system

Abstract

We provide the system. [Solution] A means for a user to acquire an image of their own face using the camera of a smart device, and an image acquisition means for processing the acquired face image, A generation means for generating a post-makeup facial image based on a generative model for analyzing facial shape and skin tone, A means for displaying the face image after makeup application, generated by the generation means, on the user's smart device, and a presentation means for providing information related to the makeup, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In conventional makeup technologies, there is a problem that it takes a lot of time and cost for users to try out the most suitable makeup style for themselves. Also, in many cases, it is impossible to try it without going to a store, and it is difficult to provide an environment where makeup can be easily tried. Furthermore, it is difficult to find makeup suitable for an individual face shape and skin tone, and the means for receiving appropriate advice are limited.

Means for Solving the Problems

[0005] This invention solves these problems by allowing users to acquire images of their own faces using the camera of a smart device, analyzing the shape of their faces and skin tone based on a generative model, and generating realistic images of their faces after makeup has been applied. Specifically, it provides a system that includes image acquisition means, generation means, presentation means, and decision-making means for recommending makeup products and brands based on the user's attributes and counseling content. This system displays the generated images of faces after makeup on the user's smart device and also provides related makeup information and products. In this way, users can easily try out appropriate makeup styles, eliminating the difficulty of product selection and the hassle of trial and error.

[0006] "Image acquisition means" refers to a means for a user to acquire an image of their own face using the camera of a smart device.

[0007] The "generation means" refers to a means for processing acquired facial images and generating a post-makeup facial image based on a generative model that analyzes facial shape and skin tone.

[0008] "Presentation means" refers to means for displaying the post-makeup face image generated by the generation means on the user's smart device and for presenting related makeup information and products.

[0009] A "user" is an individual who utilizes makeup counseling and related services.

[0010] A "smart device" refers to a portable electronic device, such as a smartphone or tablet, that has internet connectivity and can run a variety of applications.

[0011] A "generative model" is a general term for machine learning models and algorithms used to analyze a user's facial shape and skin tone and generate a makeup-applied facial image.

[0012] "Decision-making tools" refer to methods for recommending appropriate makeup products and brands based on the user's attributes and counseling content.

[0013] A "face image" refers to image data of a user's face.

[0014] "Skin tone" refers to the characteristics that indicate the color and texture of a user's skin.

[0015] A "post-makeup face image" is an image created by a generation method that simulates the user's face after makeup has been applied.

[0016] "Counseling content" refers to information such as the user's desired makeup style, favorite brands, and favorite celebrities.

[0017] "Attributes" refer to personal characteristics of a user, such as gender, age, and skin type.

[0018] "Recommendation" means suggesting specific makeup products or brands to users based on analysis results.

[0019] A "purchase site" is a website or online store where users can buy makeup products online.

[0020] "Targeted advertising" refers to the delivery of advertisements that are customized based on the user's attributes and behavioral history.

[0021] A "special offer" refers to benefits such as discounts or promotions offered to specific users.

[0022] "Behavioral tracking" refers to recording and analyzing users' actions within an app (such as clicks, purchases, and page views). [Brief explanation of the drawing]

[0023] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0024] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0025] First, let's explain the terminology used in the following explanation.

[0026] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0027] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0028] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0029] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0030] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0031] [First Embodiment]

[0032] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0033] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0034] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0035] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0036] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0037] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0038] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0039] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0040] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0041] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0042] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0043] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0044] Embodiments of the present invention will be described in detail below. This system acquires a facial image using the user's smart device, generates a facial image with makeup applied using a generative model, and displays it on the terminal.

[0045] System Overview

[0046] The system includes image acquisition, generation, and presentation means. The user uses a smart device (such as a smartphone or tablet) to acquire an image of their face and inputs information necessary for makeup consultation. This data is sent to a server, where a generation model performs analysis. Based on the analysis results, a post-makeup face image is generated and presented to the user's device.

[0047] Program execution flow

[0048] 1. Image acquisition and upload

[0049] The user takes a picture of their face using the camera on their smart device. The device displays the captured image for confirmation, and when the user clicks the "Upload" button, the image is sent to the server.

[0050] Example: The user opens the app and takes a photo of their face in selfie mode. After taking the photo, they press the upload button, and the image is sent to the server.

[0051] 2. Entering counseling details

[0052] The device displays a form for the user to enter information such as their makeup consultation details, ideal style, and preferred brands. Once the user completes the form and clicks the submit button, the data is sent to the server.

[0053] Example: A user enters "I would like natural makeup" into the form and clicks the submit button.

[0054] 3. Analysis of images and counseling content

[0055] The server analyzes the received facial image and counseling content. Using a generative model, it analyzes the user's facial shape and skin tone, and processes the data to determine the user's ideal makeup style.

[0056] Specific example: The server analyzes a facial image, determines that the user's skin tone is neutral, and then decides on a suitable makeup style.

[0057] 4. Generating realistic makeup-applied facial images

[0058] The server uses a generative model to generate a post-makeup facial image based on the analysis results. The generated facial image reflects the user's counseling content.

[0059] Specific example: The generative model generates a facial image with the user's desired natural makeup applied, allowing it to be compared to the original image.

[0060] 5. Recommendations for makeup products and brands

[0061] The server recommends appropriate makeup products and brands based on the user's attributes (gender, age) and counseling content. This information is sent to the user's device.

[0062] Specific example: The server suggests to the user, "We recommend this lip color," and provides a link to the product's purchase page.

[0063] 6. Offering targeted advertising and special offers.

[0064] The server uses user data to provide targeted advertising and special offers. It can display customized ads based on the user's browsing history.

[0065] Specific example: The server provides the user with a discount coupon for their favorite brand of product.

[0066] Program execution order (overview)

[0067] 1. The device takes a picture of the user's face and sends it to the server.

[0068] 2. The terminal displays a counseling information input form, and the user enters the information and sends it to the server.

[0069] 3. The server analyzes the facial image and counseling content, and uses a generative model to generate a post-makeup facial image.

[0070] 4. The server sends the generated facial image to the user's device and displays it.

[0071] 5. The server recommends appropriate makeup products and brands and displays them on the user's device.

[0072] 6. The server provides targeted advertising and special offers based on the user's behavioral history.

[0073] This system allows users to try out the makeup style that best suits them without spending time or money, and to easily select and purchase products.

[0074] The following describes the processing flow.

[0075] Step 1:

[0076] The user activates their smart device and opens the app. The app displays a camera interface and provides instructions to the user for taking a picture of their face.

[0077] Step 2:

[0078] The device activates the smart device's camera and takes a picture of the user's face. After taking the picture, the device provides an interface for the user to review the image and click an "Upload" button if they are satisfied.

[0079] Step 3:

[0080] After the "Upload" button is clicked, the device sends the captured facial image to the server. The image is securely transferred over the internet.

[0081] Step 4:

[0082] The user then accesses a counseling form displayed within the app. The form includes fields for entering details such as makeup consultation topics, desired style, and preferred brands.

[0083] Step 5:

[0084] The device sends the entered data to the server after the user enters information into the counseling form and clicks the "Submit" button.

[0085] Step 6:

[0086] The server receives the uploaded facial image and counseling content and activates the image analysis module. The server uses a generative model to analyze the user's facial shape and skin tone.

[0087] Step 7:

[0088] The server analyzes the counseling content using a text mining tool to extract the user's preferences and desired makeup style. This information is used as data to generate a post-makeup facial image.

[0089] Step 8:

[0090] The server uses a generative model to generate a post-makeup facial image based on facial image analysis and extracted counseling content. The generated image reflects changes in real time.

[0091] Step 9:

[0092] The server sends the generated, makeup-applied facial image to the user's device. The image is then transferred to the user's smart device via the internet.

[0093] Step 10:

[0094] The device displays the user with the received image of their face after applying makeup. The user can see how their face will look with makeup applied.

[0095] Step 11:

[0096] The server recommends suitable makeup products and brands based on the user's attributes and consultation content. This information, along with a link to the purchasing site, is sent to the user's device.

[0097] Step 12:

[0098] The device displays received recommendations to the user and encourages purchases through the provided links. Users can click the links to purchase the recommended products online.

[0099] Step 13:

[0100] The server analyzes user behavior data to deliver targeted ads and provide special offers. It generates customized ads based on user attributes and behavioral history and sends them to the user's device.

[0101] Step 14:

[0102] The device displays personalized advertisements and special offers received by the user. The user can view these and take further action as needed.

[0103] The above series of steps provides users with an easy process to try out different makeup styles and select the products that best suit them.

[0104] (Example 1)

[0105] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0106] Traditional makeup simulation systems made it difficult for users to obtain their own facial images and try out appropriate makeup based on them. Furthermore, they lacked features to recommend suitable makeup products and brands, as well as to provide targeted advertising. As a result, users had to spend time and money experimenting to find the optimal makeup look.

[0107] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0108] In this invention, the server includes image acquisition means, generation means, presentation means, data transmission means, analysis means, recommendation means, and advertising provision means. This allows users to easily acquire their own facial images, generate realistic makeup-applied facial images using a generation AI model, and review them. Furthermore, it becomes possible to recommend appropriate makeup products and brands based on the user's attribute information and behavioral history, and to provide customized targeted advertising and special offers.

[0109] "Image acquisition means" refers to a method by which a user takes an image of their own face using a computer camera and acquires that image data.

[0110] "Generation means" refers to a means of analyzing acquired facial images and user counseling information, and generating a post-makeup facial image using a generation AI model.

[0111] "Presentation means" refers to a means of displaying the generated, makeup-applied facial image on the user's device.

[0112] "Data transmission means" refers to the means for sending facial images and counseling information acquired by the user to the server.

[0113] "Analysis means" refers to the means by which the server analyzes the facial images and counseling information it receives and performs data processing to generate a post-makeup facial image using a generation AI model.

[0114] A "recommendation method" is a means of recommending appropriate makeup products and brands based on the user's attribute information and counseling content.

[0115] "Advertising delivery methods" refer to methods for generating and providing targeted advertisements and special offers based on users' behavioral history and attribute information.

[0116] The system according to the present invention acquires a facial image using the user's computer camera, generates a facial image with makeup applied using a generation AI model, and displays it on a terminal. The overall configuration of this system includes image acquisition means, generation means, presentation means, data transmission means, analysis means, recommendation means, and advertising provision means.

[0117] Hardware and software usage

[0118] 1. Image acquisition method

[0119] The user takes a picture of their face using their computer's camera. This can be a standard webcam or the built-in camera of a smart device. The face image is then temporarily stored on the device.

[0120] 2. Data transmission means

[0121] The device includes a software module for sending captured facial images to a server. This module executes a protocol for securely transmitting image data to the server over the internet.

[0122] 3. Generation means

[0123] The server inputs the received facial image into a generating AI model, which then generates a post-makeup facial image based on the user's counseling information. The generating AI model is based on deep learning technology and uses advanced image processing techniques to produce realistic makeup effects.

[0124] 4. Analysis tools

[0125] The server includes an analysis module for analyzing the shape and skin tone of facial images. This provides data for the generative AI model to determine the optimal makeup style.

[0126] 5. Presentation means

[0127] The server sends the generated, makeup-applied facial image to the user's device. The device includes a user interface for displaying the received image.

[0128] 6. Recommendation methods

[0129] The server recommends appropriate makeup products and brands based on the user's attribute information (gender, age) and counseling information. This information is sent to the user's device, which then displays it.

[0130] 7. Advertising Delivery Methods

[0131] The server generates targeted ads and special offers based on the user's behavioral history and attribute information. This advertising information is sent to the user's device, which then displays them.

[0132] Specific example

[0133] 1. The user takes a picture of their face using a webcam and clicks the application's upload button to send the image to the server.

[0134] 2. The device displays a form about the user's makeup preferences and ideal style, and the user enters the necessary information and sends it to the server.

[0135] 3. The server analyzes the facial image and counseling information, and uses a generative AI model to generate a post-makeup facial image.

[0136] 4. The server sends the generated facial image to the user's terminal, and the user checks the image in the application.

[0137] 5. The server recommends appropriate makeup products and brands based on the user's attribute information, and sends that information to the device for display to the user.

[0138] 6. The server generates special offers and targeted advertisements based on the user's behavior history, sends them to the device, and displays them to the user.

[0139] Examples of prompts for generative AI models

[0140] "Please apply the natural makeup look desired by the user to the face image."

[0141] "Please provide the optimal makeup style based on the user's face shape and skin tone."

[0142] "Please suggest lip colors that would be best suited for the user."

[0143] This allows users to easily try out the makeup styles that best suit them, and easily select and purchase the appropriate products. This system not only saves users time and money, but also provides an advanced makeup simulation experience.

[0144] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0145] Step 1:

[0146] The user takes a picture of their face using the computer's camera. The input is a real-time facial image, and the output is a digital image temporarily stored on the device. The user starts this process by clicking the "Capture" button in the application. This action captures the facial image on the device.

[0147] Step 2:

[0148] The device displays the facial image taken by the user and prompts the user for confirmation. The user sends the image to the server by clicking the "Upload" button. The input is a temporarily stored facial image, and the output is data sent to the server via the internet. Through this operation, the device uploads the facial image data to the server.

[0149] Step 3:

[0150] The server receives the uploaded facial image. The input is the facial image data sent from the terminal, and the output is the facial image data stored on the server side. Through this process, the server prepares the facial image for image analysis.

[0151] Step 4:

[0152] The terminal displays a form for the user to enter information about their makeup preferences, ideal style, and favorite brands. The user fills in the required information in the form and clicks the "Submit" button. The input is the counseling information entered by the user, and the output is data sent to the server via the internet. Through this action, the terminal sends the counseling information to the server.

[0153] Step 5:

[0154] The server analyzes the received facial images and counseling information. The input is facial image data and counseling information, and the output is the analysis results regarding facial shape and skin tone, and the determination of a makeup style based on these results. Through this operation, the server provides data to the generative AI model and starts the analysis.

[0155] Step 6:

[0156] The server uses a generative AI model to generate a post-makeup face image based on the analysis results. The input is the analysis result data, and the output is the generated post-makeup face image. Through this operation, the server creates the generated post-makeup face image.

[0157] Step 7:

[0158] The server sends the generated, made-up face image to the user's device. The input is the generated face image, and the output is the data sent to the device via the internet. Through this operation, the server delivers the face image to the user's device.

[0159] Step 8:

[0160] The terminal displays the received face image after makeup application. The input is face image data sent from the server, and the output is the face image after makeup application displayed to the user. The user can review the results and request adjustments as needed.

[0161] Step 9:

[0162] The server recommends appropriate makeup products and brands based on user attribute information and counseling information. The input is user attribute information and counseling information, and the output is a list of recommended makeup products and brands. Through this process, the server identifies recommended products and generates information about them.

[0163] Step 10:

[0164] The server sends information about recommended makeup products and brands to the user's device. The input is recommendation information, and the output is data sent to the device via the internet. Through this process, the server delivers recommendation information to the user's device.

[0165] Step 11:

[0166] The terminal displays received recommendation information to the user. The input is recommendation information sent from the server, and the output is a product list and brand information displayed to the user. The user can then consider purchasing products based on this information.

[0167] Step 12:

[0168] The server generates targeted ads and special offers based on the user's behavior history and attribute information. The input is the user's behavior history and attribute information, and the output is customized ads and special offers. Through this process, the server generates targeted ads.

[0169] Step 13:

[0170] The server sends the generated targeted ads and special offers to the user's device. The input is the generated ads and special offers, and the output is the data sent to the device via the internet. Through this operation, the server delivers ads and offers to the user's device.

[0171] Step 14:

[0172] The device displays targeted ads and special offers received by the user. The input is advertising information sent from the server, and the output is the advertising and offer information displayed to the user. The user can then use this information to make purchasing decisions.

[0173] (Application Example 1)

[0174] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0175] Modern consumers have a need to check whether makeup products suit them without actually trying them out. However, current systems make it difficult to try out various makeup styles in real time, and furthermore, there is a lack of coordination between the recommendation of appropriate products and brands and the provision of advertising.

[0176] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0177] In this invention, the server includes image acquisition means, generation means, presentation means, recommendation means, and advertising provision means. This enables users to acquire facial images using a smart device and try out various makeup styles in real time. It also enables product recommendations based on the generated facial images and the provision of customized advertisements based on the user's preferences and behavioral history.

[0178] "Image acquisition means" refers to a device or function that allows a user to acquire their own facial image and transmit it to a server.

[0179] "Generation means" refers to a device or function that generates a post-makeup facial image based on a generative AI model for analyzing facial shape and skin tone.

[0180] "Presentation means" refers to a device or function that displays the generated, post-makeup facial image on the user's device or a store display.

[0181] A "recommendation method" is a device or function that recommends appropriate makeup products or brands based on the generated facial image and the user's counseling content.

[0182] "Advertising delivery means" refers to a device or function that provides customized advertisements or special offers based on the user's attributes and behavioral history.

[0183] This invention relates to a system in which a user acquires an image of their face using a smart device, generates a makeup-applied image of their face using a generative model, and displays it on the terminal. The system includes image acquisition means, generation means, presentation means, recommendation means, and advertising provision means.

[0184] System Program Overview

[0185] 1. Image acquisition method:

[0186] The user uses a smart device (e.g., smartphone, tablet, etc.) to acquire an image of their own face and sends that image to a server. This function utilizes an imaging device used in mobile communication devices (e.g., smartphone camera) and an image capture application (e.g., OpenCV).

[0187] 2. Generation means:

[0188] The server inputs the received facial image into a generative AI model, which analyzes the facial shape and skin tone. The generative model (e.g., GAN, TensorFlow, PyTorch) then generates a makeup-applied facial image based on these analysis results. This generated facial image is processed in real time.

[0189] 3. Means of presentation:

[0190] The generated facial image will be displayed on the user's device (e.g., smartphone, tablet) or on a display installed in the store. Hardware for this will include a web server (e.g., Nginx) and a front-end framework (e.g., React.js).

[0191] 4. Recommendation methods:

[0192] The server recommends appropriate makeup products and brands based on the generated facial image and the user's consultation content. This recommendation process utilizes user attribute analysis and product database matching algorithms (e.g., ElasticSearch).

