System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving a photo of a child and a photo of a parent or grandparent; means for pre-processing the received photos and extracting facial feature points; means for formatting inputs to a generative AI model using the extracted feature points; means for generating a growth prediction photo of the child using the generative AI model; and means for outputting the generated growth prediction photo.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] Predicting a child's future appearance is an interesting topic for parents and grandparents, and has high entertainment value. However, there has not been a method for easily generating a child's growth projection photo. Therefore, there is a need for a simple means for predicting how a child will grow up in the future using photos of parents and grandparents. The present invention addresses these needs by providing a system for easily and effectively generating a child's growth projection photo. [Means for solving the problem]

[0005] The present invention is a system that includes a means for receiving photos of a child and photos of the parents or grandparents, a means for preprocessing the received photos and extracting facial features, a means for shaping input data to a generative AI model using the extracted features, a means for generating predicted growth photos of the child using the generative AI model, and a means for outputting the generated predicted growth photos. Specifically, the system further includes a means for sending the generated predicted growth photos to a user terminal, and the generative AI model learns the features of the parents or grandparents to provide more accurate predicted photos. This allows parents and grandparents to easily enjoy what their child will look like in the future.

[0006] "Child's photo" is image data of a child's current face.

[0007] "Photo of parent or grandparent" is image data of the face of the child's parent or grandparent.

[0008] The "receiving means" is a function for receiving photo data uploaded by a user onto the server.

[0009] "Preprocessing" refers to the process of adjusting the resolution of the photo data, trimming the face, and extracting facial features.

[0010] "Feature points" are data that indicate position information of the eyes, nose, mouth, etc. on a face.

[0011] A "generative AI model" is an artificial intelligence model that generates predicted photos of a child's growth based on input feature point data.

[0012] "Means of formatting" refers to the process of converting extracted feature point data into a format suitable for the generative AI model.

[0013] A "growth prediction photo" is a photo of a child's future face predicted using a generative AI model.

[0014] The "output means" is a function that provides the generated growth prediction photo in a format that can be used by the user.

[0015] A "user device" is a device (e.g., a smartphone or PC) on which a user uploads photos and checks the generated growth prediction photos.

[0016] "Learning" is the process of extracting features from photos of parents or grandparents, which the generative AI model uses to improve its prediction accuracy. [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 illustrating 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 generates predicted photos of a child's growth, and uses a generative AI model to predict and generate future photos of the child based on photos of the child and photos of the parents or grandparents entered by the user.

[0039] The system has the following main steps:

[0040] 1. Upload a photo

[0041] A user uses a device (such as a smartphone or computer) to upload photos of their child and parents or grandparents to a dedicated app or website.

[0042] The terminal transmits the uploaded photo data to the server.

[0043] 2. Receiving and saving photo data

[0044] The server receives the photo data sent from the terminal.

[0045] The server stores the received photo data in a file system or database.

[0046] 3. Data Preprocessing

[0047] The server reads the stored photo data.

[0048] The server uses an image processing library to standardize the resolution of each photo and crop the face area.

[0049] The server extracts facial feature points (e.g., the positions of the eyes, nose, and mouth) from the cropped photo.

[0050] 4. Training the generative AI model

[0051] The server formats the input data for the generative AI model based on the child's current feature points and those of the parents or grandparents.

[0052] The server inputs the post-surgery data into a generative AI model to generate a predicted photo. The generative AI model has previously learned the characteristics of the parents and grandparents, and uses this information to predict the child's future face.

[0053] 5. Output of generated results

[0054] The server transmits the generated growth prediction photo to the user's terminal.

[0055] The terminal displays the generated growth prediction photo.

[0056] Specific examples

[0057] For example, consider a case where a user uses a smartphone to upload current photos of their child and a photo of the parent to the system.

[0058] 1. Upload a photo

[0059] Users use the camera function on their smartphone to take photos of their child and parent and upload them through a dedicated app.

[0060] The device (smartphone) sends the captured photo to the server.

[0061] 2. Receiving and saving photo data

[0062] A server receives uploaded photo data of the child and parent.

[0063] The server stores the received photo data in a database.

[0064] 3. Data Preprocessing

[0065] The server loads the stored photo.

[0066] The server uses an open-source image processing library (e.g., OpenCV) to standardize the resolution of each photo and crop the face area.

[0067] The server extracts facial feature points and stores them in a database.

[0068] 4. Training the generative AI model

[0069] The server combines the facial feature points of the child with those of the parents to create input data for the generative AI model.

[0070] The server then feeds this input data to a generative AI model, which generates a photo of the child as they grow up. The generative AI model has already learned the characteristics of the parents and grandparents, and uses this information to predict what the child will look like in the future.

[0071] 5. Output of generated results

[0072] The server sends the generated growth prediction photo to the user's smartphone.

[0073] The device (smartphone) displays the generated growth prediction photos in a dedicated app, allowing users to check them and enjoy seeing what their child will look like in the future.

[0074] Through these steps, users can easily enjoy future photos of their children from the comfort of their own home. The predicted growth photos provided by the system are generated based on the characteristics of the parents or grandparents, resulting in realistic and interesting results.

[0075] The processing flow will be explained below.

[0076] Step 1:

[0077] The user uses the device to upload photos of their child and their parents or grandparents to a dedicated app or website. When the user clicks the upload button, the device sends the selected photo files to the server using an HTTP request.

[0078] Step 2:

[0079] The server receives the HTTP request and saves the sent photo data to the file system or database, records the path to the save destination, and adds the information to the database.

[0080] Step 3:

[0081] The server reads the stored photo data, standardizes the resolution of each photo using an image processing library (e.g., OpenCV), and runs a face detection algorithm to crop the face area.

[0082] Step 4:

[0083] The server extracts facial feature points (eyes, nose, and mouth) from the cropped face image using Dlib or a facial feature point detection algorithm, and stores the extracted feature point data in a database.

[0084] Step 5:

[0085] The server combines the child's feature point data with that of the parents or grandparents to create input data for the generative AI model. Data standardization (e.g., normalization using the mean and standard deviation) is also performed here.

[0086] Step 6:

[0087] The server inputs the formatted data into a generative AI model to generate a photo of the child's expected growth. This generative AI model is pre-trained on the characteristics of the parents and grandparents, and makes predictions based on this.

[0088] Step 7:

[0089] The server saves the generated growth prediction photo as an image file and converts it into a format that is easy for users to view (e.g., JPEG or PNG). After conversion, it generates an HTTP response and sends it to the user's device.

[0090] Step 8:

[0091] The device receives the generated photo data sent from the server. The received photo data is displayed through a dedicated application or web browser, allowing the user to check it. For example, a function is provided to display multiple age variations in slideshow format.

[0092] The above is a specific process flow for generating a photo of a child's expected growth.

[0093] Example 1

[0094] 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."

[0095] Conventional technologies have faced many challenges in accurately capturing individual facial features and providing users with results quickly and effectively when generating predicted images of a child's future face. In particular, the process of receiving photos, preprocessing, feature point extraction, inputting them into a generative model, and outputting the generated results is not performed smoothly, resulting in a poor user experience. There is a need for a system that solves this problem and allows users to easily and quickly obtain predicted photos of their child's growth.

[0096] 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.

[0097] In this invention, the server includes means for receiving a photo of the child and a photo of the parent or grandparent from a user terminal, means for resizing the received photo to a uniform resolution and cropping the face, means for extracting facial feature points from the cropped photo, means for shaping input data to a generative AI model using the extracted feature points, means for generating a photo of the child's predicted growth using the generative AI model, means for transmitting the generated photo of the predicted growth to the user terminal, and means for displaying the generated photo of the predicted growth on the user terminal. This makes it possible to realize a system that is easy for users to operate and allows them to quickly check results.

[0098] A "user terminal" is a computing device operated by a user, and is a general term for devices such as smartphones and personal computers used to perform tasks such as taking and uploading photos.

[0099] A "server" is a computer system responsible for receiving, storing, and processing data sent from user terminals.

[0100] "Receiving a photo" refers to the act of sending a photo of a child and photo data of a parent or grandparent from a user terminal to a server.

[0101] "Resolution resizing" refers to the process of changing the pixel count of an uploaded photo to unify its resolution to a specific standard size.

[0102] "Facial cropping" is an image processing technique that cuts out only the facial area from a photograph and removes the background and unnecessary parts.

[0103] "Feature point extraction" is the process of extracting specific positional information such as the eyes, nose, and mouth from a cropped facial photograph.

[0104] A "generative AI model" is an artificial intelligence model that has learned the facial features of parents and grandparents, and is an algorithm that uses this to predict and generate a child's future face.

[0105] "Input data formatting" refers to the process of preprocessing feature data to provide it in an appropriate format for a generative AI model.

[0106] A "growth prediction photo" is an image of a child's future face, predicted and generated using a generative AI model.

[0107] "Output" refers to the process of sending the generated growth prediction photo to a user terminal and displaying it to the user.

[0108] The present invention is a system for generating a child's growth forecast photo, which uses a generative AI model to predict the child's future face based on a user-provided photo of the child and photos of the parents or grandparents. The following describes an embodiment of the system in detail.

[0109] This system works in cooperation with a user device, a server, an image processing library, a generative AI model, and a database. Users take or upload photos using their device, such as a smartphone or PC, and the data is sent to the server. The server performs a series of preprocessing steps on the received photo data to extract feature points, and then generates a future facial image using the generative AI model.

[0110] The specific software and hardware used are as follows:

[0111] User terminal: A general-purpose computing device such as a smartphone or PC.

[0112] Server: A powerful computer system that stores and processes data.

[0113] Image processing libraries: Use open source libraries such as OpenCV and Dlib.

[0114] Generative AI models: Use pre-trained models using machine learning frameworks such as TensorFlow and PyTorch.

[0115] Database: A relational database such as MySQL or PostgreSQL to store photo and feature point data.

[0116] As a specific example of operation, consider a case where a user uses a smartphone to upload a current photo of the child and a photo of the parent to the system.

[0117] 1. Photo upload: Users use their smartphone's camera to take photos of their children and parents and upload them through a dedicated app.

[0118] 2. Receiving and storing photo data: The server receives the uploaded photo data of the child and parent and stores it in a database.

[0119] 3. Data preprocessing: The server reads the stored photos, standardizes the resolution of each photo using OpenCV, crops the face area, and extracts facial feature points and stores them in a database.

[0120] 4. Learning and prediction of the generative AI model: The server combines the facial feature points of the child and the parent to create input data for the generative AI model, which is then input into the generative AI model to generate a predicted photo of the child's growth.

[0121] 5. Output of generated results: The server sends the generated growth prediction photo to the user's smartphone, where it is displayed using a dedicated app on the device.

[0122] Examples of prompts include the following:

[0123] "Generate a future photo of the child's face using a photo of the child's current face and a photo of the parents' faces as input."

[0124] This allows users to easily enjoy future photos of their children from the comfort of their own home. The predicted growth photos provided by the system are generated based on the characteristics of the parents or grandparents, resulting in realistic and interesting results.

[0125] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0126] Step 1:

[0127] Upload a photo

[0128] A user takes photos of their child and their parents or grandparents and uploads these photos to a server via the Internet using a dedicated app.

[0129] Input: A photo of the child and a photo of the parent or grandparent (JPEG, PNG, or other format)

[0130] Specific operation: The user launches the dedicated app and takes a photo using the photo capture function, or selects an existing photo from the device's photo gallery. Then, the user presses the upload button, which generates an HTTP / HTTPS request to send the photo data to the server.

[0131] Step 2:

[0132] Receiving and saving photo data

[0133] The server receives the photo data sent from the user terminal, checks whether it is in the correct format, and then saves it.

[0134] Input: Photo data sent from the user device (HTTP / HTTPS request)

[0135] Output: Photo data stored in a database or file system

[0136] Specific operation: The server verifies the format and size of the received photo data and determines the appropriate storage path. The photo data is saved to the file system, and the reference path is stored in the database.

[0137] Step 3:

[0138] Data Preprocessing

[0139] The server reads the stored photo data and performs preprocessing to unify the resolution, crop faces, and extract feature points.

[0140] Input: Saved photo data

[0141] Output: Cropped face photo data and feature point data

[0142] What it does: The server uses OpenCV to resize the photo resolution (e.g., to 512x512 pixels), then uses the Dlib library to crop the face and extract the eye, nose, and mouth feature points from the face, which are then stored in a database.

[0143] Step 4:

[0144] Shaping input data for generative AI models

[0145] The server formats the feature data into a format suitable for input into a generative AI model.

[0146] Input: Feature point data for children and parents or grandparents

[0147] Output: Input data to the generative AI model

[0148] Specific operation: The server converts the feature point data into a Numpy array or similar format, and formats it in the format expected by the generative AI model. This includes specific arraying and data normalization.

[0149] Step 5:

[0150] Predictions from generative AI models

[0151] The server inputs the retouched input data into a generative AI model to generate a photo of the child's predicted growth.

[0152] Input: Formatted input data

[0153] Output: Generated growth prediction photo

[0154] How it works: The server inputs the formatted input data into the generative AI model and executes the model's inference process. The inference result is image data that predicts the child's future face. This image data is temporarily stored.

[0155] Step 6:

[0156] Output of generated results

[0157] The server transmits the generated growth prediction photo to the user terminal, which displays it.

[0158] Input: Generated growth prediction photo

[0159] Output: A photo of predicted growth displayed on the user's device

[0160] Specific operation: The server converts the generated photo into Base64 format or image file format and sends it to the user's device using the HTTP / HTTPS protocol. The photo received by the user's device is displayed in the image view of the dedicated app. The user can view it and enjoy the image of their future child.

[0161] (Application example 1)

[0162] 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."

[0163] In recent years, there has been an increasing demand for technology to predict children's growth, but current technology faces issues in terms of accuracy and convenience. In particular, there are few systems that can be easily used at home or used as a service in physical stores, and they do not meet the diverse needs of customers. There is a need for a system that can solve this problem and easily generate more accurate growth forecast photos.

[0164] 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.

[0165] In this invention, the server includes means for receiving photos of the child and photos of the parents or grandparents, means for preprocessing the received photos and extracting facial feature points, means for shaping input data to a generative AI model using the extracted feature points, means for generating predicted growth photos of the child using the generative AI model, means for outputting the generated predicted growth photos, and means for displaying the generated predicted growth photos on a customer's device via a dedicated app for the photo studio. This makes it possible to provide highly accurate predicted growth photos to customers not only at home but also as a service in physical stores.

[0166] "Child photo" is a current photo of the child that is used to make the growth prediction.

[0167] A "parent or grandparent photo" is a photo of a parent or grandparent that is relevant to the child in the growth prediction.

[0168] The "receiving means" is a means for receiving photo data from the user terminal to the server.

[0169] "Preprocessing" refers to performing initial processing such as adjusting the resolution of received photo data and trimming it.

[0170] "Facial feature points" are points that indicate specific parts of the face, such as the positions of the eyes, nose, and mouth.

[0171] A "generative AI model" is an artificial intelligence model that learns the characteristics of parents and grandparents in advance and generates predicted photos of a child's growth.

[0172] "Means for formatting input data" refers to means for arranging feature points into a format suitable for a generative AI model.

[0173] "Growth Prediction Photos" are photos of children's futures predicted using a generative AI model.

[0174] The "output means" is a means for displaying the generated growth prediction photograph to the user or customer.

[0175] A "photo studio dedicated app" is a mobile application developed to complement the services of a photo studio.

[0176] "Customer device" refers to an electronic device owned by the customer, such as a smartphone or tablet.

[0177] The present invention relates to a system for generating a photo of a child's future growth projection, and is implemented by the following method.

[0178] First, a user opens a dedicated app on a smartphone or tablet and uploads current photos of their child and photos of their parents or grandparents. The user's device then sends the uploaded photo data to a cloud server, which receives the photo data and automatically saves it.

[0179] Next, the cloud server preprocesses the received photo data. This preprocessing involves using an image processing library (e.g., OpenCV) to standardize the resolution of each photo and crop the facial area. It also performs processing to extract facial feature points (such as the positions of the eyes, nose, and mouth). The feature points are then extracted from the preprocessed data and formatted as input data for the generative AI model.

[0180] The cloud server uses a trained generative AI model (e.g., StyleGAN) to generate predicted photos of the child's growth based on the extracted feature points. Because the generative AI model has already learned the characteristics of the parents and grandparents, it can generate more realistic predicted photos.

[0181] The generated growth prediction photos are sent directly from the cloud server to the user's device via a dedicated app at the photo studio. Users can use the dedicated app to check the generated predicted photos and enjoy watching their child's growth. This system is also provided as a service at photo studios, so users can immediately receive highly accurate growth prediction photos at the photo studio.

[0182] As a concrete example, consider a photo gallery app where a user uploads a current photo of their child and a photo of their parents. Throughout this process, the following prompt is used: "Use the uploaded photos of the child and the parents to predict and generate a future photo of the child."

[0183] The system's components include devices such as smartphones and tablets, a cloud server, the image processing library OpenCV, and the generative AI model StyleGAN. This makes it possible to provide services at home or in photo studios, allowing users to easily generate and view photos of their children's growth predictions at any time.

[0184] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0185] Step 1:

[0186] The user uses a smartphone or tablet to upload a current photo of their child and a photo of their parents or grandparents to a dedicated app. The input is a photo of the child and a photo of the parents or grandparents. This photo data is uploaded and sent to a cloud server. The output is the photo data transferred to the cloud server.

[0187] Step 2:

[0188] The server saves the received photo data and stores it in a database. The input is the photo data sent by the user. Specifically, the server saves the photo data in a specific folder and stores the corresponding metadata in the database. The output is the saved photo data and its metadata.

[0189] Step 3:

[0190] The server uses an image processing library (OpenCV) to preprocess the photo data. The input is the stored photo data. Specifically, the server standardizes the resolution of the photos and crops the facial area. This preprocessing ensures accurate feature point extraction in the subsequent process. The output is cropped facial image data with a standardized resolution.

[0191] Step 4:

[0192] The server extracts facial feature points (such as the positions of the eyes, nose, and mouth) from the cropped face image. The input is the cropped face image data. Specifically, it uses OpenCV's face recognition algorithm to detect the feature points and saves them in a database. The output is the extracted facial feature point data.

[0193] Step 5:

[0194] The server uses the extracted feature point data to format it as input data for a generative AI model (StyleGAN). The input is facial feature point data. Specifically, it converts the feature point data into a format suitable for the AI ​​model. The output is formatted input data for the AI ​​model.

[0195] Step 6:

[0196] The server provides the formatted input data to the generative AI model to generate predicted photos of the child's growth. The input is the formatted AI model input data. Specifically, the generative AI model is executed to generate predicted photos of the child's future. The output is the generated predicted photos of the child's growth.

[0197] Step 7:

[0198] The server stores the generated growth prediction photos on a cloud server and sends them to the user's device via the photo studio's dedicated app. The input is the generated growth prediction photos. Specifically, the server converts the generated photos into an appropriate format for display on the user interface of the dedicated app and sends them to the user's device. The output is the growth prediction photos displayed on the user's device.

[0199] Through these steps, users can view highly accurate photos of their child's growth predictions through a dedicated app. This can also be used as a service in photo studios, improving customer satisfaction.

[0200] 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.

[0201] This invention combines an emotion engine with a system that generates photos of children's future growth, providing a more personalized experience. Based on photos of the child and parents or grandparents entered by the user, a generative AI model is used to predict and generate future photos of the child, and furthermore, the user's emotions are recognized, improving the user experience.

[0202] The main steps of the system are explained.

[0203] 1. Upload a photo

[0204] A user uses a device (such as a smartphone or computer) to upload photos of their child and parents or grandparents to a dedicated app or website.

[0205] The terminal transmits the uploaded photo data to the server.

[0206] 2. Receiving and saving photo data

[0207] The server receives the photo data sent from the terminal.

[0208] The server stores the received photo data in a file system or database.

[0209] 3. Data Preprocessing

[0210] The server reads the stored photo data.

[0211] The server uses an image processing library to standardize the resolution of each photo and crop the face area.

[0212] The server extracts facial feature points (e.g., the positions of the eyes, nose, and mouth) from the cropped photo.

[0213] 4. Training the generative AI model

[0214] The server formats the input data for the generative AI model based on the child's current feature points and those of the parents or grandparents.

[0215] The server inputs the post-surgery data into a generative AI model to generate a predicted photo. The generative AI model has previously learned the characteristics of the parents and grandparents, and uses this information to predict the child's future face.

