCs.

[1510] "Server" means a centralized computer system that receives images and transformation options sent from a user device, transforms the images using a deep learning model, and generates a new image that is sent back to the user device.

[1511] "Images" are visual data such as photographs and illustrations uploaded by users.

[1512] "Conversion options" are settings that represent a particular style or theme (e.g., "Anime Characters," "Celebrities," "Animals," etc.) that is applied to an image.

[1513] A "deep learning model" is a machine learning model that has been trained to transform images into a specific style using deep learning algorithms.

[1514] A "new generated image" is another visual data generated by transforming the original image using a deep learning model.

[1515] "Sharing" refers to the act of a user sending and publishing a newly generated image to others via social networking sites, messaging applications, etc.

[1516] The present invention provides a system that allows users to upload their own images, convert the images into a specific style, and share the generated images with others. An embodiment of this system will be described in detail below.

[1517] System Configuration

[1518] The system of the present invention mainly comprises the following components:

[1519] 1. User device: A device on which a user inputs and selects an image, specifies conversion options, sends it to the server, and receives, displays, and shares the processed image. This includes smartphones, tablets, PCs, etc.

[1520] 2. Server: Receives the image and conversion options sent from the user device, converts the image using a deep learning model, generates a new image, and sends it back to the user device.

[1521] 3. Network: The Internet or other communication network that allows data communication between user terminals and the server.

[1522] Program processing

[1523] When a user wants to edit their own image, they first launch the application on their device. The user clicks the "Upload Photo" button and selects a photo from their gallery. After the user selects an image, the device displays a preview of the image and asks the user for confirmation. For the confirmed image, the application presents the user with transformation options (e.g., "Anime Character," "Celebrity," "Dog," "Cat," etc.). After the user selects the desired transformation option, the device temporarily saves the selected image and transformation option and sends this data to the server.

[1524] Specific processing flow

[1525] 1. User uploads an image

[1526] The user launches the application on their device, clicks the "Upload Photos" button, and the gallery is displayed. They can then select the image they want to upload. The selected image is then displayed on the preview screen.

[1527] 2. The user selects conversion options

[1528] After viewing the image in the preview screen, the user selects a conversion option (e.g., "Anime Character," "Celebrity," "Dog," "Cat," etc.) from a menu within the application. A dialog displays the selection and asks the user for confirmation.

[1529] 3. The device sends the data to the server

[1530] Once the user has selected the conversion options, the device temporarily stores the selected image and conversion options, and then sends the image data and conversion options to the server using an HTTP request.

[1531] 4. The server receives and analyzes the data

[1532] The server parses the received HTTP request and separates the image data and conversion options. The image data is saved in temporary storage, and the conversion options are stored in variables.

[1533] 5. The server converts the image

[1534] The server selects an appropriate deep learning model based on the conversion options. The selected model may use TensorFlow or PyTorch. The server inputs the image data into the deep learning model and converts it into the specified style. New converted image data is generated.

[1535] 6. The server sends the converted image back to the device.

[1536] The server encodes the converted image data and returns it to the user device. The HTTP response is used again for the return. The server records the processing results in a log and performs error handling as necessary.

[1537] 7. User reviews and shares the image

[1538] The user's device decodes the converted image data received from the server and displays it on the screen. The user can then view the image and easily share it via social media or messaging apps by clicking the share button within the application.

[1539] Specific examples

[1540] For example, if a user wants to transform their selfie into a cartoon character, the process would look like this:

[1541] 1. The user uploads a selfie to the application and selects the option to convert it as an "anime character."

[1542] 2. The device sends the selfie and conversion options to the server.

[1543] 3. The server receives the selfie and selects an anime character generation model.

[1544] 4. The server uses the model to transform the selfie into an anime character.

[1545] 5. The server returns the newly generated anime character-style image to the device.

[1546] 6. The device displays the returned image and asks the user to confirm it.

[1547] 7. The user reviews the image and shares it via social media or messaging apps.

[1548] Prompt Sentence Examples

[1549] To adjust the quality and style of the resulting image, you can provide prompts to the generative AI model, such as:

[1550] "Transform your selfie into an anime character-style image."

[1551] This prompt will guide the AI ​​model through the process of transforming the selfie into an "anime character" image. Additional prompts can be used to specify more specific styles and characteristics, if desired.

[1552] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1553] Processing flow

[1554] Step 1:

[1555] The user uploads an image

[1556] Specific operation: The user launches the application on their device and clicks the "Upload Photo" button. The gallery will be displayed, and they can select the image they want to upload. The selected image will be displayed on the preview screen.

[1557] Input: An image file selected by the user.

[1558] Output: Preview image displayed on the device

[1559] Step 2:

[1560] The user selects conversion options

[1561] What it does: After viewing an image in the preview screen, the user selects a conversion option from a menu within the application (e.g., "Anime Character," "Celebrity," "Dog," "Cat," etc.) A dialog appears displaying the selection and asking the user for confirmation.