[0193] 5. Advertising delivery methods:

[0194] The server delivers customized ads and special offers based on user attributes and behavioral history. For ad delivery, it utilizes advertising technology platforms (e.g., Google Ads API).

[0195] Explanation of the process

[0196] Upon receiving a user's facial image, the server first performs image analysis to detect skin tone and facial shape. Next, it inputs the image into a generative model to generate a facial image corresponding to the desired makeup style. The generated facial image is then displayed on the user's device or in-store display. Subsequently, based on the analysis data, the server recommends suitable makeup products and brands, and displays further customized advertisements and special offers.

[0197] Specific example

[0198] For example, when a customer enters a store and scans their face with smart glasses installed in the store, the image is immediately sent to a server, and an AI generation model begins analysis. For customers who have entered their preference for natural makeup, the generation model generates an image of their face with a natural makeup style applied and displays it on the screen. Furthermore, lip colors and eyeshadows that match that style are recommended, and special offers and discount coupons for purchase are also presented.

[0199] Example of a prompt

[0200] Image analysis:

[0201] plain

[0202] Upload a customer's facial image and run it through the AI ​​model to generate a facial image with natural makeup.

[0203] Product Recommendations:

[0204] plain

[0205] Please recommend lip colors and eyeshadows that are suitable for natural makeup, and provide details about the products and any special offers.

[0206] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0207] Step 1:

[0208] The user obtains a facial image using a smart device (e.g., a smartphone). The input is a facial image taken with the device's camera, and this image is temporarily stored on the device. After the user confirms the image, they click the "Upload" button to send the image to the server.

[0209] Step 2:

[0210] The server receives a face image sent by the user and begins image analysis. The analysis uses face recognition technology and skin tone analysis algorithms (e.g., OpenCV, TensorFlow). This detects the shape of the user's face and skin tone. The input is a face image, and the output is face shape data and skin tone data.

[0211] Step 3:

[0212] The server uses a generative AI model (e.g., GAN) to generate a post-makeup face image based on the acquired facial shape and skin tone data. The input to the generative AI model is the analysis results, and the output is the generated post-makeup face image. This generates a real-time face image that matches the user's desired makeup style.

[0213] Step 4:

[0214] The generated facial image is sent from the server to the user's smart device or a store display for display. This display uses a web server (e.g., Nginx) and a frontend framework (e.g., React.js). The input is the generated facial image, and the output is the displayed facial image.

[0215] Step 5:

[0216] The server recommends appropriate makeup products and brands based on the generated facial image and the user's counseling content. This uses user attribute analysis and a matching algorithm for the product database (e.g., ElasticSearch). The input is user attribute data and the generated facial image, and the output is a list of recommended products.

[0217] Step 6:

[0218] The server delivers customized ads and special offers based on user attributes and behavioral history. For ad delivery, it utilizes an advertising technology platform (e.g., Google Ads API). The input is user behavioral history data, and the output is customized ads and special offers.

[0219] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0220] Embodiments of the present invention will be described in detail below. This system acquires a facial image using a smart device, generates a post-makeup facial image using a generative model, and displays it on the terminal. Furthermore, by combining this with an emotion engine that recognizes the user's emotions, a more personalized makeup experience is provided.

[0221] System Overview

[0222] The system includes image acquisition means, generation means, presentation means, emotion engine, and decision-making means. The user uses a smart device (such as a smartphone or tablet) to acquire an image of their face and inputs information necessary for makeup counseling. This data is sent to a server, where a generation model analyzes it, and the system performs emotion recognition using the emotion engine and produces a post-makeup facial image. Based on the analysis results, appropriate information is presented to the user's device.

[0223] Program execution flow

[0224] 1. Image acquisition and upload

[0225] The user takes a picture of their face using the camera on their smart device. The device displays the captured image for confirmation, and when the user clicks the "Upload" button, the image is sent to the server.

[0226] Example: The user opens the app and takes a photo of their face in selfie mode. After taking the photo, they press the upload button, and the image is sent to the server.

[0227] 2. Entering counseling details

[0228] The device displays a form for the user to enter information such as their makeup consultation details, ideal style, and preferred brands. Once the user completes the form and clicks the submit button, the data is sent to the server.

[0229] Example: A user enters "I would like natural makeup" into the form and clicks the submit button.

[0230] 3. Analysis of images and counseling content

[0231] The server analyzes the received facial image and counseling content. Using a generative model, it analyzes the user's facial shape and skin tone, and processes the data to determine the user's ideal makeup style.

[0232] Specific example: The server analyzes a facial image, determines that the user's skin tone is neutral, and then decides on a suitable makeup style.

[0233] 4. Generating realistic makeup-applied facial images

[0234] The server uses a generative model to generate a post-makeup facial image based on the analysis results. The generated facial image reflects the user's counseling content.

[0235] Specific example: The generative model generates a facial image with the user's desired natural makeup applied, allowing it to be compared to the original image.

[0236] 5. Recommendations for makeup products and brands

[0237] The server recommends appropriate makeup products and brands based on the user's attributes (gender, age) and counseling content. This information is sent to the user's device.

[0238] Specific example: The server suggests to the user, "We recommend this lip color," and provides a link to the product's purchase page.

[0239] 6. Emotion recognition by an emotion engine

[0240] The server uses an emotion engine to analyze the user's facial expressions and voice as they input counseling information and view their post-makeup facial image, recognizing their emotions. Based on the recognized emotions, the server adjusts the makeup style and recommended products in real time.

[0241] Specific example: The emotion engine recognizes the smile a user shows when viewing a photo of their face after applying makeup, measures their satisfaction level, and then suggests products in colors that suit them better.

[0242] 7. Presentation of makeup results

[0243] The server sends the generated, made-up face image and feedback from the emotion engine to the user's device. The device displays this to the user, allowing them to see how their face looks with makeup applied.

[0244] Specific example: The server generates a face image after applying makeup, and the results of the emotion engine's analysis (such as satisfaction level) are sent to the user's device for the user to review.

[0245] 8. Utilization of the information provided

[0246] Users review the presented makeup products and brands, and if necessary, access the purchasing site to buy the items.

[0247] Specific example: A user purchases their favorite lip color from an online store.

[0248] Achieving the System's Objectives

[0249] Through these steps, users can not only try out makeup styles that suit them, but the app's emotion engine will also help it understand their preferences more accurately, leading to customized makeup suggestions. This improves the user experience and makes it possible to provide a more satisfying makeup experience.

[0250] The following describes the processing flow.

[0251] Step 1:

[0252] The user activates their smart device and opens the app. The app displays a camera interface and provides instructions to the user for taking a picture of their face.

[0253] Step 2:

[0254] The device activates the smart device's camera and takes a picture of the user's face. After taking the picture, the device provides an interface for the user to review the image and click an "Upload" button if they are satisfied.

[0255] Step 3:

[0256] After the "Upload" button is clicked, the device sends the captured facial image to the server. The image is securely transferred over the internet.

[0257] Step 4:

[0258] The user then accesses a counseling form displayed within the app. The form includes fields for entering details such as makeup consultation topics, desired style, and preferred brands.

[0259] Step 5:

[0260] The device sends the entered data to the server after the user enters information into the counseling form and clicks the "Submit" button.

[0261] Step 6:

[0262] The server receives the uploaded facial image and counseling content and activates the image analysis module. The server uses a generative model to analyze the user's facial shape and skin tone.

[0263] Step 7:

[0264] The server analyzes the counseling content using a text mining tool to extract the user's preferences and desired makeup style. This information is used as data to generate a post-makeup facial image.

[0265] Step 8:

[0266] The server uses a generative model to generate a post-makeup facial image based on facial image analysis and extracted counseling content. The generated image reflects changes in real time.

[0267] Step 9:

[0268] The server sends the generated, makeup-applied facial image to the user's device. The image is then transferred to the user's smart device via the internet.

[0269] Step 10:

[0270] The device displays the user with the received image of their face after applying makeup. The user can see how their face will look with makeup applied.

[0271] Step 11:

[0272] The server recommends suitable makeup products and brands based on the user's attributes and consultation content. This information, along with a link to the purchasing site, is sent to the user's device.

[0273] Step 12:

[0274] The device displays received recommendations to the user and encourages purchases through the provided links. Users can click the links to purchase the recommended products online.

[0275] Step 13:

[0276] The server uses an emotion engine to analyze the user's facial expressions and voice to recognize their emotions. This emotion recognition occurs when counseling information is entered and when viewing a facial image after makeup application.

[0277] Specific example: The emotion engine analyzes the user's facial expressions as they enter information into a counseling form to detect whether the user is satisfied.

[0278] Step 14:

[0279] The server adjusts the makeup styles and recommended products in real time based on the emotion recognition results from the emotion engine. This ensures that suggestions best match the user's emotions.

[0280] Specific example: The emotion engine detects expressions of joy when the user sees a picture of their face after applying makeup, and then suggests more suitable makeup products based on that level of satisfaction.

[0281] Step 15:

[0282] The server generates targeted advertisements and special offers based on the user's behavior history and sends them to the user's terminal. As a result, advertisements that the user is likely to be interested in are displayed.

[0283] Step 16:

[0284] The terminal displays the received targeted advertisements and special offers to the user. The user can view them and take corresponding actions if necessary.

[0285] The above series of steps realizes a series of processes for the user to easily try makeup styles suitable for themselves and select the optimal products. In addition, the introduction of the emotion engine provides a more personalized experience that reflects the user's emotions.

[0286] (Example 2)

[0287] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart device 14 is referred to as the "terminal".

[0288] In the conventional makeup system, there was a problem that it took a lot of time and effort for the user to try the makeup style optimal for themselves. In addition, the information selected by the user was limited, and it was difficult for many people to find the makeup style that really suited them. Furthermore, since there was a lack of personalized proposals considering the user's emotions, improving satisfaction was an issue.

[0289] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following respective means.

[0290] In this invention, the server includes an image acquisition means, a generation means, a presentation means, an emotion recognition means, and a decision-making means. This allows the user to easily acquire an image of their face, analyze the image using an AI model, and receive customized makeup suggestions based on the user's emotions.

[0291] "Image acquisition means" refers to a means by which a user acquires an image of their own face using the camera on a mobile information terminal.

[0292] The "generation method" refers to a method for generating a post-makeup facial image based on a generative AI model for analyzing facial shape and skin tone.

[0293] "Presentation means" refers to the means by which the terminal displays the generated post-makeup facial image and related information to the user.

[0294] "Emotion recognition means" refers to a method that uses an emotion engine to analyze the user's facial expressions and voice when they input counseling information and when they check their face image after applying makeup, thereby recognizing the user's emotions.

[0295] "Decision-making means" refers to the method of determining the makeup style to offer and the recommended products based on image analysis and emotion recognition results.

[0296] A "portable information device" refers to an information processing device that a user can carry with them, and examples include smartphones and tablets.

[0297] A "photography device" is a camera built into a mobile information terminal that has the function of allowing the user to take an image of their own face.

[0298] A "generative AI model" is a model that uses artificial intelligence algorithms to analyze facial images and generate a post-makeup facial image based on the user's preferences.

[0299] An "emotion engine" is a software component that analyzes a user's facial expressions and voice to recognize their emotions.

[0300] "Makeup style" refers to the design and method of makeup desired by the user, and includes the specific details of the makeup applied to each part of the face.

[0301] "Recommended products" are cosmetics and related products that are deemed appropriate based on the user's attributes and emotional recognition results.

[0302] Embodiments of the present invention will be described in detail below. This system acquires a facial image using a mobile device, generates a post-makeup facial image using a generation AI model, and displays it on the device. Furthermore, by combining it with emotion recognition means, a more personalized makeup experience is provided.

[0303] The system includes image acquisition, generation, and presentation means, emotion recognition means, and decision-making means. The user uses a mobile device (such as a smartphone or tablet) to acquire an image of their face and input information necessary for counseling. This data is transmitted to a server, where a generation AI model analyzes it, and the system performs emotion recognition using the emotion recognition means and analyzes the resulting image of the face after makeup application. Based on the analysis results, appropriate information is presented to the user's device.

[0304] First, the user takes a facial image using the camera on their mobile device. When the user presses the capture button, the image is displayed on the device. The user then reviews the image and clicks the "upload" button, which sends the image to the server. Next, the device displays a makeup consultation form to the user. The user enters their ideal makeup style, brands, concerns, etc., and once completed, clicks the submit button to send this information to the server.

[0305] The server analyzes the received face image and counseling content. Specifically, it uses image analysis software to identify the shape of the face and the skin tone, and inputs the results into the generative AI model. The generative AI model generates a face image after makeup based on the user's preferences. The generated face image is customized to reflect the user's counseling content.

[0306] Next, the server recommends appropriate makeup products and brands based on the user's attributes (gender, age) and counseling content. This information is sent to the user's terminal and presented to the user. Furthermore, the server uses emotion recognition means to analyze the expressions and voices of the user when inputting counseling information and when viewing the face image after makeup, and recognizes the user's emotions. Based on the recognized emotions, the makeup style and recommended products provided are adjusted in real time.

[0307] Finally, the generated face image after makeup and emotion recognition information are sent to the user's terminal, and the user can confirm them. After that, the user can also confirm the presented makeup products and brands and access the purchase site to purchase the products. Through these series of processes, the user can easily try out a makeup style suitable for themselves and receive customized proposals by the emotion recognition means, thus realizing a more satisfactory makeup experience.

[0308] As a specific example, when the user hopes for "natural makeup" and wants to use products of a specific brand, the input is as follows.

[0309] Example: I hope for natural makeup. Please recommend a lip color that suits me.

[0310] By using this system, the user can confirm in real time how their face will be made up and receive more personalized proposals by the emotion recognition means. As a result, the user's satisfaction is improved, and it is possible to provide a higher level of makeup experience.

[0311] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0312] Step 1:

[0313] The user launches the camera app on their mobile device and takes an image of their face. When the user presses the capture button, the image is displayed on the device. After the user confirms and clicks the "Upload" button, the device sends the image to the server.

[0314] Specific operation: The user opens the camera app and takes a selfie of their face. After taking the picture, the image is displayed on the screen. When the user presses the upload button, the image is sent to the server.

[0315] Input: A captured image of a face.

[0316] Processing: The terminal displays the user's facial image for verification and sends it to the server.

[0317] Output: Face image uploaded to the server.

[0318] Step 2:

[0319] The device displays a makeup consultation form to the user. The user enters their ideal makeup style, preferred brands, and makeup concerns. Once the user has finished entering the information and clicks the submit button, the information is sent to the server.

[0320] Specific operation: The user enters a request such as "I want natural makeup" into a form within the app and selects their preferred brand. Once the input is complete, they click the submit button.

[0321] Input: User counseling information (makeup style, brand, concerns).

[0322] Processing: The terminal receives user input and sends it to the server.

[0323] Output: Counseling information sent to the server.

[0324] Step 3:

[0325] The server analyzes the received facial image and counseling content. First, it uses image analysis software to identify the user's facial shape, skin tone, and facial features. Then, it uses a generative AI model to generate a post-makeup facial image based on the user's preferences.

[0326] Specific operation: Image analysis software identifies the shape of the face and skin tone, and inputs this information into a generating AI model. The generating AI model then generates a post-makeup facial image based on the counseling information.

[0327] Input: User's facial image, counseling information.

[0328] Processing: Face image generation using image analysis and generative AI models.

[0329] Output: The generated image of the face after applying makeup.

[0330] Step 4:

[0331] The server recommends appropriate makeup products and brands based on the user's attributes (gender, age) and counseling content. This information is then sent to the user's device.

[0332] Specific operation: The server analyzes the user's attributes and counseling information, selects appropriate makeup products and brands, and generates recommendation information. The generated information is then sent to the user's device.

[0333] Input: User attributes, counseling information.

[0334] Processing: Selection of makeup products and brands, and generation of recommendation information.

[0335] Output: Recommendation information sent to the user's device.

[0336] Step 5:

[0337] The server uses emotion recognition to analyze the user's facial expressions and voice as they input counseling information and view images of their face after makeup application, thereby recognizing the user's emotions. Based on the recognized emotions, the server adjusts the makeup style and recommended products in real time.

[0338] Specific operation: Emotion recognition means analyze facial expressions and voice to identify the user's emotions. Based on the results, the makeup style and recommended products are adjusted.

[0339] Input: User's facial expressions and voice data.

[0340] Processing: Emotion recognition and real-time adjustment.

[0341] Output: Adjusted makeup styles and recommended products.

[0342] Step 6:

[0343] The server sends the generated post-makeup facial image and emotion recognition results to the user's device. The device displays this to the user, allowing them to see how their face will look after the make-up.

[0344] Specific operation: The server sends the generated image of the face after applying makeup and the emotion recognition results, and the terminal displays them. The user confirms the displayed information.

[0345] Input: Generated facial image, emotion recognition result.

[0346] Processing: Data transmission from server to terminal, and display on terminal.

[0347] Output: The post-makeup facial image and emotion recognition results displayed on the user's device.

[0348] Step 7:

[0349] Users review the presented makeup products and brands, and if necessary, access the purchasing site to buy the items.

[0350] Specific actions: The user clicks on a link to a presented lip color or other product, accesses the online store, and completes the purchase process.

[0351] Input: Recommended makeup products and brand information.

[0352] Process: The user checks the product and accesses the online store.

[0353] Output: Purchased makeup products.

[0354] (Application Example 2)

[0355] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0356] In modern brick-and-mortar stores, providing personalized makeup experiences tailored to customers' emotions and preferences is challenging. Furthermore, limited means of visualizing the results beforehand make improving customer satisfaction difficult. Additionally, there's a lack of systems that allow customers to easily select the most suitable makeup products and brands on the spot.

[0357] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0358] In this invention, the server includes an image acquisition means, a generation means, a presentation means, an emotion recognition means, a real-time processing means, and a decision-making means. This enables personalized makeup suggestions and product recommendations through the acquisition of a user's facial image, generation of a post-makeup facial image, emotion recognition, and real-time analysis.

[0359] "Image acquisition means" refers to a means for a user to acquire an image of their own face using the camera of a smart device.

[0360] The "generation method" is a means of generating a post-makeup facial image based on a generative model for analyzing facial shape and skin tone.

[0361] "Presentation means" refers to a means of visually displaying the generated post-makeup facial image and analysis results to the user.