[0216] 5. Output of generated results

[0217] The server transmits the generated growth prediction photo to the user's terminal.

[0218] The terminal displays the generated growth prediction photo.

[0219] 6. Use of Emotion Engines

[0220] The device uses a camera to capture the user's facial expressions while viewing photos, and the emotion engine analyzes the images to recognize the user's emotions, for example, whether the user is smiling, surprised, or expressing other emotions.

[0221] The emotion engine transmits the recognized emotion information to the server.

[0222] The server personalizes the generated growth prediction photos based on the received emotion information, providing results that meet the user's preferences, such as generating more photos of the ages that the user finds particularly exciting.

[0223] Specific examples

[0224] For example, consider a case where a user uses a smartphone to upload current photos of their child and a photo of the parent to the system.

[0225] 1. Upload a photo

[0226] Users use the camera function on their smartphone to take photos of their child and parent and upload them through a dedicated app.

[0227] The device (smartphone) sends the captured photo to the server.

[0228] 2. Receiving and saving photo data

[0229] A server receives uploaded photo data of the child and parent.

[0230] The server stores the received photo data in a database.

[0231] 3. Data Preprocessing

[0232] The server loads the stored photo.

[0233] The server uses an open-source image processing library (e.g., OpenCV) to standardize the resolution of each photo and crop the face area.

[0234] The server extracts facial feature points and stores them in a database.

[0235] 4. Training the generative AI model

[0236] The server combines the facial feature points of the child with those of the parents to create input data for the generative AI model.

[0237] The server then feeds this input data to a generative AI model, which generates a photo of the child as they grow up. The generative AI model has already learned the characteristics of the parents and grandparents, and uses this information to predict the child's future face.

[0238] 5. Output of generated results

[0239] The server sends the generated growth prediction photo to the user's smartphone.

[0240] The device (smartphone) displays the generated growth prediction photo using a dedicated app.

[0241] 6. Use of Emotion Engines

[0242] The device uses a camera to capture the user's facial expressions while viewing photos, and the emotion engine recognizes emotions from the facial expressions, for example, analyzing whether the user is smiling.

[0243] The emotion engine sends the recognized emotion to the server.

[0244] The server uses the emotional information to adjust the generation AI model for future use, or generates photos according to the user's preferences.

[0245] Through these steps, the present invention enables the generation of personalized child growth forecast photos for each user, providing greater entertainment value.The use of an emotion engine allows the system to be more precisely adjusted based on the user's reactions and emotions, providing optimal results for each individual user.

[0246] The processing flow will be explained below.

[0247] Step 1:

[0248] The user uses the device to upload photos of their child and their parents or grandparents to a dedicated app or website. When the user clicks the upload button, the device sends the selected photo files to the server using an HTTP request.

[0249] Step 2:

[0250] The server receives the HTTP request and saves the sent photo data to the file system or database, records the path to the save destination, and adds the information to the database.

[0251] Step 3:

[0252] The server reads the stored photo data, standardizes the resolution of each photo using an image processing library (e.g., OpenCV), and runs a face detection algorithm to crop the face area.

[0253] Step 4:

[0254] The server extracts facial feature points (eyes, nose, and mouth) from the cropped face image using Dlib or a facial feature point detection algorithm, and stores the extracted feature point data in a database.

[0255] Step 5:

[0256] The server combines the child's feature point data with that of the parents or grandparents to create input data for the generative AI model. Data standardization (e.g., normalization using the mean and standard deviation) is also performed here.

[0257] Step 6:

[0258] The server inputs the formatted data into a generative AI model to generate a photo of the child's expected growth. This generative AI model is pre-trained on the characteristics of the parents and grandparents, and makes predictions based on this.

[0259] Step 7:

[0260] The server saves the generated growth prediction photo as an image file and converts it into a format that is easy for users to view (e.g., JPEG or PNG). After conversion, it generates an HTTP response and sends it to the user's device.

[0261] Step 8:

[0262] The device receives the generated photo data sent from the server. The received photo data is displayed through a dedicated application or web browser, allowing the user to check it. For example, a function is provided to display multiple age variations in slideshow format.

[0263] Step 9:

[0264] The device uses a camera to capture the user's facial expressions while viewing photos, and the emotion engine analyzes the facial images to recognize the user's emotions, such as whether the user is smiling or surprised.

[0265] Step 10:

[0266] The emotion engine transmits the recognized emotion information to the server.

[0267] Step 11:

[0268] The server personalizes the generated growth prediction photos based on the received emotion information, providing results that meet the user's preferences, such as generating more photos of the ages that the user finds particularly exciting.

[0269] Step 12:

[0270] The server will adjust the generation AI model based on the emotional information from the next time onwards, so that it will generate predicted photos that better suit the user's preferences.

[0271] The above is the specific processing flow of the invention that combines an emotion engine that recognizes the user's emotions.

[0272] Example 2

[0273] 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."

[0274] Conventional systems that generate photos of children's growth predictions have had the problem of reducing the user experience because the generated photos do not necessarily reflect the emotions and preferences of individual users. In addition, the generated photos often have a cold, impersonal feel, making it difficult to feel close to the child.

[0275] 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.

[0276] In this invention, the server includes means for receiving photos of the child and photos of the parents or grandparents, means for preprocessing the received photos and extracting facial feature points, means for shaping input data to a generative AI model using the extracted feature points, means for generating predicted growth photos of the child using the generative AI model, means for outputting the generated predicted growth photos, means for capturing a user's facial expression and recognizing emotions, and means for personalizing the generated photos based on the recognized emotion information. This enables personalization according to the user's emotions, not only providing a higher user experience but also making the generated photos more familiar to the user.

[0277] "Children's photos" refers to image data that includes a child's face.

[0278] "Parent or grandparent photo" refers to image data that shows the face of a child's parent or grandparent.

[0279] The "receiving means" is a communication interface for receiving photo data from other devices (for example, an HTTP request via the Internet).

[0280] "Means for pre-processing and extracting facial features" refers to the process of analyzing photographic data using image processing technology to extract facial contours and features such as eyes, nose, and mouth.

[0281] "Means for formatting input data for a generative AI model" refers to the process of processing the extracted features into an appropriate format and preparing them as input to a generative AI model.

[0282] "Method of generating predicted photos of a child's growth using a generative AI model" refers to the process in which an AI algorithm uses shaped input data to predict a child's future face and generate it as an image.

[0283] The "means for outputting the generated growth prediction photograph" refers to a process for displaying, saving, or transmitting the generated image data to another device.

[0284] "Means for capturing the user's facial expressions and recognizing emotions" refers to the process of taking a picture of the user's face with a camera and analyzing the image to determine the user's emotions.

[0285] "Means for personalizing the generated photo based on recognized emotional information" refers to the process of adjusting the generated image data based on the user's emotional data to make it more in line with the user's preferences.

[0286] MODE FOR CARRYING OUT THE INVENTION

[0287] This invention combines an emotion engine with a system that generates photos of children's future growth, providing a more personalized experience. Based on photos of the child and parents or grandparents entered by the user, a generative AI model is used to predict and generate future photos of the child, and furthermore, the user's emotions are recognized, improving the user experience.

[0288] First, users upload photos of their child and their parents or grandparents through a dedicated app or website. Using a smartphone or computer, users can easily select, take, and upload photos by following the app's instructions. Specifically, the following hardware and software are required:

[0289] Hardware:

[0290] Smartphones, PCs, servers

[0291] Camera function (built into smartphones and computers)

[0292] software:

[0293] Dedicated app and website

[0294] Image processing library (e.g. OpenCV)

[0295] Generative AI models (e.g., implemented in TensorFlow or PyTorch)

[0296] Emotion engine (e.g. Microsoft Azure Emotion API)

[0297] When a photo is uploaded, the device sends it to the server. The server receives the photo data and stores it in a file system or database. The server then reads the stored photo data and uses an image processing library (e.g., OpenCV) to unify the resolution of each photo and crop the facial area. From the cropped photos, the server extracts facial feature points (e.g., the positions of the eyes, nose, and mouth).

[0298] Next, the server combines the facial feature points of the child with those of the parents or grandparents to create input data for the generative AI model. The resulting data is then input into the generative AI model to predict and generate the child's future face. The generative AI model has previously learned the features of the parents and grandparents, and predicts the child's future face based on this information.

[0299] The generated growth prediction photos are sent from the server to the user's device and displayed on the device. Users can view, comment on, and save the photos through the app.

[0300] Furthermore, the system uses an emotion engine to recognize the user's emotions. While the user is viewing photos, the device's camera captures the user's facial expressions, which are then analyzed by the emotion engine. The emotion engine identifies whether the user is smiling, surprised, etc., and sends this emotional information to the server. The server can then personalize the generated growth prediction photos based on the received emotional information. For example, it can adjust the system to generate more photos of the age at which the user is particularly excited.

[0301] Specific examples

[0302] For example, if a user uses a smartphone to upload a current photo of the child and a photo of the parent to the system:

[0303] 1. Upload a photo

[0304] Users take photos of their children and parents using the camera on their smartphones and upload them through a dedicated app.

[0305] The device (smartphone) sends the photos it has taken to the server.

[0306] 2. Receiving and saving photo data

[0307] The server receives the uploaded photo data of the child and the parent.

[0308] The server stores the received photo data in a database.

[0309] 3. Data Preprocessing

[0310] The server loads the stored photo.

[0311] The server uses an open source image processing library (e.g., OpenCV) to standardize the resolution of each photo and crop the face area.

[0312] The server extracts facial feature points and stores them in a database.

[0313] 4. Training the generative AI model

[0314] The server combines the child's facial feature points with the parent's to create input data for the generative AI model.

[0315] The server feeds this input data into a generative AI model to generate a photo of the child's predicted growth.

[0316] 5. Output of generated results

[0317] The server sends the generated growth forecast photo to the user's smartphone.

[0318] The device (smartphone) displays the generated growth prediction photos using a dedicated app.

[0319] 6. Use of Emotion Engines

[0320] The device uses a camera to capture the user's facial expressions while viewing photos, and the emotion engine analyzes the expressions.

[0321] The terminal uses an emotion engine to recognize emotions and transmits them to the server.

[0322] The server adjusts the generation AI model based on the emotional information for future generations, generating photos that suit the user's preferences.

[0323] This allows the present invention to provide users with personalized photos of their child's predicted growth, providing greater entertainment value.The use of an emotion engine allows the system to adjust based on the user's reactions and emotions, providing optimal results for each individual user.

[0324] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0325] Step 1:

[0326] Users access a dedicated app or website, select a photo of their child and a photo of their parents or grandparents, or take a new photo and press the upload button.

[0327] Input: User selects or takes a photo

[0328] Output: Selected or taken photo data

[0329] Specific operation: The user launches the dedicated app on their smartphone or computer and clicks the "Upload photo" button within the app. If using a camera, the user launches the camera function within the app and takes a new photo.

[0330] Step 2:

[0331] The device sends the selected photo to the server.

[0332] Input: Photo data selected or taken by the user

[0333] Output: Photo data sent to the server

[0334] What it does: The app sends the photos to the server as an HTTP POST request, with a progress bar indicating the upload is in progress.

[0335] Step 3:

[0336] The server receives the photo data sent from the device and stores it in a file system or database.

[0337] Input: Photo data sent from the device

[0338] Output: Photo data stored in a file system or database

[0339] Specific operation: The server receives the photo data and stores it in a specified folder in the file system (e.g., / var / www / html / uploads / ) or in a database.

[0340] Step 4:

[0341] The server reads the stored photo data and uses an image processing library to unify the resolution of each photo and crop the facial areas.

[0342] Input: Photo data stored in a file system or database

[0343] Output: Photo data with uniform resolution and cropped face area

[0344] What it does: The server uses the OpenCV library to standardize the photo resolution to 1080x1080 pixels, and then uses algorithms like Haar Cascade to crop the face and remove unnecessary background.

[0345] Step 5:

[0346] The server extracts facial feature points (e.g., the positions of the eyes, nose, and mouth) from the cropped photo.

[0347] Input: Cropped photo data

[0348] Output: Extracted facial feature points data

[0349] What it does: The server uses the Dlib library to extract 68 facial feature points from the cropped photo.

[0350] Step 6:

[0351] The server combines the child's facial feature points with those of the parents or grandparents to form input data for the generative AI model.

[0352] Input: Child's facial feature point data and parent or grandparent's facial feature point data

[0353] Output: Formatted input data for a generative AI model

[0354] Specific operation: The server concatenates the coordinates of facial feature points into a series of vectors and converts them into the input format for the generative AI model.

[0355] Step 7:

[0356] The server inputs the formatted data into a generative AI model to predict and generate the child's future face.

[0357] Input: Formatted input data

[0358] Output: Generated growth prediction photo

[0359] How it works: The server inputs data into a generative AI model built with TensorFlow and PyTorch, predicts the child's future face, and generates a new photo.

[0360] Step 8:

[0361] The server transmits the generated growth prediction photo to the terminal.

[0362] Input: Generated growth prediction photo

[0363] Output: Growth prediction photo sent to the device

[0364] Specific operation: The server converts the generated photo into a format such as JPEG and sends it to the user's device as an HTTP response.

[0365] Step 9:

[0366] The terminal displays the generated growth prediction photo to the user.

[0367] Input: Growth prediction photo sent from the server

[0368] Output: A photo of the predicted growth shown to the user

[0369] Specific operation: The device displays the received photo in an app or website, and when the user taps the image, it becomes full-screen and can be zoomed in and out.

[0370] Step 10:

[0371] The device uses a camera to capture the user's facial expressions while viewing photos, and the emotion engine analyzes the images to recognize the user's emotions.

[0372] Input: User facial expression image

[0373] Output: Emotion recognition result data

[0374] Specific operation: The device automatically activates the camera and takes photos at regular intervals. An emotion engine (e.g., Microsoft Azure Emotion API) is used to analyze the captured images and recognize the user's emotions.

[0375] Step 11:

[0376] The device transmits the recognized emotion data to the server.

[0377] Input: Emotion recognition result data

[0378] Output: Emotion data sent to the server

[0379] Specific operation: The device sends the recognized emotion data in JSON format to the server. Example: "Smile: 80%, Surprise: 20%".

[0380] Step 12:

[0381] The server personalizes the generated photo based on the received emotion information.

[0382] Input: Emotional information data

[0383] Output: Personalized growth forecast photo

[0384] Specific operation: The server analyzes the received emotional information, adjusts the generation AI model from the next time onwards, and generates photos that suit the user's preferences. Adjustments are made, such as generating more photos of the age at which the user is most smiling.

[0385] (Application example 2)

[0386] 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."

[0387] While conventional growth prediction photo generation systems can predict future facial features based on photos of children and parents, they lack a means to determine how satisfying the generated photos are to users. As a result, they are unable to fully meet user needs, resulting in a limited user experience. Furthermore, since there is no system that can provide personalized predicted photos, they are unable to provide uniform results.

[0388] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving photos of the child and photos of the parents or grandparents, means for preprocessing the received photos and extracting facial feature points, means for shaping input data to the generative AI model using the extracted feature points, means for generating predicted growth photos of the child using the generative AI model, means for outputting the predicted growth photos, means for recognizing the user's facial expression and analyzing the emotion, and means for personalizing the predicted growth photos based on the user's emotion. This makes it possible to provide predicted growth photos personalized in accordance with the user's emotion, significantly improving the satisfaction of the user experience.

[0389] "Means for receiving photos" refers to the method by which the system receives photos of the child and parent or grandparent from the digital device.

[0390] The "pre-processing means" is a method for performing image processing such as unifying the resolution of received photographs and trimming facial areas.

[0391] The "means for extracting facial feature points" is a method for obtaining position information of important facial parts (for example, eyes, nose, and mouth) from a cropped facial photograph.

[0392] "Means for formatting input data for generative AI models" refers to a method for converting extracted feature points into an appropriate format and preparing them so that the AI ​​model can read them.

[0393] The "growth prediction photo generation method" is a method that uses a generative AI model to create a photo of a child's future face from shaped input data.

[0394] The "means for outputting predicted photos" is a method for displaying or transmitting the generated growth prediction photos to the user.

[0395] The "emotion recognition means" is a method for capturing facial expressions with a camera when a user views a generated photo and analyzing the emotions.

[0396] The "photo personalization means" is a method for adjusting the generated growth prediction photo to suit the user's preferences based on the recognized user's emotions.

[0397] The "user terminal transmission means" is a method for transmitting the generated growth prediction photo to a device used by the user.

[0398] A "generative AI model" is an artificial intelligence model that predicts a child's future face based on the characteristics of parents and grandparents learned in the past.

[0399] This invention combines emotion recognition functionality with a system for generating photos of children's future growth, providing a more personalized user experience. The system uses the following hardware and software: an image processing library (e.g., OpenCV), an artificial intelligence (AI) model (e.g., TensorFlow), and an emotion recognition engine (e.g., EmotionEngine).

[0400] First, a user takes photos of their child and their parents or grandparents using their smartphone, and uploads these photos to a cloud server through a dedicated application. The server receives the uploaded photos and stores them.

[0401] The received photos are first preprocessed using image processing libraries such as OpenCV to standardize the resolution of the photos and crop the facial area, then extract key facial features and format this data so that it can be fed into the generative AI model.

[0402] The rectified feature data is then input into a generative AI model such as TensorFlow to generate a photo of the child's future face. The generated photo of the predicted growth is then sent back to the user's smartphone by the server.

[0403] When a user views the generated photo, their smartphone camera captures their facial expression, which is then analyzed by the Emotion Engine. The emotional information obtained as a result of the analysis is sent to the server, and the growth prediction photo is personalized and regenerated based on this emotional data.

[0404] For example, if the user is smiling, a growth projection photo that best matches that emotion is generated. By repeating this process, it is possible to provide more finely tuned personalized results.

[0405] As a concrete example, the following is an example of a prompt sentence for a generative AI model:

[0406] "Generate a future photo of a 10-year-old based on the given child and parent photos."

[0407] As described above, this system analyzes the user's emotions in real time and generates personalized growth prediction photos accordingly, thereby improving the user experience.

[0408] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0409] Step 1:

[0410] A user uses a smartphone to take photos of their child and their parents or grandparents, and then uploads these photos to a cloud server using a dedicated application. The input here is the photo file taken with the smartphone camera, and the output is the photo file saved on the cloud server. Specifically, when the user presses the "upload photo" button in the app, the device sends the photo data to the server.

[0411] Step 2:

[0412] The server receives and stores the photo data sent from the device. The input is the photo data sent from the device, and the output is the photo data stored in the server's storage. Specifically, the server's receiving API receives the data and stores it in a database.

[0413] Step 3:

[0414] The server preprocesses the stored photo data. The target of preprocessing is the stored photo data, and in this step, the resolution is unified and facial areas are cropped. The output is preprocessed image data. Specifically, the server uses the OpenCV library to unify the image resolution, detect and crop facial areas.

[0415] Step 4:

[0416] The server extracts facial feature points from the preprocessed photo data. The input is the preprocessed image data, and the output is facial feature point data. In this step, OpenCV is used to detect important points on the face, such as the eyes, nose, and mouth. Specific operations involve the use of image analysis algorithms.

[0417] Step 5:

[0418] The server formats the input data for the generative AI model based on the extracted feature points. The input here is facial feature point data, and the output is data formatted in a format that can be applied to the generative AI model. Specifically, the server converts the feature point data into a one-dimensional array or tensor format.

[0419] Step 6:

[0420] The server uses a generative AI model to generate predicted photos of the child's growth. The input is shaped facial feature point data, and the output is the generated predicted photo of the child's growth. Specifically, a generative AI model such as TensorFlow runs to generate predicted photos based on facial feature points.

[0421] Step 7:

[0422] The server sends the generated growth forecast photo to the user's terminal. The input is the generated growth forecast photo, and the output is the growth forecast photo displayed on the user's terminal. Specifically, the server sends the data using the HTTP protocol.

[0423] Step 8:

[0424] When a user views the generated growth prediction photo on their smartphone, the device's camera captures the user's facial expression, which is then analyzed by the emotion engine. The input is the user's facial image captured by the smartphone camera, and the output is the analyzed emotion data. Specifically, the Emotion Engine receives the facial expression image and identifies the emotion.

[0425] Step 9:

[0426] The server personalizes the growth prediction photo based on the analyzed emotional data. The input is the analyzed emotional data and the generated growth prediction photo, and the output is a specific growth prediction photo selected based on the user's emotions. Specifically, the server runs the generative AI model again according to the emotional data to regenerate a result that best suits the user's emotions.