[1562] Input: User selected conversion options

[1563] Output: A confirmation dialog displayed on the terminal

[1564] Step 3:

[1565] The device sends the data to the server

[1566] Specific operation: After the user has selected the conversion options, the device temporarily saves the selected image and conversion options, and then sends the image data and conversion options to the server using an HTTP request.

[1567] Input: Selected image data and conversion options

[1568] Output: HTTP request sent to the server

[1569] Step 4:

[1570] The server receives and analyzes the data

[1571] Specific operation: The server parses the received HTTP request and separates the image data and conversion options. The image data is saved in temporary storage, and the conversion options are stored in variables.

[1572] Input: Image data and conversion options sent as an HTTP request

[1573] Output: Parsed image data and conversion options

[1574] Step 5:

[1575] The server converts the image

[1576] Specific operation: The server selects an appropriate deep learning model based on the conversion options. The selected model may use TensorFlow or PyTorch. The server inputs the image data into the deep learning model and converts it into the specified style. New converted image data is generated.

[1577] Input: Parsed image data and transformation options

[1578] Output: New image data after conversion processing

[1579] Step 6:

[1580] The server sends the converted image back to the device.

[1581] Specific operation: The server encodes the converted image data and returns it to the user device. The HTTP response is used again for the return. The server records the processing result in a log and performs error handling as necessary.

[1582] Input: New image data after conversion processing

[1583] Output: The HTTP response sent back to the device

[1584] Step 7:

[1585] Users review and share images

[1586] Specific operation: The user device decodes the converted image data received from the server and displays it on the screen. The user can then view the image and easily share it via social media or messaging apps by clicking the share button in the application.

[1587] Input: The converted image data sent back to the device

[1588] Output: The converted image displayed on the device and the shared image

[1589] (Application example 1)

[1590] 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."

[1591] Conventional image conversion technologies simply convert images statically, limiting their use as content. Furthermore, there are limited ways to generate and share more diverse content using the converted images. Therefore, there is a need for technology that improves the user experience and enhances the scalability of generated content.

[1592] 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.

[1593] In this invention, the server includes a means for processing user-entered images using a generative artificial intelligence model to generate new images, a means for generating custom videos or moving images using the generated new images, and a means for sharing the generated content via multiple information distribution services or messaging applications, thereby enabling users to not only enjoy high-quality image conversion but also easily generate and share a variety of content based on the generated images.

[1594] "User" refers to the person using the system who inputs their image, selects conversion options, and reviews and shares the generated content.

[1595] "Conversion options" refer to specific styles and settings that users can select when converting images using a deep learning model.

[1596] "Server" refers to a device or system that receives images and conversion options sent from a user terminal, processes the images using a generative artificial intelligence model, generates new images or video, and returns them to the user terminal.

[1597] A "generative artificial intelligence model" is a deep learning-based model used for image transformation, which refers to a technique for transforming an input image according to a specific style.

[1598] "Custom video" or "motion picture" refers to a moving image or animation created from newly generated images.

[1599] An "information distribution service" is an online platform for sharing user-generated content with others, including social networking services and messaging applications.

[1600] "Sharing" refers to the act of sending generated content to other users or platforms where it can be accessed or viewed.

[1601] The present invention provides a system that allows users to upload their own images, convert those images into specific people, animals, characters, etc., and share the generated images and videos. Specific embodiments of this system are described below.

[1602] System Overview

[1603] The system mainly consists of the following components:

[1604] 1. User terminal: A device that allows users to input and select images, specify conversion options, send them to the server, and receive, display, and share processed images, custom videos, and moving images. This includes smartphones, tablets, and PCs.

[1605] 2. Server: Receives images and conversion options sent from the user terminal, processes the images using a generative artificial intelligence model, generates new images and videos, and sends them back to the user terminal.

[1606] 3. Network: The Internet or other communication network that allows data communication between user terminals and the server.

[1607] Program processing

[1608] User terminal processing

[1609] When a user wants to edit their own image, they launch the application on their device. Within the application, the user clicks the "Upload Photo" button and selects a photo from their gallery. Once the user selects an image, the device displays a preview of the image and asks the user for confirmation. For the confirmed image, the application presents the user with transformation options (e.g., "Anime Character," "Celebrity," "Dog," "Cat," etc.). Once the user selects the desired transformation option, the device temporarily saves the selected image and transformation option and sends this data to the server.

[1610] Server Processing

[1611] The server receives the images and conversion options sent from the user device. It decodes the received data and separates the images from the conversion options. Next, the server selects a generative artificial intelligence (AI) model based on the specified conversion options. The image data is input into the selected model and converted into a specific style. PyTorch is used as the deep learning library. The generated images are then used to generate custom videos and moving images. At this stage, PIL (Python Imaging Library) and the generative artificial intelligence model are used. New processed image data and moving images are generated, encoded, and sent back to the user device.