[0362] "Emotion recognition means" refers to a means of recognizing the user's emotions and adjusting makeup suggestions based on the results of that recognition.

[0363] The "real-time processing method" is a means of analyzing the user's satisfaction level and reaction in real time when they check their face image after applying makeup, and providing the optimal makeup style.

[0364] "Decision-making means" refers to methods for recommending the most suitable makeup products and brands to a user based on data from emotion recognition means and real-time processing means.

[0365] A "server" is a computer system used to process image data and analysis results, and to execute generative models and emotion recognition algorithms.

[0366] Embodiments of the present invention will be described in detail below.

[0367] System Configuration

[0368] This system includes the following means: image acquisition means, generation means, presentation means, emotion recognition means, real-time processing means, and decision-making means. The entire system consists of the user's smart device and a server that processes the data.

[0369] Image acquisition method

[0370] The user takes a picture of their face using the camera on a smart device (e.g., a smartphone). This image is acquired by the "image acquisition means" and sent to the server.

[0371] generation means

[0372] The server applies a generative AI model to the received facial image to analyze its shape and skin tone. Based on the analysis results, it generates a post-makeup image that reflects the user's desired makeup style. Machine learning frameworks such as TensorFlow and Keras are used for this generation process.

[0373] Presentation means

[0374] The generated image of the face after applying makeup is displayed on the user's smart device via a presentation mechanism. This allows the user to see the results of the makeup in real time.

[0375] emotion recognition means

[0376] The server uses emotion recognition engines such as DeepFace to analyze the user's emotions when they view their face image after applying makeup. This makes it possible to suggest makeup looks that match the user's satisfaction level and preferences.

[0377] Real-time processing means

[0378] The server analyzes the user's facial expressions and reactions in real time as they review their post-makeup facial image. Image processing libraries such as OpenCV are used for this process. The analysis results are immediately fed back and reflected in the generative model.

[0379] decision making means

[0380] Based on data obtained from emotion recognition and real-time processing systems, the server makes decisions. Specifically, it recommends the most suitable makeup products and brands to the user and provides that information to the user through a presentation system.

[0381] Explanation of specific examples

[0382] For example, a user takes a photo of their face using a smart device installed in a physical store. The image is sent to a server, where a generative model analyzes it. A new image of the user's face with natural makeup applied is then generated and displayed on the user's smart device. Furthermore, the user's facial expressions are analyzed, and if they are highly satisfied, specific makeup products or brands are recommended.

[0383] Example of a prompt

[0384] "Enter the user's face image and generate a post-makeup image. If the user's emotion is 'happy,' apply a natural makeup style."

[0385] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0386] Step 1:

[0387] The user uses the camera on their smart device to capture an image of their face.

[0388] Input: Face image taken from the user's smart device

[0389] Output: Acquired facial image

[0390] Specific operation: The user launches the smartphone's camera app and takes a selfie of their face. The captured image is then saved to the device.

[0391] Step 2:

[0392] The acquired facial images are uploaded to the server.

[0393] Input: Face image saved on the device

[0394] Output: Face image transferred to the server

[0395] Specific operation: When the user clicks the "Upload" button within the application, the device sends the acquired facial image to the server.

[0396] Step 3:

[0397] The server receives the transmitted facial image and uses a generating AI model to analyze the facial shape and skin tone.

[0398] Input: Face image sent to the server

[0399] Output: Analysis results (face shape, skin tone)

[0400] Specific operation: The server receives a facial image, runs a generative AI model using TensorFlow or Keras, and extracts and analyzes the facial shape and skin tone.

[0401] Step 4:

[0402] The generation method generates a post-makeup facial image based on the analysis results.

[0403] Input: Analysis results of facial shape and skin tone

[0404] Output: Face image after makeup application

[0405] Specific operation: The server uses the analysis results to generate a facial image after applying the user's desired makeup style.

[0406] Step 5:

[0407] The generated, post-makeup facial image is displayed to the user using a presentation device.

[0408] Input: Face image after makeup

[0409] Output: Face image after makeup application displayed on the user's terminal

[0410] Specific operation: The server sends the generated facial image to the user's smart device, and that image is displayed within the application.

[0411] Step 6:

[0412] Using emotion recognition technology, the system recognizes the emotions a user experiences when reviewing their face image after applying makeup.

[0413] Input: User's facial expression data

[0414] Output: User sentiment analysis results

[0415] Specific operation: The user's facial expressions when viewing the generated makeup-applied face image are captured by the smart device's camera, and emotions are analyzed using an emotion recognition engine such as DeepFace.

[0416] Step 7:

[0417] Real-time processing capabilities allow for real-time analysis of user satisfaction and reactions.

[0418] Input: User reaction data and sentiment analysis results

[0419] Output: Reaction analysis results

[0420] Specific operation: Capture and analyze in real time the user's satisfaction level and reactions to a presented image of their face after applying makeup.

[0421] Step 8:

[0422] Based on data from emotion recognition and real-time processing methods, the system uses decision-making mechanisms to recommend the most suitable makeup products and brands to the user.

[0423] Input: Emotion recognition results, reaction analysis results

[0424] Output: Recommended makeup products and brand information

[0425] Specific operation: Based on the emotion recognition results and reaction analysis results, the server determines the most suitable makeup products and brands for the user, and sends that information to the user's terminal for display.

[0426] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0427] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0428] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0429] [Second Embodiment]

[0430] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0431] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0432] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0433] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0434] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0435] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0436] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0437] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0438] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0439] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0440] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0441] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0442] Embodiments of the present invention will be described in detail below. This system acquires a facial image using the user's smart device, generates a facial image with makeup applied using a generative model, and displays it on the terminal.

[0443] System Overview

[0444] The system includes image acquisition, generation, and presentation means. The user uses a smart device (such as a smartphone or tablet) to acquire an image of their face and inputs information necessary for makeup consultation. This data is sent to a server, where a generation model performs analysis. Based on the analysis results, a post-makeup face image is generated and presented to the user's device.

[0445] Program execution flow

[0446] 1. Image acquisition and upload

[0447] The user takes a picture of their face using the camera on their smart device. The device displays the captured image for confirmation, and when the user clicks the "Upload" button, the image is sent to the server.

[0448] Example: The user opens the app and takes a photo of their face in selfie mode. After taking the photo, they press the upload button, and the image is sent to the server.

[0449] 2. Entering counseling details

[0450] The device displays a form for the user to enter information such as their makeup consultation details, ideal style, and preferred brands. Once the user completes the form and clicks the submit button, the data is sent to the server.

[0451] Example: A user enters "I would like natural makeup" into the form and clicks the submit button.

[0452] 3. Analysis of images and counseling content

[0453] The server analyzes the received facial image and counseling content. Using a generative model, it analyzes the user's facial shape and skin tone, and processes the data to determine the user's ideal makeup style.

[0454] Specific example: The server analyzes a facial image, determines that the user's skin tone is neutral, and then decides on a suitable makeup style.

[0455] 4. Generating realistic makeup-applied facial images

[0456] The server uses a generative model to generate a post-makeup facial image based on the analysis results. The generated facial image reflects the user's counseling content.

[0457] Specific example: The generative model generates a facial image with the user's desired natural makeup applied, allowing it to be compared to the original image.

[0458] 5. Recommendations for makeup products and brands

[0459] The server recommends appropriate makeup products and brands based on the user's attributes (gender, age) and counseling content. This information is sent to the user's device.

[0460] Specific example: The server suggests to the user, "We recommend this lip color," and provides a link to the product's purchase page.

[0461] 6. Offering targeted advertising and special offers.

[0462] The server uses user data to provide targeted advertising and special offers. It can display customized ads based on the user's browsing history.

[0463] Specific example: The server provides the user with a discount coupon for their favorite brand of product.

[0464] Program execution order (overview)

[0465] 1. The device takes a picture of the user's face and sends it to the server.

[0466] 2. The terminal displays a counseling information input form, and the user enters the information and sends it to the server.

[0467] 3. The server analyzes the facial image and counseling content, and uses a generative model to generate a post-makeup facial image.

[0468] 4. The server sends the generated facial image to the user's device and displays it.

[0469] 5. The server recommends appropriate makeup products and brands and displays them on the user's device.

[0470] 6. The server provides targeted advertising and special offers based on the user's behavioral history.

[0471] This system allows users to try out the makeup style that best suits them without spending time or money, and to easily select and purchase products.

[0472] The following describes the processing flow.

[0473] Step 1:

[0474] The user activates their smart device and opens the app. The app displays a camera interface and provides instructions to the user for taking a picture of their face.

[0475] Step 2:

[0476] The device activates the smart device's camera and takes a picture of the user's face. After taking the picture, the device provides an interface for the user to review the image and click an "Upload" button if they are satisfied.

[0477] Step 3:

[0478] After the "Upload" button is clicked, the device sends the captured facial image to the server. The image is securely transferred over the internet.

[0479] Step 4:

[0480] The user then accesses a counseling form displayed within the app. The form includes fields for entering details such as makeup consultation topics, desired style, and preferred brands.

[0481] Step 5:

[0482] The device sends the entered data to the server after the user enters information into the counseling form and clicks the "Submit" button.

[0483] Step 6:

[0484] The server receives the uploaded facial image and counseling content and activates the image analysis module. The server uses a generative model to analyze the user's facial shape and skin tone.

[0485] Step 7:

[0486] The server analyzes the counseling content using a text mining tool to extract the user's preferences and desired makeup style. This information is used as data to generate a post-makeup facial image.

[0487] Step 8:

[0488] The server uses a generative model to generate a post-makeup facial image based on facial image analysis and extracted counseling content. The generated image reflects changes in real time.

[0489] Step 9:

[0490] The server sends the generated, makeup-applied facial image to the user's device. The image is then transferred to the user's smart device via the internet.

[0491] Step 10:

[0492] The device displays the user with the received image of their face after applying makeup. The user can see how their face will look with makeup applied.

[0493] Step 11:

[0494] The server recommends suitable makeup products and brands based on the user's attributes and consultation content. This information, along with a link to the purchasing site, is sent to the user's device.

[0495] Step 12:

[0496] The device displays received recommendations to the user and encourages purchases through the provided links. Users can click the links to purchase the recommended products online.

[0497] Step 13:

[0498] The server analyzes user behavior data to deliver targeted ads and provide special offers. It generates customized ads based on user attributes and behavioral history and sends them to the user's device.

[0499] Step 14:

[0500] The device displays personalized advertisements and special offers received by the user. The user can view these and take further action as needed.

[0501] The above series of steps provides users with an easy process to try out different makeup styles and select the products that best suit them.

[0502] (Example 1)

[0503] Next, we will describe Example 1. 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."

[0504] Traditional makeup simulation systems made it difficult for users to obtain their own facial images and try out appropriate makeup based on them. Furthermore, they lacked features to recommend suitable makeup products and brands, as well as to provide targeted advertising. As a result, users had to spend time and money experimenting to find the optimal makeup look.

[0505] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0506] In this invention, the server includes image acquisition means, generation means, presentation means, data transmission means, analysis means, recommendation means, and advertising provision means. This allows users to easily acquire their own facial images, generate realistic makeup-applied facial images using a generation AI model, and review them. Furthermore, it becomes possible to recommend appropriate makeup products and brands based on the user's attribute information and behavioral history, and to provide customized targeted advertising and special offers.

[0507] "Image acquisition means" refers to a method by which a user takes an image of their own face using a computer camera and acquires that image data.

[0508] "Generation means" refers to a means of analyzing acquired facial images and user counseling information, and generating a post-makeup facial image using a generation AI model.

[0509] "Presentation means" refers to a means of displaying the generated, makeup-applied facial image on the user's device.

[0510] "Data transmission means" refers to the means for sending facial images and counseling information acquired by the user to the server.

[0511] "Analysis means" refers to the means by which the server analyzes the facial images and counseling information it receives and performs data processing to generate a post-makeup facial image using a generation AI model.

[0512] A "recommendation method" is a means of recommending appropriate makeup products and brands based on the user's attribute information and counseling content.

[0513] "Advertising delivery methods" refer to methods for generating and providing targeted advertisements and special offers based on users' behavioral history and attribute information.

[0514] The system according to the present invention acquires a facial image using the user's computer camera, generates a facial image with makeup applied using a generation AI model, and displays it on a terminal. The overall configuration of this system includes image acquisition means, generation means, presentation means, data transmission means, analysis means, recommendation means, and advertising provision means.

[0515] Hardware and software usage

[0516] 1. Image acquisition method

[0517] The user takes a picture of their face using their computer's camera. This can be a standard webcam or the built-in camera of a smart device. The face image is then temporarily stored on the device.

[0518] 2. Data transmission means

[0519] The device includes a software module for sending captured facial images to a server. This module executes a protocol for securely transmitting image data to the server over the internet.

[0520] 3. Generation means

[0521] The server inputs the received facial image into a generating AI model, which then generates a post-makeup facial image based on the user's counseling information. The generating AI model is based on deep learning technology and uses advanced image processing techniques to produce realistic makeup effects.

[0522] 4. Analysis tools

[0523] The server includes an analysis module for analyzing the shape and skin tone of facial images. This provides data for the generative AI model to determine the optimal makeup style.

[0524] 5. Presentation means

[0525] The server sends the generated, makeup-applied facial image to the user's device. The device includes a user interface for displaying the received image.

[0526] 6. Recommendation methods

[0527] The server recommends appropriate makeup products and brands based on the user's attribute information (gender, age) and counseling information. This information is sent to the user's device, which then displays it.

[0528] 7. Advertising Delivery Methods

[0529] The server generates targeted ads and special offers based on the user's behavioral history and attribute information. This advertising information is sent to the user's device, which then displays them.

[0530] Specific example

[0531] 1. The user takes a picture of their face using a webcam and clicks the application's upload button to send the image to the server.

[0532] 2. The device displays a form about the user's makeup preferences and ideal style, and the user enters the necessary information and sends it to the server.

[0533] 3. The server analyzes the facial image and counseling information, and uses a generative AI model to generate a post-makeup facial image.

[0534] 4. The server sends the generated facial image to the user's terminal, and the user checks the image in the application.

[0535] 5. The server recommends appropriate makeup products and brands based on the user's attribute information, and sends that information to the device for display to the user.

[0536] 6. The server generates special offers and targeted advertisements based on the user's behavior history, sends them to the device, and displays them to the user.

[0537] Examples of prompts for generative AI models

[0538] "Please apply the natural makeup look desired by the user to the face image."

[0539] "Please provide the optimal makeup style based on the user's face shape and skin tone."

[0540] "Please suggest lip colors that would be best suited for the user."

[0541] This allows users to easily try out the makeup styles that best suit them, and easily select and purchase the appropriate products. This system not only saves users time and money, but also provides an advanced makeup simulation experience.

[0542] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0543] Step 1:

[0544] The user takes a picture of their face using the computer's camera. The input is a real-time facial image, and the output is a digital image temporarily stored on the device. The user starts this process by clicking the "Capture" button in the application. This action captures the facial image on the device.

[0545] Step 2:

[0546] The device displays the facial image taken by the user and prompts the user for confirmation. The user sends the image to the server by clicking the "Upload" button. The input is a temporarily stored facial image, and the output is data sent to the server via the internet. Through this operation, the device uploads the facial image data to the server.

[0547] Step 3:

[0548] The server receives the uploaded facial image. The input is the facial image data sent from the terminal, and the output is the facial image data stored on the server side. Through this process, the server prepares the facial image for image analysis.

[0549] Step 4:

[0550] The terminal displays a form for the user to enter information about their makeup preferences, ideal style, and favorite brands. The user fills in the required information in the form and clicks the "Submit" button. The input is the counseling information entered by the user, and the output is data sent to the server via the internet. Through this action, the terminal sends the counseling information to the server.

[0551] Step 5:

[0552] The server analyzes the received facial images and counseling information. The input is facial image data and counseling information, and the output is the analysis results regarding facial shape and skin tone, and the determination of a makeup style based on these results. Through this operation, the server provides data to the generative AI model and starts the analysis.

[0553] Step 6:

[0554] The server uses a generative AI model to generate a post-makeup face image based on the analysis results. The input is the analysis result data, and the output is the generated post-makeup face image. Through this operation, the server creates the generated post-makeup face image.

[0555] Step 7:

[0556] The server sends the generated, made-up face image to the user's device. The input is the generated face image, and the output is the data sent to the device via the internet. Through this operation, the server delivers the face image to the user's device.

[0557] Step 8:

[0558] The terminal displays the received face image after makeup application. The input is face image data sent from the server, and the output is the face image after makeup application displayed to the user. The user can review the results and request adjustments as needed.

[0559] Step 9:

[0560] The server recommends appropriate makeup products and brands based on user attribute information and counseling information. The input is user attribute information and counseling information, and the output is a list of recommended makeup products and brands. Through this process, the server identifies recommended products and generates information about them.

[0561] Step 10:

[0562] The server sends information about recommended makeup products and brands to the user's device. The input is recommendation information, and the output is data sent to the device via the internet. Through this process, the server delivers recommendation information to the user's device.

[0563] Step 11:

[0564] The terminal displays received recommendation information to the user. The input is recommendation information sent from the server, and the output is a product list and brand information displayed to the user. The user can then consider purchasing products based on this information.

[0565] Step 12:

[0566] The server generates targeted ads and special offers based on the user's behavior history and attribute information. The input is the user's behavior history and attribute information, and the output is customized ads and special offers. Through this process, the server generates targeted ads.

[0567] Step 13:

[0568] The server sends the generated targeted ads and special offers to the user's device. The input is the generated ads and special offers, and the output is the data sent to the device via the internet. Through this operation, the server delivers ads and offers to the user's device.

[0569] Step 14:

[0570] The device displays targeted ads and special offers received by the user. The input is advertising information sent from the server, and the output is the advertising and offer information displayed to the user. The user can then use this information to make purchasing decisions.

[0571] (Application Example 1)

[0572] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0573] Modern consumers have a need to check whether makeup products suit them without actually trying them out. However, current systems make it difficult to try out various makeup styles in real time, and furthermore, there is a lack of coordination between the recommendation of appropriate products and brands and the provision of advertising.

[0574] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0575] In this invention, the server includes image acquisition means, generation means, presentation means, recommendation means, and advertising provision means. This enables users to acquire facial images using a smart device and try out various makeup styles in real time. It also enables product recommendations based on the generated facial images and the provision of customized advertisements based on the user's preferences and behavioral history.