[0427] This allows the user to view personalized growth prediction photos that match their emotions.

[0428] 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.

[0429] 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.

[0430] 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.

[0431] [Second embodiment]

[0432] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0433] 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.

[0434] 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).

[0435] 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.

[0436] 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.

[0437] 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).

[0438] 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.

[0439] 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.

[0440] 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.

[0441] 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.

[0442] 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.

[0443] 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."

[0444] This invention is a system that generates predicted photos of a child's growth, and uses a generative AI model to predict and generate future photos of the child based on photos of the child and photos of the parents or grandparents entered by the user.

[0445] The system has the following main steps:

[0446] 1. Upload a photo

[0447] A user uses a device (such as a smartphone or computer) to upload photos of their child and parents or grandparents to a dedicated app or website.

[0448] The terminal transmits the uploaded photo data to the server.

[0449] 2. Receiving and saving photo data

[0450] The server receives the photo data sent from the terminal.

[0451] The server stores the received photo data in a file system or database.

[0452] 3. Data Preprocessing

[0453] The server reads the stored photo data.

[0454] The server uses an image processing library to standardize the resolution of each photo and crop the face area.

[0455] The server extracts facial feature points (e.g., the positions of the eyes, nose, and mouth) from the cropped photo.

[0456] 4. Training the generative AI model

[0457] The server formats the input data for the generative AI model based on the child's current feature points and those of the parents or grandparents.

[0458] The server inputs the post-surgery data into a generative AI model to generate a predicted photo. The generative AI model has previously learned the characteristics of the parents and grandparents, and uses this information to predict the child's future face.

[0459] 5. Output of generated results

[0460] The server transmits the generated growth prediction photo to the user's terminal.

[0461] The terminal displays the generated growth prediction photo.

[0462] Specific examples

[0463] For example, consider a case where a user uses a smartphone to upload current photos of their child and a photo of the parent to the system.

[0464] 1. Upload a photo

[0465] Users use the camera function on their smartphone to take photos of their child and parent and upload them through a dedicated app.

[0466] The device (smartphone) sends the captured photo to the server.

[0467] 2. Receiving and saving photo data

[0468] A server receives uploaded photo data of the child and parent.

[0469] The server stores the received photo data in a database.

[0470] 3. Data Preprocessing

[0471] The server loads the stored photo.

[0472] The server uses an open-source image processing library (e.g., OpenCV) to standardize the resolution of each photo and crop the face area.

[0473] The server extracts facial feature points and stores them in a database.

[0474] 4. Training the generative AI model

[0475] The server combines the facial feature points of the child with those of the parents to create input data for the generative AI model.

[0476] The server then feeds this input data to a generative AI model, which generates a photo of the child as they grow up. The generative AI model has already learned the characteristics of the parents and grandparents, and uses this information to predict what the child will look like in the future.

[0477] 5. Output of generated results

[0478] The server sends the generated growth prediction photo to the user's smartphone.

[0479] The device (smartphone) displays the generated growth prediction photos in a dedicated app, allowing users to check them and enjoy seeing what their child will look like in the future.

[0480] Through these steps, users can easily enjoy future photos of their children from the comfort of their own home. The predicted growth photos provided by the system are generated based on the characteristics of the parents or grandparents, resulting in realistic and interesting results.

[0481] The processing flow will be explained below.

[0482] Step 1:

[0483] The user uses the device to upload photos of their child and their parents or grandparents to a dedicated app or website. When the user clicks the upload button, the device sends the selected photo files to the server using an HTTP request.

[0484] Step 2:

[0485] The server receives the HTTP request and saves the sent photo data to the file system or database, records the path to the save destination, and adds the information to the database.

[0486] Step 3:

[0487] The server reads the stored photo data, standardizes the resolution of each photo using an image processing library (e.g., OpenCV), and runs a face detection algorithm to crop the face area.

[0488] Step 4:

[0489] The server extracts facial feature points (eyes, nose, and mouth) from the cropped face image using Dlib or a facial feature point detection algorithm, and stores the extracted feature point data in a database.

[0490] Step 5:

[0491] The server combines the child's feature point data with that of the parents or grandparents to create input data for the generative AI model. Data standardization (e.g., normalization using the mean and standard deviation) is also performed here.

[0492] Step 6:

[0493] The server inputs the formatted data into a generative AI model to generate a photo of the child's expected growth. This generative AI model is pre-trained on the characteristics of the parents and grandparents, and makes predictions based on this.

[0494] Step 7:

[0495] The server saves the generated growth prediction photo as an image file and converts it into a format that is easy for users to view (e.g., JPEG or PNG). After conversion, it generates an HTTP response and sends it to the user's device.

[0496] Step 8:

[0497] The device receives the generated photo data sent from the server. The received photo data is displayed through a dedicated application or web browser, allowing the user to check it. For example, a function is provided to display multiple age variations in slideshow format.

[0498] The above is a specific process flow for generating a photo of a child's expected growth.

[0499] Example 1

[0500] 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."

[0501] Conventional technologies have faced many challenges in accurately capturing individual facial features and providing users with results quickly and effectively when generating predicted images of a child's future face. In particular, the process of receiving photos, preprocessing, feature point extraction, inputting them into a generative model, and outputting the generated results is not performed smoothly, resulting in a poor user experience. There is a need for a system that solves this problem and allows users to easily and quickly obtain predicted photos of their child's growth.

[0502] 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.

[0503] In this invention, the server includes means for receiving a photo of the child and a photo of the parent or grandparent from a user terminal, means for resizing the received photo to a uniform resolution and cropping the face, means for extracting facial feature points from the cropped photo, means for shaping input data to a generative AI model using the extracted feature points, means for generating a photo of the child's predicted growth using the generative AI model, means for transmitting the generated photo of the predicted growth to the user terminal, and means for displaying the generated photo of the predicted growth on the user terminal. This makes it possible to realize a system that is easy for users to operate and allows them to quickly check results.

[0504] A "user terminal" is a computing device operated by a user, and is a general term for devices such as smartphones and personal computers used to perform tasks such as taking and uploading photos.

[0505] A "server" is a computer system responsible for receiving, storing, and processing data sent from user terminals.

[0506] "Receiving a photo" refers to the act of sending a photo of a child and photo data of a parent or grandparent from a user terminal to a server.

[0507] "Resolution resizing" refers to the process of changing the pixel count of an uploaded photo to unify its resolution to a specific standard size.

[0508] "Facial cropping" is an image processing technique that cuts out only the facial area from a photograph and removes the background and unnecessary parts.

[0509] "Feature point extraction" is the process of extracting specific positional information such as the eyes, nose, and mouth from a cropped facial photograph.

[0510] A "generative AI model" is an artificial intelligence model that has learned the facial features of parents and grandparents, and is an algorithm that uses this to predict and generate a child's future face.

[0511] "Input data formatting" refers to the process of preprocessing feature data to provide it in an appropriate format for a generative AI model.

[0512] A "growth prediction photo" is an image of a child's future face, predicted and generated using a generative AI model.

[0513] "Output" refers to the process of sending the generated growth prediction photo to a user terminal and displaying it to the user.

[0514] The present invention is a system for generating a child's growth forecast photo, which uses a generative AI model to predict the child's future face based on a user-provided photo of the child and photos of the parents or grandparents. The following describes an embodiment of the system in detail.

[0515] This system works in cooperation with a user device, a server, an image processing library, a generative AI model, and a database. Users take or upload photos using their device, such as a smartphone or PC, and the data is sent to the server. The server performs a series of preprocessing steps on the received photo data to extract feature points, and then generates a future facial image using the generative AI model.

[0516] The specific software and hardware used are as follows:

[0517] User terminal: A general-purpose computing device such as a smartphone or PC.

[0518] Server: A powerful computer system that stores and processes data.

[0519] Image processing libraries: Use open source libraries such as OpenCV and Dlib.

[0520] Generative AI models: Use pre-trained models using machine learning frameworks such as TensorFlow and PyTorch.

[0521] Database: A relational database such as MySQL or PostgreSQL to store photo and feature point data.

[0522] As a specific example of operation, consider a case where a user uses a smartphone to upload a current photo of the child and a photo of the parent to the system.

[0523] 1. Photo upload: Users use their smartphone's camera to take photos of their children and parents and upload them through a dedicated app.

[0524] 2. Receiving and storing photo data: The server receives the uploaded photo data of the child and parent and stores it in a database.

[0525] 3. Data preprocessing: The server reads the stored photos, standardizes the resolution of each photo using OpenCV, crops the face area, and extracts facial feature points and stores them in a database.

[0526] 4. Learning and prediction of the generative AI model: The server combines the facial feature points of the child and the parent to create input data for the generative AI model, which is then input into the generative AI model to generate a predicted photo of the child's growth.

[0527] 5. Output of generated results: The server sends the generated growth prediction photo to the user's smartphone, where it is displayed using a dedicated app on the device.

[0528] Examples of prompts include the following:

[0529] "Generate a future photo of the child's face using a photo of the child's current face and a photo of the parents' faces as input."

[0530] This allows users to easily enjoy future photos of their children from the comfort of their own home. The predicted growth photos provided by the system are generated based on the characteristics of the parents or grandparents, resulting in realistic and interesting results.

[0531] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0532] Step 1:

[0533] Upload a photo

[0534] A user takes photos of their child and their parents or grandparents and uploads these photos to a server via the Internet using a dedicated app.

[0535] Input: A photo of the child and a photo of the parent or grandparent (JPEG, PNG, or other format)

[0536] Specific operation: The user launches the dedicated app and takes a photo using the photo capture function, or selects an existing photo from the device's photo gallery. Then, the user presses the upload button, which generates an HTTP / HTTPS request to send the photo data to the server.

[0537] Step 2:

[0538] Receiving and saving photo data

[0539] The server receives the photo data sent from the user terminal, checks whether it is in the correct format, and then saves it.

[0540] Input: Photo data sent from the user device (HTTP / HTTPS request)

[0541] Output: Photo data stored in a database or file system

[0542] Specific operation: The server verifies the format and size of the received photo data and determines the appropriate storage path. The photo data is saved to the file system, and the reference path is stored in the database.

[0543] Step 3:

[0544] Data Preprocessing

[0545] The server reads the stored photo data and performs preprocessing to unify the resolution, crop faces, and extract feature points.

[0546] Input: Saved photo data

[0547] Output: Cropped face photo data and feature point data

[0548] What it does: The server uses OpenCV to resize the photo resolution (e.g., to 512x512 pixels), then uses the Dlib library to crop the face and extract the eye, nose, and mouth feature points from the face, which are then stored in a database.

[0549] Step 4:

[0550] Shaping input data for generative AI models

[0551] The server formats the feature data into a format suitable for input into a generative AI model.

[0552] Input: Feature point data for children and parents or grandparents

[0553] Output: Input data to the generative AI model

[0554] Specific operation: The server converts the feature point data into a Numpy array or similar format, and formats it in the format expected by the generative AI model. This includes specific arraying and data normalization.

[0555] Step 5:

[0556] Predictions from generative AI models

[0557] The server inputs the retouched input data into a generative AI model to generate a photo of the child's predicted growth.

[0558] Input: Formatted input data

[0559] Output: Generated growth prediction photo

[0560] How it works: The server inputs the formatted input data into the generative AI model and executes the model's inference process. The inference result is image data that predicts the child's future face. This image data is temporarily stored.

[0561] Step 6:

[0562] Output of generated results

[0563] The server transmits the generated growth prediction photo to the user terminal, which displays it.

[0564] Input: Generated growth prediction photo

[0565] Output: A photo of predicted growth displayed on the user's device

[0566] Specific operation: The server converts the generated photo into Base64 format or image file format and sends it to the user's device using the HTTP / HTTPS protocol. The photo received by the user's device is displayed in the image view of the dedicated app. The user can view it and enjoy the image of their future child.

[0567] (Application example 1)

[0568] 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."

[0569] In recent years, there has been an increasing demand for technology to predict children's growth, but current technology faces issues in terms of accuracy and convenience. In particular, there are few systems that can be easily used at home or used as a service in physical stores, and they do not meet the diverse needs of customers. There is a need for a system that can solve this problem and easily generate more accurate growth forecast photos.

[0570] 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.

[0571] In this invention, the server includes means for receiving photos of the child and photos of the parents or grandparents, means for preprocessing the received photos and extracting facial feature points, means for shaping input data to a generative AI model using the extracted feature points, means for generating predicted growth photos of the child using the generative AI model, means for outputting the generated predicted growth photos, and means for displaying the generated predicted growth photos on a customer's device via a dedicated app for the photo studio. This makes it possible to provide highly accurate predicted growth photos to customers not only at home but also as a service in physical stores.

[0572] "Child photo" is a current photo of the child that is used to make the growth prediction.

[0573] A "parent or grandparent photo" is a photo of a parent or grandparent that is relevant to the child in the growth prediction.

[0574] The "receiving means" is a means for receiving photo data from the user terminal to the server.

[0575] "Preprocessing" refers to performing initial processing such as adjusting the resolution of received photo data and trimming it.

[0576] "Facial feature points" are points that indicate specific parts of the face, such as the positions of the eyes, nose, and mouth.

[0577] A "generative AI model" is an artificial intelligence model that learns the characteristics of parents and grandparents in advance and generates predicted photos of a child's growth.

[0578] "Means for formatting input data" refers to means for arranging feature points into a format suitable for a generative AI model.

[0579] "Growth Prediction Photos" are photos of children's futures predicted using a generative AI model.

[0580] The "output means" is a means for displaying the generated growth prediction photograph to the user or customer.

[0581] A "photo studio dedicated app" is a mobile application developed to complement the services of a photo studio.

[0582] "Customer device" refers to an electronic device owned by the customer, such as a smartphone or tablet.

[0583] The present invention relates to a system for generating a photo of a child's future growth projection, and is implemented by the following method.

[0584] First, a user opens a dedicated app on a smartphone or tablet and uploads current photos of their child and photos of their parents or grandparents. The user's device then sends the uploaded photo data to a cloud server, which receives the photo data and automatically saves it.

[0585] Next, the cloud server preprocesses the received photo data. This preprocessing involves using an image processing library (e.g., OpenCV) to standardize the resolution of each photo and crop the facial area. It also performs processing to extract facial feature points (such as the positions of the eyes, nose, and mouth). The feature points are then extracted from the preprocessed data and formatted as input data for the generative AI model.

[0586] The cloud server uses a trained generative AI model (e.g., StyleGAN) to generate predicted photos of the child's growth based on the extracted feature points. Because the generative AI model has already learned the characteristics of the parents and grandparents, it can generate more realistic predicted photos.

[0587] The generated growth prediction photos are sent directly from the cloud server to the user's device via a dedicated app at the photo studio. Users can use the dedicated app to check the generated predicted photos and enjoy watching their child's growth. This system is also provided as a service at photo studios, so users can immediately receive highly accurate growth prediction photos at the photo studio.

[0588] As a concrete example, consider a photo gallery app where a user uploads a current photo of their child and a photo of their parents. Throughout this process, the following prompt is used: "Use the uploaded photos of the child and the parents to predict and generate a future photo of the child."

[0589] The system's components include devices such as smartphones and tablets, a cloud server, the image processing library OpenCV, and the generative AI model StyleGAN. This makes it possible to provide services at home or in photo studios, allowing users to easily generate and view photos of their children's growth predictions at any time.

[0590] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0591] Step 1:

[0592] The user uses a smartphone or tablet to upload a current photo of their child and a photo of their parents or grandparents to a dedicated app. The input is a photo of the child and a photo of the parents or grandparents. This photo data is uploaded and sent to a cloud server. The output is the photo data transferred to the cloud server.

[0593] Step 2:

[0594] The server saves the received photo data and stores it in a database. The input is the photo data sent by the user. Specifically, the server saves the photo data in a specific folder and stores the corresponding metadata in the database. The output is the saved photo data and its metadata.

[0595] Step 3:

[0596] The server uses an image processing library (OpenCV) to preprocess the photo data. The input is the stored photo data. Specifically, the server standardizes the resolution of the photos and crops the facial area. This preprocessing ensures accurate feature point extraction in the subsequent process. The output is cropped facial image data with a standardized resolution.

[0597] Step 4:

[0598] The server extracts facial feature points (such as the positions of the eyes, nose, and mouth) from the cropped face image. The input is the cropped face image data. Specifically, it uses OpenCV's face recognition algorithm to detect the feature points and saves them in a database. The output is the extracted facial feature point data.

[0599] Step 5:

[0600] The server uses the extracted feature point data to format it as input data for a generative AI model (StyleGAN). The input is facial feature point data. Specifically, it converts the feature point data into a format suitable for the AI ​​model. The output is formatted input data for the AI ​​model.

[0601] Step 6:

[0602] The server provides the formatted input data to the generative AI model to generate predicted photos of the child's growth. The input is the formatted AI model input data. Specifically, the generative AI model is executed to generate predicted photos of the child's future. The output is the generated predicted photos of the child's growth.

[0603] Step 7:

[0604] The server stores the generated growth prediction photos on a cloud server and sends them to the user's device via the photo studio's dedicated app. The input is the generated growth prediction photos. Specifically, the server converts the generated photos into an appropriate format for display on the user interface of the dedicated app and sends them to the user's device. The output is the growth prediction photos displayed on the user's device.

[0605] Through these steps, users can view highly accurate photos of their child's growth predictions through a dedicated app. This can also be used as a service in photo studios, improving customer satisfaction.

[0606] 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.

[0607] This invention combines an emotion engine with a system that generates photos of children's future growth, providing a more personalized experience. Based on photos of the child and parents or grandparents entered by the user, a generative AI model is used to predict and generate future photos of the child, and furthermore, the user's emotions are recognized, improving the user experience.

[0608] The main steps of the system are explained.

[0609] 1. Upload a photo

[0610] A user uses a device (such as a smartphone or computer) to upload photos of their child and parents or grandparents to a dedicated app or website.

[0611] The terminal transmits the uploaded photo data to the server.

[0612] 2. Receiving and saving photo data

[0613] The server receives the photo data sent from the terminal.

[0614] The server stores the received photo data in a file system or database.

[0615] 3. Data Preprocessing

[0616] The server reads the stored photo data.

[0617] The server uses an image processing library to standardize the resolution of each photo and crop the face area.

[0618] The server extracts facial feature points (e.g., the positions of the eyes, nose, and mouth) from the cropped photo.

[0619] 4. Training the generative AI model

[0620] The server formats the input data for the generative AI model based on the child's current feature points and those of the parents or grandparents.

[0621] The server inputs the post-surgery data into a generative AI model to generate a predicted photo. The generative AI model has previously learned the characteristics of the parents and grandparents, and uses this information to predict the child's future face.

[0622] 5. Output of generated results

[0623] The server transmits the generated growth prediction photo to the user's terminal.

[0624] The terminal displays the generated growth prediction photo.

[0625] 6. Use of Emotion Engines

[0626] The device uses a camera to capture the user's facial expressions while viewing photos, and the emotion engine analyzes the images to recognize the user's emotions, for example, whether the user is smiling, surprised, or expressing other emotions.

[0627] The emotion engine transmits the recognized emotion information to the server.

[0628] The server personalizes the generated growth prediction photos based on the received emotion information, providing results that meet the user's preferences, such as generating more photos of the ages that the user finds particularly exciting.

[0629] Specific examples

[0630] For example, consider a case where a user uses a smartphone to upload current photos of their child and a photo of the parent to the system.

[0631] 1. Upload a photo

[0632] Users use the camera function on their smartphone to take photos of their child and parent and upload them through a dedicated app.

[0633] The device (smartphone) sends the captured photo to the server.

[0634] 2. Receiving and saving photo data

[0635] A server receives uploaded photo data of the child and parent.

[0636] The server stores the received photo data in a database.

[0637] 3. Data Preprocessing

[0638] The server loads the stored photo.

[0639] The server uses an open-source image processing library (e.g., OpenCV) to standardize the resolution of each photo and crop the face area.

[0640] The server extracts facial feature points and stores them in a database.

[0641] 4. Training the generative AI model

[0642] The server combines the facial feature points of the child with those of the parents to create input data for the generative AI model.

[0643] The server then feeds this input data to a generative AI model, which generates a photo of the child as they grow up. The generative AI model has already learned the characteristics of the parents and grandparents, and uses this information to predict the child's future face.