[1612] An example

[1613] For example, if a user wants to transform their selfie into a cartoon character and create a short video from it to share with friends, here's what happens:

[1614] 1. The user uploads a selfie to the application and selects the option to convert it into an "anime character."

[1615] 2. The device sends the selfie and conversion options to the server.

[1616] 3. The server receives the selfie and selects an anime character generation model.

[1617] 4. The server uses a generative artificial intelligence model to transform the selfie into an anime character.

[1618] 5. The server creates a short video or animation using the newly generated anime character-style image.

[1619] 6. The server returns the generated content to the device.

[1620] 7. The device displays the returned images and videos for the user to review.

[1621] 8. The user reviews the images and videos and shares them via social media or messaging apps.

[1622] Prompt Sentence Examples

[1623] For example, by entering a prompt such as "Please convert this selfie into an anime character style," the user can easily obtain the desired conversion result.

[1624] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1625] Step 1:

[1626] The user launches the application and clicks the "Upload Photo" button.

[1627] Specifically, the user selects a photo from their gallery. The input is the image file selected by the user, and the device displays a preview of the image. The output is the image displayed on the preview screen.

[1628] Step 2:

[1629] The terminal asks the user for confirmation, and then presents the user with conversion options (e.g., "anime character," "celebrity," "dog," "cat," etc.) for the confirmed image.

[1630] The input is the conversion options selected by the user, which the terminal temporarily stores, and the output is the data for the selected conversion options.

[1631] Step 3:

[1632] The terminal sends the selected image and conversion options to the server.

[1633] The input is the image and conversion options selected by the user, and the terminal sends this data to the server via the network. The output is the image data and conversion options sent to the server.

[1634] Step 4:

[1635] The server receives the image and conversion options sent from the user terminal.

[1636] The input is image data and conversion options sent from the terminal, which the server decodes and separates into the image and conversion options, and the output is the separated image data and conversion options.

[1637] Step 5:

[1638] The server selects a generative artificial intelligence model based on the specified transformation options.

[1639] The input is a set of isolated transformation options, and the server selects an appropriate model from among multiple generative artificial intelligence models. The output is the selected generative artificial intelligence model.

[1640] Step 6:

[1641] The server inputs the image data into the selected model and transforms the image into a particular style.

[1642] The input is image data and a selected generative artificial intelligence model, the server uses the model to transform the image, and the output is the new transformed image data.

[1643] Step 7:

[1644] The server uses the new images to generate custom video or animation.

[1645] The input is the new transformed image data that the server uses to generate the video or animation, and the output is the custom video or animation that is generated.

[1646] Step 8:

[1647] The server encodes the generated custom video or animation and sends it back to the user's device.

[1648] The input is the generated custom video or animation that the server encodes and sends back to the user's device over the network, and the output is the custom video or animation sent to the user's device.

[1649] Step 9:

[1650] The user terminal displays the returned custom video or moving image for the user to review.

[1651] The input is a custom video or animation returned from the server, which the terminal displays and asks the user for confirmation. The output is the displayed custom video or animation.

[1652] Step 10:

[1653] Users can view images and videos and share them via social media or messaging applications.

[1654] The input is a verified custom video or moving image, and the user selects the platform to share it on. The output is content shared to social media or messaging applications.

[1655] 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.

[1656] This invention relates to a system that allows users to upload their own images, convert them into specific people, animals, characters, etc., and share the generated images. In addition, the invention aims to provide more appropriate and personalized conversion options by combining an emotion engine that recognizes the user's emotions.

[1657] System Configuration

[1658] The system of the present invention mainly comprises the following components:

[1659] 1. User device: A device on which a user inputs and selects an image, specifies conversion options, sends the image to the server, and receives, displays, and shares the processed image. This includes smartphones, tablets, and PCs. It also has the function of sending the user's facial expression and voice data to the emotion engine.

[1660] 2. Server: Receives the image and conversion options sent from the user device, processes the image using a deep learning model, generates a new image, and sends it back to the user device. Furthermore, it utilizes data from the emotion engine to suggest and apply appropriate conversion options.

[1661] 3. Emotion Engine: A component that includes algorithms for estimating emotions based on the user's facial recognition data and voice data, and proposing and selecting the optimal conversion options.

[1662] 4. Network: The Internet or other communications network that allows data communication between user terminals and the server.

[1663] Program processing

[1664] User terminal processing

[1665] When a user wants to edit their own image, they launch the application on their device. Within the application, the user clicks the "Upload Photo" button and selects a photo from their gallery. Once the user selects an image, the device displays a preview of the image and asks the user for confirmation. For the confirmed image, the application presents the user with transformation options (e.g., "Anime Character," "Celebrity," "Dog," "Cat," etc.).

[1666] Furthermore, the device sends the user's facial recognition data and voice data to the emotion engine to estimate their emotions. The emotion engine then suggests optimal conversion options based on the estimated emotions. When the user accepts the optimal suggestion or selects another option, the device temporarily stores the selected image and conversion options and transmits this data to the server.