[0576] "Image acquisition means" refers to a device or function that allows a user to acquire their own facial image and transmit it to a server.

[0577] "Generation means" refers to a device or function that generates a post-makeup facial image based on a generative AI model for analyzing facial shape and skin tone.

[0578] "Presentation means" refers to a device or function that displays the generated, post-makeup facial image on the user's device or a store display.

[0579] A "recommendation method" is a device or function that recommends appropriate makeup products or brands based on the generated facial image and the user's counseling content.

[0580] "Advertising delivery means" refers to a device or function that provides customized advertisements or special offers based on the user's attributes and behavioral history.

[0581] This invention relates to a system in which a user acquires an image of their face using a smart device, generates a makeup-applied image of their face using a generative model, and displays it on the terminal. The system includes image acquisition means, generation means, presentation means, recommendation means, and advertising provision means.

[0582] System Program Overview

[0583] 1. Image acquisition method:

[0584] The user uses a smart device (e.g., smartphone, tablet, etc.) to acquire an image of their own face and sends that image to a server. This function utilizes an imaging device used in mobile communication devices (e.g., smartphone camera) and an image capture application (e.g., OpenCV).

[0585] 2. Generation means:

[0586] The server inputs the received facial image into a generative AI model, which analyzes the facial shape and skin tone. The generative model (e.g., GAN, TensorFlow, PyTorch) then generates a makeup-applied facial image based on these analysis results. This generated facial image is processed in real time.

[0587] 3. Means of presentation:

[0588] The generated facial image will be displayed on the user's device (e.g., smartphone, tablet) or on a display installed in the store. Hardware for this will include a web server (e.g., Nginx) and a front-end framework (e.g., React.js).

[0589] 4. Recommendation methods:

[0590] The server recommends appropriate makeup products and brands based on the generated facial image and the user's consultation content. This recommendation process utilizes user attribute analysis and product database matching algorithms (e.g., ElasticSearch).

[0591] 5. Advertising delivery methods:

[0592] The server delivers customized ads and special offers based on user attributes and behavioral history. For ad delivery, it utilizes advertising technology platforms (e.g., Google Ads API).

[0593] Explanation of the process

[0594] Upon receiving a user's facial image, the server first performs image analysis to detect skin tone and facial shape. Next, it inputs the image into a generative model to generate a facial image corresponding to the desired makeup style. The generated facial image is then displayed on the user's device or in-store display. Subsequently, based on the analysis data, the server recommends suitable makeup products and brands, and displays further customized advertisements and special offers.

[0595] Specific example

[0596] For example, when a customer enters a store and scans their face with smart glasses installed in the store, the image is immediately sent to a server, and an AI generation model begins analysis. For customers who have entered their preference for natural makeup, the generation model generates an image of their face with a natural makeup style applied and displays it on the screen. Furthermore, lip colors and eyeshadows that match that style are recommended, and special offers and discount coupons for purchase are also presented.

[0597] Example of a prompt

[0598] Image analysis:

[0599] plain

[0600] Upload a customer's facial image and run it through the AI ​​model to generate a facial image with natural makeup.

[0601] Product Recommendations:

[0602] plain

[0603] Please recommend lip colors and eyeshadows that are suitable for natural makeup, and provide details about the products and any special offers.

[0604] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0605] Step 1:

[0606] The user obtains a facial image using a smart device (e.g., a smartphone). The input is a facial image taken with the device's camera, and this image is temporarily stored on the device. After the user confirms the image, they click the "Upload" button to send the image to the server.

[0607] Step 2:

[0608] The server receives a face image sent by the user and begins image analysis. The analysis uses face recognition technology and skin tone analysis algorithms (e.g., OpenCV, TensorFlow). This detects the shape of the user's face and skin tone. The input is a face image, and the output is face shape data and skin tone data.

[0609] Step 3:

[0610] The server uses a generative AI model (e.g., GAN) to generate a post-makeup face image based on the acquired facial shape and skin tone data. The input to the generative AI model is the analysis results, and the output is the generated post-makeup face image. This generates a real-time face image that matches the user's desired makeup style.

[0611] Step 4:

[0612] The generated facial image is sent from the server to the user's smart device or a store display for display. This display uses a web server (e.g., Nginx) and a frontend framework (e.g., React.js). The input is the generated facial image, and the output is the displayed facial image.

[0613] Step 5:

[0614] The server recommends appropriate makeup products and brands based on the generated facial image and the user's counseling content. This uses user attribute analysis and a matching algorithm for the product database (e.g., ElasticSearch). The input is user attribute data and the generated facial image, and the output is a list of recommended products.

[0615] Step 6:

[0616] The server delivers customized ads and special offers based on user attributes and behavioral history. For ad delivery, it utilizes an advertising technology platform (e.g., Google Ads API). The input is user behavioral history data, and the output is customized ads and special offers.

[0617] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0618] Embodiments of the present invention will be described in detail below. This system acquires a facial image using a smart device, generates a post-makeup facial image using a generative model, and displays it on the terminal. Furthermore, by combining this with an emotion engine that recognizes the user's emotions, a more personalized makeup experience is provided.

[0619] System Overview

[0620] The system includes image acquisition means, generation means, presentation means, emotion engine, and decision-making means. The user uses a smart device (such as a smartphone or tablet) to acquire an image of their face and inputs information necessary for makeup counseling. This data is sent to a server, where a generation model analyzes it, and the system performs emotion recognition using the emotion engine and produces a post-makeup facial image. Based on the analysis results, appropriate information is presented to the user's device.

[0621] Program execution flow

[0622] 1. Image acquisition and upload

[0623] The user takes a picture of their face using the camera on their smart device. The device displays the captured image for confirmation, and when the user clicks the "Upload" button, the image is sent to the server.

[0624] Example: The user opens the app and takes a photo of their face in selfie mode. After taking the photo, they press the upload button, and the image is sent to the server.

[0625] 2. Entering counseling details

[0626] The device displays a form for the user to enter information such as their makeup consultation details, ideal style, and preferred brands. Once the user completes the form and clicks the submit button, the data is sent to the server.

[0627] Example: A user enters "I would like natural makeup" into the form and clicks the submit button.

[0628] 3. Analysis of images and counseling content

[0629] The server analyzes the received facial image and counseling content. Using a generative model, it analyzes the user's facial shape and skin tone, and processes the data to determine the user's ideal makeup style.

[0630] Specific example: The server analyzes a facial image, determines that the user's skin tone is neutral, and then decides on a suitable makeup style.

[0631] 4. Generating realistic makeup-applied facial images

[0632] The server uses a generative model to generate a post-makeup facial image based on the analysis results. The generated facial image reflects the user's counseling content.

[0633] Specific example: The generative model generates a facial image with the user's desired natural makeup applied, allowing it to be compared to the original image.

[0634] 5. Recommendations for makeup products and brands

[0635] The server recommends appropriate makeup products and brands based on the user's attributes (gender, age) and counseling content. This information is sent to the user's device.

[0636] Specific example: The server suggests to the user, "We recommend this lip color," and provides a link to the product's purchase page.

[0637] 6. Emotion recognition by an emotion engine

[0638] The server uses an emotion engine to analyze the user's facial expressions and voice as they input counseling information and view their post-makeup facial image, recognizing their emotions. Based on the recognized emotions, the server adjusts the makeup style and recommended products in real time.

[0639] Specific example: The emotion engine recognizes the smile a user shows when viewing a photo of their face after applying makeup, measures their satisfaction level, and then suggests products in colors that suit them better.

[0640] 7. Presentation of makeup results

[0641] The server sends the generated, made-up face image and feedback from the emotion engine to the user's device. The device displays this to the user, allowing them to see how their face looks with makeup applied.

[0642] Specific example: The server generates a face image after applying makeup, and the results of the emotion engine's analysis (such as satisfaction level) are sent to the user's device for the user to review.

[0643] 8. Utilization of the information provided

[0644] Users review the presented makeup products and brands, and if necessary, access the purchasing site to buy the items.

[0645] Specific example: A user purchases their favorite lip color from an online store.

[0646] Achieving the System's Objectives

[0647] Through these steps, users can not only try out makeup styles that suit them, but the app's emotion engine will also help it understand their preferences more accurately, leading to customized makeup suggestions. This improves the user experience and makes it possible to provide a more satisfying makeup experience.

[0648] The following describes the processing flow.

[0649] Step 1:

[0650] The user activates their smart device and opens the app. The app displays a camera interface and provides instructions to the user for taking a picture of their face.

[0651] Step 2:

[0652] The device activates the smart device's camera and takes a picture of the user's face. After taking the picture, the device provides an interface for the user to review the image and click an "Upload" button if they are satisfied.

[0653] Step 3:

[0654] After the "Upload" button is clicked, the device sends the captured facial image to the server. The image is securely transferred over the internet.

[0655] Step 4:

[0656] The user then accesses a counseling form displayed within the app. The form includes fields for entering details such as makeup consultation topics, desired style, and preferred brands.

[0657] Step 5:

[0658] The device sends the entered data to the server after the user enters information into the counseling form and clicks the "Submit" button.

[0659] Step 6:

[0660] The server receives the uploaded facial image and counseling content and activates the image analysis module. The server uses a generative model to analyze the user's facial shape and skin tone.

[0661] Step 7:

[0662] The server analyzes the counseling content using a text mining tool to extract the user's preferences and desired makeup style. This information is used as data to generate a post-makeup facial image.

[0663] Step 8:

[0664] The server uses a generative model to generate a post-makeup facial image based on facial image analysis and extracted counseling content. The generated image reflects changes in real time.

[0665] Step 9:

[0666] The server sends the generated, makeup-applied facial image to the user's device. The image is then transferred to the user's smart device via the internet.

[0667] Step 10:

[0668] The device displays the user with the received image of their face after applying makeup. The user can see how their face will look with makeup applied.

[0669] Step 11:

[0670] The server recommends suitable makeup products and brands based on the user's attributes and consultation content. This information, along with a link to the purchasing site, is sent to the user's device.

[0671] Step 12:

[0672] The device displays received recommendations to the user and encourages purchases through the provided links. Users can click the links to purchase the recommended products online.

[0673] Step 13:

[0674] The server uses an emotion engine to analyze the user's facial expressions and voice to recognize their emotions. This emotion recognition occurs when counseling information is entered and when viewing a facial image after makeup application.

[0675] Specific example: The emotion engine analyzes the user's facial expressions as they enter information into a counseling form to detect whether the user is satisfied.

[0676] Step 14:

[0677] The server adjusts the makeup styles and recommended products in real time based on the emotion recognition results from the emotion engine. This ensures that suggestions best match the user's emotions.

[0678] Specific example: The emotion engine detects expressions of joy when the user sees a picture of their face after applying makeup, and then suggests more suitable makeup products based on that level of satisfaction.

[0679] Step 15:

[0680] The server generates targeted ads and special offers based on the user's browsing history and sends them to the user's device. This ensures that the user sees ads that are likely to be of interest to them.

[0681] Step 16:

[0682] The device displays targeted advertisements and special offers received by the user. The user can view these and take appropriate action as needed.

[0683] The above series of steps provides a convenient process for users to easily try out makeup styles that suit them and select the optimal products. Furthermore, the introduction of an emotion engine provides a more personalized experience that reflects the user's emotions.

[0684] (Example 2)

[0685] Next, we will describe Example 2. 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".

[0686] Traditional makeup systems presented a significant challenge: users had to expend considerable time and effort trying to find the makeup style that best suited them. Furthermore, the limited information available to users made it difficult for many to find a truly suitable style. Additionally, the lack of personalized suggestions that considered user emotions hindered user satisfaction.

[0687] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0688] In this invention, the server includes an image acquisition means, a generation means, a presentation means, an emotion recognition means, and a decision-making means. This allows the user to easily acquire an image of their face, analyze the image using an AI model, and receive customized makeup suggestions based on the user's emotions.

[0689] "Image acquisition means" refers to a means by which a user acquires an image of their own face using the camera on a mobile information terminal.

[0690] The "generation method" refers to a method for generating a post-makeup facial image based on a generative AI model for analyzing facial shape and skin tone.

[0691] "Presentation means" refers to the means by which the terminal displays the generated post-makeup facial image and related information to the user.

[0692] "Emotion recognition means" refers to a method that uses an emotion engine to analyze the user's facial expressions and voice when they input counseling information and when they check their face image after applying makeup, thereby recognizing the user's emotions.

[0693] "Decision-making means" refers to the method of determining the makeup style to offer and the recommended products based on image analysis and emotion recognition results.

[0694] A "portable information device" refers to an information processing device that a user can carry with them, and examples include smartphones and tablets.

[0695] A "photography device" is a camera built into a mobile information terminal that has the function of allowing the user to take an image of their own face.

[0696] A "generative AI model" is a model that uses artificial intelligence algorithms to analyze facial images and generate a post-makeup facial image based on the user's preferences.

[0697] An "emotion engine" is a software component that analyzes a user's facial expressions and voice to recognize their emotions.

[0698] "Makeup style" refers to the design and method of makeup desired by the user, and includes the specific details of the makeup applied to each part of the face.

[0699] "Recommended products" are cosmetics and related products that are deemed appropriate based on the user's attributes and emotional recognition results.

[0700] Embodiments of the present invention will be described in detail below. This system acquires a facial image using a mobile device, generates a post-makeup facial image using a generation AI model, and displays it on the device. Furthermore, by combining it with emotion recognition means, a more personalized makeup experience is provided.

[0701] The system includes image acquisition, generation, and presentation means, emotion recognition means, and decision-making means. The user uses a mobile device (such as a smartphone or tablet) to acquire an image of their face and input information necessary for counseling. This data is transmitted to a server, where a generation AI model analyzes it, and the system performs emotion recognition using the emotion recognition means and analyzes the resulting image of the face after makeup application. Based on the analysis results, appropriate information is presented to the user's device.

[0702] First, the user takes a facial image using the camera on their mobile device. When the user presses the capture button, the image is displayed on the device. The user then reviews the image and clicks the "upload" button, which sends the image to the server. Next, the device displays a makeup consultation form to the user. The user enters their ideal makeup style, brands, concerns, etc., and once completed, clicks the submit button to send this information to the server.

[0703] The server analyzes the received facial image and counseling content. Specifically, it uses image analysis software to identify the facial shape and skin tone, and inputs the results into a generating AI model. The generating AI model then generates a post-makeup facial image based on the user's preferences. The generated facial image is customized to reflect the user's counseling content.

[0704] Next, the server recommends appropriate makeup products and brands based on the user's attributes (gender, age) and counseling content. This information is sent to the user's device and presented to them. Furthermore, the server uses emotion recognition to analyze the user's facial expressions and voice when they input counseling information and view images of their face after applying makeup, recognizing the user's emotions. Based on the recognized emotions, the server adjusts the makeup style and recommended products in real time.

[0705] Finally, the generated post-makeup facial image and emotion recognition information are sent to the user's device for review. The user can then review the suggested makeup products and brands, and even access the purchasing site to buy them. This entire process allows users to easily experiment with different makeup styles and, through emotion recognition, receive customized suggestions, resulting in a more satisfying makeup experience.

[0706] For example, if a user wants "natural makeup" and wants to use products from a specific brand, they would enter the following:

[0707] Example: I want natural makeup. Please suggest a lip color that suits me.

[0708] This system allows users to see how their face is being made up in real time and receive more personalized suggestions through emotion recognition. This improves user satisfaction and provides a higher level of makeup experience.

[0709] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0710] Step 1:

[0711] The user launches the camera app on their mobile device and takes an image of their face. When the user presses the capture button, the image is displayed on the device. After the user confirms and clicks the "Upload" button, the device sends the image to the server.

[0712] Specific operation: The user opens the camera app and takes a selfie of their face. After taking the picture, the image is displayed on the screen. When the user presses the upload button, the image is sent to the server.

[0713] Input: A captured image of a face.

[0714] Processing: The terminal displays the user's facial image for verification and sends it to the server.

[0715] Output: Face image uploaded to the server.

[0716] Step 2:

[0717] The device displays a makeup consultation form to the user. The user enters their ideal makeup style, preferred brands, and makeup concerns. Once the user has finished entering the information and clicks the submit button, the information is sent to the server.

[0718] Specific operation: The user enters a request such as "I want natural makeup" into a form within the app and selects their preferred brand. Once the input is complete, they click the submit button.

[0719] Input: User counseling information (makeup style, brand, concerns).

[0720] Processing: The terminal receives user input and sends it to the server.

[0721] Output: Counseling information sent to the server.

[0722] Step 3:

[0723] The server analyzes the received facial image and counseling content. First, it uses image analysis software to identify the user's facial shape, skin tone, and facial features. Then, it uses a generative AI model to generate a post-makeup facial image based on the user's preferences.

[0724] Specific operation: Image analysis software identifies the shape of the face and skin tone, and inputs this information into a generating AI model. The generating AI model then generates a post-makeup facial image based on the counseling information.

[0725] Input: User's facial image, counseling information.

[0726] Processing: Face image generation using image analysis and generative AI models.

[0727] Output: The generated image of the face after applying makeup.

[0728] Step 4:

[0729] The server recommends appropriate makeup products and brands based on the user's attributes (gender, age) and counseling content. This information is then sent to the user's device.

[0730] Specific operation: The server analyzes the user's attributes and counseling information, selects appropriate makeup products and brands, and generates recommendation information. The generated information is then sent to the user's device.

[0731] Input: User attributes, counseling information.

[0732] Processing: Selection of makeup products and brands, and generation of recommendation information.

[0733] Output: Recommendation information sent to the user's device.

[0734] Step 5:

[0735] The server uses emotion recognition to analyze the user's facial expressions and voice as they input counseling information and view images of their face after makeup application, thereby recognizing the user's emotions. Based on the recognized emotions, the server adjusts the makeup style and recommended products in real time.

[0736] Specific operation: Emotion recognition means analyze facial expressions and voice to identify the user's emotions. Based on the results, the makeup style and recommended products are adjusted.

[0737] Input: User's facial expressions and voice data.

[0738] Processing: Emotion recognition and real-time adjustment.

[0739] Output: Adjusted makeup styles and recommended products.