[0644] 5. Output of generated results

[0645] The server sends the generated growth prediction photo to the user's smartphone.

[0646] The device (smartphone) displays the generated growth prediction photo using a dedicated app.

[0647] 6. Use of Emotion Engines

[0648] The device uses a camera to capture the user's facial expressions while viewing photos, and the emotion engine recognizes emotions from the facial expressions, for example, analyzing whether the user is smiling.

[0649] The emotion engine sends the recognized emotion to the server.

[0650] The server uses the emotional information to adjust the generation AI model for future use, or generates photos according to the user's preferences.

[0651] Through these steps, the present invention enables the generation of personalized child growth forecast photos for each user, providing greater entertainment value.The use of an emotion engine allows the system to be more precisely adjusted based on the user's reactions and emotions, providing optimal results for each individual user.

[0652] The processing flow will be explained below.

[0653] Step 1:

[0654] The user uses the device to upload photos of their child and their parents or grandparents to a dedicated app or website. When the user clicks the upload button, the device sends the selected photo files to the server using an HTTP request.

[0655] Step 2:

[0656] The server receives the HTTP request and saves the sent photo data to the file system or database, records the path to the save destination, and adds the information to the database.

[0657] Step 3:

[0658] The server reads the stored photo data, standardizes the resolution of each photo using an image processing library (e.g., OpenCV), and runs a face detection algorithm to crop the face area.

[0659] Step 4:

[0660] The server extracts facial feature points (eyes, nose, and mouth) from the cropped face image using Dlib or a facial feature point detection algorithm, and stores the extracted feature point data in a database.

[0661] Step 5:

[0662] The server combines the child's feature point data with that of the parents or grandparents to create input data for the generative AI model. Data standardization (e.g., normalization using the mean and standard deviation) is also performed here.

[0663] Step 6:

[0664] The server inputs the formatted data into a generative AI model to generate a photo of the child's expected growth. This generative AI model is pre-trained on the characteristics of the parents and grandparents, and makes predictions based on this.

[0665] Step 7:

[0666] The server saves the generated growth prediction photo as an image file and converts it into a format that is easy for users to view (e.g., JPEG or PNG). After conversion, it generates an HTTP response and sends it to the user's device.

[0667] Step 8:

[0668] The device receives the generated photo data sent from the server. The received photo data is displayed through a dedicated application or web browser, allowing the user to check it. For example, a function is provided to display multiple age variations in slideshow format.

[0669] Step 9:

[0670] The device uses a camera to capture the user's facial expressions while viewing photos, and the emotion engine analyzes the facial images to recognize the user's emotions, such as whether the user is smiling or surprised.

[0671] Step 10:

[0672] The emotion engine transmits the recognized emotion information to the server.

[0673] Step 11:

[0674] The server personalizes the generated growth prediction photos based on the received emotion information, providing results that meet the user's preferences, such as generating more photos of the ages that the user finds particularly exciting.

[0675] Step 12:

[0676] The server will adjust the generation AI model based on the emotional information from the next time onwards, so that it will generate predicted photos that better suit the user's preferences.

[0677] The above is the specific processing flow of the invention that combines an emotion engine that recognizes the user's emotions.

[0678] Example 2

[0679] 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."

[0680] Conventional systems that generate photos of children's growth predictions have had the problem of reducing the user experience because the generated photos do not necessarily reflect the emotions and preferences of individual users. In addition, the generated photos often have a cold, impersonal feel, making it difficult to feel close to the child.

[0681] 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.

[0682] In this invention, the server includes means for receiving photos of the child and photos of the parents or grandparents, means for preprocessing the received photos and extracting facial feature points, means for shaping input data to a generative AI model using the extracted feature points, means for generating predicted growth photos of the child using the generative AI model, means for outputting the generated predicted growth photos, means for capturing a user's facial expression and recognizing emotions, and means for personalizing the generated photos based on the recognized emotion information. This enables personalization according to the user's emotions, not only providing a higher user experience but also making the generated photos more familiar to the user.

[0683] "Children's photos" refers to image data that includes a child's face.

[0684] "Parent or grandparent photo" refers to image data that shows the face of a child's parent or grandparent.

[0685] The "receiving means" is a communication interface for receiving photo data from other devices (for example, an HTTP request via the Internet).

[0686] "Means for pre-processing and extracting facial features" refers to the process of analyzing photographic data using image processing technology to extract facial contours and features such as eyes, nose, and mouth.

[0687] "Means for formatting input data for a generative AI model" refers to the process of processing the extracted features into an appropriate format and preparing them as input to a generative AI model.

[0688] "Method of generating predicted photos of a child's growth using a generative AI model" refers to the process in which an AI algorithm uses shaped input data to predict a child's future face and generate it as an image.

[0689] The "means for outputting the generated growth prediction photograph" refers to a process for displaying, saving, or transmitting the generated image data to another device.

[0690] "Means for capturing the user's facial expressions and recognizing emotions" refers to the process of taking a picture of the user's face with a camera and analyzing the image to determine the user's emotions.

[0691] "Means for personalizing the generated photo based on recognized emotional information" refers to the process of adjusting the generated image data based on the user's emotional data to make it more in line with the user's preferences.

[0692] MODE FOR CARRYING OUT THE INVENTION

[0693] This invention combines an emotion engine with a system that generates photos of children's future growth, providing a more personalized experience. Based on photos of the child and parents or grandparents entered by the user, a generative AI model is used to predict and generate future photos of the child, and furthermore, the user's emotions are recognized, improving the user experience.

[0694] First, users upload photos of their child and their parents or grandparents through a dedicated app or website. Using a smartphone or computer, users can easily select, take, and upload photos by following the app's instructions. Specifically, the following hardware and software are required:

[0695] Hardware:

[0696] Smartphones, PCs, servers

[0697] Camera function (built into smartphones and computers)

[0698] software:

[0699] Dedicated app and website

[0700] Image processing library (e.g. OpenCV)

[0701] Generative AI models (e.g., implemented in TensorFlow or PyTorch)

[0702] Emotion engine (e.g. Microsoft Azure Emotion API)

[0703] When a photo is uploaded, the device sends it to the server. The server receives the photo data and stores it in a file system or database. The server then reads the stored photo data and uses an image processing library (e.g., OpenCV) to unify the resolution of each photo and crop the facial area. From the cropped photos, the server extracts facial feature points (e.g., the positions of the eyes, nose, and mouth).

[0704] Next, the server combines the facial feature points of the child with those of the parents or grandparents to create input data for the generative AI model. The resulting data is then input into the generative AI model to predict and generate the child's future face. The generative AI model has previously learned the features of the parents and grandparents, and predicts the child's future face based on this information.

[0705] The generated growth prediction photos are sent from the server to the user's device and displayed on the device. Users can view, comment on, and save the photos through the app.

[0706] Furthermore, the system uses an emotion engine to recognize the user's emotions. While the user is viewing photos, the device's camera captures the user's facial expressions, which are then analyzed by the emotion engine. The emotion engine identifies whether the user is smiling, surprised, etc., and sends this emotional information to the server. The server can then personalize the generated growth prediction photos based on the received emotional information. For example, it can adjust the system to generate more photos of the age at which the user is particularly excited.

[0707] Specific examples

[0708] For example, if a user uses a smartphone to upload a current photo of the child and a photo of the parent to the system:

[0709] 1. Upload a photo

[0710] Users take photos of their children and parents using the camera on their smartphones and upload them through a dedicated app.

[0711] The device (smartphone) sends the photos it has taken to the server.

[0712] 2. Receiving and saving photo data

[0713] The server receives the uploaded photo data of the child and the parent.

[0714] The server stores the received photo data in a database.

[0715] 3. Data Preprocessing

[0716] The server loads the stored photo.

[0717] The server uses an open source image processing library (e.g., OpenCV) to standardize the resolution of each photo and crop the face area.

[0718] The server extracts facial feature points and stores them in a database.

[0719] 4. Training the generative AI model

[0720] The server combines the child's facial feature points with the parent's to create input data for the generative AI model.

[0721] The server feeds this input data into a generative AI model to generate a photo of the child's predicted growth.

[0722] 5. Output of generated results

[0723] The server sends the generated growth forecast photo to the user's smartphone.

[0724] The device (smartphone) displays the generated growth prediction photos using a dedicated app.

[0725] 6. Use of Emotion Engines

[0726] The device uses a camera to capture the user's facial expressions while viewing photos, and the emotion engine analyzes the expressions.

[0727] The terminal uses an emotion engine to recognize emotions and transmits them to the server.

[0728] The server adjusts the generation AI model based on the emotional information for future generations, generating photos that suit the user's preferences.

[0729] This allows the present invention to provide users with personalized photos of their child's predicted growth, providing greater entertainment value.The use of an emotion engine allows the system to adjust based on the user's reactions and emotions, providing optimal results for each individual user.

[0730] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0731] Step 1:

[0732] Users access a dedicated app or website, select a photo of their child and a photo of their parents or grandparents, or take a new photo and press the upload button.

[0733] Input: User selects or takes a photo

[0734] Output: Selected or taken photo data

[0735] Specific operation: The user launches the dedicated app on their smartphone or computer and clicks the "Upload photo" button within the app. If using a camera, the user launches the camera function within the app and takes a new photo.

[0736] Step 2:

[0737] The device sends the selected photo to the server.

[0738] Input: Photo data selected or taken by the user

[0739] Output: Photo data sent to the server

[0740] What it does: The app sends the photos to the server as an HTTP POST request, with a progress bar indicating the upload is in progress.

[0741] Step 3:

[0742] The server receives the photo data sent from the device and stores it in a file system or database.

[0743] Input: Photo data sent from the device

[0744] Output: Photo data stored in a file system or database

[0745] Specific operation: The server receives the photo data and stores it in a specified folder in the file system (e.g., / var / www / html / uploads / ) or in a database.

[0746] Step 4:

[0747] The server reads the stored photo data and uses an image processing library to unify the resolution of each photo and crop the facial areas.

[0748] Input: Photo data stored in a file system or database

[0749] Output: Photo data with uniform resolution and cropped face area

[0750] What it does: The server uses the OpenCV library to standardize the photo resolution to 1080x1080 pixels, and then uses algorithms like Haar Cascade to crop the face and remove unnecessary background.

[0751] Step 5:

[0752] The server extracts facial feature points (e.g., the positions of the eyes, nose, and mouth) from the cropped photo.

[0753] Input: Cropped photo data

[0754] Output: Extracted facial feature points data

[0755] What it does: The server uses the Dlib library to extract 68 facial feature points from the cropped photo.

[0756] Step 6:

[0757] The server combines the child's facial feature points with those of the parents or grandparents to form input data for the generative AI model.

[0758] Input: Child's facial feature point data and parent or grandparent's facial feature point data

[0759] Output: Formatted input data for a generative AI model

[0760] Specific operation: The server concatenates the coordinates of facial feature points into a series of vectors and converts them into the input format for the generative AI model.

[0761] Step 7:

[0762] The server inputs the formatted data into a generative AI model to predict and generate the child's future face.

[0763] Input: Formatted input data

[0764] Output: Generated growth prediction photo

[0765] How it works: The server inputs data into a generative AI model built with TensorFlow and PyTorch, predicts the child's future face, and generates a new photo.

[0766] Step 8:

[0767] The server transmits the generated growth prediction photo to the terminal.

[0768] Input: Generated growth prediction photo

[0769] Output: Growth prediction photo sent to the device

[0770] Specific operation: The server converts the generated photo into a format such as JPEG and sends it to the user's device as an HTTP response.

[0771] Step 9:

[0772] The terminal displays the generated growth prediction photo to the user.

[0773] Input: Growth prediction photo sent from the server

[0774] Output: A photo of the predicted growth shown to the user

[0775] Specific operation: The device displays the received photo in an app or website, and when the user taps the image, it becomes full-screen and can be zoomed in and out.

[0776] Step 10:

[0777] The device uses a camera to capture the user's facial expressions while viewing photos, and the emotion engine analyzes the images to recognize the user's emotions.

[0778] Input: User facial expression image

[0779] Output: Emotion recognition result data

[0780] Specific operation: The device automatically activates the camera and takes photos at regular intervals. An emotion engine (e.g., Microsoft Azure Emotion API) is used to analyze the captured images and recognize the user's emotions.

[0781] Step 11:

[0782] The device transmits the recognized emotion data to the server.

[0783] Input: Emotion recognition result data

[0784] Output: Emotion data sent to the server

[0785] Specific operation: The device sends the recognized emotion data in JSON format to the server. Example: "Smile: 80%, Surprise: 20%".

[0786] Step 12:

[0787] The server personalizes the generated photo based on the received emotion information.

[0788] Input: Emotional information data

[0789] Output: Personalized growth forecast photo

[0790] Specific operation: The server analyzes the received emotional information, adjusts the generation AI model from the next time onwards, and generates photos that suit the user's preferences. Adjustments are made, such as generating more photos of the age at which the user is most smiling.

[0791] (Application example 2)

[0792] 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."

[0793] While conventional growth prediction photo generation systems can predict future facial features based on photos of children and parents, they lack a means to determine how satisfying the generated photos are to users. As a result, they are unable to fully meet user needs, resulting in a limited user experience. Furthermore, since there is no system that can provide personalized predicted photos, they are unable to provide uniform results.

[0794] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving photos of the child and photos of the parents or grandparents, means for preprocessing the received photos and extracting facial feature points, means for shaping input data to the generative AI model using the extracted feature points, means for generating predicted growth photos of the child using the generative AI model, means for outputting the predicted growth photos, means for recognizing the user's facial expression and analyzing the emotion, and means for personalizing the predicted growth photos based on the user's emotion. This makes it possible to provide predicted growth photos personalized in accordance with the user's emotion, significantly improving the satisfaction of the user experience.

[0795] "Means for receiving photos" refers to the method by which the system receives photos of the child and parent or grandparent from the digital device.

[0796] The "pre-processing means" is a method for performing image processing such as unifying the resolution of received photographs and trimming facial areas.

[0797] The "means for extracting facial feature points" is a method for obtaining position information of important facial parts (for example, eyes, nose, and mouth) from a cropped facial photograph.

[0798] "Means for formatting input data for generative AI models" refers to a method for converting extracted feature points into an appropriate format and preparing them so that the AI ​​model can read them.

[0799] The "growth prediction photo generation method" is a method that uses a generative AI model to create a photo of a child's future face from shaped input data.

[0800] The "means for outputting predicted photos" is a method for displaying or transmitting the generated growth prediction photos to the user.

[0801] The "emotion recognition means" is a method for capturing facial expressions with a camera when a user views a generated photo and analyzing the emotions.

[0802] The "photo personalization means" is a method for adjusting the generated growth prediction photo to suit the user's preferences based on the recognized user's emotions.

[0803] The "user terminal transmission means" is a method for transmitting the generated growth prediction photo to a device used by the user.

[0804] A "generative AI model" is an artificial intelligence model that predicts a child's future face based on the characteristics of parents and grandparents learned in the past.

[0805] This invention combines emotion recognition functionality with a system for generating photos of children's future growth, providing a more personalized user experience. The system uses the following hardware and software: an image processing library (e.g., OpenCV), an artificial intelligence (AI) model (e.g., TensorFlow), and an emotion recognition engine (e.g., EmotionEngine).

[0806] First, a user takes photos of their child and their parents or grandparents using their smartphone, and uploads these photos to a cloud server through a dedicated application. The server receives the uploaded photos and stores them.

[0807] The received photos are first preprocessed using image processing libraries such as OpenCV to standardize the resolution of the photos and crop the facial area, then extract key facial features and format this data so that it can be fed into the generative AI model.

[0808] The rectified feature data is then input into a generative AI model such as TensorFlow to generate a photo of the child's future face. The generated photo of the predicted growth is then sent back to the user's smartphone by the server.

[0809] When a user views the generated photo, their smartphone camera captures their facial expression, which is then analyzed by the Emotion Engine. The emotional information obtained as a result of the analysis is sent to the server, and the growth prediction photo is personalized and regenerated based on this emotional data.

[0810] For example, if the user is smiling, a growth projection photo that best matches that emotion is generated. By repeating this process, it is possible to provide more finely tuned personalized results.

[0811] As a concrete example, the following is an example of a prompt sentence for a generative AI model:

[0812] "Generate a future photo of a 10-year-old based on the given child and parent photos."

[0813] As described above, this system analyzes the user's emotions in real time and generates personalized growth prediction photos accordingly, thereby improving the user experience.

[0814] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0815] Step 1:

[0816] A user uses a smartphone to take photos of their child and their parents or grandparents, and then uploads these photos to a cloud server using a dedicated application. The input here is the photo file taken with the smartphone camera, and the output is the photo file saved on the cloud server. Specifically, when the user presses the "upload photo" button in the app, the device sends the photo data to the server.

[0817] Step 2:

[0818] The server receives and stores the photo data sent from the device. The input is the photo data sent from the device, and the output is the photo data stored in the server's storage. Specifically, the server's receiving API receives the data and stores it in a database.

[0819] Step 3:

[0820] The server preprocesses the stored photo data. The target of preprocessing is the stored photo data, and in this step, the resolution is unified and facial areas are cropped. The output is preprocessed image data. Specifically, the server uses the OpenCV library to unify the image resolution, detect and crop facial areas.

[0821] Step 4:

[0822] The server extracts facial feature points from the preprocessed photo data. The input is the preprocessed image data, and the output is facial feature point data. In this step, OpenCV is used to detect important points on the face, such as the eyes, nose, and mouth. Specific operations involve the use of image analysis algorithms.

[0823] Step 5:

[0824] The server formats the input data for the generative AI model based on the extracted feature points. The input here is facial feature point data, and the output is data formatted in a format that can be applied to the generative AI model. Specifically, the server converts the feature point data into a one-dimensional array or tensor format.

[0825] Step 6:

[0826] The server uses a generative AI model to generate predicted photos of the child's growth. The input is shaped facial feature point data, and the output is the generated predicted photo of the child's growth. Specifically, a generative AI model such as TensorFlow runs to generate predicted photos based on facial feature points.

[0827] Step 7:

[0828] The server sends the generated growth forecast photo to the user's terminal. The input is the generated growth forecast photo, and the output is the growth forecast photo displayed on the user's terminal. Specifically, the server sends the data using the HTTP protocol.

[0829] Step 8:

[0830] When a user views the generated growth prediction photo on their smartphone, the device's camera captures the user's facial expression, which is then analyzed by the emotion engine. The input is the user's facial image captured by the smartphone camera, and the output is the analyzed emotion data. Specifically, the Emotion Engine receives the facial expression image and identifies the emotion.

[0831] Step 9:

[0832] The server personalizes the growth prediction photo based on the analyzed emotional data. The input is the analyzed emotional data and the generated growth prediction photo, and the output is a specific growth prediction photo selected based on the user's emotions. Specifically, the server runs the generative AI model again according to the emotional data to regenerate a result that best suits the user's emotions.

[0833] This allows the user to view personalized growth prediction photos that match their emotions.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] [Third embodiment]

[0838] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0839] 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.

[0840] 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).

[0841] 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.

[0842] 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.

[0843] 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).

[0844] 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.

[0845] 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.

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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."

[0850] This invention is a system that generates predicted photos of a child's growth, and uses a generative AI model to predict and generate future photos of the child based on photos of the child and photos of the parents or grandparents entered by the user.

[0851] The system has the following main steps:

[0852] 1. Upload a photo

[0853] A user uses a device (such as a smartphone or computer) to upload photos of their child and parents or grandparents to a dedicated app or website.

[0854] The terminal transmits the uploaded photo data to the server.

[0855] 2. Receiving and saving photo data

[0856] The server receives the photo data sent from the terminal.

[0857] The server stores the received photo data in a file system or database.

[0858] 3. Data Preprocessing

[0859] The server reads the stored photo data.

[0860] The server uses an image processing library to standardize the resolution of each photo and crop the face area.

[0861] The server extracts facial feature points (e.g., the positions of the eyes, nose, and mouth) from the cropped photo.

[0862] 4. Training the generative AI model

[0863] The server formats the input data for the generative AI model based on the child's current feature points and those of the parents or grandparents.

[0864] The server inputs the post-surgery data into a generative AI model to generate a predicted photo. The generative AI model has previously learned the characteristics of the parents and grandparents, and uses this information to predict the child's future face.

[0865] 5. Output of generated results

[0866] The server transmits the generated growth prediction photo to the user's terminal.