[1667] Server Processing

[1668] The server receives the image and conversion options sent from the user device. It decodes the received data and separates the image from the conversion options. The server then selects the required deep learning model based on the specified conversion options, inputs the image data into the model, and generates a new image. The generated image data is then encoded and sent back to the user device.

[1669] Specific examples

[1670] For example, if a user wants to convert their selfie into an anime character style, the process would be as follows:

[1671] 1. The user uploads a selfie to the application and selects the desired conversion options.

[1672] 2. The device displays a preview of the selfie image and also sends the user's facial recognition data to the emotion engine.

[1673] 3. The emotion engine estimates the user's emotion (e.g., joy, surprise, etc.) and suggests "anime character" as the optimal conversion option.

[1674] 4. If the user accepts the suggestion, the device sends the selected selfie and the "Anime Character" conversion option to the server.

[1675] 5. The server receives the selfie and selects an anime character generation model.

[1676] 6. The server uses the model to transform the selfie into an anime character image and sends the resulting image back to the device.

[1677] 7. The device displays the returned image and asks the user to confirm it.

[1678] 8. The user reviews the image and selects the option to share it via social media or messaging apps.

[1679] This system allows users to easily enjoy personalized image processing based on emotions, even without any special technical skills, and easily share the results with others.

[1680] The processing flow will be explained below.

[1681] Step 1:

[1682] The user launches a photo editing app on their device.

[1683] Step 2:

[1684] The user clicks the "Upload Photo" button within the app and selects the photo they want to edit from their gallery.

[1685] Step 3:

[1686] The device displays a preview of the selected photo for the user to confirm, and also presents conversion options (e.g., "celebrity," "anime character," "dog," "cat," etc.) to the user.

[1687] Step 4:

[1688] The terminal collects the user's facial recognition data and voice data and sends them to the emotion engine.

[1689] Step 5:

[1690] The emotion engine analyzes the received facial recognition data and voice data to estimate the user's emotion.

[1691] Step 6:

[1692] The emotion engine suggests optimal conversion options based on the estimated emotion.

[1693] Step 7:

[1694] The user accepts the proposed conversion options or selects other conversion options.

[1695] Step 8:

[1696] The device temporarily saves the selected photo and the confirmed conversion options.

[1697] Step 9:

[1698] The device encodes the photo data and conversion options into JSON format and prepares an HTTP request to send to the server.

[1699] Step 10:

[1700] The device sends an HTTP request containing the encoded data to the server.

[1701] Step 11:

[1702] The server receives the HTTP request sent from the terminal and decodes the JSON data.

[1703] Step 12:

[1704] The server separates the decoded photo data and the transformation options, and selects the required deep learning model based on the transformation options.

[1705] Step 13:

[1706] The server inputs the photo data into a deep learning model and converts the image into the specified style.

[1707] Step 14:

[1708] The server generates new converted image data and encodes it in JPEG format or the like.

[1709] Step 15:

[1710] The server prepares and sends an HTTP response to return the new encoded image data to the user's terminal.

[1711] Step 16:

[1712] The terminal receives the HTTP response sent back from the server and decodes the encoded image data.

[1713] Step 17:

[1714] The device will then display the new decoded image in the app for the user to review.

[1715] Step 18:

[1716] The user reviews the new image and chooses to share it via social media or messaging applications.

[1717] Step 19:

[1718] The device will provide sharing options based on the user's selection, launching the specified social networking site or messaging application to share the new image.

[1719] Example 2

[1720] 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."

[1721] In recent years, advances in image editing technology have made it possible for individuals to easily process and edit images. However, existing systems have difficulty in providing personalized editing that takes user emotions into account, and this poses a high hurdle for general users without special technical skills. To solve this problem, there is a need for a simple and intuitive image conversion system that can recognize user emotions and suggest optimal conversion options.

[1722] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1723] In this invention, the server includes a means for processing an image using a deep learning model to generate a new image, a means for returning the generated new image to the user's terminal, and a means including an emotion engine for recognizing the user's emotion and suggesting conversion options based on the emotion, thereby enabling the user to easily perform personalized image conversion based on their own emotion.

[1724] A "user" is an individual or entity that inputs an image, selects conversion options, and reviews and shares the resulting image.

[1725] "User terminal" refers to a device on which a user inputs and selects an image, specifies conversion options, sends the image to the server, and receives, displays, and shares the processed image. This includes smartphones, tablets, PCs, etc.

[1726] A "server" is a device or system that receives an image and conversion options sent from a user terminal, processes the image using a deep learning model, generates a new image, and returns it to the user terminal.

[1727] "Image" refers to data containing visual information such as a photograph or picture entered by the user.

[1728] "Conversion options" are options for how the user can process or edit an image. Examples include "anime characters," "celebrities," "dogs," and "cats."

[1729] A "deep learning model" is a model that uses advanced machine learning algorithms to process input data, learn and recognize specific patterns, and generate images.