[0740] Step 6:

[0741] The server sends the generated post-makeup facial image and emotion recognition results to the user's device. The device displays this to the user, allowing them to see how their face will look after the make-up.

[0742] Specific operation: The server sends the generated image of the face after applying makeup and the emotion recognition results, and the terminal displays them. The user confirms the displayed information.

[0743] Input: Generated facial image, emotion recognition result.

[0744] Processing: Data transmission from server to terminal, and display on terminal.

[0745] Output: The post-makeup facial image and emotion recognition results displayed on the user's device.

[0746] Step 7:

[0747] Users review the presented makeup products and brands, and if necessary, access the purchasing site to buy the items.

[0748] Specific actions: The user clicks on a link to a presented lip color or other product, accesses the online store, and completes the purchase process.

[0749] Input: Recommended makeup products and brand information.

[0750] Process: The user checks the product and accesses the online store.

[0751] Output: Purchased makeup products.

[0752] (Application Example 2)

[0753] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0754] In modern brick-and-mortar stores, providing personalized makeup experiences tailored to customers' emotions and preferences is challenging. Furthermore, limited means of visualizing the results beforehand make improving customer satisfaction difficult. Additionally, there's a lack of systems that allow customers to easily select the most suitable makeup products and brands on the spot.

[0755] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0756] In this invention, the server includes an image acquisition means, a generation means, a presentation means, an emotion recognition means, a real-time processing means, and a decision-making means. This enables personalized makeup suggestions and product recommendations through the acquisition of a user's facial image, generation of a post-makeup facial image, emotion recognition, and real-time analysis.

[0757] "Image acquisition means" refers to a means for a user to acquire an image of their own face using the camera of a smart device.

[0758] The "generation method" is a means of generating a post-makeup facial image based on a generative model for analyzing facial shape and skin tone.

[0759] "Presentation means" refers to a means of visually displaying the generated post-makeup facial image and analysis results to the user.

[0760] "Emotion recognition means" refers to a means of recognizing the user's emotions and adjusting makeup suggestions based on the results of that recognition.

[0761] The "real-time processing method" is a means of analyzing the user's satisfaction level and reaction in real time when they check their face image after applying makeup, and providing the optimal makeup style.

[0762] "Decision-making means" refers to methods for recommending the most suitable makeup products and brands to a user based on data from emotion recognition means and real-time processing means.

[0763] A "server" is a computer system used to process image data and analysis results, and to execute generative models and emotion recognition algorithms.

[0764] Embodiments of the present invention will be described in detail below.

[0765] System Configuration

[0766] This system includes the following means: image acquisition means, generation means, presentation means, emotion recognition means, real-time processing means, and decision-making means. The entire system consists of the user's smart device and a server that processes the data.

[0767] Image acquisition method

[0768] The user takes a picture of their face using the camera on a smart device (e.g., a smartphone). This image is acquired by the "image acquisition means" and sent to the server.

[0769] generation means

[0770] The server applies a generative AI model to the received facial image to analyze its shape and skin tone. Based on the analysis results, it generates a post-makeup image that reflects the user's desired makeup style. Machine learning frameworks such as TensorFlow and Keras are used for this generation process.

[0771] Presentation means

[0772] The generated image of the face after applying makeup is displayed on the user's smart device via a presentation mechanism. This allows the user to see the results of the makeup in real time.

[0773] emotion recognition means

[0774] The server uses emotion recognition engines such as DeepFace to analyze the user's emotions when they view their face image after applying makeup. This makes it possible to suggest makeup looks that match the user's satisfaction level and preferences.

[0775] Real-time processing means

[0776] The server analyzes the user's facial expressions and reactions in real time as they review their post-makeup facial image. Image processing libraries such as OpenCV are used for this process. The analysis results are immediately fed back and reflected in the generative model.

[0777] decision making means

[0778] Based on data obtained from emotion recognition and real-time processing systems, the server makes decisions. Specifically, it recommends the most suitable makeup products and brands to the user and provides that information to the user through a presentation system.

[0779] Explanation of specific examples

[0780] For example, a user takes a photo of their face using a smart device installed in a physical store. The image is sent to a server, where a generative model analyzes it. A new image of the user's face with natural makeup applied is then generated and displayed on the user's smart device. Furthermore, the user's facial expressions are analyzed, and if they are highly satisfied, specific makeup products or brands are recommended.

[0781] Example of a prompt

[0782] "Enter the user's face image and generate a post-makeup image. If the user's emotion is 'happy,' apply a natural makeup style."

[0783] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0784] Step 1:

[0785] The user uses the camera on their smart device to capture an image of their face.

[0786] Input: Face image taken from the user's smart device

[0787] Output: Acquired facial image

[0788] Specific operation: The user launches the smartphone's camera app and takes a selfie of their face. The captured image is then saved to the device.

[0789] Step 2:

[0790] The acquired facial images are uploaded to the server.

[0791] Input: Face image saved on the device

[0792] Output: Face image transferred to the server

[0793] Specific operation: When the user clicks the "Upload" button within the application, the device sends the acquired facial image to the server.

[0794] Step 3:

[0795] The server receives the transmitted facial image and uses a generating AI model to analyze the facial shape and skin tone.

[0796] Input: Face image sent to the server

[0797] Output: Analysis results (face shape, skin tone)

[0798] Specific operation: The server receives a facial image, runs a generative AI model using TensorFlow or Keras, and extracts and analyzes the facial shape and skin tone.

[0799] Step 4:

[0800] The generation method generates a post-makeup facial image based on the analysis results.

[0801] Input: Analysis results of facial shape and skin tone

[0802] Output: Face image after makeup application

[0803] Specific operation: The server uses the analysis results to generate a facial image after applying the user's desired makeup style.

[0804] Step 5:

[0805] The generated, post-makeup facial image is displayed to the user using a presentation device.

[0806] Input: Face image after makeup

[0807] Output: Face image after makeup application displayed on the user's terminal

[0808] Specific operation: The server sends the generated facial image to the user's smart device, and that image is displayed within the application.

[0809] Step 6:

[0810] Using emotion recognition technology, the system recognizes the emotions a user experiences when reviewing their face image after applying makeup.

[0811] Input: User's facial expression data

[0812] Output: User sentiment analysis results

[0813] Specific operation: The user's facial expressions when viewing the generated makeup-applied face image are captured by the smart device's camera, and emotions are analyzed using an emotion recognition engine such as DeepFace.

[0814] Step 7:

[0815] Real-time processing capabilities allow for real-time analysis of user satisfaction and reactions.

[0816] Input: User reaction data and sentiment analysis results

[0817] Output: Reaction analysis results

[0818] Specific operation: Capture and analyze in real time the user's satisfaction level and reactions to a presented image of their face after applying makeup.

[0819] Step 8:

[0820] Based on data from emotion recognition and real-time processing methods, the system uses decision-making mechanisms to recommend the most suitable makeup products and brands to the user.

[0821] Input: Emotion recognition results, reaction analysis results

[0822] Output: Recommended makeup products and brand information

[0823] Specific operation: Based on the emotion recognition results and reaction analysis results, the server determines the most suitable makeup products and brands for the user, and sends that information to the user's terminal for display.

[0824] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0825] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0826] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0827] [Third Embodiment]

[0828] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0829] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0830] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0831] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0832] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0833] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0834] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0835] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0836] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0837] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0838] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0839] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0840] Embodiments of the present invention will be described in detail below. This system acquires a facial image using the user's smart device, generates a facial image with makeup applied using a generative model, and displays it on the terminal.

[0841] System Overview

[0842] The system includes means for acquiring, generating, and presenting images. The user uses a smart device (such as a smartphone or tablet) to acquire an image of their face and inputs information necessary for makeup consultation. This data is sent to a server, where a generation model performs analysis. Based on the analysis results, a post-makeup face image is generated and presented to the user's device.

[0843] Program processing flow

[0844] 1. Image acquisition and upload

[0845] The user takes a picture of their face using the camera on their smart device. The device displays the captured image for confirmation, and when the user clicks the "Upload" button, the image is sent to the server.

[0846] Example: The user opens the app and takes a photo of their face in selfie mode. After taking the photo, they press the upload button, and the image is sent to the server.

[0847] 2. Entering counseling details

[0848] The device displays a form for the user to enter information such as their makeup consultation details, ideal style, and preferred brands. Once the user completes the input and clicks the submit button, the data is sent to the server.

[0849] Example: A user enters "I would like natural makeup" into the form and clicks the submit button.

[0850] 3. Analysis of images and counseling content

[0851] The server analyzes the received facial image and counseling content. Using a generative model, it analyzes the user's facial shape and skin tone, and processes the data to determine the user's ideal makeup style.

[0852] Specific example: The server analyzes a facial image, determines that the user's skin tone is neutral, and then decides on a suitable makeup style.

[0853] 4. Generating realistic makeup-applied facial images

[0854] The server uses a generative model to generate a post-makeup facial image based on the analysis results. The generated facial image reflects the user's counseling content.

[0855] Specific example: The generative model generates a facial image with the user's desired natural makeup applied, allowing it to be compared to the original image.

[0856] 5. Recommendations for makeup products and brands

[0857] The server recommends appropriate makeup products and brands based on the user's attributes (gender, age) and counseling content. This information is sent to the user's device.

[0858] Specific example: The server suggests to the user, "We recommend this lip color," and provides a link to the product's purchase page.

[0859] 6. Offering targeted advertising and special offers.

[0860] The server uses user data to provide targeted advertising and special offers. It can display customized ads based on the user's browsing history.

[0861] Specific example: The server provides the user with a discount coupon for their favorite brand of product.

[0862] Program execution order (overview)

[0863] 1. The device takes a picture of the user's face and sends it to the server.

[0864] 2. The terminal displays a counseling information input form, and the user enters the information and sends it to the server.

[0865] 3. The server analyzes the facial image and counseling content, and uses a generative model to generate a post-makeup facial image.

[0866] 4. The server sends the generated facial image to the user's device and displays it.

[0867] 5. The server recommends appropriate makeup products and brands and displays them on the user's device.

[0868] 6. The server provides targeted advertising and special offers based on the user's behavioral history.

[0869] This system allows users to try out the makeup style that best suits them without spending time or money, and to easily select and purchase products.

[0870] The following describes the processing flow.

[0871] Step 1:

[0872] The user activates their smart device and opens the app. The app displays a camera interface and provides instructions to the user for taking a picture of their face.

[0873] Step 2:

[0874] The device activates the smart device's camera and takes a picture of the user's face. After taking the picture, the device provides an interface for the user to review the image and click an "Upload" button if they are satisfied.

[0875] Step 3:

[0876] After the "Upload" button is clicked, the device sends the captured facial image to the server. The image is securely transferred over the internet.

[0877] Step 4:

[0878] The user then accesses a counseling form displayed within the app. The form includes fields for entering details such as makeup consultation topics, desired style, and preferred brands.

[0879] Step 5:

[0880] The device sends the entered data to the server after the user enters information into the counseling form and clicks the "Submit" button.

[0881] Step 6:

[0882] The server receives the uploaded facial image and counseling content and activates the image analysis module. The server uses a generative model to analyze the user's facial shape and skin tone.

[0883] Step 7:

[0884] The server analyzes the counseling content using a text mining tool to extract the user's preferences and desired makeup style. This information is used as data to generate a post-makeup facial image.

[0885] Step 8:

[0886] The server uses a generative model to generate a post-makeup facial image based on facial image analysis and extracted counseling content. The generated image reflects changes in real time.

[0887] Step 9:

[0888] The server sends the generated, makeup-applied facial image to the user's device. The image is then transferred to the user's smart device via the internet.

[0889] Step 10:

[0890] The device displays the user with the received image of their face after applying makeup. The user can see how their face will look with makeup applied.

[0891] Step 11:

[0892] The server recommends suitable makeup products and brands based on the user's attributes and consultation content. This information, along with a link to the purchasing site, is sent to the user's device.

[0893] Step 12:

[0894] The device displays received recommendations to the user and encourages purchases through the provided links. Users can click the links to purchase the recommended products online.

[0895] Step 13:

[0896] The server analyzes user behavior data to deliver targeted ads and provide special offers. It generates customized ads based on user attributes and behavioral history and sends them to the user's device.

[0897] Step 14:

[0898] The device displays personalized advertisements and special offers received by the user. The user can view these and take further action as needed.

[0899] The above series of steps provides users with an easy process to try out different makeup styles and select the products that best suit them.

[0900] (Example 1)

[0901] Next, we will describe Example 1. 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."

[0902] Traditional makeup simulation systems made it difficult for users to obtain their own facial images and try out appropriate makeup based on them. Furthermore, they lacked features to recommend suitable makeup products and brands, as well as to provide targeted advertising. As a result, users had to spend time and money experimenting to find the optimal makeup look.

[0903] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0904] In this invention, the server includes image acquisition means, generation means, presentation means, data transmission means, analysis means, recommendation means, and advertising provision means. This allows users to easily acquire their own facial images, generate realistic makeup-applied facial images using a generation AI model, and review them. Furthermore, it becomes possible to recommend appropriate makeup products and brands based on the user's attribute information and behavioral history, and to provide customized targeted advertising and special offers.

[0905] "Image acquisition means" refers to a method by which a user takes an image of their own face using a computer camera and acquires that image data.

[0906] "Generation means" refers to a means of analyzing acquired facial images and user counseling information, and generating a post-makeup facial image using a generation AI model.

[0907] "Presentation means" refers to a means of displaying the generated, makeup-applied facial image on the user's device.

[0908] "Data transmission means" refers to the means for sending facial images and counseling information acquired by the user to the server.

[0909] "Analysis means" refers to the means by which the server analyzes the facial images and counseling information it receives and performs data processing to generate a post-makeup facial image using a generation AI model.

[0910] A "recommendation method" is a means of recommending appropriate makeup products and brands based on the user's attribute information and counseling content.

[0911] "Advertising delivery methods" refer to methods for generating and providing targeted advertisements and special offers based on users' behavioral history and attribute information.

[0912] The system according to the present invention acquires a facial image using the user's computer camera, generates a facial image with makeup applied using a generation AI model, and displays it on a terminal. The overall configuration of this system includes image acquisition means, generation means, presentation means, data transmission means, analysis means, recommendation means, and advertising provision means.

[0913] Hardware and software usage

[0914] 1. Image acquisition method

[0915] The user takes a picture of their face using their computer's camera. This can be a standard webcam or the built-in camera of a smart device. The face image is then temporarily stored on the device.

[0916] 2. Data transmission means

[0917] The device includes a software module for sending captured facial images to a server. This module executes a protocol for securely transmitting image data to the server over the internet.

[0918] 3. Generation means

[0919] The server inputs the received facial image into a generating AI model, which then generates a post-makeup facial image based on the user's counseling information. The generating AI model is based on deep learning technology and uses advanced image processing techniques to produce realistic makeup effects.

[0920] 4. Analysis tools

[0921] The server includes an analysis module for analyzing the shape and skin tone of facial images. This provides data for the generative AI model to determine the optimal makeup style.

[0922] 5. Presentation means

[0923] The server sends the generated, makeup-applied facial image to the user's device. The device includes a user interface for displaying the received image.

[0924] 6. Recommendation methods

[0925] The server recommends appropriate makeup products and brands based on the user's attribute information (gender, age) and counseling information. This information is sent to the user's device, which then displays it.

[0926] 7. Advertising Delivery Methods

[0927] The server generates targeted ads and special offers based on the user's behavior history and attribute information. This advertising information is sent to the user's device, which then displays them.

[0928] Specific example

[0929] 1. The user takes a picture of their face using a webcam and clicks the application's upload button to send the image to the server.

[0930] 2. The device displays a form about the user's makeup preferences and ideal style, and the user enters the necessary information and sends it to the server.

[0931] 3. The server analyzes the facial image and counseling information, and uses a generative AI model to generate a post-makeup facial image.

[0932] 4. The server sends the generated facial image to the user's terminal, and the user checks the image in the application.

[0933] 5. The server recommends appropriate makeup products and brands based on the user's attribute information, and sends that information to the device for display to the user.

[0934] 6. The server generates special offers and targeted advertisements based on the user's behavior history, sends them to the device, and displays them to the user.

[0935] Examples of prompts for generative AI models

[0936] "Please apply the natural makeup look desired by the user to the face image."

[0937] "Please provide the optimal makeup style based on the user's face shape and skin tone."

[0938] "Please suggest lip colors that would be best suited for the user."

[0939] This allows users to easily try out the makeup style that best suits them, and easily select and purchase the appropriate products. This system not only saves users time and money, but also provides an advanced makeup simulation experience.

[0940] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0941] Step 1:

[0942] The user takes a picture of their face using the computer's camera. The input is a real-time facial image, and the output is a digital image temporarily stored on the device. The user starts this process by clicking the "Capture" button in the application. This action captures the facial image on the device.

[0943] Step 2:

[0944] The device displays the facial image taken by the user and prompts the user for confirmation. The user sends the image to the server by clicking the "Upload" button. The input is a temporarily stored facial image, and the output is data sent to the server via the internet. Through this operation, the device uploads the facial image data to the server.

[0945] Step 3:

[0946] The server receives the uploaded facial image. The input is the facial image data sent from the terminal, and the output is the facial image data stored on the server side. Through this process, the server prepares the facial image for image analysis.

[0947] Step 4:

[0948] The terminal displays a form for the user to enter information about their makeup preferences, ideal style, and favorite brands. The user fills in the required information in the form and clicks the "Submit" button. The input is the counseling information entered by the user, and the output is data sent to the server via the internet. Through this action, the terminal sends the counseling information to the server.

[0949] Step 5:

[0950] The server analyzes the received facial images and counseling information. The input is facial image data and counseling information, and the output is the analysis results regarding facial shape and skin tone, and the determination of a makeup style based on these results. Through this operation, the server provides data to the generative AI model and starts the analysis.

[0951] Step 6:

[0952] The server uses a generative AI model to generate a post-makeup face image based on the analysis results. The input is the analysis data, and the output is the generated post-makeup face image. Through this operation, the server creates the generated post-makeup face image.

[0953] Step 7:

[0954] The server sends the generated, made-up face image to the user's device. The input is the generated face image, and the output is the data sent to the device via the internet. Through this operation, the server delivers the face image to the user's device.