[0867] The terminal displays the generated growth prediction photo.

[0868] Specific examples

[0869] For example, consider a case where a user uses a smartphone to upload current photos of their child and a photo of the parent to the system.

[0870] 1. Upload a photo

[0871] Users use the camera function on their smartphone to take photos of their child and parent and upload them through a dedicated app.

[0872] The device (smartphone) sends the captured photo to the server.

[0873] 2. Receiving and saving photo data

[0874] A server receives uploaded photo data of the child and parent.

[0875] The server stores the received photo data in a database.

[0876] 3. Data Preprocessing

[0877] The server loads the stored photo.

[0878] The server uses an open-source image processing library (e.g., OpenCV) to standardize the resolution of each photo and crop the face area.

[0879] The server extracts facial feature points and stores them in a database.

[0880] 4. Training the generative AI model

[0881] The server combines the facial feature points of the child with those of the parents to create input data for the generative AI model.

[0882] The server then feeds this input data to a generative AI model, which generates a photo of the child as they grow up. The generative AI model has already learned the characteristics of the parents and grandparents, and uses this information to predict what the child will look like in the future.

[0883] 5. Output of generated results

[0884] The server sends the generated growth prediction photo to the user's smartphone.

[0885] The device (smartphone) displays the generated growth prediction photos in a dedicated app, allowing users to check them and enjoy seeing what their child will look like in the future.

[0886] Through these steps, users can easily enjoy future photos of their children from the comfort of their own home. The predicted growth photos provided by the system are generated based on the characteristics of the parents or grandparents, resulting in realistic and interesting results.

[0887] The processing flow will be explained below.

[0888] Step 1:

[0889] The user uses the device to upload photos of their child and their parents or grandparents to a dedicated app or website. When the user clicks the upload button, the device sends the selected photo files to the server using an HTTP request.

[0890] Step 2:

[0891] The server receives the HTTP request and saves the sent photo data to the file system or database, records the path to the save destination, and adds the information to the database.

[0892] Step 3:

[0893] The server reads the stored photo data, standardizes the resolution of each photo using an image processing library (e.g., OpenCV), and runs a face detection algorithm to crop the face area.

[0894] Step 4:

[0895] The server extracts facial feature points (eyes, nose, and mouth) from the cropped face image using Dlib or a facial feature point detection algorithm, and stores the extracted feature point data in a database.

[0896] Step 5:

[0897] The server combines the child's feature point data with that of the parents or grandparents to create input data for the generative AI model. Data standardization (e.g., normalization using the mean and standard deviation) is also performed here.

[0898] Step 6:

[0899] The server inputs the formatted data into a generative AI model to generate a photo of the child's expected growth. This generative AI model is pre-trained on the characteristics of the parents and grandparents, and makes predictions based on this.

[0900] Step 7:

[0901] The server saves the generated growth prediction photo as an image file and converts it into a format that is easy for users to view (e.g., JPEG or PNG). After conversion, it generates an HTTP response and sends it to the user's device.

[0902] Step 8:

[0903] The device receives the generated photo data sent from the server. The received photo data is displayed through a dedicated application or web browser, allowing the user to check it. For example, a function is provided to display multiple age variations in slideshow format.

[0904] The above is a specific process flow for generating a photo of a child's expected growth.

[0905] Example 1

[0906] 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."

[0907] Conventional technologies have faced many challenges in accurately capturing individual facial features and providing users with results quickly and effectively when generating predicted images of a child's future face. In particular, the process of receiving photos, preprocessing, feature point extraction, inputting them into a generative model, and outputting the generated results is not performed smoothly, resulting in a poor user experience. There is a need for a system that solves this problem and allows users to easily and quickly obtain predicted photos of their child's growth.

[0908] 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.

[0909] In this invention, the server includes means for receiving a photo of the child and a photo of the parent or grandparent from a user terminal, means for resizing the received photo to a uniform resolution and cropping the face, means for extracting facial feature points from the cropped photo, means for shaping input data to a generative AI model using the extracted feature points, means for generating a photo of the child's predicted growth using the generative AI model, means for transmitting the generated photo of the predicted growth to the user terminal, and means for displaying the generated photo of the predicted growth on the user terminal. This makes it possible to realize a system that is easy for users to operate and allows them to quickly check results.

[0910] A "user terminal" is a computing device operated by a user, and is a general term for devices such as smartphones and personal computers used to perform tasks such as taking and uploading photos.

[0911] A "server" is a computer system responsible for receiving, storing, and processing data sent from user terminals.

[0912] "Receiving a photo" refers to the act of sending a photo of a child and photo data of a parent or grandparent from a user terminal to a server.

[0913] "Resolution resizing" refers to the process of changing the pixel count of an uploaded photo to unify its resolution to a specific standard size.

[0914] "Facial cropping" is an image processing technique that cuts out only the facial area from a photograph and removes the background and unnecessary parts.

[0915] "Feature point extraction" is the process of extracting specific positional information such as the eyes, nose, and mouth from a cropped facial photograph.

[0916] A "generative AI model" is an artificial intelligence model that has learned the facial features of parents and grandparents, and is an algorithm that uses this to predict and generate a child's future face.

[0917] "Input data formatting" refers to the process of preprocessing feature data to provide it in an appropriate format for a generative AI model.

[0918] A "growth prediction photo" is an image of a child's future face, predicted and generated using a generative AI model.

[0919] "Output" refers to the process of sending the generated growth prediction photo to a user terminal and displaying it to the user.

[0920] The present invention is a system for generating a child's growth forecast photo, which uses a generative AI model to predict the child's future face based on a user-provided photo of the child and photos of the parents or grandparents. The following describes an embodiment of the system in detail.

[0921] This system works in cooperation with a user device, a server, an image processing library, a generative AI model, and a database. Users take or upload photos using their device, such as a smartphone or PC, and the data is sent to the server. The server performs a series of preprocessing steps on the received photo data to extract feature points, and then generates a future facial image using the generative AI model.

[0922] The specific software and hardware used are as follows:

[0923] User terminal: A general-purpose computing device such as a smartphone or PC.

[0924] Server: A powerful computer system that stores and processes data.

[0925] Image processing libraries: Use open source libraries such as OpenCV and Dlib.

[0926] Generative AI models: Use pre-trained models using machine learning frameworks such as TensorFlow and PyTorch.

[0927] Database: A relational database such as MySQL or PostgreSQL to store photo and feature point data.

[0928] As a specific example of operation, consider a case where a user uses a smartphone to upload a current photo of the child and a photo of the parent to the system.

[0929] 1. Photo upload: Users use their smartphone's camera to take photos of their children and parents and upload them through a dedicated app.

[0930] 2. Receiving and storing photo data: The server receives the uploaded photo data of the child and parent and stores it in a database.

[0931] 3. Data preprocessing: The server reads the stored photos, standardizes the resolution of each photo using OpenCV, crops the face area, and extracts facial feature points and stores them in a database.

[0932] 4. Learning and prediction of the generative AI model: The server combines the facial feature points of the child and the parent to create input data for the generative AI model, which is then input into the generative AI model to generate a predicted photo of the child's growth.

[0933] 5. Output of generated results: The server sends the generated growth prediction photo to the user's smartphone, where it is displayed using a dedicated app on the device.

[0934] Examples of prompts include the following:

[0935] "Generate a future photo of the child's face using a photo of the child's current face and a photo of the parents' faces as input."

[0936] This allows users to easily enjoy future photos of their children from the comfort of their own home. The predicted growth photos provided by the system are generated based on the characteristics of the parents or grandparents, resulting in realistic and interesting results.

[0937] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0938] Step 1:

[0939] Upload a photo

[0940] A user takes photos of their child and their parents or grandparents and uploads these photos to a server via the Internet using a dedicated app.

[0941] Input: A photo of the child and a photo of the parent or grandparent (JPEG, PNG, or other format)

[0942] Specific operation: The user launches the dedicated app and takes a photo using the photo capture function, or selects an existing photo from the device's photo gallery. Then, the user presses the upload button, which generates an HTTP / HTTPS request to send the photo data to the server.

[0943] Step 2:

[0944] Receiving and saving photo data

[0945] The server receives the photo data sent from the user terminal, checks whether it is in the correct format, and then saves it.

[0946] Input: Photo data sent from the user device (HTTP / HTTPS request)

[0947] Output: Photo data stored in a database or file system

[0948] Specific operation: The server verifies the format and size of the received photo data and determines the appropriate storage path. The photo data is saved to the file system, and the reference path is stored in the database.

[0949] Step 3:

[0950] Data Preprocessing

[0951] The server reads the stored photo data and performs preprocessing to unify the resolution, crop faces, and extract feature points.

[0952] Input: Saved photo data

[0953] Output: Cropped face photo data and feature point data

[0954] What it does: The server uses OpenCV to resize the photo resolution (e.g., to 512x512 pixels), then uses the Dlib library to crop the face and extract the eye, nose, and mouth feature points from the face, which are then stored in a database.

[0955] Step 4:

[0956] Shaping input data for generative AI models

[0957] The server formats the feature data into a format suitable for input into a generative AI model.

[0958] Input: Feature point data for children and parents or grandparents

[0959] Output: Input data to the generative AI model

[0960] Specific operation: The server converts the feature point data into a Numpy array or similar format, and formats it in the format expected by the generative AI model. This includes specific arraying and data normalization.

[0961] Step 5:

[0962] Predictions from generative AI models

[0963] The server inputs the retouched input data into a generative AI model to generate a photo of the child's predicted growth.

[0964] Input: Formatted input data

[0965] Output: Generated growth prediction photo

[0966] How it works: The server inputs the formatted input data into the generative AI model and executes the model's inference process. The inference result is image data that predicts the child's future face. This image data is temporarily stored.

[0967] Step 6:

[0968] Output of generated results

[0969] The server transmits the generated growth prediction photo to the user terminal, which displays it.

[0970] Input: Generated growth prediction photo

[0971] Output: A photo of predicted growth displayed on the user's device

[0972] Specific operation: The server converts the generated photo into Base64 format or image file format and sends it to the user's device using the HTTP / HTTPS protocol. The photo received by the user's device is displayed in the image view of the dedicated app. The user can view it and enjoy the image of their future child.

[0973] (Application example 1)

[0974] 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."

[0975] In recent years, there has been an increasing demand for technology to predict children's growth, but current technology faces issues in terms of accuracy and convenience. In particular, there are few systems that can be easily used at home or used as a service in physical stores, and they do not meet the diverse needs of customers. There is a need for a system that can solve this problem and easily generate more accurate growth forecast photos.

[0976] 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.

[0977] In this invention, the server includes means for receiving photos of the child and photos of the parents or grandparents, means for preprocessing the received photos and extracting facial feature points, means for shaping input data to a generative AI model using the extracted feature points, means for generating predicted growth photos of the child using the generative AI model, means for outputting the generated predicted growth photos, and means for displaying the generated predicted growth photos on a customer's device via a dedicated app for the photo studio. This makes it possible to provide highly accurate predicted growth photos to customers not only at home but also as a service in physical stores.

[0978] "Child photo" is a current photo of the child that is used to make the growth prediction.

[0979] A "parent or grandparent photo" is a photo of a parent or grandparent that is relevant to the child in the growth prediction.

[0980] The "receiving means" is a means for receiving photo data from the user terminal to the server.

[0981] "Preprocessing" refers to performing initial processing such as adjusting the resolution of received photo data and trimming it.

[0982] "Facial feature points" are points that indicate specific parts of the face, such as the positions of the eyes, nose, and mouth.

[0983] A "generative AI model" is an artificial intelligence model that learns the characteristics of parents and grandparents in advance and generates predicted photos of a child's growth.

[0984] "Means for formatting input data" refers to means for arranging feature points into a format suitable for a generative AI model.

[0985] "Growth Prediction Photos" are photos of children's futures predicted using a generative AI model.

[0986] The "output means" is a means for displaying the generated growth prediction photograph to the user or customer.

[0987] A "photo studio dedicated app" is a mobile application developed to complement the services of a photo studio.

[0988] "Customer device" refers to an electronic device owned by the customer, such as a smartphone or tablet.

[0989] The present invention relates to a system for generating a photo of a child's future growth projection, and is implemented by the following method.

[0990] First, a user opens a dedicated app on a smartphone or tablet and uploads current photos of their child and photos of their parents or grandparents. The user's device then sends the uploaded photo data to a cloud server, which receives the photo data and automatically saves it.

[0991] Next, the cloud server preprocesses the received photo data. This preprocessing involves using an image processing library (e.g., OpenCV) to standardize the resolution of each photo and crop the facial area. It also performs processing to extract facial feature points (such as the positions of the eyes, nose, and mouth). The feature points are then extracted from the preprocessed data and formatted as input data for the generative AI model.

[0992] The cloud server uses a trained generative AI model (e.g., StyleGAN) to generate predicted photos of the child's growth based on the extracted feature points. Because the generative AI model has already learned the characteristics of the parents and grandparents, it can generate more realistic predicted photos.

[0993] The generated growth prediction photos are sent directly from the cloud server to the user's device via a dedicated app at the photo studio. Users can use the dedicated app to check the generated predicted photos and enjoy watching their child's growth. This system is also provided as a service at photo studios, so users can immediately receive highly accurate growth prediction photos at the photo studio.

[0994] As a concrete example, consider a photo gallery app where a user uploads a current photo of their child and a photo of their parents. Throughout this process, the following prompt is used: "Use the uploaded photos of the child and the parents to predict and generate a future photo of the child."

[0995] The system's components include devices such as smartphones and tablets, a cloud server, the image processing library OpenCV, and the generative AI model StyleGAN. This makes it possible to provide services at home or in photo studios, allowing users to easily generate and view photos of their children's growth predictions at any time.

[0996] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0997] Step 1:

[0998] The user uses a smartphone or tablet to upload a current photo of their child and a photo of their parents or grandparents to a dedicated app. The input is a photo of the child and a photo of the parents or grandparents. This photo data is uploaded and sent to a cloud server. The output is the photo data transferred to the cloud server.

[0999] Step 2:

[1000] The server saves the received photo data and stores it in a database. The input is the photo data sent by the user. Specifically, the server saves the photo data in a specific folder and stores the corresponding metadata in the database. The output is the saved photo data and its metadata.

[1001] Step 3:

[1002] The server uses an image processing library (OpenCV) to preprocess the photo data. The input is the stored photo data. Specifically, the server standardizes the resolution of the photos and crops the facial area. This preprocessing ensures accurate feature point extraction in the subsequent process. The output is cropped facial image data with a standardized resolution.

[1003] Step 4:

[1004] The server extracts facial feature points (such as the positions of the eyes, nose, and mouth) from the cropped face image. The input is the cropped face image data. Specifically, it uses OpenCV's face recognition algorithm to detect the feature points and saves them in a database. The output is the extracted facial feature point data.

[1005] Step 5:

[1006] The server uses the extracted feature point data to format it as input data for a generative AI model (StyleGAN). The input is facial feature point data. Specifically, it converts the feature point data into a format suitable for the AI ​​model. The output is formatted input data for the AI ​​model.

[1007] Step 6:

[1008] The server provides the formatted input data to the generative AI model to generate predicted photos of the child's growth. The input is the formatted AI model input data. Specifically, the generative AI model is executed to generate predicted photos of the child's future. The output is the generated predicted photos of the child's growth.

[1009] Step 7:

[1010] The server stores the generated growth prediction photos on a cloud server and sends them to the user's device via the photo studio's dedicated app. The input is the generated growth prediction photos. Specifically, the server converts the generated photos into an appropriate format for display on the user interface of the dedicated app and sends them to the user's device. The output is the growth prediction photos displayed on the user's device.

[1011] Through these steps, users can view highly accurate photos of their child's growth predictions through a dedicated app. This can also be used as a service in photo studios, improving customer satisfaction.

[1012] 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.

[1013] This invention combines an emotion engine with a system that generates photos of children's future growth, providing a more personalized experience. Based on photos of the child and parents or grandparents entered by the user, a generative AI model is used to predict and generate future photos of the child, and furthermore, the user's emotions are recognized, improving the user experience.

[1014] The main steps of the system are explained.

[1015] 1. Upload a photo

[1016] A user uses a device (such as a smartphone or computer) to upload photos of their child and parents or grandparents to a dedicated app or website.

[1017] The terminal transmits the uploaded photo data to the server.

[1018] 2. Receiving and saving photo data

[1019] The server receives the photo data sent from the terminal.

[1020] The server stores the received photo data in a file system or database.

[1021] 3. Data Preprocessing

[1022] The server reads the stored photo data.

[1023] The server uses an image processing library to standardize the resolution of each photo and crop the face area.

[1024] The server extracts facial feature points (e.g., the positions of the eyes, nose, and mouth) from the cropped photo.

[1025] 4. Training the generative AI model

[1026] The server formats the input data for the generative AI model based on the child's current feature points and those of the parents or grandparents.

[1027] The server inputs the post-surgery data into a generative AI model to generate a predicted photo. The generative AI model has previously learned the characteristics of the parents and grandparents, and uses this information to predict the child's future face.

[1028] 5. Output of generated results

[1029] The server transmits the generated growth prediction photo to the user's terminal.

[1030] The terminal displays the generated growth prediction photo.

[1031] 6. Use of Emotion Engines

[1032] The device uses a camera to capture the user's facial expressions while viewing photos, and the emotion engine analyzes the images to recognize the user's emotions, for example, whether the user is smiling, surprised, or expressing other emotions.

[1033] The emotion engine transmits the recognized emotion information to the server.

[1034] The server personalizes the generated growth prediction photos based on the received emotion information, providing results that meet the user's preferences, such as generating more photos of the ages that the user finds particularly exciting.

[1035] Specific examples

[1036] For example, consider a case where a user uses a smartphone to upload current photos of their child and a photo of the parent to the system.

[1037] 1. Upload a photo

[1038] Users use the camera function on their smartphone to take photos of their child and parent and upload them through a dedicated app.

[1039] The device (smartphone) sends the captured photo to the server.

[1040] 2. Receiving and saving photo data

[1041] A server receives uploaded photo data of the child and parent.

[1042] The server stores the received photo data in a database.

[1043] 3. Data Preprocessing

[1044] The server loads the stored photo.

[1045] The server uses an open-source image processing library (e.g., OpenCV) to standardize the resolution of each photo and crop the face area.

[1046] The server extracts facial feature points and stores them in a database.

[1047] 4. Training the generative AI model

[1048] The server combines the facial feature points of the child with those of the parents to create input data for the generative AI model.

[1049] The server then feeds this input data to a generative AI model, which generates a photo of the child as they grow up. The generative AI model has already learned the characteristics of the parents and grandparents, and uses this information to predict the child's future face.

[1050] 5. Output of generated results

[1051] The server sends the generated growth prediction photo to the user's smartphone.

[1052] The device (smartphone) displays the generated growth prediction photo using a dedicated app.

[1053] 6. Use of Emotion Engines

[1054] The device uses a camera to capture the user's facial expressions while viewing photos, and the emotion engine recognizes emotions from the facial expressions, for example, analyzing whether the user is smiling.

[1055] The emotion engine sends the recognized emotion to the server.

[1056] The server uses the emotional information to adjust the generation AI model for future use, or generates photos according to the user's preferences.

[1057] Through these steps, the present invention enables the generation of personalized child growth forecast photos for each user, providing greater entertainment value.The use of an emotion engine allows the system to be more precisely adjusted based on the user's reactions and emotions, providing optimal results for each individual user.

[1058] The processing flow will be explained below.

[1059] Step 1:

[1060] The user uses the device to upload photos of their child and their parents or grandparents to a dedicated app or website. When the user clicks the upload button, the device sends the selected photo files to the server using an HTTP request.

[1061] Step 2:

[1062] The server receives the HTTP request and saves the sent photo data to the file system or database, records the path to the save destination, and adds the information to the database.

[1063] Step 3:

[1064] The server reads the stored photo data, standardizes the resolution of each photo using an image processing library (e.g., OpenCV), and runs a face detection algorithm to crop the face area.

[1065] Step 4:

[1066] The server extracts facial feature points (eyes, nose, and mouth) from the cropped face image using Dlib or a facial feature point detection algorithm, and stores the extracted feature point data in a database.

[1067] Step 5:

[1068] The server combines the child's feature point data with that of the parents or grandparents to create input data for the generative AI model. Data standardization (e.g., normalization using the mean and standard deviation) is also performed here.