[1730] The "emotion engine" is a component that includes algorithms for estimating emotions based on the user's facial recognition data and voice data, and proposing and selecting optimal conversion options.

[1731] A "preview" is a temporary display that allows the user to check the image selected and the editing operations performed.

[1732] "Encoding" is the process of converting data into a particular format.

[1733] "Decoding" is the process of restoring encoded data to its original form.

[1734] This invention relates to a system that allows users to convert their own images into specific people, animals, characters, etc., and share the generated images. Furthermore, the invention aims to combine an emotion engine that recognizes the user's emotions to provide more appropriate and personalized conversion options. Specific embodiments for implementing this system are described below.

[1735] System Configuration

[1736] The system of the present invention mainly comprises the following components:

[1737] 1. User device: A device on which users input and select images, specify conversion options, send them to the server, and receive, display, and share the processed images. This includes smartphones, tablets, PCs, etc., and also has the function of sending the user's facial expression data and voice data to the emotion engine.

[1738] 2. Server: Receives the image and conversion options sent from the user device, processes the image using a deep learning model, generates a new image, and sends it back to the user device. It also uses data from the emotion engine to suggest and apply appropriate conversion options.

[1739] 3. Emotion Engine: This component includes algorithms for estimating emotions based on the user's facial recognition data and voice data, and for suggesting and selecting optimal conversion options.

[1740] 4. Network: The Internet or other communications network that allows data communication between user terminals and the server.

[1741] System Operation

[1742] When a user wants to edit their own image, they launch the application on their device. The user clicks the "Upload Photo" button in the application and selects a photo from their gallery. After the user selects an image, the device displays a preview of the image and asks the user for confirmation. For the confirmed image, the application presents the user with transformation options (e.g., "Anime Character," "Celebrity," "Dog," "Cat," etc.). In addition, the device sends the user's facial recognition data and voice data to an emotion engine to estimate their emotion. The emotion engine suggests the optimal transformation option based on the estimated emotion. If the user accepts the optimal suggestion or selects another option, the device temporarily saves the selected image and transformation option and sends this data to the server.

[1743] The server receives the image and conversion options sent from the user device. It decodes the received data and separates the image from the conversion options. The server then selects the required deep learning model based on the specified conversion options, inputs the image data into the model, and generates a new image. The generated image data is then encoded and sent back to the user device.

[1744] Specific examples

[1745] For example, if a user wants to convert their selfie into an anime character style, the process would be as follows:

[1746] 1. The user uploads a selfie to the application and selects the desired conversion options.

[1747] 2. The device displays a preview of the selfie image and also sends the user's facial recognition data to the emotion engine.

[1748] 3. The emotion engine estimates the user's emotion (e.g., joy, surprise, etc.) and suggests "anime character" as the optimal conversion option.

[1749] 4. If the user accepts the suggestion, the device sends the selected selfie and the "Anime Character" conversion option to the server.

[1750] 5. The server receives the selfie and selects an anime character generation model.

[1751] 6. The server uses the model to transform the selfie into an anime character image and sends the resulting image back to the device.

[1752] 7. The device displays the returned image and asks the user to confirm it.

[1753] 8. The user reviews the image and selects the option to share it via social media or messaging apps.

[1754] Example of input prompt for generative AI model

[1755] "A user uploaded a selfie and selected the 'Anime Character' conversion option. Please convert this selfie to look like an anime character."

[1756] This system allows users to easily enjoy personalized image processing based on emotions, even without any special technical skills, and easily share the results with others.

[1757] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1758] Step 1:

[1759] The user launches an application on the device.

[1760] Input: The user taps on an app on their smartphone.

[1761] Output: The main screen of the application is displayed.

[1762] Specific behavior: The user taps the icon to launch the app, and the app displays the main screen.

[1763] Step 2:

[1764] A user uploads an image.

[1765] Input: User presses the "Upload Photo" button and selects a photo from the gallery.

[1766] Output: The selected image is displayed in the application.

[1767] Specific operation: The user presses a button, moves to an image selection screen, and selects an image such as a selfie from the gallery.

[1768] Step 3:

[1769] Your device will display a preview of the image and ask for confirmation.

[1770] Input: An image selected by the user.

[1771] Output: A preview of the image and a confirmation message asking "Are you sure this is the image?"

[1772] What happens: The device generates a preview of the image and displays a confirmation dialog.

[1773] Step 4:

[1774] The terminal presents conversion options to the user.

[1775] Input: User sees the image and answers "yes."

[1776] Output: You will see conversion options such as anime characters, celebrities, dogs, cats, etc.

[1777] Specific behavior: The device renders a UI to display the options.

[1778] Step 5:

[1779] The device sends facial recognition data and voice data to the emotion engine.

[1780] Input: User's facial recognition and voice data.

[1781] Output: Data sent to the emotion engine.

[1782] Specific operation: The device captures data using the camera and microphone and sends it to the emotion engine.