[0955] Step 8:

[0956] The terminal displays the received face image after makeup application. The input is face image data sent from the server, and the output is the face image after makeup application displayed to the user. The user can review the results and request adjustments as needed.

[0957] Step 9:

[0958] The server recommends appropriate makeup products and brands based on user attribute information and counseling information. The input is user attribute information and counseling information, and the output is a list of recommended makeup products and brands. Through this process, the server identifies recommended products and generates information about them.

[0959] Step 10:

[0960] The server sends information about recommended makeup products and brands to the user's device. The input is recommendation information, and the output is data sent to the device via the internet. Through this process, the server delivers recommendation information to the user's device.

[0961] Step 11:

[0962] The terminal displays received recommendation information to the user. The input is recommendation information sent from the server, and the output is a product list and brand information displayed to the user. The user can then consider purchasing products based on this information.

[0963] Step 12:

[0964] The server generates targeted ads and special offers based on the user's behavior history and attribute information. The input is the user's behavior history and attribute information, and the output is customized ads and special offers. Through this process, the server generates targeted ads.

[0965] Step 13:

[0966] The server sends the generated targeted ads and special offers to the user's device. The input is the generated ads and special offers, and the output is the data sent to the device via the internet. Through this operation, the server delivers the ads and offers to the user's device.

[0967] Step 14:

[0968] The device displays targeted ads and special offers received by the user. The input is advertising information sent from the server, and the output is the advertising and offer information displayed to the user. The user can then make purchasing decisions based on this information.

[0969] (Application Example 1)

[0970] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0971] Modern consumers have a need to check whether makeup products suit them without actually trying them out. However, current systems make it difficult to try out various makeup styles in real time, and furthermore, there is a lack of coordination between the recommendation of appropriate products and brands and the provision of advertising.

[0972] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0973] In this invention, the server includes image acquisition means, generation means, presentation means, recommendation means, and advertising provision means. This enables users to acquire facial images using a smart device and try out various makeup styles in real time. It also enables product recommendations based on the generated facial images and the provision of customized advertisements based on the user's preferences and behavioral history.

[0974] "Image acquisition means" refers to a device or function that allows a user to acquire their own facial image and transmit it to a server.

[0975] "Generation means" refers to a device or function that generates a post-makeup facial image based on a generative AI model for analyzing facial shape and skin tone.

[0976] "Presentation means" refers to a device or function that displays the generated, post-makeup facial image on the user's device or a store display.

[0977] A "recommendation method" is a device or function that recommends appropriate makeup products or brands based on the generated facial image and the user's counseling content.

[0978] "Advertising delivery means" refers to a device or function that provides customized advertisements or special offers based on the user's attributes and behavioral history.

[0979] This invention relates to a system in which a user acquires an image of their face using a smart device, generates a makeup-applied image of their face using a generative model, and displays it on the terminal. The system includes image acquisition means, generation means, presentation means, recommendation means, and advertising provision means.

[0980] System Program Overview

[0981] 1. Image acquisition method:

[0982] The user uses a smart device (e.g., smartphone, tablet, etc.) to acquire an image of their own face and sends that image to a server. This function utilizes an imaging device used in mobile communication devices (e.g., smartphone camera) and an image capture application (e.g., OpenCV).

[0983] 2. Generation means:

[0984] The server inputs the received facial image into a generative AI model, which analyzes the facial shape and skin tone. The generative model (e.g., GAN, TensorFlow, PyTorch) then generates a makeup-applied facial image based on these analysis results. This generated facial image is processed in real time.

[0985] 3. Means of presentation:

[0986] The generated facial image will be displayed on the user's device (e.g., smartphone, tablet) or on a display installed in the store. Hardware for this will include a web server (e.g., Nginx) and a front-end framework (e.g., React.js).

[0987] 4. Recommendation methods:

[0988] The server recommends appropriate makeup products and brands based on the generated facial image and the user's consultation content. This recommendation process utilizes user attribute analysis and product database matching algorithms (e.g., ElasticSearch).

[0989] 5. Advertising delivery methods:

[0990] The server delivers customized ads and special offers based on the user's attributes and behavioral history. For ad delivery, it utilizes advertising technology platforms (e.g., Google Ads API).

[0991] Explanation of the process

[0992] Upon receiving a user's facial image, the server first performs image analysis to detect skin tone and facial shape. Next, it inputs the image into a generative model to generate a facial image corresponding to the desired makeup style. The generated facial image is then displayed on the user's device or in-store display. Subsequently, based on the analysis data, the server recommends suitable makeup products and brands, and displays further customized advertisements and special offers.

[0993] Specific example

[0994] For example, when a customer enters a store and scans their face with smart glasses installed in the store, the image is immediately sent to a server, and an AI generation model begins analysis. For customers who have entered their preference for natural makeup, the generation model generates an image of their face with a natural makeup style and displays it on the screen. Furthermore, lip colors and eyeshadows that match that style are recommended, and special offers and discount coupons for purchase are also presented.

[0995] Example of a prompt

[0996] Image analysis:

[0997] plain

[0998] Upload a customer's facial image and run it through the AI ​​model to generate a facial image with natural makeup.

[0999] Product Recommendations:

[1000] plain

[1001] Please recommend lip colors and eyeshadows that are suitable for natural makeup, and provide details about the products and any special offers.

[1002] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1003] Step 1:

[1004] The user obtains a facial image using a smart device (e.g., a smartphone). The input is a facial image taken with the device's camera, and this image is temporarily stored on the device. After the user confirms the image, they click the "Upload" button to send the image to the server.

[1005] Step 2:

[1006] The server receives a face image sent by the user and begins image analysis. The analysis uses face recognition technology and skin tone analysis algorithms (e.g., OpenCV, TensorFlow). This detects the shape of the user's face and skin tone. The input is a face image, and the output is face shape data and skin tone data.

[1007] Step 3:

[1008] The server uses a generative AI model (e.g., GAN) to generate a post-makeup face image based on the acquired facial shape and skin tone data. The input to the generative AI model is the analysis results, and the output is the generated post-makeup face image. This generates a real-time face image that matches the user's desired makeup style.

[1009] Step 4:

[1010] The generated facial image is sent from the server to the user's smart device or a store display for display. This display uses a web server (e.g., Nginx) and a frontend framework (e.g., React.js). The input is the generated facial image, and the output is the displayed facial image.

[1011] Step 5:

[1012] The server recommends appropriate makeup products and brands based on the generated facial image and the user's counseling content. This uses user attribute analysis and a matching algorithm for the product database (e.g., ElasticSearch). The input is user attribute data and the generated facial image, and the output is a list of recommended products.

[1013] Step 6:

[1014] The server delivers customized ads and special offers based on user attributes and behavioral history. For ad delivery, it utilizes an advertising technology platform (e.g., Google Ads API). The input is user behavioral history data, and the output is customized ads and special offers.

[1015] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1016] Embodiments of the present invention will be described in detail below. This system acquires a facial image using a smart device, generates a post-makeup facial image using a generative model, and displays it on the terminal. Furthermore, by combining this with an emotion engine that recognizes the user's emotions, a more personalized makeup experience is provided.

[1017] System Overview

[1018] The system includes image acquisition means, generation means, presentation means, emotion engine, and decision-making means. The user uses a smart device (such as a smartphone or tablet) to acquire an image of their face and inputs information necessary for makeup counseling. This data is sent to a server, where a generation model analyzes it, and the system performs emotion recognition using the emotion engine and produces a post-makeup facial image. Based on the analysis results, appropriate information is presented to the user's device.

[1019] Program processing flow

[1020] 1. Image acquisition and upload

[1021] The user takes a picture of their face using the camera on their smart device. The device displays the captured image for confirmation, and when the user clicks the "Upload" button, the image is sent to the server.

[1022] Example: The user opens the app and takes a photo of their face in selfie mode. After taking the photo, they press the upload button, and the image is sent to the server.

[1023] 2. Enter the counseling details.

[1024] The device displays a form for the user to enter details such as their makeup consultation needs, ideal style, and preferred brands. Once the user completes the form and clicks the submit button, the data is sent to the server.

[1025] Example: A user enters "I would like natural makeup" into the form and clicks the submit button.

[1026] 3. Analysis of images and counseling content

[1027] The server analyzes the received facial image and counseling content. Using a generative model, it analyzes the user's facial shape and skin tone, and processes the data to determine the user's ideal makeup style.

[1028] Specific example: The server analyzes a facial image, determines that the user's skin tone is neutral, and then decides on a suitable makeup style.

[1029] 4. Generating realistic makeup-applied facial images

[1030] The server uses a generative model to generate a post-makeup facial image based on the analysis results. The generated facial image reflects the user's counseling content.

[1031] Specific example: The generative model generates a facial image with the user's desired natural makeup applied, allowing it to be compared to the original image.

[1032] 5. Recommendations for makeup products and brands

[1033] The server recommends appropriate makeup products and brands based on the user's attributes (gender, age) and counseling content. This information is sent to the user's device.

[1034] Specific example: The server suggests to the user, "We recommend this lip color," and provides a link to the product's purchase page.

[1035] 6. Emotion recognition by an emotion engine

[1036] The server uses an emotion engine to analyze the user's facial expressions and voice as they input counseling information and view their post-makeup facial image, recognizing their emotions. Based on the recognized emotions, the server adjusts the makeup style and recommended products in real time.

[1037] Specific example: The emotion engine recognizes the smile a user shows when viewing a photo of their face after applying makeup, measures their satisfaction level, and then suggests products in colors that suit them better.

[1038] 7. Presentation of makeup results

[1039] The server sends the generated, made-up face image and feedback from the emotion engine to the user's device. The device displays this to the user, allowing them to see how their face looks with makeup applied.

[1040] Specific example: The server generates a face image after applying makeup, and the results of the emotion engine's analysis (such as satisfaction level) are sent to the user's device for the user to review.

[1041] 8. Utilization of the information provided

[1042] Users review the presented makeup products and brands, and if necessary, access the purchasing site to buy the items.

[1043] Specific example: A user purchases their favorite lip color from an online store.

[1044] Achieving the System's Objectives

[1045] Through these steps, users can not only try out makeup styles that suit them, but the app's emotion engine will also help it understand their preferences more accurately, leading to customized makeup suggestions. This improves the user experience and makes it possible to provide a more satisfying makeup experience.

[1046] The following describes the processing flow.

[1047] Step 1:

[1048] The user activates their smart device and opens the app. The app displays a camera interface and provides instructions to the user for taking a picture of their face.

[1049] Step 2:

[1050] The device activates the smart device's camera and takes a picture of the user's face. After taking the picture, the device provides an interface for the user to review the image and click an "Upload" button if they are satisfied.

[1051] Step 3:

[1052] After the "Upload" button is clicked, the device sends the captured facial image to the server. The image is securely transferred over the internet.

[1053] Step 4:

[1054] The user then accesses a counseling form displayed within the app. The form includes fields for entering details such as makeup consultation topics, desired style, and preferred brands.

[1055] Step 5:

[1056] The device sends the entered data to the server after the user enters information into the counseling form and clicks the "Submit" button.

[1057] Step 6:

[1058] The server receives the uploaded facial image and counseling content and activates the image analysis module. The server uses a generative model to analyze the user's facial shape and skin tone.

[1059] Step 7:

[1060] The server analyzes the counseling content using a text mining tool to extract the user's preferences and desired makeup style. This information is used as data to generate a post-makeup facial image.

[1061] Step 8:

[1062] The server uses a generative model to generate a post-makeup facial image based on facial image analysis and extracted counseling content. The generated image reflects changes in real time.

[1063] Step 9:

[1064] The server sends the generated, makeup-applied facial image to the user's device. The image is then transferred to the user's smart device via the internet.

[1065] Step 10:

[1066] The device displays the user with the received image of their face after applying makeup. The user can see how their face will look with makeup applied.

[1067] Step 11:

[1068] The server recommends suitable makeup products and brands based on the user's attributes and consultation content. This information, along with a link to the purchasing site, is sent to the user's device.

[1069] Step 12:

[1070] The device displays received recommendations to the user and encourages purchases through the provided links. Users can click the links to purchase the recommended products online.

[1071] Step 13:

[1072] The server uses an emotion engine to analyze the user's facial expressions and voice to recognize their emotions. This emotion recognition occurs when counseling information is entered and when viewing a facial image after makeup application.

[1073] Specific example: The emotion engine analyzes the user's facial expressions as they enter information into a counseling form to detect whether the user is satisfied.

[1074] Step 14:

[1075] The server adjusts the makeup styles and recommended products in real time based on the emotion recognition results from the emotion engine. This ensures that suggestions best match the user's emotions.

[1076] Specific example: The emotion engine detects expressions of joy when the user sees a picture of their face after applying makeup, and then suggests more suitable makeup products based on their level of satisfaction.

[1077] Step 15:

[1078] The server generates targeted ads and special offers based on the user's browsing history and sends them to the user's device. This ensures that the user sees ads that are likely to be of interest to them.

[1079] Step 16:

[1080] The device displays targeted advertisements and special offers received by the user. The user can view these and take appropriate action as needed.

[1081] The above series of steps provides a convenient process for users to easily try out makeup styles that suit them and select the optimal products. Furthermore, the introduction of an emotion engine provides a more personalized experience that reflects the user's emotions.

[1082] (Example 2)

[1083] Next, we will describe Example 2. 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."

[1084] Traditional makeup systems presented a significant challenge: users had to expend considerable time and effort trying to find the makeup style that best suited them. Furthermore, the limited information available to users made it difficult for many to find a truly suitable style. Additionally, the lack of personalized suggestions that considered user emotions hindered user satisfaction.

[1085] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1086] In this invention, the server includes an image acquisition means, a generation means, a presentation means, an emotion recognition means, and a decision-making means. This allows the user to easily acquire an image of their face, have the image analyzed using an AI model, and receive customized makeup suggestions based on the user's emotions.

[1087] "Image acquisition means" refers to a means by which a user acquires an image of their own face using the camera on a mobile information terminal.

[1088] The "generation method" refers to a means of generating a post-makeup facial image based on a generative AI model for analyzing facial shape and skin tone.

[1089] "Presentation means" refers to the means by which the terminal displays the generated post-makeup facial image and related information to the user.

[1090] "Emotion recognition means" refers to a method of recognizing a user's emotions by using an emotion engine to analyze their facial expressions and voice when they input counseling information and when they review images of their face after applying makeup.

[1091] "Decision-making means" refers to the means of determining the makeup style to offer and the recommended products based on image analysis and emotion recognition results.

[1092] A "portable information device" refers to an information processing device that a user can carry with them, and examples include smartphones and tablets.

[1093] A "photography device" is a camera built into a mobile information terminal that has the function of allowing the user to take an image of their own face.

[1094] A "generative AI model" is an algorithm that uses artificial intelligence to analyze facial images and generate a post-makeup image of the face based on the user's preferences.

[1095] An "emotion engine" is a software component that analyzes a user's facial expressions and voice to recognize their emotions.

[1096] "Makeup style" refers to the design and method of makeup desired by the user, and includes the specific details of the makeup applied to each part of the face.

[1097] "Recommended products" are cosmetics and related products that are deemed appropriate based on the user's attributes and emotional recognition results.

[1098] Embodiments of the present invention will be described in detail below. This system acquires a facial image using a mobile device, generates a post-makeup facial image using a generation AI model, and displays it on the device. Furthermore, by combining it with emotion recognition means, a more personalized makeup experience is provided.

[1099] The system includes image acquisition, generation, and presentation means, emotion recognition means, and decision-making means. The user uses a mobile device (such as a smartphone or tablet) to acquire an image of their face and input information necessary for counseling. This data is transmitted to a server, where a generation AI model analyzes it, and the system performs emotion recognition using the emotion recognition means and analyzes the resulting image of the face after makeup application. Based on the analysis results, appropriate information is presented to the user's device.

[1100] First, the user takes a facial image using the camera on their mobile device. When the user presses the capture button, the image is displayed on the device. The user then reviews the image and clicks the "upload" button, which sends the image to the server. Next, the device displays a makeup consultation form to the user. The user enters their ideal makeup style, brands, concerns, etc., and once completed, clicks the submit button to send this information to the server.

[1101] The server analyzes the received facial image and counseling content. Specifically, it uses image analysis software to identify the facial shape and skin tone, and inputs the results into a generating AI model. The generating AI model then generates a post-makeup facial image based on the user's preferences. The generated facial image is customized to reflect the user's counseling content.

[1102] Next, the server recommends appropriate makeup products and brands based on the user's attributes (gender, age) and counseling content. This information is sent to the user's device and presented to them. Furthermore, the server uses emotion recognition to analyze the user's facial expressions and voice when they input counseling information and view images of their face after applying makeup, recognizing the user's emotions. Based on the recognized emotions, the server adjusts the makeup style and recommended products in real time.

[1103] Finally, the generated post-makeup facial image and emotion recognition information are sent to the user's device for review. The user can then review the suggested makeup products and brands, and even access the purchasing site to buy them. This entire process allows users to easily experiment with different makeup styles and, through emotion recognition, receive customized suggestions, resulting in a more satisfying makeup experience.

[1104] For example, if a user wants "natural makeup" and wants to use products from a specific brand, they would enter the following:

[1105] Example: I want natural makeup. Please suggest a lip color that suits me.

[1106] This system allows users to see how their face is being made up in real time and receive more personalized suggestions through emotion recognition. This improves user satisfaction and provides a higher level of makeup experience.

[1107] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1108] Step 1:

[1109] The user launches the camera app on their mobile device and takes an image of their face. When the user presses the capture button, the image is displayed on the device. After the user confirms and clicks the "Upload" button, the device sends the image to the server.

[1110] Specific operation: The user opens the camera app and takes a selfie of their face. After taking the picture, the image is displayed on the screen. When the user presses the upload button, the image is sent to the server.

[1111] Input: A captured image of a face.

[1112] Processing: The terminal displays the user's facial image for verification and sends it to the server.

[1113] Output: Face image uploaded to the server.

[1114] Step 2:

[1115] The device displays a makeup consultation form to the user. The user enters their ideal makeup style, preferred brands, and makeup concerns. Once the user has finished entering the information and clicks the submit button, the information is sent to the server.

[1116] Specific operation: The user enters a request such as "I want natural makeup" into a form within the app and selects their preferred brand. Once the input is complete, they click the submit button.