[1069] Step 6:

[1070] The server inputs the formatted data into a generative AI model to generate a photo of the child's expected growth. This generative AI model is pre-trained on the characteristics of the parents and grandparents, and makes predictions based on this.

[1071] Step 7:

[1072] The server saves the generated growth prediction photo as an image file and converts it into a format that is easy for users to view (e.g., JPEG or PNG). After conversion, it generates an HTTP response and sends it to the user's device.

[1073] Step 8:

[1074] The device receives the generated photo data sent from the server. The received photo data is displayed through a dedicated application or web browser, allowing the user to check it. For example, a function is provided to display multiple age variations in slideshow format.

[1075] Step 9:

[1076] The device uses a camera to capture the user's facial expressions while viewing photos, and the emotion engine analyzes the facial images to recognize the user's emotions, such as whether the user is smiling or surprised.

[1077] Step 10:

[1078] The emotion engine transmits the recognized emotion information to the server.

[1079] Step 11:

[1080] The server personalizes the generated growth prediction photos based on the received emotion information, providing results that meet the user's preferences, such as generating more photos of the ages that the user finds particularly exciting.

[1081] Step 12:

[1082] The server will adjust the generation AI model based on the emotional information from the next time onwards, so that it will generate predicted photos that better suit the user's preferences.

[1083] The above is the specific processing flow of the invention that combines an emotion engine that recognizes the user's emotions.

[1084] Example 2

[1085] 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."

[1086] Conventional systems that generate photos of children's growth predictions have had the problem of reducing the user experience because the generated photos do not necessarily reflect the emotions and preferences of individual users. In addition, the generated photos often have a cold, impersonal feel, making it difficult to feel close to the child.

[1087] 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.

[1088] In this invention, the server includes means for receiving photos of the child and photos of the parents or grandparents, means for preprocessing the received photos and extracting facial feature points, means for shaping input data to a generative AI model using the extracted feature points, means for generating predicted growth photos of the child using the generative AI model, means for outputting the generated predicted growth photos, means for capturing a user's facial expression and recognizing emotions, and means for personalizing the generated photos based on the recognized emotion information. This enables personalization according to the user's emotions, not only providing a higher user experience but also making the generated photos more familiar to the user.

[1089] "Children's photos" refers to image data that includes a child's face.

[1090] "Parent or grandparent photo" refers to image data that shows the face of a child's parent or grandparent.

[1091] The "receiving means" is a communication interface for receiving photo data from other devices (for example, an HTTP request via the Internet).

[1092] "Means for pre-processing and extracting facial features" refers to the process of analyzing photographic data using image processing technology to extract facial contours and features such as eyes, nose, and mouth.

[1093] "Means for formatting input data for a generative AI model" refers to the process of processing the extracted features into an appropriate format and preparing them as input to a generative AI model.

[1094] "Method of generating predicted photos of a child's growth using a generative AI model" refers to the process in which an AI algorithm uses shaped input data to predict a child's future face and generate it as an image.

[1095] The "means for outputting the generated growth prediction photograph" refers to a process for displaying, saving, or transmitting the generated image data to another device.

[1096] "Means for capturing the user's facial expressions and recognizing emotions" refers to the process of taking a picture of the user's face with a camera and analyzing the image to determine the user's emotions.

[1097] "Means for personalizing the generated photo based on recognized emotional information" refers to the process of adjusting the generated image data based on the user's emotional data to make it more in line with the user's preferences.

[1098] MODE FOR CARRYING OUT THE INVENTION

[1099] This invention combines an emotion engine with a system that generates photos of children's future growth, providing a more personalized experience. Based on photos of the child and parents or grandparents entered by the user, a generative AI model is used to predict and generate future photos of the child, and furthermore, the user's emotions are recognized, improving the user experience.

[1100] First, users upload photos of their child and their parents or grandparents through a dedicated app or website. Using a smartphone or computer, users can easily select, take, and upload photos by following the app's instructions. Specifically, the following hardware and software are required:

[1101] Hardware:

[1102] Smartphones, PCs, servers

[1103] Camera function (built into smartphones and computers)

[1104] software:

[1105] Dedicated app and website

[1106] Image processing library (e.g. OpenCV)

[1107] Generative AI models (e.g., implemented in TensorFlow or PyTorch)

[1108] Emotion engine (e.g. Microsoft Azure Emotion API)

[1109] When a photo is uploaded, the device sends it to the server. The server receives the photo data and stores it in a file system or database. The server then reads the stored photo data and uses an image processing library (e.g., OpenCV) to unify the resolution of each photo and crop the facial area. From the cropped photos, the server extracts facial feature points (e.g., the positions of the eyes, nose, and mouth).

[1110] Next, the server combines the facial feature points of the child with those of the parents or grandparents to create input data for the generative AI model. The resulting data is then input into the generative AI model to predict and generate the child's future face. The generative AI model has previously learned the features of the parents and grandparents, and predicts the child's future face based on this information.

[1111] The generated growth prediction photos are sent from the server to the user's device and displayed on the device. Users can view, comment on, and save the photos through the app.

[1112] Furthermore, the system uses an emotion engine to recognize the user's emotions. While the user is viewing photos, the device's camera captures the user's facial expressions, which are then analyzed by the emotion engine. The emotion engine identifies whether the user is smiling, surprised, etc., and sends this emotional information to the server. The server can then personalize the generated growth prediction photos based on the received emotional information. For example, it can adjust the system to generate more photos of the age at which the user is particularly excited.

[1113] Specific examples

[1114] For example, if a user uses a smartphone to upload a current photo of the child and a photo of the parent to the system:

[1115] 1. Upload a photo

[1116] Users take photos of their children and parents using the camera on their smartphones and upload them through a dedicated app.

[1117] The device (smartphone) sends the photos it has taken to the server.

[1118] 2. Receiving and saving photo data

[1119] The server receives the uploaded photo data of the child and the parent.

[1120] The server stores the received photo data in a database.

[1121] 3. Data Preprocessing

[1122] The server loads the stored photo.

[1123] The server uses an open source image processing library (e.g., OpenCV) to standardize the resolution of each photo and crop the face area.

[1124] The server extracts facial feature points and stores them in a database.

[1125] 4. Training the generative AI model

[1126] The server combines the child's facial feature points with the parent's to create input data for the generative AI model.

[1127] The server feeds this input data into a generative AI model to generate a photo of the child's predicted growth.

[1128] 5. Output of generated results

[1129] The server sends the generated growth forecast photo to the user's smartphone.

[1130] The device (smartphone) displays the generated growth prediction photos using a dedicated app.

[1131] 6. Use of Emotion Engines

[1132] The device uses a camera to capture the user's facial expressions while viewing photos, and the emotion engine analyzes the expressions.

[1133] The terminal uses an emotion engine to recognize emotions and transmits them to the server.

[1134] The server adjusts the generation AI model based on the emotional information for future generations, generating photos that suit the user's preferences.

[1135] This allows the present invention to provide users with personalized photos of their child's predicted growth, providing greater entertainment value.The use of an emotion engine allows the system to adjust based on the user's reactions and emotions, providing optimal results for each individual user.

[1136] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1137] Step 1:

[1138] Users access a dedicated app or website, select a photo of their child and a photo of their parents or grandparents, or take a new photo and press the upload button.

[1139] Input: User selects or takes a photo

[1140] Output: Selected or taken photo data

[1141] Specific operation: The user launches the dedicated app on their smartphone or computer and clicks the "Upload photo" button within the app. If using a camera, the user launches the camera function within the app and takes a new photo.

[1142] Step 2:

[1143] The device sends the selected photo to the server.

[1144] Input: Photo data selected or taken by the user

[1145] Output: Photo data sent to the server

[1146] What it does: The app sends the photos to the server as an HTTP POST request, with a progress bar indicating the upload is in progress.

[1147] Step 3:

[1148] The server receives the photo data sent from the device and stores it in a file system or database.

[1149] Input: Photo data sent from the device

[1150] Output: Photo data stored in a file system or database

[1151] Specific operation: The server receives the photo data and stores it in a specified folder in the file system (e.g., / var / www / html / uploads / ) or in a database.

[1152] Step 4:

[1153] The server reads the stored photo data and uses an image processing library to unify the resolution of each photo and crop the facial areas.

[1154] Input: Photo data stored in a file system or database

[1155] Output: Photo data with uniform resolution and cropped face area

[1156] What it does: The server uses the OpenCV library to standardize the photo resolution to 1080x1080 pixels, and then uses algorithms like Haar Cascade to crop the face and remove unnecessary background.

[1157] Step 5:

[1158] The server extracts facial feature points (e.g., the positions of the eyes, nose, and mouth) from the cropped photo.

[1159] Input: Cropped photo data

[1160] Output: Extracted facial feature points data

[1161] What it does: The server uses the Dlib library to extract 68 facial feature points from the cropped photo.

[1162] Step 6:

[1163] The server combines the child's facial feature points with those of the parents or grandparents to form input data for the generative AI model.

[1164] Input: Child's facial feature point data and parent or grandparent's facial feature point data

[1165] Output: Formatted input data for a generative AI model

[1166] Specific operation: The server concatenates the coordinates of facial feature points into a series of vectors and converts them into the input format for the generative AI model.

[1167] Step 7:

[1168] The server inputs the formatted data into a generative AI model to predict and generate the child's future face.

[1169] Input: Formatted input data

[1170] Output: Generated growth prediction photo

[1171] How it works: The server inputs data into a generative AI model built with TensorFlow and PyTorch, predicts the child's future face, and generates a new photo.

[1172] Step 8:

[1173] The server transmits the generated growth prediction photo to the terminal.

[1174] Input: Generated growth prediction photo

[1175] Output: Growth prediction photo sent to the device

[1176] Specific operation: The server converts the generated photo into a format such as JPEG and sends it to the user's device as an HTTP response.

[1177] Step 9:

[1178] The terminal displays the generated growth prediction photo to the user.

[1179] Input: Growth prediction photo sent from the server

[1180] Output: A photo of the predicted growth shown to the user

[1181] Specific operation: The device displays the received photo in an app or website, and when the user taps the image, it becomes full-screen and can be zoomed in and out.

[1182] Step 10:

[1183] The device uses a camera to capture the user's facial expressions while viewing photos, and the emotion engine analyzes the images to recognize the user's emotions.

[1184] Input: User facial expression image

[1185] Output: Emotion recognition result data

[1186] Specific operation: The device automatically activates the camera and takes photos at regular intervals. An emotion engine (e.g., Microsoft Azure Emotion API) is used to analyze the captured images and recognize the user's emotions.

[1187] Step 11:

[1188] The device transmits the recognized emotion data to the server.

[1189] Input: Emotion recognition result data

[1190] Output: Emotion data sent to the server

[1191] Specific operation: The device sends the recognized emotion data in JSON format to the server. Example: "Smile: 80%, Surprise: 20%".

[1192] Step 12:

[1193] The server personalizes the generated photo based on the received emotion information.

[1194] Input: Emotional information data

[1195] Output: Personalized growth forecast photo

[1196] Specific operation: The server analyzes the received emotional information, adjusts the generation AI model from the next time onwards, and generates photos that suit the user's preferences. Adjustments are made, such as generating more photos of the age at which the user is most smiling.

[1197] (Application example 2)

[1198] 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."

[1199] While conventional growth prediction photo generation systems can predict future facial features based on photos of children and parents, they lack a means to determine how satisfying the generated photos are to users. As a result, they are unable to fully meet user needs, resulting in a limited user experience. Furthermore, since there is no system that can provide personalized predicted photos, they are unable to provide uniform results.

[1200] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving photos of the child and photos of the parents or grandparents, means for preprocessing the received photos and extracting facial feature points, means for shaping input data to the generative AI model using the extracted feature points, means for generating predicted growth photos of the child using the generative AI model, means for outputting the predicted growth photos, means for recognizing the user's facial expression and analyzing the emotion, and means for personalizing the predicted growth photos based on the user's emotion. This makes it possible to provide predicted growth photos personalized in accordance with the user's emotion, significantly improving the satisfaction of the user experience.

[1201] "Means for receiving photos" refers to the method by which the system receives photos of the child and parent or grandparent from the digital device.

[1202] The "pre-processing means" is a method for performing image processing such as unifying the resolution of received photographs and trimming facial areas.

[1203] The "means for extracting facial feature points" is a method for obtaining position information of important facial parts (for example, eyes, nose, and mouth) from a cropped facial photograph.

[1204] "Means for formatting input data for generative AI models" refers to a method for converting extracted feature points into an appropriate format and preparing them so that the AI ​​model can read them.

[1205] The "growth prediction photo generation method" is a method that uses a generative AI model to create a photo of a child's future face from shaped input data.

[1206] The "means for outputting predicted photos" is a method for displaying or transmitting the generated growth prediction photos to the user.

[1207] The "emotion recognition means" is a method for capturing facial expressions with a camera when a user views a generated photo and analyzing the emotions.

[1208] The "photo personalization means" is a method for adjusting the generated growth prediction photo to suit the user's preferences based on the recognized user's emotions.

[1209] The "user terminal transmission means" is a method for transmitting the generated growth prediction photo to a device used by the user.

[1210] A "generative AI model" is an artificial intelligence model that predicts a child's future face based on the characteristics of parents and grandparents learned in the past.

[1211] This invention combines emotion recognition functionality with a system for generating photos of children's future growth, providing a more personalized user experience. The system uses the following hardware and software: an image processing library (e.g., OpenCV), an artificial intelligence (AI) model (e.g., TensorFlow), and an emotion recognition engine (e.g., EmotionEngine).

[1212] First, a user takes photos of their child and their parents or grandparents using their smartphone, and uploads these photos to a cloud server through a dedicated application. The server receives the uploaded photos and stores them.

[1213] The received photos are first preprocessed using image processing libraries such as OpenCV to standardize the resolution of the photos and crop the facial area, then extract key facial features and format this data so that it can be fed into the generative AI model.

[1214] The rectified feature data is then input into a generative AI model such as TensorFlow to generate a photo of the child's future face. The generated photo of the predicted growth is then sent back to the user's smartphone by the server.

[1215] When a user views the generated photo, their smartphone camera captures their facial expression, which is then analyzed by the Emotion Engine. The emotional information obtained as a result of the analysis is sent to the server, and the growth prediction photo is personalized and regenerated based on this emotional data.

[1216] For example, if the user is smiling, a growth projection photo that best matches that emotion is generated. By repeating this process, it is possible to provide more finely tuned personalized results.

[1217] As a concrete example, the following is an example of a prompt sentence for a generative AI model:

[1218] "Generate a future photo of a 10-year-old based on the given child and parent photos."

[1219] As described above, this system analyzes the user's emotions in real time and generates personalized growth prediction photos accordingly, thereby improving the user experience.

[1220] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1221] Step 1:

[1222] A user uses a smartphone to take photos of their child and their parents or grandparents, and then uploads these photos to a cloud server using a dedicated application. The input here is the photo file taken with the smartphone camera, and the output is the photo file saved on the cloud server. Specifically, when the user presses the "upload photo" button in the app, the device sends the photo data to the server.

[1223] Step 2:

[1224] The server receives and stores the photo data sent from the device. The input is the photo data sent from the device, and the output is the photo data stored in the server's storage. Specifically, the server's receiving API receives the data and stores it in a database.

[1225] Step 3:

[1226] The server preprocesses the stored photo data. The target of preprocessing is the stored photo data, and in this step, the resolution is unified and facial areas are cropped. The output is preprocessed image data. Specifically, the server uses the OpenCV library to unify the image resolution, detect and crop facial areas.

[1227] Step 4:

[1228] The server extracts facial feature points from the preprocessed photo data. The input is the preprocessed image data, and the output is facial feature point data. In this step, OpenCV is used to detect important points on the face, such as the eyes, nose, and mouth. Specific operations involve the use of image analysis algorithms.

[1229] Step 5:

[1230] The server formats the input data for the generative AI model based on the extracted feature points. The input here is facial feature point data, and the output is data formatted in a format that can be applied to the generative AI model. Specifically, the server converts the feature point data into a one-dimensional array or tensor format.

[1231] Step 6:

[1232] The server uses a generative AI model to generate predicted photos of the child's growth. The input is shaped facial feature point data, and the output is the generated predicted photo of the child's growth. Specifically, a generative AI model such as TensorFlow runs to generate predicted photos based on facial feature points.

[1233] Step 7:

[1234] The server sends the generated growth forecast photo to the user's terminal. The input is the generated growth forecast photo, and the output is the growth forecast photo displayed on the user's terminal. Specifically, the server sends the data using the HTTP protocol.

[1235] Step 8:

[1236] When a user views the generated growth prediction photo on their smartphone, the device's camera captures the user's facial expression, which is then analyzed by the emotion engine. The input is the user's facial image captured by the smartphone camera, and the output is the analyzed emotion data. Specifically, the Emotion Engine receives the facial expression image and identifies the emotion.

[1237] Step 9:

[1238] The server personalizes the growth prediction photo based on the analyzed emotional data. The input is the analyzed emotional data and the generated growth prediction photo, and the output is a specific growth prediction photo selected based on the user's emotions. Specifically, the server runs the generative AI model again according to the emotional data to regenerate a result that best suits the user's emotions.

[1239] This allows the user to view personalized growth prediction photos that match their emotions.

[1240] 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.

[1241] 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.

[1242] 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.

[1243] [Fourth embodiment]

[1244] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1245] 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.

[1246] 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).

[1247] 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.

[1248] 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.

[1249] 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).

[1250] 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.

[1251] 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.

[1252] 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.

[1253] 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.

[1254] 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.

[1255] 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.

[1256] 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."

[1257] This invention is a system that generates predicted photos of a child's growth, and uses a generative AI model to predict and generate future photos of the child based on photos of the child and photos of the parents or grandparents entered by the user.

[1258] The system has the following main steps:

[1259] 1. Upload a photo

[1260] A user uses a device (such as a smartphone or computer) to upload photos of their child and parents or grandparents to a dedicated app or website.

[1261] The terminal transmits the uploaded photo data to the server.

[1262] 2. Receiving and saving photo data

[1263] The server receives the photo data sent from the terminal.

[1264] The server stores the received photo data in a file system or database.

[1265] 3. Data Preprocessing

[1266] The server reads the stored photo data.

[1267] The server uses an image processing library to standardize the resolution of each photo and crop the face area.

[1268] The server extracts facial feature points (e.g., the positions of the eyes, nose, and mouth) from the cropped photo.

[1269] 4. Training the generative AI model

[1270] The server formats the input data for the generative AI model based on the child's current feature points and those of the parents or grandparents.

[1271] The server inputs the post-surgery data into a generative AI model to generate a predicted photo. The generative AI model has previously learned the characteristics of the parents and grandparents, and uses this information to predict the child's future face.

[1272] 5. Output of generated results

[1273] The server transmits the generated growth prediction photo to the user's terminal.

[1274] The terminal displays the generated growth prediction photo.

[1275] Specific examples

[1276] For example, consider a case where a user uses a smartphone to upload current photos of their child and a photo of the parent to the system.

[1277] 1. Upload a photo

[1278] Users use the camera function on their smartphone to take photos of their child and parent and upload them through a dedicated app.

[1279] The device (smartphone) sends the captured photo to the server.

[1280] 2. Receiving and saving photo data

[1281] A server receives uploaded photo data of the child and parent.

[1282] The server stores the received photo data in a database.

[1283] 3. Data Preprocessing

[1284] The server loads the stored photo.

[1285] The server uses an open-source image processing library (e.g., OpenCV) to standardize the resolution of each photo and crop the face area.

[1286] The server extracts facial feature points and stores them in a database.

[1287] 4. Training the generative AI model

[1288] The server combines the facial feature points of the child with those of the parents to create input data for the generative AI model.

[1289] The server then feeds this input data to a generative AI model, which generates a photo of the child as they grow up. The generative AI model has already learned the characteristics of the parents and grandparents, and uses this information to predict what the child will look like in the future.

[1290] 5. Output of generated results

[1291] The server sends the generated growth prediction photo to the user's smartphone.

[1292] The device (smartphone) displays the generated growth prediction photos in a dedicated app, allowing users to check them and enjoy seeing what their child will look like in the future.

[1293] Through these steps, users can easily enjoy future photos of their children from the comfort of their own home. The predicted growth photos provided by the system are generated based on the characteristics of the parents or grandparents, resulting in realistic and interesting results.

[1294] The processing flow will be explained below.

[1295] Step 1:

[1296] The user uses the device to upload photos of their child and their parents or grandparents to a dedicated app or website. When the user clicks the upload button, the device sends the selected photo files to the server using an HTTP request.