[1783] Step 6:

[1784] The device presents suggestions from the emotion engine to the user.

[1785] Input: Transformation option suggestions from the sentiment engine.

[1786] Output: The best conversion options based on the estimated sentiment are displayed to the user.

[1787] Specific operation: The device receives the response from the emotion engine and displays the suggestions.

[1788] Step 7:

[1789] The user selects a conversion option.

[1790] Input: User's choice of conversion options.

[1791] Output: The selected conversion options will be saved to your device.

[1792] What happens: The user taps an option and the device records the selection.

[1793] Step 8:

[1794] The device sends the selected image and conversion options to the server.

[1795] Input: Selected image and conversion options.

[1796] Output: The image and conversion options are sent to the server.

[1797] Specific operation: The terminal forms transmission data and transmits the data to the server through the network.

[1798] Step 9:

[1799] The server receives the image and conversion options.

[1800] Input: Image sent from the device and conversion options.

[1801] Output: Decoded result of received data.

[1802] What it does: The server decodes the received data and separates the image and conversion options.

[1803] Step 10:

[1804] The server selects the required deep learning model.

[1805] Input: Conversion options.

[1806] Output: The selected deep learning model.

[1807] What happens: The server looks up the appropriate model from the database or file system.

[1808] Step 11:

[1809] The server inputs the image into the model and generates a new image.

[1810] Input: Original image data, selected deep learning model.

[1811] Output: The new image generated.

[1812] Specific operation: The server inputs image data into the model, processes it, and generates a new image.

[1813] Step 12:

[1814] The server encodes the generated image and sends it back to the user's terminal.

[1815] Input: The new image generated.

[1816] Output: The encoded image data.

[1817] Specific operation: The server encodes the image in a timely manner and transmits it to the user terminal via the network.

[1818] Step 13:

[1819] The terminal displays the returned image and prompts the user to confirm it.

[1820] Input: The encoded image data returned from the server.

[1821] Output: The new image displayed.

[1822] What happens: The device decodes the image and displays it to the user for confirmation.

[1823] Step 14:

[1824] The user can view the image and share it via social media or messaging applications.

[1825] Input: User confirmation.

[1826] Output: Link or data for sharing.

[1827] What happens: The user clicks the "Share" button and selects the option to send the image to the social networking or messaging application of their choice.

[1828] (Application example 2)

[1829] 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."

[1830] Conventional image processing systems lack a means to provide personalized transformation options based on the user's emotions, making it difficult to create optimal content for the user. Furthermore, when users use images as virtual try-on simulations, they have difficulty selecting appropriate outfits and accessories, resulting in an unsatisfactory try-on experience.

[1831] The specification processing by the specification 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 acquiring the user's facial expression data and voice data and sending them to the emotion engine, means for proposing optimal conversion options based on the emotions estimated by the emotion engine, and means for applying a specific model from among multiple deep learning models based on the selected conversion options and suggestions from the emotion engine. This enables personalized image conversion and virtual try-on simulations that take the user's emotions into consideration.

[1832] A "user" is someone who uses the system to enhance their own images and review and share the transformed images.

[1833] "Images" are visual data such as photographs or illustrations that users upload to the system.

[1834] "Conversion options" refer to image processing styles and themes that users can select, including anime character style, animal style, celebrity style, etc.

[1835] "Facial expression data" is data used to capture the user's facial expressions and estimate their emotions based on that information.

[1836] "Voice data" is data that captures the user's vocalizations and is used to estimate emotions based on that voice information.

[1837] An "emotion engine" is an algorithm or program that analyzes facial expression data and voice data, estimates the user's emotions, and suggests optimal conversion options.

[1838] A "deep learning model" is a neural network that is trained with large amounts of data to transform input images into a specific style.

[1839] The "server" is the central processing unit of the system, a computer that processes images and conversion options sent by users, generates new images, and returns them.

[1840] "Terminal" refers to a device that a user uses to upload images, receive converted images, and view and share them, including smartphones, tablets, and PCs.

[1841] A "preview" is a temporary image that is displayed to allow a user to check the image they have uploaded.

[1842] A "social networking service" is an online platform used by users to share generated images, also known as an SNS.

[1843] A "messaging application" is a communication tool that users use to share generated images.

[1844] A "personalized image" is an image that is customized based on the user's feelings and preferences.

[1845] "Virtual try-on simulation" is a process in which a user virtually tries on outfits and accessories in images uploaded by the user.

[1846] The following describes an embodiment of the present invention. The system allows users to upload their own images, convert them into specific characters, people, animals, etc., and then review and share the generated images. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides more appropriate and personalized conversion options.

[1847] Hardware and Software

[1848] The main components of the system are:

[1849] User device: A smartphone, tablet, PC, etc. This is the device where users input and select images, and receive, display, and share the processed images. React Native and JavaScript are used to upload images and display previews.

[1850] Server: Receives images, processes them using deep learning models, generates new images, and sends them back to the user device. Can use cloud services such as AWS EC2.