[1117] Input: User counseling information (makeup style, brand, concerns).

[1118] Processing: The terminal receives user input and sends it to the server.

[1119] Output: Counseling information sent to the server.

[1120] Step 3:

[1121] The server analyzes the received facial image and counseling content. First, it uses image analysis software to identify the user's facial shape, skin tone, and facial features. Then, it uses a generative AI model to generate a post-makeup facial image based on the user's preferences.

[1122] Specific operation: Image analysis software identifies the shape of the face and skin tone, and inputs this information into a generating AI model. The generating AI model then generates a post-makeup facial image based on the counseling information.

[1123] Input: User's facial image, counseling information.

[1124] Processing: Face image generation using image analysis and generative AI models.

[1125] Output: The generated image of the face after applying makeup.

[1126] Step 4:

[1127] The server recommends appropriate makeup products and brands based on the user's attributes (gender, age) and counseling content. This information is then sent to the user's device.

[1128] Specific operation: The server analyzes the user's attributes and counseling information, selects appropriate makeup products and brands, and generates recommendation information. The generated information is then sent to the user's device.

[1129] Input: User attributes, counseling information.

[1130] Processing: Selection of makeup products and brands, and generation of recommendation information.

[1131] Output: Recommendation information sent to the user's device.

[1132] Step 5:

[1133] The server uses emotion recognition to analyze the user's facial expressions and voice as they input counseling information and view images of their face after makeup application, thereby recognizing the user's emotions. Based on the recognized emotions, the server adjusts the makeup style and recommended products in real time.

[1134] Specific operation: Emotion recognition means analyze facial expressions and voice to identify the user's emotions. Based on the results, the makeup style and recommended products are adjusted.

[1135] Input: User's facial expressions and voice data.

[1136] Processing: Emotion recognition and real-time adjustment.

[1137] Output: Adjusted makeup styles and recommended products.

[1138] Step 6:

[1139] The server sends the generated post-makeup facial image and emotion recognition results to the user's device. The device displays this to the user, allowing them to see how their face will look after the makeup is applied.

[1140] Specific operation: The server sends the generated image of the face after applying makeup and the emotion recognition results, and the terminal displays them. The user confirms the displayed information.

[1141] Input: Generated facial image, emotion recognition result.

[1142] Processing: Data transmission from server to terminal, and display on terminal.

[1143] Output: The post-makeup facial image and emotion recognition results displayed on the user's device.

[1144] Step 7:

[1145] Users review the presented makeup products and brands, and if necessary, access the purchasing site to buy the items.

[1146] Specific actions: The user clicks on a link to a presented lip color or other product, accesses the online store, and completes the purchase process.

[1147] Input: Recommended makeup products and brand information.

[1148] Process: The user checks the product and accesses the online store.

[1149] Output: Purchased makeup products.

[1150] (Application Example 2)

[1151] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1152] In modern brick-and-mortar stores, providing personalized makeup experiences tailored to customers' emotions and preferences is challenging. Furthermore, limited means of visualizing the results beforehand make improving customer satisfaction difficult. Additionally, there's a lack of systems that allow customers to easily select the most suitable makeup products and brands on the spot.

[1153] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1154] In this invention, the server includes an image acquisition means, a generation means, a presentation means, an emotion recognition means, a real-time processing means, and a decision-making means. This enables personalized makeup suggestions and product recommendations through the acquisition of a user's facial image, generation of a post-makeup facial image, emotion recognition, and real-time analysis.

[1155] "Image acquisition means" refers to a means for a user to acquire an image of their own face using the camera of a smart device.

[1156] The "generation method" is a means of generating a post-makeup facial image based on a generative model for analyzing facial shape and skin tone.

[1157] "Presentation means" refers to a means of visually displaying the generated post-makeup facial image and analysis results to the user.

[1158] "Emotion recognition means" refers to a means of recognizing the user's emotions and adjusting makeup suggestions based on the results of that recognition.

[1159] The "real-time processing method" is a means of analyzing the user's satisfaction level and reaction in real time when they check their face image after applying makeup, and providing the optimal makeup style.

[1160] "Decision-making means" refers to methods for recommending the most suitable makeup products and brands to a user based on data from emotion recognition means and real-time processing means.

[1161] A "server" is a computer system used to process image data and analysis results, and to execute generative models and emotion recognition algorithms.

[1162] Embodiments of the present invention will be described in detail below.

[1163] System Configuration

[1164] This system includes the following means: image acquisition means, generation means, presentation means, emotion recognition means, real-time processing means, and decision-making means. The entire system consists of the user's smart device and a server that processes the data.

[1165] Image acquisition method

[1166] The user takes a picture of their face using the camera on a smart device (e.g., a smartphone). This image is acquired by the "image acquisition means" and sent to the server.

[1167] generation means

[1168] The server applies a generative AI model to the received facial image to analyze its shape and skin tone. Based on the analysis results, it generates a post-makeup image that reflects the user's desired makeup style. Machine learning frameworks such as TensorFlow and Keras are used for this generation process.

[1169] Presentation means

[1170] The generated image of the face after applying makeup is displayed on the user's smart device via a presentation mechanism. This allows the user to see the results of the makeup in real time.

[1171] emotion recognition means

[1172] The server uses emotion recognition engines such as DeepFace to analyze the user's emotions when they view their face image after applying makeup. This makes it possible to suggest makeup looks that match the user's satisfaction level and preferences.

[1173] Real-time processing means

[1174] The server analyzes the user's facial expressions and reactions in real time as they view their post-makeup facial image. Image processing libraries such as OpenCV are used for this process. The analysis results are immediately fed back and reflected in the generative model.

[1175] decision making means

[1176] Based on data obtained from emotion recognition and real-time processing systems, the server makes decisions. Specifically, it recommends the most suitable makeup products and brands to the user and provides that information to the user through a presentation system.

[1177] Explanation of specific examples

[1178] For example, a user takes a photo of their face using a smart device installed in a physical store. The image is sent to a server, where a generative model analyzes it. A new image of the user's face with natural makeup applied is then generated and displayed on the user's smart device. Furthermore, the user's facial expressions are analyzed, and if they are highly satisfied, specific makeup products or brands are recommended.

[1179] Example of a prompt

[1180] "Enter the user's face image and generate a post-makeup image. If the user's emotion is 'happy,' apply a natural makeup style."

[1181] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1182] Step 1:

[1183] The user uses the camera on their smart device to capture an image of their face.

[1184] Input: Face image taken from the user's smart device

[1185] Output: Acquired facial image

[1186] Specific operation: The user launches the smartphone's camera app and takes a selfie of their face. The captured image is then saved to the device.

[1187] Step 2:

[1188] The acquired facial images are uploaded to the server.

[1189] Input: Face image saved on the device

[1190] Output: Face image transferred to the server

[1191] Specific operation: When the user clicks the "Upload" button within the application, the device sends the acquired facial image to the server.

[1192] Step 3:

[1193] The server receives the transmitted facial image and uses a generating AI model to analyze the facial shape and skin tone.

[1194] Input: Face image sent to the server

[1195] Output: Analysis results (face shape, skin tone)

[1196] Specific operation: The server receives a facial image, runs a generative AI model using TensorFlow or Keras, and extracts and analyzes the facial shape and skin tone.

[1197] Step 4:

[1198] The generation method generates a post-makeup facial image based on the analysis results.

[1199] Input: Analysis results of facial shape and skin tone

[1200] Output: Face image after makeup application

[1201] Specific operation: The server uses the analysis results to generate a facial image after applying the user's desired makeup style.

[1202] Step 5:

[1203] The generated, post-makeup facial image is displayed to the user using a presentation device.

[1204] Input: Face image after makeup

[1205] Output: Face image after makeup application displayed on the user's terminal

[1206] Specific operation: The server sends the generated facial image to the user's smart device, and that image is displayed within the application.

[1207] Step 6:

[1208] Using emotion recognition technology, the system recognizes the emotions a user experiences when reviewing their face image after applying makeup.

[1209] Input: User's facial expression data

[1210] Output: User sentiment analysis results

[1211] Specific operation: The user's facial expressions when viewing the generated makeup-applied face image are captured by the smart device's camera, and emotions are analyzed using an emotion recognition engine such as DeepFace.

[1212] Step 7:

[1213] Real-time processing capabilities allow for real-time analysis of user satisfaction and reactions.

[1214] Input: User reaction data and sentiment analysis results

[1215] Output: Reaction analysis results

[1216] Specific operation: Capture and analyze in real time the user's satisfaction level and reactions to a presented image of their face after applying makeup.

[1217] Step 8:

[1218] Based on data from emotion recognition and real-time processing methods, the system uses decision-making mechanisms to recommend the most suitable makeup products and brands to the user.

[1219] Input: Emotion recognition results, reaction analysis results

[1220] Output: Recommended makeup products and brand information

[1221] Specific operation: Based on the emotion recognition results and reaction analysis results, the server determines the most suitable makeup products and brands for the user, and sends that information to the user's terminal for display.

[1222] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1223] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1224] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1225] [Fourth Embodiment]

[1226] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1227] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1228] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1229] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1230] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1231] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1232] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1233] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1234] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1235] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[1236] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1237] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1238] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1239] Embodiments of the present invention will be described in detail below. This system acquires a facial image using the user's smart device, generates a facial image with makeup applied using a generative model, and displays it on the terminal.

[1240] System Overview

[1241] The system includes means for acquiring, generating, and presenting images. The user uses a smart device (such as a smartphone or tablet) to acquire an image of their face and inputs information necessary for makeup consultation. This data is sent to a server, where a generation model performs analysis. Based on the analysis results, a post-makeup face image is generated and presented to the user's device.

[1242] Program processing flow

[1243] 1. Image acquisition and upload

[1244] The user takes a picture of their face using the camera on their smart device. The device displays the captured image for confirmation, and when the user clicks the "Upload" button, the image is sent to the server.

[1245] Example: The user opens the app and takes a photo of their face in selfie mode. After taking the photo, they press the upload button, and the image is sent to the server.

[1246] 2. Enter the counseling details.

[1247] The device displays a form for the user to enter information such as their makeup consultation details, ideal style, and preferred brands. Once the user completes the input and clicks the submit button, the data is sent to the server.

[1248] Example: A user enters "I would like natural makeup" into the form and clicks the submit button.

[1249] 3. Analysis of images and counseling content

[1250] The server analyzes the received facial image and counseling content. Using a generative model, it analyzes the user's facial shape and skin tone, and processes the data to determine the user's ideal makeup style.

[1251] Specific example: The server analyzes a facial image, determines that the user's skin tone is neutral, and then decides on a suitable makeup style.

[1252] 4. Generating realistic makeup-applied facial images

[1253] The server uses a generative model to generate a post-makeup facial image based on the analysis results. The generated facial image reflects the user's counseling content.

[1254] Specific example: The generative model generates a facial image with the user's desired natural makeup applied, allowing it to be compared to the original image.

[1255] 5. Recommendations for makeup products and brands

[1256] The server recommends appropriate makeup products and brands based on the user's attributes (gender, age) and counseling content. This information is sent to the user's device.

[1257] Specific example: The server suggests to the user, "We recommend this lip color," and provides a link to the product's purchase page.

[1258] 6. Offering targeted advertising and special offers.

[1259] The server uses user data to provide targeted advertising and special offers. It can display customized ads based on the user's browsing history.

[1260] Specific example: The server provides the user with a discount coupon for their favorite brand of product.

[1261] Program execution order (overview)

[1262] 1. The device takes a picture of the user's face and sends it to the server.

[1263] 2. The terminal displays a counseling information input form, and the user enters the information and sends it to the server.

[1264] 3. The server analyzes the facial image and counseling content, and uses a generative model to generate a post-makeup facial image.

[1265] 4. The server sends the generated facial image to the user's device and displays it.

[1266] 5. The server recommends appropriate makeup products and brands and displays them on the user's device.

[1267] 6. The server provides targeted advertising and special offers based on the user's behavioral history.

[1268] This system allows users to try out the makeup style that best suits them without spending time or money, and to easily select and purchase products.

[1269] The following describes the processing flow.

[1270] Step 1:

[1271] The user activates their smart device and opens the app. The app displays a camera interface and provides instructions to the user for taking a picture of their face.

[1272] Step 2:

[1273] The device activates the smart device's camera and takes a picture of the user's face. After taking the picture, the device provides an interface for the user to review the image and click an "Upload" button if they are satisfied.

[1274] Step 3:

[1275] After the "Upload" button is clicked, the device sends the captured facial image to the server. The image is securely transferred over the internet.

[1276] Step 4:

[1277] The user then accesses a counseling form displayed within the app. The form includes fields for entering details such as makeup consultation topics, desired style, and preferred brands.

[1278] Step 5:

[1279] The device sends the entered data to the server after the user enters information into the counseling form and clicks the "Submit" button.

[1280] Step 6:

[1281] The server receives the uploaded facial image and counseling content and activates the image analysis module. The server uses a generative model to analyze the user's facial shape and skin tone.

[1282] Step 7:

[1283] The server analyzes the counseling content using a text mining tool to extract the user's preferences and desired makeup style. This information is used as data to generate a post-makeup facial image.

[1284] Step 8:

[1285] The server uses a generative model to generate a post-makeup facial image based on facial image analysis and extracted counseling content. The generated image reflects changes in real time.

[1286] Step 9:

[1287] The server sends the generated, makeup-applied facial image to the user's device. The image is then transferred to the user's smart device via the internet.

[1288] Step 10:

[1289] The device displays the user with the received image of their face after applying makeup. The user can see how their face will look with makeup applied.

[1290] Step 11:

[1291] The server recommends suitable makeup products and brands based on the user's attributes and consultation content. This information, along with a link to the purchasing site, is sent to the user's device.

[1292] Step 12:

[1293] The device displays received recommendations to the user and encourages purchases through the provided links. Users can click the links to purchase the recommended products online.

[1294] Step 13:

[1295] The server analyzes user behavior data to deliver targeted ads and provide special offers. It generates customized ads based on user attributes and behavioral history and sends them to the user's device.

[1296] Step 14:

[1297] The device displays personalized advertisements and special offers received by the user. The user can view these and take further action as needed.

[1298] The above series of steps provides users with an easy process to try out different makeup styles and select the products that best suit them.

[1299] (Example 1)

[1300] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1301] Traditional makeup simulation systems made it difficult for users to obtain their own facial images and try out appropriate makeup based on them. Furthermore, they lacked features to recommend suitable makeup products and brands, as well as to provide targeted advertising. As a result, users had to spend time and money experimenting to find the optimal makeup look.

[1302] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1303] In this invention, the server includes image acquisition means, generation means, presentation means, data transmission means, analysis means, recommendation means, and advertising provision means. This allows users to easily acquire their own facial images, generate realistic makeup-applied facial images using a generation AI model, and review them. Furthermore, it becomes possible to recommend appropriate makeup products and brands based on the user's attribute information and behavioral history, and to provide customized targeted advertising and special offers.

[1304] "Image acquisition means" refers to a method by which a user takes an image of their own face using a computer camera and acquires that image data.

[1305] "Generation means" refers to a means of analyzing acquired facial images and user counseling information, and generating a post-makeup facial image using a generation AI model.

[1306] "Presentation means" refers to a means of displaying the generated, makeup-applied facial image on the user's device.

[1307] "Data transmission means" refers to the means for sending facial images and counseling information acquired by the user to the server.

[1308] "Analysis means" refers to the means by which the server analyzes the facial images and counseling information it receives and performs data processing to generate a post-makeup facial image using a generation AI model.

[1309] A "recommendation method" is a means of recommending appropriate makeup products and brands based on the user's attribute information and counseling content.

[1310] "Advertising delivery methods" refer to methods for generating and providing targeted advertisements and special offers based on users' behavioral history and attribute information.

[1311] The system according to the present invention acquires a facial image using the user's computer camera, generates a facial image with makeup applied using a generation AI model, and displays it on a terminal. The overall configuration of this system includes image acquisition means, generation means, presentation means, data transmission means, analysis means, recommendation means, and advertising provision means.

[1312] Hardware and software usage

[1313] 1. Image acquisition method

[1314] The user takes a picture of their face using their computer's camera. This can be a standard webcam or the built-in camera of a smart device. The face image is then temporarily stored on the device.

[1315] 2. Data transmission means

[1316] The device includes a software module for sending captured facial images to a server. This module executes a protocol for securely transmitting image data to the server over the internet.

[1317] 3. Generation means

[1318] The server inputs the received facial image into a generating AI model, which then generates a post-makeup facial image based on the user's counseling information. The generating AI model is based on deep learning technology and uses advanced image processing techniques to produce realistic makeup effects.

[1319] 4. Analysis tools

[1320] The server includes an analysis module for analyzing the shape and skin tone of facial images. This provides data for the generative AI model to determine the optimal makeup style.

[1321] 5. Presentation means

[1322] The server sends the generated, makeup-applied facial image to the user's device. The device includes a user interface for displaying the received image.

[1323] 6. Recommendation methods

[1324] The server recommends appropriate makeup products and brands based on the user's attribute information (gender, age) and counseling information. This information is sent to the user's device, which then displays it.

[1325] 7. Advertising Delivery Methods

[1326] The server generates targeted ads and special offers based on the user's behavior history and attribute information. This advertising information is sent to the user's device, which then displays them.

[1327] Specific example

[1328] 1. The user takes a picture of their face using a webcam and clicks the application's upload button to send the image to the server.

[1329] 2. The device displays a form about the user's makeup preferences and ideal style, and the user enters the necessary information and sends it to the server.

[1330] 3. The server analyzes the facial image and counseling information, and uses a generative AI model to generate a post-makeup facial image.

[1331] 4. The server sends the generated facial image to the user's terminal, and the user checks the image in the application.

[1332] 5. The server recommends appropriate makeup products and brands based on the user's attribute information, and sends that information to the device for display to the user.

[1333] 6. The server generates special offers and targeted advertisements based on the user's behavior history, sends them to the device, and displays them to the user.

[1334] Examples of prompts for generative AI models

[1335] "Please apply the natural makeup look desired by the user to the face image."

[1336] "Please provide the optimal makeup style based on the user's face shape and skin tone."

[1337] "Please suggest lip colors that would be best suited for the user."