[1297] Step 2:

[1298] The server receives the HTTP request and saves the sent photo data to the file system or database, records the path to the save destination, and adds the information to the database.

[1299] Step 3:

[1300] The server reads the stored photo data, standardizes the resolution of each photo using an image processing library (e.g., OpenCV), and runs a face detection algorithm to crop the face area.

[1301] Step 4:

[1302] The server extracts facial feature points (eyes, nose, and mouth) from the cropped face image using Dlib or a facial feature point detection algorithm, and stores the extracted feature point data in a database.

[1303] Step 5:

[1304] The server combines the child's feature point data with that of the parents or grandparents to create input data for the generative AI model. Data standardization (e.g., normalization using the mean and standard deviation) is also performed here.

[1305] Step 6:

[1306] The server inputs the formatted data into a generative AI model to generate a photo of the child's expected growth. This generative AI model is pre-trained on the characteristics of the parents and grandparents, and makes predictions based on this.

[1307] Step 7:

[1308] The server saves the generated growth prediction photo as an image file and converts it into a format that is easy for users to view (e.g., JPEG or PNG). After conversion, it generates an HTTP response and sends it to the user's device.

[1309] Step 8:

[1310] The device receives the generated photo data sent from the server. The received photo data is displayed through a dedicated application or web browser, allowing the user to check it. For example, a function is provided to display multiple age variations in slideshow format.

[1311] The above is a specific process flow for generating a photo of a child's expected growth.

[1312] Example 1

[1313] 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."

[1314] Conventional technologies have faced many challenges in accurately capturing individual facial features and providing users with results quickly and effectively when generating predicted images of a child's future face. In particular, the process of receiving photos, preprocessing, feature point extraction, inputting them into a generative model, and outputting the generated results is not performed smoothly, resulting in a poor user experience. There is a need for a system that solves this problem and allows users to easily and quickly obtain predicted photos of their child's growth.

[1315] 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.

[1316] In this invention, the server includes means for receiving a photo of the child and a photo of the parent or grandparent from a user terminal, means for resizing the received photo to a uniform resolution and cropping the face, means for extracting facial feature points from the cropped photo, means for shaping input data to a generative AI model using the extracted feature points, means for generating a photo of the child's predicted growth using the generative AI model, means for transmitting the generated photo of the predicted growth to the user terminal, and means for displaying the generated photo of the predicted growth on the user terminal. This makes it possible to realize a system that is easy for users to operate and allows them to quickly check results.

[1317] A "user terminal" is a computing device operated by a user, and is a general term for devices such as smartphones and personal computers used to perform tasks such as taking and uploading photos.

[1318] A "server" is a computer system responsible for receiving, storing, and processing data sent from user terminals.

[1319] "Receiving a photo" refers to the act of sending a photo of a child and photo data of a parent or grandparent from a user terminal to a server.

[1320] "Resolution resizing" refers to the process of changing the pixel count of an uploaded photo to unify its resolution to a specific standard size.

[1321] "Facial cropping" is an image processing technique that cuts out only the facial area from a photograph and removes the background and unnecessary parts.

[1322] "Feature point extraction" is the process of extracting specific positional information such as the eyes, nose, and mouth from a cropped facial photograph.

[1323] A "generative AI model" is an artificial intelligence model that has learned the facial features of parents and grandparents, and is an algorithm that uses this to predict and generate a child's future face.

[1324] "Input data formatting" refers to the process of preprocessing feature data to provide it in an appropriate format for a generative AI model.

[1325] A "growth prediction photo" is an image of a child's future face, predicted and generated using a generative AI model.

[1326] "Output" refers to the process of sending the generated growth prediction photo to a user terminal and displaying it to the user.

[1327] The present invention is a system for generating a child's growth forecast photo, which uses a generative AI model to predict the child's future face based on a user-provided photo of the child and photos of the parents or grandparents. The following describes an embodiment of the system in detail.

[1328] This system works in cooperation with a user device, a server, an image processing library, a generative AI model, and a database. Users take or upload photos using their device, such as a smartphone or PC, and the data is sent to the server. The server performs a series of preprocessing steps on the received photo data to extract feature points, and then generates a future facial image using the generative AI model.

[1329] The specific software and hardware used are as follows:

[1330] User terminal: A general-purpose computing device such as a smartphone or PC.

[1331] Server: A powerful computer system that stores and processes data.

[1332] Image processing libraries: Use open source libraries such as OpenCV and Dlib.

[1333] Generative AI models: Use pre-trained models using machine learning frameworks such as TensorFlow and PyTorch.

[1334] Database: A relational database such as MySQL or PostgreSQL to store photo and feature point data.

[1335] As a specific example of operation, consider a case where a user uses a smartphone to upload a current photo of the child and a photo of the parent to the system.

[1336] 1. Photo upload: Users use their smartphone's camera to take photos of their children and parents and upload them through a dedicated app.

[1337] 2. Receiving and storing photo data: The server receives the uploaded photo data of the child and parent and stores it in a database.

[1338] 3. Data preprocessing: The server reads the stored photos, standardizes the resolution of each photo using OpenCV, crops the face area, and extracts facial feature points and stores them in a database.

[1339] 4. Learning and prediction of the generative AI model: The server combines the facial feature points of the child and the parent to create input data for the generative AI model, which is then input into the generative AI model to generate a predicted photo of the child's growth.

[1340] 5. Output of generated results: The server sends the generated growth prediction photo to the user's smartphone, where it is displayed using a dedicated app on the device.

[1341] Examples of prompts include the following:

[1342] "Generate a future photo of the child's face using a photo of the child's current face and a photo of the parents' faces as input."

[1343] This allows users to easily enjoy future photos of their children from the comfort of their own home. The predicted growth photos provided by the system are generated based on the characteristics of the parents or grandparents, resulting in realistic and interesting results.

[1344] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1345] Step 1:

[1346] Upload a photo

[1347] A user takes photos of their child and their parents or grandparents and uploads these photos to a server via the Internet using a dedicated app.

[1348] Input: A photo of the child and a photo of the parent or grandparent (JPEG, PNG, or other format)

[1349] Specific operation: The user launches the dedicated app and takes a photo using the photo capture function, or selects an existing photo from the device's photo gallery. Then, the user presses the upload button, which generates an HTTP / HTTPS request to send the photo data to the server.

[1350] Step 2:

[1351] Receiving and saving photo data

[1352] The server receives the photo data sent from the user terminal, checks whether it is in the correct format, and then saves it.

[1353] Input: Photo data sent from the user device (HTTP / HTTPS request)

[1354] Output: Photo data stored in a database or file system

[1355] Specific operation: The server verifies the format and size of the received photo data and determines the appropriate storage path. The photo data is saved to the file system, and the reference path is stored in the database.

[1356] Step 3:

[1357] Data Preprocessing

[1358] The server reads the stored photo data and performs preprocessing to unify the resolution, crop faces, and extract feature points.

[1359] Input: Saved photo data

[1360] Output: Cropped face photo data and feature point data

[1361] What it does: The server uses OpenCV to resize the photo resolution (e.g., to 512x512 pixels), then uses the Dlib library to crop the face and extract the eye, nose, and mouth feature points from the face, which are then stored in a database.

[1362] Step 4:

[1363] Shaping input data for generative AI models

[1364] The server formats the feature data into a format suitable for input into a generative AI model.

[1365] Input: Feature point data for children and parents or grandparents

[1366] Output: Input data to the generative AI model

[1367] Specific operation: The server converts the feature point data into a Numpy array or similar format, and formats it in the format expected by the generative AI model. This includes specific arraying and data normalization.

[1368] Step 5:

[1369] Predictions from generative AI models

[1370] The server inputs the retouched input data into a generative AI model to generate a photo of the child's predicted growth.

[1371] Input: Formatted input data

[1372] Output: Generated growth prediction photo

[1373] How it works: The server inputs the formatted input data into the generative AI model and executes the model's inference process. The inference result is image data that predicts the child's future face. This image data is temporarily stored.

[1374] Step 6:

[1375] Output of generated results

[1376] The server transmits the generated growth prediction photo to the user terminal, which displays it.

[1377] Input: Generated growth prediction photo

[1378] Output: A photo of predicted growth displayed on the user's device

[1379] Specific operation: The server converts the generated photo into Base64 format or image file format and sends it to the user's device using the HTTP / HTTPS protocol. The photo received by the user's device is displayed in the image view of the dedicated app. The user can view it and enjoy the image of their future child.

[1380] (Application example 1)

[1381] 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."

[1382] In recent years, there has been an increasing demand for technology to predict children's growth, but current technology faces issues in terms of accuracy and convenience. In particular, there are few systems that can be easily used at home or used as a service in physical stores, and they do not meet the diverse needs of customers. There is a need for a system that can solve this problem and easily generate more accurate growth forecast photos.

[1383] 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.

[1384] In this invention, the server includes means for receiving photos of the child and photos of the parents or grandparents, means for preprocessing the received photos and extracting facial feature points, means for shaping input data to a generative AI model using the extracted feature points, means for generating predicted growth photos of the child using the generative AI model, means for outputting the generated predicted growth photos, and means for displaying the generated predicted growth photos on a customer's device via a dedicated app for the photo studio. This makes it possible to provide highly accurate predicted growth photos to customers not only at home but also as a service in physical stores.

[1385] "Child photo" is a current photo of the child that is used to make the growth prediction.

[1386] A "parent or grandparent photo" is a photo of a parent or grandparent that is relevant to the child in the growth prediction.

[1387] The "receiving means" is a means for receiving photo data from the user terminal to the server.

[1388] "Preprocessing" refers to performing initial processing such as adjusting the resolution of received photo data and trimming it.

[1389] "Facial feature points" are points that indicate specific parts of the face, such as the positions of the eyes, nose, and mouth.

[1390] A "generative AI model" is an artificial intelligence model that learns the characteristics of parents and grandparents in advance and generates predicted photos of a child's growth.

[1391] "Means for formatting input data" refers to means for arranging feature points into a format suitable for a generative AI model.

[1392] "Growth Prediction Photos" are photos of children's futures predicted using a generative AI model.

[1393] The "output means" is a means for displaying the generated growth prediction photograph to the user or customer.

[1394] A "photo studio dedicated app" is a mobile application developed to complement the services of a photo studio.

[1395] "Customer device" refers to an electronic device owned by the customer, such as a smartphone or tablet.

[1396] The present invention relates to a system for generating a photo of a child's future growth projection, and is implemented by the following method.

[1397] First, a user opens a dedicated app on a smartphone or tablet and uploads current photos of their child and photos of their parents or grandparents. The user's device then sends the uploaded photo data to a cloud server, which receives the photo data and automatically saves it.

[1398] Next, the cloud server preprocesses the received photo data. This preprocessing involves using an image processing library (e.g., OpenCV) to standardize the resolution of each photo and crop the facial area. It also performs processing to extract facial feature points (such as the positions of the eyes, nose, and mouth). The feature points are then extracted from the preprocessed data and formatted as input data for the generative AI model.

[1399] The cloud server uses a trained generative AI model (e.g., StyleGAN) to generate predicted photos of the child's growth based on the extracted feature points. Because the generative AI model has already learned the characteristics of the parents and grandparents, it can generate more realistic predicted photos.

[1400] The generated growth prediction photos are sent directly from the cloud server to the user's device via a dedicated app at the photo studio. Users can use the dedicated app to check the generated predicted photos and enjoy watching their child's growth. This system is also provided as a service at photo studios, so users can immediately receive highly accurate growth prediction photos at the photo studio.

[1401] As a concrete example, consider a photo gallery app where a user uploads a current photo of their child and a photo of their parents. Throughout this process, the following prompt is used: "Use the uploaded photos of the child and the parents to predict and generate a future photo of the child."

[1402] The system's components include devices such as smartphones and tablets, a cloud server, the image processing library OpenCV, and the generative AI model StyleGAN. This makes it possible to provide services at home or in photo studios, allowing users to easily generate and view photos of their children's growth predictions at any time.

[1403] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1404] Step 1:

[1405] The user uses a smartphone or tablet to upload a current photo of their child and a photo of their parents or grandparents to a dedicated app. The input is a photo of the child and a photo of the parents or grandparents. This photo data is uploaded and sent to a cloud server. The output is the photo data transferred to the cloud server.

[1406] Step 2:

[1407] The server saves the received photo data and stores it in a database. The input is the photo data sent by the user. Specifically, the server saves the photo data in a specific folder and stores the corresponding metadata in the database. The output is the saved photo data and its metadata.

[1408] Step 3:

[1409] The server uses an image processing library (OpenCV) to preprocess the photo data. The input is the stored photo data. Specifically, the server standardizes the resolution of the photos and crops the facial area. This preprocessing ensures accurate feature point extraction in the subsequent process. The output is cropped facial image data with a standardized resolution.

[1410] Step 4:

[1411] The server extracts facial feature points (such as the positions of the eyes, nose, and mouth) from the cropped face image. The input is the cropped face image data. Specifically, it uses OpenCV's face recognition algorithm to detect the feature points and saves them in a database. The output is the extracted facial feature point data.

[1412] Step 5:

[1413] The server uses the extracted feature point data to format it as input data for a generative AI model (StyleGAN). The input is facial feature point data. Specifically, it converts the feature point data into a format suitable for the AI ​​model. The output is formatted input data for the AI ​​model.

[1414] Step 6:

[1415] The server provides the formatted input data to the generative AI model to generate predicted photos of the child's growth. The input is the formatted AI model input data. Specifically, the generative AI model is executed to generate predicted photos of the child's future. The output is the generated predicted photos of the child's growth.

[1416] Step 7:

[1417] The server stores the generated growth prediction photos on a cloud server and sends them to the user's device via the photo studio's dedicated app. The input is the generated growth prediction photos. Specifically, the server converts the generated photos into an appropriate format for display on the user interface of the dedicated app and sends them to the user's device. The output is the growth prediction photos displayed on the user's device.

[1418] Through these steps, users can view highly accurate photos of their child's growth predictions through a dedicated app. This can also be used as a service in photo studios, improving customer satisfaction.

[1419] 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.

[1420] This invention combines an emotion engine with a system that generates photos of children's future growth, providing a more personalized experience. Based on photos of the child and parents or grandparents entered by the user, a generative AI model is used to predict and generate future photos of the child, and furthermore, the user's emotions are recognized, improving the user experience.

[1421] The main steps of the system are explained.

[1422] 1. Upload a photo

[1423] A user uses a device (such as a smartphone or computer) to upload photos of their child and parents or grandparents to a dedicated app or website.

[1424] The terminal transmits the uploaded photo data to the server.

[1425] 2. Receiving and saving photo data

[1426] The server receives the photo data sent from the terminal.

[1427] The server stores the received photo data in a file system or database.

[1428] 3. Data Preprocessing

[1429] The server reads the stored photo data.

[1430] The server uses an image processing library to standardize the resolution of each photo and crop the face area.

[1431] The server extracts facial feature points (e.g., the positions of the eyes, nose, and mouth) from the cropped photo.

[1432] 4. Training the generative AI model

[1433] The server formats the input data for the generative AI model based on the child's current feature points and those of the parents or grandparents.

[1434] The server inputs the post-surgery data into a generative AI model to generate a predicted photo. The generative AI model has previously learned the characteristics of the parents and grandparents, and uses this information to predict the child's future face.

[1435] 5. Output of generated results

[1436] The server transmits the generated growth prediction photo to the user's terminal.

[1437] The terminal displays the generated growth prediction photo.

[1438] 6. Use of Emotion Engines

[1439] The device uses a camera to capture the user's facial expressions while viewing photos, and the emotion engine analyzes the images to recognize the user's emotions, for example, whether the user is smiling, surprised, or expressing other emotions.

[1440] The emotion engine transmits the recognized emotion information to the server.

[1441] The server personalizes the generated growth prediction photos based on the received emotion information, providing results that meet the user's preferences, such as generating more photos of the ages that the user finds particularly exciting.

[1442] Specific examples

[1443] For example, consider a case where a user uses a smartphone to upload current photos of their child and a photo of the parent to the system.

[1444] 1. Upload a photo

[1445] Users use the camera function on their smartphone to take photos of their child and parent and upload them through a dedicated app.

[1446] The device (smartphone) sends the captured photo to the server.

[1447] 2. Receiving and saving photo data

[1448] A server receives uploaded photo data of the child and parent.

[1449] The server stores the received photo data in a database.

[1450] 3. Data Preprocessing

[1451] The server loads the stored photo.

[1452] The server uses an open-source image processing library (e.g., OpenCV) to standardize the resolution of each photo and crop the face area.

[1453] The server extracts facial feature points and stores them in a database.

[1454] 4. Training the generative AI model

[1455] The server combines the facial feature points of the child with those of the parents to create input data for the generative AI model.

[1456] The server then feeds this input data to a generative AI model, which generates a photo of the child as they grow up. The generative AI model has already learned the characteristics of the parents and grandparents, and uses this information to predict the child's future face.

[1457] 5. Output of generated results

[1458] The server sends the generated growth prediction photo to the user's smartphone.

[1459] The device (smartphone) displays the generated growth prediction photo using a dedicated app.

[1460] 6. Use of Emotion Engines

[1461] The device uses a camera to capture the user's facial expressions while viewing photos, and the emotion engine recognizes emotions from the facial expressions, for example, analyzing whether the user is smiling.

[1462] The emotion engine sends the recognized emotion to the server.

[1463] The server uses the emotional information to adjust the generation AI model for future use, or generates photos according to the user's preferences.

[1464] Through these steps, the present invention enables the generation of personalized child growth forecast photos for each user, providing greater entertainment value.The use of an emotion engine allows the system to be more precisely adjusted based on the user's reactions and emotions, providing optimal results for each individual user.

[1465] The processing flow will be explained below.

[1466] Step 1:

[1467] The user uses the device to upload photos of their child and their parents or grandparents to a dedicated app or website. When the user clicks the upload button, the device sends the selected photo files to the server using an HTTP request.

[1468] Step 2:

[1469] The server receives the HTTP request and saves the sent photo data to the file system or database, records the path to the save destination, and adds the information to the database.

[1470] Step 3:

[1471] The server reads the stored photo data, standardizes the resolution of each photo using an image processing library (e.g., OpenCV), and runs a face detection algorithm to crop the face area.

[1472] Step 4:

[1473] The server extracts facial feature points (eyes, nose, and mouth) from the cropped face image using Dlib or a facial feature point detection algorithm, and stores the extracted feature point data in a database.

[1474] Step 5:

[1475] The server combines the child's feature point data with that of the parents or grandparents to create input data for the generative AI model. Data standardization (e.g., normalization using the mean and standard deviation) is also performed here.

[1476] Step 6:

[1477] The server inputs the formatted data into a generative AI model to generate a photo of the child's expected growth. This generative AI model is pre-trained on the characteristics of the parents and grandparents, and makes predictions based on this.

[1478] Step 7:

[1479] The server saves the generated growth prediction photo as an image file and converts it into a format that is easy for users to view (e.g., JPEG or PNG). After conversion, it generates an HTTP response and sends it to the user's device.

[1480] Step 8:

[1481] The device receives the generated photo data sent from the server. The received photo data is displayed through a dedicated application or web browser, allowing the user to check it. For example, a function is provided to display multiple age variations in slideshow format.

[1482] Step 9:

[1483] The device uses a camera to capture the user's facial expressions while viewing photos, and the emotion engine analyzes the facial images to recognize the user's emotions, such as whether the user is smiling or surprised.

[1484] Step 10:

[1485] The emotion engine transmits the recognized emotion information to the server.

[1486] Step 11:

[1487] The server personalizes the generated growth prediction photos based on the received emotion information, providing results that meet the user's preferences, such as generating more photos of the ages that the user finds particularly exciting.

[1488] Step 12:

[1489] The server will adjust the generation AI model based on the emotional information from the next time onwards, so that it will generate predicted photos that better suit the user's preferences.

[1490] The above is the specific processing flow of the invention that combines an emotion engine that recognizes the user's emotions.

[1491] Example 2

[1492] 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."

[1493] Conventional systems that generate photos of children's growth predictions have had the problem of reducing the user experience because the generated photos do not necessarily reflect the emotions and preferences of individual users. In addition, the generated photos often have a cold, impersonal feel, making it difficult to feel close to the child.

[1494] 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.