[1851] Emotion engine: An algorithm that estimates emotions based on the user's facial expression and voice data and suggests optimal conversion options. Microsoft Azure's Emotion API can be used.

[1852] Deep learning models: Use frameworks such as TensorFlow to perform image transformation.

[1853] Processing flow

[1854] User device operation

[1855] 1. The user launches the application and clicks the "Upload Photo" button to select their own image.

[1856] 2. A preview of the image is displayed and the user confirms it.

[1857] 3. The user device acquires facial expression data and voice data and sends them to the emotion engine.

[1858] 4. The emotion engine estimates the emotion and presents the user with recommended transformation options (e.g., anime character style).

[1859] 5. If the user accepts the offer or selects another option, the data is sent to the server.

[1860] Server Processing

[1861] 1. The server receives the image and conversion options sent by the user.

[1862] 2. Select a deep learning model, input an image, and generate a new image.

[1863] 3. The generated image is sent back to the user's device.

[1864] Displaying the user terminal

[1865] 1. The generated image is displayed and the user confirms it.

[1866] 2. Users have the option to share the image on social media or messaging applications.

[1867] Specific examples

[1868] For example, if a user wants to convert their selfie into an anime character style, the process would be as follows:

[1869] 1. The user uploads a selfie to the application and selects the conversion option.

[1870] 2. The application displays a preview of the selfie image and sends the user's facial recognition data to the emotion engine.

[1871] 3. The emotion engine estimates the user's emotion (e.g., joy, surprise, etc.) and suggests "anime character" as the optimal conversion option.

[1872] 4. If the user accepts the suggestion, the device sends the selected selfie and the "Anime Character" conversion option to the server.

[1873] 5. The server receives the selfie and selects an anime character generation model.

[1874] 6. The server uses the model to transform the selfie into an anime character image and sends the resulting image back to the device.

[1875] 7. The device displays the returned image and asks the user to confirm it.

[1876] 8. The user reviews the image and selects the option to share it via social media or messaging apps.

[1877] Prompt Sentence Examples

[1878] Users upload an image and send facial expression data to an emotion engine API (e.g., EmotionAPI), which then suggests recommended try-on options to the user.

[1879] This allows users to easily enjoy emotion-based personalized image processing and virtual try-on simulations without any special technical skills, and the results can be easily shared with others.

[1880] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1881] Step 1:

[1882] The user launches the application on their device and clicks the "Photo Upload" button to select their own image. The image is picked from the device's gallery and displayed as a preview. The input is the user's image and the output is the preview image.

[1883] Step 2:

[1884] The device acquires the user's facial expression and voice data and sends them to the emotion engine. The facial expression data is captured using a camera, and the voice data is recorded using a microphone. The input is the facial expression data and voice data, and the output is the emotion estimation result.

[1885] Step 3:

[1886] The emotion engine analyzes the received facial expression and voice data to estimate the user's emotion. Based on the estimated emotion, it proposes optimal conversion options. The input is facial expression and voice data, and the output is the estimated emotion and recommended conversion options.

[1887] Step 4:

[1888] The device presents the recommendation from the emotion engine to the user. If the user accepts the recommendation or selects another conversion option, their selection information is temporarily saved. The input is the estimated emotion and the recommended conversion option, and the output is the user's selection information.

[1889] Step 5:

[1890] The terminal sends the selected conversion options and the image to the server. The input is the user's image and conversion options, and the output is the request data to the server.

[1891] Step 6:

[1892] The server receives and decodes the image and conversion options sent from the terminal. The input is the request data, and the output is the decoded image and conversion options.

[1893] Step 7:

[1894] The server selects the optimal deep learning model based on the suggestions from the emotion engine. The inputs are the transformation options and the suggestions from the emotion engine, and the output is the selected deep learning model.

[1895] Step 8:

[1896] The server processes the image using the selected deep learning model to generate a new image. The inputs are the decoded image and the deep learning model, and the output is the generated new image.

[1897] Step 9:

[1898] The server encodes the new image and sends it back to the user terminal. The input is the new image and the output is the encoded image data.

[1899] Step 10:

[1900] The terminal decodes the received image and displays it to the user. The input is the encoded image data and the output is the decoded image.

[1901] Step 11:

[1902] The user can view the new image and select the option to share it on social media or messaging applications. The input is the decoded image and the output is the shared content.

[1903] 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.

[1904] 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.

[1905] 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.

[1906] 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.

[1907] 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.

[1908] 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.

[1909] 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).

[1910] 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, motorcycles, and other devices, 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.

[1911] 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."

[1912] 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.

[1913] 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).

[1914] 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.

[1915] 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.

[1916] 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.

[1917] 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.

[1918] 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.

[1919] 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.

[1920] 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.

[1921] 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.

[1922] 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.

[1923] 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.

[1924] The following is further disclosed regarding the above embodiment.

[1925] (Claim 1)

[1926] a means for a user to input an image of themselves;

[1927] means for selecting transformation options to be applied to said image;

[1928] means for transmitting the image and selected conversion options to a server;

[1929] means for processing the image at the server using a deep learning model to generate a new image;

[1930] means for returning the generated new image to the user's terminal;

[1931] a means for users to review and share the new image;

[1932] A system including:

[1933] (Claim 2)

[1934] 2. The system of claim 1, wherein the server includes means for applying a particular model from among a plurality of deep learning models to the received image based on a selected transformation option.

[1935] (Claim 3)

[1936] 10. The system of claim 1, wherein the terminal includes means for sharing the new image via a plurality of social networking services or messaging applications in response to a user's sharing preferences.

[1937] "Example 1"

[1938] (Claim 1)

[1939] a means for a user to input an image of themselves;

[1940] means for selecting transformation options to be applied to said image;

[1941] means for transmitting the image and selected conversion options to a server;

[1942] means for transforming the image using a deep learning model at the server;

[1943] A means for generating a new image after the conversion process;

[1944] means for returning the generated new image to the user terminal;

[1945] a means for users to review and share the new image;

[1946] A system including:

[1947] (Claim 2)

[1948] 2. The system of claim 1, wherein the server includes means for applying a particular model from among a plurality of deep learning models to the received image based on a selected transformation option.

[1949] (Claim 3)

[1950] 10. The system of claim 1, wherein the terminal includes means for sharing the new image via a plurality of social networking services or messaging applications in response to a user's sharing preferences.

[1951] "Application Example 1"

[1952] (Claim 1)

[1953] a means for a user to input an image of themselves;

[1954] means for selecting transformation options to be applied to said image;

[1955] means for transmitting the image and selected conversion options to a server;

[1956] means for processing the image using a generative artificial intelligence model at the server to generate a new image;

[1957] means for returning the generated new image to the user's terminal;

[1958] means for generating custom video or motion pictures using the new images;

[1959] means for sharing the generated content via multiple information distribution services or messaging applications;

[1960] A system including:

[1961] (Claim 2)

[1962] 2. The system of claim 1, wherein the server includes means for applying a particular model from among a plurality of generative artificial intelligence models to the received image based on a selected transformation option.

[1963] (Claim 3)

[1964] 10. The system of claim 1, wherein the terminal includes means for sharing new images and videos via a plurality of information distribution services or messaging applications in response to a user's sharing preferences.

[1965] "Example 2: Combining Emotion Engines"

[1966] (Claim 1)

[1967] a means for a user to input an image of themselves;

[1968] means for selecting transformation options to be applied to said image;

[1969] means for transmitting the image and selected conversion options to a server;

[1970] means for processing the image at the server using a deep learning model to generate a new image;

[1971] means for returning the generated new image to the user's terminal;

[1972] a means for users to review and share the new image;

[1973] means including an emotion engine for recognizing an emotion of a user and suggesting conversion options based on the emotion;

[1974] A system including:

[1975] (Claim 2)

[1976] 2. The system of claim 1, wherein the server includes means for applying a particular model from among a plurality of deep learning models to the received image based on a selected transformation option.

[1977] (Claim 3)

[1978] 10. The system of claim 1, wherein the terminal includes means for sharing the new image via a plurality of social networking services or messaging applications in response to a user's sharing preferences.

[1979] "Application example 2 when combining emotion engines"

[1980] (Claim 1)

[1981] a means for a user to input an image of themselves;

[1982] means for selecting transformation options to be applied to said image;

[1983] A means for acquiring facial expression data and voice data of a user and transmitting the data to an emotion engine;

[1984] a means for the emotion engine to suggest optimal conversion options based on the estimated emotion;

[1985] means for transmitting the image and selected conversion options to a server;

[1986] means for processing the image at the server using a deep learning model to generate a new image;

[1987] means for returning the generated new image to the user's terminal;

[1988] a means for users to review and share the new image;

[1989] A system including:

[1990] (Claim 2)

[1991] 2. The system of claim 1, wherein the server includes means for applying a specific model from among a plurality of deep learning models to the received image based on selected transformation options and suggestions from the emotion engine.

[1992] (Claim 3)

[1993] 10. The system of claim 1, wherein the terminal includes means for sharing the new image via a plurality of social networking services or messaging applications in response to a user's sharing preferences. [Explanation of symbols]

[1994] 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. a means for a user to input an image of themselves; means for selecting transformation options to be applied to said image; means for transmitting the image and selected conversion options to a server; means for processing the image at the server using a deep learning model to generate a new image; means for returning the generated new image to the user's terminal; a means for users to review and share the new image; A system including:

2. The system of claim 1 , wherein the server includes means for applying a specific model from among a plurality of deep learning models to the received image based on a selected transformation option.

3. The system of claim 1 , wherein the terminal includes means for sharing the new image via a plurality of social networking services or messaging applications in response to a user's sharing preferences.

Images