[1495] In this invention, the server includes means for receiving photos of the child and photos of the parents or grandparents, means for preprocessing the received photos and extracting facial feature points, means for shaping input data to a generative AI model using the extracted feature points, means for generating predicted growth photos of the child using the generative AI model, means for outputting the generated predicted growth photos, means for capturing a user's facial expression and recognizing emotions, and means for personalizing the generated photos based on the recognized emotion information. This enables personalization according to the user's emotions, not only providing a higher user experience but also making the generated photos more familiar to the user.

[1496] "Children's photos" refers to image data that includes a child's face.

[1497] "Parent or grandparent photo" refers to image data that shows the face of a child's parent or grandparent.

[1498] The "receiving means" is a communication interface for receiving photo data from other devices (for example, an HTTP request via the Internet).

[1499] "Means for pre-processing and extracting facial features" refers to the process of analyzing photographic data using image processing technology to extract facial contours and features such as eyes, nose, and mouth.

[1500] "Means for formatting input data for a generative AI model" refers to the process of processing the extracted features into an appropriate format and preparing them as input to a generative AI model.

[1501] "Method of generating predicted photos of a child's growth using a generative AI model" refers to the process in which an AI algorithm uses shaped input data to predict a child's future face and generate it as an image.

[1502] The "means for outputting the generated growth prediction photograph" refers to a process for displaying, saving, or transmitting the generated image data to another device.

[1503] "Means for capturing the user's facial expressions and recognizing emotions" refers to the process of taking a picture of the user's face with a camera and analyzing the image to determine the user's emotions.

[1504] "Means for personalizing the generated photo based on recognized emotional information" refers to the process of adjusting the generated image data based on the user's emotional data to make it more in line with the user's preferences.

[1505] MODE FOR CARRYING OUT THE INVENTION

[1506] This invention combines an emotion engine with a system that generates photos of children's future growth, providing a more personalized experience. Based on photos of the child and parents or grandparents entered by the user, a generative AI model is used to predict and generate future photos of the child, and furthermore, the user's emotions are recognized, improving the user experience.

[1507] First, users upload photos of their child and their parents or grandparents through a dedicated app or website. Using a smartphone or computer, users can easily select, take, and upload photos by following the app's instructions. Specifically, the following hardware and software are required:

[1508] Hardware:

[1509] Smartphones, PCs, servers

[1510] Camera function (built into smartphones and computers)

[1511] software:

[1512] Dedicated app and website

[1513] Image processing library (e.g. OpenCV)

[1514] Generative AI models (e.g., implemented in TensorFlow or PyTorch)

[1515] Emotion engine (e.g. Microsoft Azure Emotion API)

[1516] When a photo is uploaded, the device sends it to the server. The server receives the photo data and stores it in a file system or database. The server then reads the stored photo data and uses an image processing library (e.g., OpenCV) to unify the resolution of each photo and crop the facial area. From the cropped photos, the server extracts facial feature points (e.g., the positions of the eyes, nose, and mouth).

[1517] Next, the server combines the facial feature points of the child with those of the parents or grandparents to create input data for the generative AI model. The resulting data is then input into the generative AI model to predict and generate the child's future face. The generative AI model has previously learned the features of the parents and grandparents, and predicts the child's future face based on this information.

[1518] The generated growth prediction photos are sent from the server to the user's device and displayed on the device. Users can view, comment on, and save the photos through the app.

[1519] Furthermore, the system uses an emotion engine to recognize the user's emotions. While the user is viewing photos, the device's camera captures the user's facial expressions, which are then analyzed by the emotion engine. The emotion engine identifies whether the user is smiling, surprised, etc., and sends this emotional information to the server. The server can then personalize the generated growth prediction photos based on the received emotional information. For example, it can adjust the system to generate more photos of the age at which the user is particularly excited.

[1520] Specific examples

[1521] For example, if a user uses a smartphone to upload a current photo of the child and a photo of the parent to the system:

[1522] 1. Upload a photo

[1523] Users take photos of their children and parents using the camera on their smartphones and upload them through a dedicated app.

[1524] The device (smartphone) sends the photos it has taken to the server.

[1525] 2. Receiving and saving photo data

[1526] The server receives the uploaded photo data of the child and the parent.

[1527] The server stores the received photo data in a database.

[1528] 3. Data Preprocessing

[1529] The server loads the stored photo.

[1530] The server uses an open source image processing library (e.g., OpenCV) to standardize the resolution of each photo and crop the face area.

[1531] The server extracts facial feature points and stores them in a database.

[1532] 4. Training the generative AI model

[1533] The server combines the child's facial feature points with the parent's to create input data for the generative AI model.

[1534] The server feeds this input data into a generative AI model to generate a photo of the child's predicted growth.

[1535] 5. Output of generated results

[1536] The server sends the generated growth forecast photo to the user's smartphone.

[1537] The device (smartphone) displays the generated growth prediction photos using a dedicated app.

[1538] 6. Use of Emotion Engines

[1539] The device uses a camera to capture the user's facial expressions while viewing photos, and the emotion engine analyzes the expressions.

[1540] The terminal uses an emotion engine to recognize emotions and transmits them to the server.

[1541] The server adjusts the generation AI model based on the emotional information for future generations, generating photos that suit the user's preferences.

[1542] This allows the present invention to provide users with personalized photos of their child's predicted growth, providing greater entertainment value.The use of an emotion engine allows the system to adjust based on the user's reactions and emotions, providing optimal results for each individual user.

[1543] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1544] Step 1:

[1545] Users access a dedicated app or website, select a photo of their child and a photo of their parents or grandparents, or take a new photo and press the upload button.

[1546] Input: User selects or takes a photo

[1547] Output: Selected or taken photo data

[1548] Specific operation: The user launches the dedicated app on their smartphone or computer and clicks the "Upload photo" button within the app. If using a camera, the user launches the camera function within the app and takes a new photo.

[1549] Step 2:

[1550] The device sends the selected photo to the server.

[1551] Input: Photo data selected or taken by the user

[1552] Output: Photo data sent to the server

[1553] What it does: The app sends the photos to the server as an HTTP POST request, with a progress bar indicating the upload is in progress.

[1554] Step 3:

[1555] The server receives the photo data sent from the device and stores it in a file system or database.

[1556] Input: Photo data sent from the device

[1557] Output: Photo data stored in a file system or database

[1558] Specific operation: The server receives the photo data and stores it in a specified folder in the file system (e.g., / var / www / html / uploads / ) or in a database.

[1559] Step 4:

[1560] The server reads the stored photo data and uses an image processing library to unify the resolution of each photo and crop the facial areas.

[1561] Input: Photo data stored in a file system or database

[1562] Output: Photo data with uniform resolution and cropped face area

[1563] What it does: The server uses the OpenCV library to standardize the photo resolution to 1080x1080 pixels, and then uses algorithms like Haar Cascade to crop the face and remove unnecessary background.

[1564] Step 5:

[1565] The server extracts facial feature points (e.g., the positions of the eyes, nose, and mouth) from the cropped photo.

[1566] Input: Cropped photo data

[1567] Output: Extracted facial feature points data

[1568] What it does: The server uses the Dlib library to extract 68 facial feature points from the cropped photo.

[1569] Step 6:

[1570] The server combines the child's facial feature points with those of the parents or grandparents to form input data for the generative AI model.

[1571] Input: Child's facial feature point data and parent or grandparent's facial feature point data

[1572] Output: Formatted input data for a generative AI model

[1573] Specific operation: The server concatenates the coordinates of facial feature points into a series of vectors and converts them into the input format for the generative AI model.

[1574] Step 7:

[1575] The server inputs the formatted data into a generative AI model to predict and generate the child's future face.

[1576] Input: Formatted input data

[1577] Output: Generated growth prediction photo

[1578] How it works: The server inputs data into a generative AI model built with TensorFlow and PyTorch, predicts the child's future face, and generates a new photo.

[1579] Step 8:

[1580] The server transmits the generated growth prediction photo to the terminal.

[1581] Input: Generated growth prediction photo

[1582] Output: Growth prediction photo sent to the device

[1583] Specific operation: The server converts the generated photo into a format such as JPEG and sends it to the user's device as an HTTP response.

[1584] Step 9:

[1585] The terminal displays the generated growth prediction photo to the user.

[1586] Input: Growth prediction photo sent from the server

[1587] Output: A photo of the predicted growth shown to the user

[1588] Specific operation: The device displays the received photo in an app or website, and when the user taps the image, it becomes full-screen and can be zoomed in and out.

[1589] Step 10:

[1590] The device uses a camera to capture the user's facial expressions while viewing photos, and the emotion engine analyzes the images to recognize the user's emotions.

[1591] Input: User facial expression image

[1592] Output: Emotion recognition result data

[1593] Specific operation: The device automatically activates the camera and takes photos at regular intervals. An emotion engine (e.g., Microsoft Azure Emotion API) is used to analyze the captured images and recognize the user's emotions.

[1594] Step 11:

[1595] The device transmits the recognized emotion data to the server.

[1596] Input: Emotion recognition result data

[1597] Output: Emotion data sent to the server

[1598] Specific operation: The device sends the recognized emotion data in JSON format to the server. Example: "Smile: 80%, Surprise: 20%".

[1599] Step 12:

[1600] The server personalizes the generated photo based on the received emotion information.

[1601] Input: Emotional information data

[1602] Output: Personalized growth forecast photo

[1603] Specific operation: The server analyzes the received emotional information, adjusts the generation AI model from the next time onwards, and generates photos that suit the user's preferences. Adjustments are made, such as generating more photos of the age at which the user is most smiling.

[1604] (Application example 2)

[1605] 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."

[1606] While conventional growth prediction photo generation systems can predict future facial features based on photos of children and parents, they lack a means to determine how satisfying the generated photos are to users. As a result, they are unable to fully meet user needs, resulting in a limited user experience. Furthermore, since there is no system that can provide personalized predicted photos, they are unable to provide uniform results.

[1607] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving photos of the child and photos of the parents or grandparents, means for preprocessing the received photos and extracting facial feature points, means for shaping input data to the generative AI model using the extracted feature points, means for generating predicted growth photos of the child using the generative AI model, means for outputting the predicted growth photos, means for recognizing the user's facial expression and analyzing the emotion, and means for personalizing the predicted growth photos based on the user's emotion. This makes it possible to provide predicted growth photos personalized in accordance with the user's emotion, significantly improving the satisfaction of the user experience.

[1608] "Means for receiving photos" refers to the method by which the system receives photos of the child and parent or grandparent from the digital device.

[1609] The "pre-processing means" is a method for performing image processing such as unifying the resolution of received photographs and trimming facial areas.

[1610] The "means for extracting facial feature points" is a method for obtaining position information of important facial parts (for example, eyes, nose, and mouth) from a cropped facial photograph.

[1611] "Means for formatting input data for generative AI models" refers to a method for converting extracted feature points into an appropriate format and preparing them so that the AI ​​model can read them.

[1612] The "growth prediction photo generation method" is a method that uses a generative AI model to create a photo of a child's future face from shaped input data.

[1613] The "means for outputting predicted photos" is a method for displaying or transmitting the generated growth prediction photos to the user.

[1614] The "emotion recognition means" is a method for capturing facial expressions with a camera when a user views a generated photo and analyzing the emotions.

[1615] The "photo personalization means" is a method for adjusting the generated growth prediction photo to suit the user's preferences based on the recognized user's emotions.

[1616] The "user terminal transmission means" is a method for transmitting the generated growth prediction photo to a device used by the user.

[1617] A "generative AI model" is an artificial intelligence model that predicts a child's future face based on the characteristics of parents and grandparents learned in the past.

[1618] This invention combines emotion recognition functionality with a system for generating photos of children's future growth, providing a more personalized user experience. The system uses the following hardware and software: an image processing library (e.g., OpenCV), an artificial intelligence (AI) model (e.g., TensorFlow), and an emotion recognition engine (e.g., EmotionEngine).

[1619] First, a user takes photos of their child and their parents or grandparents using their smartphone, and uploads these photos to a cloud server through a dedicated application. The server receives the uploaded photos and stores them.

[1620] The received photos are first preprocessed using image processing libraries such as OpenCV to standardize the resolution of the photos and crop the facial area, then extract key facial features and format this data so that it can be fed into the generative AI model.

[1621] The rectified feature data is then input into a generative AI model such as TensorFlow to generate a photo of the child's future face. The generated photo of the predicted growth is then sent back to the user's smartphone by the server.

[1622] When a user views the generated photo, their smartphone camera captures their facial expression, which is then analyzed by the Emotion Engine. The emotional information obtained as a result of the analysis is sent to the server, and the growth prediction photo is personalized and regenerated based on this emotional data.

[1623] For example, if the user is smiling, a growth projection photo that best matches that emotion is generated. By repeating this process, it is possible to provide more finely tuned personalized results.

[1624] As a concrete example, the following is an example of a prompt sentence for a generative AI model:

[1625] "Generate a future photo of a 10-year-old based on the given child and parent photos."

[1626] As described above, this system analyzes the user's emotions in real time and generates personalized growth prediction photos accordingly, thereby improving the user experience.

[1627] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1628] Step 1:

[1629] A user uses a smartphone to take photos of their child and their parents or grandparents, and then uploads these photos to a cloud server using a dedicated application. The input here is the photo file taken with the smartphone camera, and the output is the photo file saved on the cloud server. Specifically, when the user presses the "upload photo" button in the app, the device sends the photo data to the server.

[1630] Step 2:

[1631] The server receives and stores the photo data sent from the device. The input is the photo data sent from the device, and the output is the photo data stored in the server's storage. Specifically, the server's receiving API receives the data and stores it in a database.

[1632] Step 3:

[1633] The server preprocesses the stored photo data. The target of preprocessing is the stored photo data, and in this step, the resolution is unified and facial areas are cropped. The output is preprocessed image data. Specifically, the server uses the OpenCV library to unify the image resolution, detect and crop facial areas.

[1634] Step 4:

[1635] The server extracts facial feature points from the preprocessed photo data. The input is the preprocessed image data, and the output is facial feature point data. In this step, OpenCV is used to detect important points on the face, such as the eyes, nose, and mouth. Specific operations involve the use of image analysis algorithms.

[1636] Step 5:

[1637] The server formats the input data for the generative AI model based on the extracted feature points. The input here is facial feature point data, and the output is data formatted in a format that can be applied to the generative AI model. Specifically, the server converts the feature point data into a one-dimensional array or tensor format.

[1638] Step 6:

[1639] The server uses a generative AI model to generate predicted photos of the child's growth. The input is shaped facial feature point data, and the output is the generated predicted photo of the child's growth. Specifically, a generative AI model such as TensorFlow runs to generate predicted photos based on facial feature points.

[1640] Step 7:

[1641] The server sends the generated growth forecast photo to the user's terminal. The input is the generated growth forecast photo, and the output is the growth forecast photo displayed on the user's terminal. Specifically, the server sends the data using the HTTP protocol.

[1642] Step 8:

[1643] When a user views the generated growth prediction photo on their smartphone, the device's camera captures the user's facial expression, which is then analyzed by the emotion engine. The input is the user's facial image captured by the smartphone camera, and the output is the analyzed emotion data. Specifically, the Emotion Engine receives the facial expression image and identifies the emotion.

[1644] Step 9:

[1645] The server personalizes the growth prediction photo based on the analyzed emotional data. The input is the analyzed emotional data and the generated growth prediction photo, and the output is a specific growth prediction photo selected based on the user's emotions. Specifically, the server runs the generative AI model again according to the emotional data to regenerate a result that best suits the user's emotions.

[1646] This allows the user to view personalized growth prediction photos that match their emotions.

[1647] 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.

[1648] 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.

[1649] 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.

[1650] 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.

[1651] 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.

[1652] 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.

[1653] 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).

[1654] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1655] 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."

[1656] 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.

[1657] 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).

[1658] 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.

[1659] 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.

[1660] 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.

[1661] 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.

[1662] 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.

[1663] 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.

[1664] 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.

[1665] 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.

[1666] 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.

[1667] 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.

[1668] The following is further disclosed regarding the above embodiment.

[1669] (Claim 1)

[1670] means for receiving a photograph of the child and a photograph of the parent or grandparent;

[1671] means for pre-processing the received photograph and extracting facial feature points;

[1672] A means for shaping input data into a generative AI model using the extracted feature points;

[1673] A means for generating a child's growth prediction photo using the generative AI model;

[1674] a means for outputting the generated growth prediction photograph;

[1675] A system including:

[1676] (Claim 2)

[1677] The system of claim 1, further comprising means for transmitting the generated growth prediction photo to a user terminal.

[1678] (Claim 3)

[1679] 10. The system of claim 1, wherein the generative AI model has learned characteristics of parents or grandparents.

[1680] "Example 1"

[1681] (Claim 1)

[1682] means for receiving a photograph of the child and a photograph of the parent or grandparent from the user terminal;

[1683] means for resizing the received photograph to a uniform resolution and cropping facial areas;

[1684] means for extracting facial feature points from the cropped photograph;

[1685] A means for shaping input data into a generative AI model using the extracted feature points;

[1686] A means for generating a child's growth prediction photo using the generative AI model;

[1687] means for transmitting the generated growth prediction photograph to a user terminal;

[1688] a means for displaying the generated growth prediction photograph on the user terminal;

[1689] A system including:

[1690] (Claim 2)

[1691] The system according to claim 1 , further comprising means for temporarily storing the generated growth prediction photograph.

[1692] (Claim 3)

[1693] 10. The system of claim 1, wherein the generative AI model has learned characteristics of parents or grandparents.

[1694] "Application Example 1"

[1695] (Claim 1)

[1696] means for receiving a photograph of the child and a photograph of the parent or grandparent;

[1697] means for pre-processing the received photograph and extracting facial feature points;

[1698] A means for shaping input data into a generative AI model using the extracted feature points;

[1699] A means for generating a child's growth prediction photo using the generative AI model;

[1700] a means for outputting the generated growth prediction photograph;

[1701] a means for displaying the generated growth forecast photo on a customer's terminal via a dedicated app of the photo studio;

[1702] A system including:

[1703] (Claim 2)

[1704] The system of claim 1, further comprising means for transmitting the generated growth prediction photo to a user terminal.

[1705] (Claim 3)

[1706] 10. The system of claim 1, wherein the generative AI model has learned characteristics of parents or grandparents.

[1707] "Example 2: Combining Emotion Engines"

[1708] (Claim 1)

[1709] means for receiving a photograph of the child and a photograph of the parent or grandparent;

[1710] means for pre-processing the received photograph and extracting facial feature points;

[1711] A means for shaping input data into a generative AI model using the extracted feature points;

[1712] A means for generating a child's growth prediction photo using the generative AI model;

[1713] a means for outputting the generated growth prediction photograph;

[1714] means for capturing a user's facial expressions and recognizing emotions;

[1715] A means for personalizing the generated photo based on the recognized emotion information; and

[1716] A system including:

[1717] (Claim 2)

[1718] The system of claim 1, further comprising means for transmitting the generated growth prediction photo to a user terminal.

[1719] (Claim 3)

[1720] 10. The system of claim 1, wherein the generative AI model has learned characteristics of parents or grandparents.

[1721] "Application example 2 when combining emotion engines"

[1722] (Claim 1)

[1723] means for receiving a photograph of the child and a photograph of the parent or grandparent;

[1724] means for pre-processing the received photograph and extracting facial feature points;

[1725] A means for shaping input data into a generative AI model using the extracted feature points;

[1726] A means for generating a child's growth prediction photo using the generative AI model;

[1727] a means for outputting the generated growth prediction photograph;

[1728] means for recognizing a user's facial expression and analyzing the emotion;

[1729] A means for personalizing the growth prediction photo based on the user's emotions;

[1730] A system including:

[1731] (Claim 2)

[1732] The system of claim 1, further comprising means for transmitting the generated growth prediction photo to a user terminal.

[1733] (Claim 3)

[1734] 10. The system of claim 1, wherein the generative AI model has learned characteristics of parents or grandparents. [Explanation of symbols]

[1735] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving a photograph of the child and a photograph of the parent or grandparent; means for pre-processing the received photograph and extracting facial feature points; A means for shaping input data into a generative AI model using the extracted feature points; A means for generating a child's growth prediction photo using the generative AI model; a means for outputting the generated growth prediction photograph; A system including:

2. The system according to claim 1 , further comprising means for transmitting the generated growth prediction photograph to a user terminal.

3. The system of claim 1 , wherein the generative AI model has learned characteristics of parents or grandparents.

Images