[1338] This allows users to easily try out the makeup style that best suits them, and easily select and purchase the appropriate products. This system not only saves users time and money, but also provides an advanced makeup simulation experience.

[1339] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1340] Step 1:

[1341] The user takes a picture of their face using the computer's camera. The input is a real-time facial image, and the output is a digital image temporarily stored on the device. The user starts this process by clicking the "Capture" button in the application. This action captures the facial image on the device.

[1342] Step 2:

[1343] The device displays the facial image taken by the user and prompts the user for confirmation. The user sends the image to the server by clicking the "Upload" button. The input is a temporarily stored facial image, and the output is data sent to the server via the internet. Through this operation, the device uploads the facial image data to the server.

[1344] Step 3:

[1345] The server receives the uploaded facial image. The input is the facial image data sent from the terminal, and the output is the facial image data stored on the server side. Through this process, the server prepares the facial image for image analysis.

[1346] Step 4:

[1347] The terminal displays a form for the user to enter information about their makeup preferences, ideal style, and favorite brands. The user fills in the required information in the form and clicks the "Submit" button. The input is the counseling information entered by the user, and the output is data sent to the server via the internet. Through this action, the terminal sends the counseling information to the server.

[1348] Step 5:

[1349] The server analyzes the received facial images and counseling information. The input is facial image data and counseling information, and the output is the analysis results regarding facial shape and skin tone, and the determination of a makeup style based on these results. Through this operation, the server provides data to the generative AI model and starts the analysis.

[1350] Step 6:

[1351] The server uses a generative AI model to generate a post-makeup face image based on the analysis results. The input is the analysis data, and the output is the generated post-makeup face image. Through this operation, the server creates the generated post-makeup face image.

[1352] Step 7:

[1353] The server sends the generated, made-up face image to the user's device. The input is the generated face image, and the output is the data sent to the device via the internet. Through this operation, the server delivers the face image to the user's device.

[1354] Step 8:

[1355] The terminal displays the received face image after makeup application. The input is face image data sent from the server, and the output is the face image after makeup application displayed to the user. The user can review the results and request adjustments as needed.

[1356] Step 9:

[1357] The server recommends appropriate makeup products and brands based on user attribute information and counseling information. The input is user attribute information and counseling information, and the output is a list of recommended makeup products and brands. Through this process, the server identifies recommended products and generates information about them.

[1358] Step 10:

[1359] The server sends information about recommended makeup products and brands to the user's device. The input is recommendation information, and the output is data sent to the device via the internet. Through this process, the server delivers recommendation information to the user's device.

[1360] Step 11:

[1361] The terminal displays received recommendation information to the user. The input is recommendation information sent from the server, and the output is a product list and brand information displayed to the user. The user can then consider purchasing products based on this information.

[1362] Step 12:

[1363] The server generates targeted ads and special offers based on the user's behavior history and attribute information. The input is the user's behavior history and attribute information, and the output is customized ads and special offers. Through this process, the server generates targeted ads.

[1364] Step 13:

[1365] The server sends the generated targeted ads and special offers to the user's device. The input is the generated ads and special offers, and the output is the data sent to the device via the internet. Through this operation, the server delivers the ads and offers to the user's device.

[1366] Step 14:

[1367] The device displays targeted ads and special offers received by the user. The input is advertising information sent from the server, and the output is the advertising and offer information displayed to the user. The user can then make purchasing decisions based on this information.

[1368] (Application Example 1)

[1369] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1370] Modern consumers have a need to check whether makeup products suit them without actually trying them out. However, current systems make it difficult to try out various makeup styles in real time, and furthermore, there is a lack of coordination between the recommendation of appropriate products and brands and the provision of advertising.

[1371] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1372] In this invention, the server includes image acquisition means, generation means, presentation means, recommendation means, and advertising provision means. This enables users to acquire facial images using a smart device and try out various makeup styles in real time. It also enables product recommendations based on the generated facial images and the provision of customized advertisements based on the user's preferences and behavioral history.

[1373] "Image acquisition means" refers to a device or function that allows a user to acquire their own facial image and transmit it to a server.

[1374] "Generation means" refers to a device or function that generates a post-makeup facial image based on a generative AI model for analyzing facial shape and skin tone.

[1375] "Presentation means" refers to a device or function that displays the generated, post-makeup facial image on the user's device or a store display.

[1376] A "recommendation method" is a device or function that recommends appropriate makeup products or brands based on the generated facial image and the user's counseling content.

[1377] "Advertising delivery means" refers to a device or function that provides customized advertisements or special offers based on the user's attributes and behavioral history.

[1378] This invention relates to a system in which a user acquires an image of their face using a smart device, generates a makeup-applied image of their face using a generative model, and displays it on the terminal. The system includes image acquisition means, generation means, presentation means, recommendation means, and advertising provision means.

[1379] System Program Overview

[1380] 1. Image acquisition method:

[1381] The user uses a smart device (e.g., smartphone, tablet, etc.) to acquire an image of their own face and sends that image to a server. This function utilizes an imaging device used in mobile communication devices (e.g., smartphone camera) and an image capture application (e.g., OpenCV).

[1382] 2. Generation means:

[1383] The server inputs the received facial image into a generative AI model, which analyzes the facial shape and skin tone. The generative model (e.g., GAN, TensorFlow, PyTorch) then generates a makeup-applied facial image based on these analysis results. This generated facial image is processed in real time.

[1384] 3. Means of presentation:

[1385] The generated facial image will be displayed on the user's device (e.g., smartphone, tablet) or on a display installed in the store. Hardware for this will include a web server (e.g., Nginx) and a front-end framework (e.g., React.js).

[1386] 4. Recommendation methods:

[1387] The server recommends appropriate makeup products and brands based on the generated facial image and the user's consultation content. This recommendation process utilizes user attribute analysis and product database matching algorithms (e.g., ElasticSearch).

[1388] 5. Advertising delivery methods:

[1389] The server delivers customized ads and special offers based on the user's attributes and behavioral history. For ad delivery, it utilizes advertising technology platforms (e.g., Google Ads API).

[1390] Explanation of the process

[1391] Upon receiving a user's facial image, the server first performs image analysis to detect skin tone and facial shape. Next, it inputs the image into a generative model to generate a facial image corresponding to the desired makeup style. The generated facial image is then displayed on the user's device or in-store display. Subsequently, based on the analysis data, the server recommends suitable makeup products and brands, and displays further customized advertisements and special offers.

[1392] Specific example

[1393] For example, when a customer enters a store and scans their face with smart glasses installed in the store, the image is immediately sent to a server, and an AI generation model begins analysis. For customers who have entered their preference for natural makeup, the generation model generates an image of their face with a natural makeup style and displays it on the screen. Furthermore, lip colors and eyeshadows that match that style are recommended, and special offers and discount coupons for purchase are also presented.

[1394] Example of a prompt

[1395] Image analysis:

[1396] plain

[1397] Upload a customer's facial image and run it through the AI ​​model to generate a facial image with natural makeup.

[1398] Product Recommendations:

[1399] plain

[1400] Please recommend lip colors and eyeshadows that are suitable for natural makeup, and provide details about the products and any special offers.

[1401] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1402] Step 1:

[1403] The user obtains a facial image using a smart device (e.g., a smartphone). The input is a facial image taken with the device's camera, and this image is temporarily stored on the device. After the user confirms the image, they click the "Upload" button to send the image to the server.

[1404] Step 2:

[1405] The server receives a face image sent by the user and begins image analysis. The analysis uses face recognition technology and skin tone analysis algorithms (e.g., OpenCV, TensorFlow). This detects the shape of the user's face and skin tone. The input is a face image, and the output is face shape data and skin tone data.

[1406] Step 3:

[1407] The server uses a generative AI model (e.g., GAN) to generate a post-makeup face image based on the acquired facial shape and skin tone data. The input to the generative AI model is the analysis results, and the output is the generated post-makeup face image. This generates a real-time face image that matches the user's desired makeup style.

[1408] Step 4:

[1409] The generated facial image is sent from the server to the user's smart device or a store display for display. This display uses a web server (e.g., Nginx) and a frontend framework (e.g., React.js). The input is the generated facial image, and the output is the displayed facial image.

[1410] Step 5:

[1411] The server recommends appropriate makeup products and brands based on the generated facial image and the user's counseling content. This uses user attribute analysis and a matching algorithm for the product database (e.g., ElasticSearch). The input is user attribute data and the generated facial image, and the output is a list of recommended products.

[1412] Step 6:

[1413] The server delivers customized ads and special offers based on user attributes and behavioral history. For ad delivery, it utilizes an advertising technology platform (e.g., Google Ads API). The input is user behavioral history data, and the output is customized ads and special offers.

[1414] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1415] Embodiments of the present invention will be described in detail below. This system acquires a facial image using a smart device, generates a post-makeup facial image using a generative model, and displays it on the terminal. Furthermore, by combining this with an emotion engine that recognizes the user's emotions, a more personalized makeup experience is provided.

[1416] System Overview

[1417] The system includes image acquisition means, generation means, presentation means, emotion engine, and decision-making means. The user uses a smart device (such as a smartphone or tablet) to acquire an image of their face and inputs information necessary for makeup counseling. This data is sent to a server, where a generation model analyzes it, and the system performs emotion recognition using the emotion engine and produces a post-makeup facial image. Based on the analysis results, appropriate information is presented to the user's device.

[1418] Program processing flow

[1419] 1. Image acquisition and upload

[1420] The user takes a picture of their face using the camera on their smart device. The device displays the captured image for confirmation, and when the user clicks the "Upload" button, the image is sent to the server.

[1421] Example: The user opens the app and takes a photo of their face in selfie mode. After taking the photo, they press the upload button, and the image is sent to the server.

[1422] 2. Enter the counseling details.

[1423] The device displays a form for the user to enter details such as their makeup consultation needs, ideal style, and preferred brands. Once the user completes the form and clicks the submit button, the data is sent to the server.

[1424] Example: A user enters "I would like natural makeup" into the form and clicks the submit button.

[1425] 3. Analysis of images and counseling content

[1426] The server analyzes the received facial image and counseling content. Using a generative model, it analyzes the user's facial shape and skin tone, and processes the data to determine the user's ideal makeup style.

[1427] Specific example: The server analyzes a facial image, determines that the user's skin tone is neutral, and then decides on a suitable makeup style.

[1428] 4. Generating realistic makeup-applied facial images

[1429] The server uses a generative model to generate a post-makeup facial image based on the analysis results. The generated facial image reflects the user's counseling content.

[1430] Specific example: The generative model generates a facial image with the user's desired natural makeup applied, allowing it to be compared to the original image.

[1431] 5. Recommendations for makeup products and brands

[1432] The server recommends appropriate makeup products and brands based on the user's attributes (gender, age) and counseling content. This information is sent to the user's device.

[1433] Specific example: The server suggests to the user, "We recommend this lip color," and provides a link to the product's purchase page.

[1434] 6. Emotion recognition by an emotion engine

[1435] The server uses an emotion engine to analyze the user's facial expressions and voice as they input counseling information and view their post-makeup facial image, recognizing their emotions. Based on the recognized emotions, the server adjusts the makeup style and recommended products in real time.

[1436] Specific example: The emotion engine recognizes the smile a user shows when viewing a photo of their face after applying makeup, measures their satisfaction level, and then suggests products in colors that suit them better.

[1437] 7. Presentation of makeup results

[1438] The server sends the generated, made-up face image and feedback from the emotion engine to the user's device. The device displays this to the user, allowing them to see how their face looks with makeup applied.

[1439] Specific example: The server generates a face image after applying makeup, and the results of the emotion engine's analysis (such as satisfaction level) are sent to the user's device for the user to review.

[1440] 8. Utilization of the information provided

[1441] Users review the presented makeup products and brands, and if necessary, access the purchasing site to buy the items.

[1442] Specific example: A user purchases their favorite lip color from an online store.

[1443] Achieving the System's Objectives

[1444] Through these steps, users can not only try out makeup styles that suit them, but the app's emotion engine will also help it understand their preferences more accurately, leading to customized makeup suggestions. This improves the user experience and makes it possible to provide a more satisfying makeup experience.

[1445] The following describes the processing flow.

[1446] Step 1:

[1447] The user activates their smart device and opens the app. The app displays a camera interface and provides instructions to the user for taking a picture of their face.

[1448] Step 2:

[1449] The device activates the smart device's camera and takes a picture of the user's face. After taking the picture, the device provides an interface for the user to review the image and click an "Upload" button if they are satisfied.

[1450] Step 3:

[1451] After the "Upload" button is clicked, the device sends the captured facial image to the server. The image is securely transferred over the internet.

[1452] Step 4:

[1453] The user then accesses a counseling form displayed within the app. The form includes fields for entering details such as makeup consultation topics, desired style, and preferred brands.

[1454] Step 5:

[1455] The device sends the entered data to the server after the user enters information into the counseling form and clicks the "Submit" button.

[1456] Step 6:

[1457] The server receives the uploaded facial image and counseling content and activates the image analysis module. The server uses a generative model to analyze the user's facial shape and skin tone.

[1458] Step 7:

[1459] The server analyzes the counseling content using a text mining tool to extract the user's preferences and desired makeup style. This information is used as data to generate a post-makeup facial image.

[1460] Step 8:

[1461] The server uses a generative model to generate a post-makeup facial image based on facial image analysis and extracted counseling content. The generated image reflects changes in real time.

[1462] Step 9:

[1463] The server sends the generated, makeup-applied facial image to the user's device. The image is then transferred to the user's smart device via the internet.

[1464] Step 10:

[1465] The device displays the user with the received image of their face after applying makeup. The user can see how their face will look with makeup applied.

[1466] Step 11:

[1467] The server recommends suitable makeup products and brands based on the user's attributes and consultation content. This information, along with a link to the purchasing site, is sent to the user's device.

[1468] Step 12:

[1469] The device displays received recommendations to the user and encourages purchases through the provided links. Users can click the links to purchase the recommended products online.

[1470] Step 13:

[1471] The server uses an emotion engine to analyze the user's facial expressions and voice to recognize their emotions. This emotion recognition occurs when counseling information is entered and when viewing a facial image after makeup application.

[1472] Specific example: The emotion engine analyzes the user's facial expressions as they enter information into a counseling form to detect whether the user is satisfied.

[1473] Step 14:

[1474] The server adjusts the makeup styles and recommended products in real time based on the emotion recognition results from the emotion engine. This ensures that suggestions best match the user's emotions.

[1475] Specific example: The emotion engine detects expressions of joy when the user sees a picture of their face after applying makeup, and then suggests more suitable makeup products based on their level of satisfaction.

[1476] Step 15:

[1477] The server generates targeted ads and special offers based on the user's browsing history and sends them to the user's device. This ensures that the user sees ads that are likely to be of interest to them.

[1478] Step 16:

[1479] The device displays targeted advertisements and special offers received by the user. The user can view these and take appropriate action as needed.

[1480] The above series of steps provides a convenient process for users to easily try out makeup styles that suit them and select the optimal products. Furthermore, the introduction of an emotion engine provides a more personalized experience that reflects the user's emotions.

[1481] (Example 2)

[1482] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1483] Traditional makeup systems presented a significant challenge: users had to expend considerable time and effort trying to find the makeup style that best suited them. Furthermore, the limited information available to users made it difficult for many to find a truly suitable style. Additionally, the lack of personalized suggestions that considered user emotions hindered user satisfaction.

[1484] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1485] In this invention, the server includes an image acquisition means, a generation means, a presentation means, an emotion recognition means, and a decision-making means. This allows the user to easily acquire an image of their face, have the image analyzed using an AI model, and receive customized makeup suggestions based on the user's emotions.

[1486] "Image acquisition means" refers to a means by which a user acquires an image of their own face using the camera on a mobile information terminal.

[1487] The "generation method" refers to a means of generating a post-makeup facial image based on a generative AI model for analyzing facial shape and skin tone.

[1488] "Presentation means" refers to the means by which the terminal displays the generated post-makeup facial image and related information to the user.

[1489] "Emotion recognition means" refers to a method of recognizing a user's emotions by using an emotion engine to analyze their facial expressions and voice when they input counseling information and when they review images of their face after applying makeup.

[1490] "Decision-making means" refers to the means of determining the makeup style to offer and the recommended products based on image analysis and emotion recognition results.

[1491] A "portable information device" refers to an information processing device that a user can carry with them, and examples include smartphones and tablets.

[1492] A "photography device" is a camera built into a mobile information terminal that has the function of allowing the user to take an image of their own face.

[1493] A "generative AI model" is an algorithm that uses artificial intelligence to analyze facial images and generate a post-makeup image of the face based on the user's preferences.

[1494] An "emotion engine" is a software component that analyzes a user's facial expressions and voice to recognize their emotions.

[1495] "Makeup style" refers to the design and method of makeup desired by the user, and includes the specific details of the makeup applied to each part of the face.

[1496] "Recommended products" are cosmetics and related products that are deemed appropriate based on the user's attributes and emotional recognition results.

[1497] Embodiments of the present invention will be described in detail below. This system acquires a facial image using a mobile device, generates a post-makeup facial image using a generation AI model, and displays it on the device. Furthermore, by combining it with emotion recognition means, a more personalized makeup experience is provided.

[1498] The system includes image acquisition, generation, and presentation means, emotion recognition means, and decision-making means. The user uses a mobile device (such as a smartphone or tablet) to acquire an image of their face and input information necessary for counseling. This data is transmitted to a server, where a generation AI model analyzes it, and the system performs emotion recognition using the emotion recognition means and analyzes the resulting image of the face after makeup application. Based on the analysis results, appropriate information is presented to the user's device.

[1499] First, the user takes a facial image using the camera on their mobile device. When the user presses the capture button, the image is displayed on the device. The user then reviews the image and clicks the "upload" button, which sends the image to the server. Next, the device displays a makeup consultation form to the user. The user enters their ideal makeup style, brands, concerns, etc., and once completed, clicks the submit button to send this information to the server.

[1500] The server analyzes the received facial image and counseling content. Specifically, it uses image analysis software to identify the facial shape and skin tone, and inputs the results into a generating AI model. The generating AI model then generates a post-makeup facial image based on the user's preferences. The generated facial image is customized to reflect the user's counseling content.

[1501] Next, the server recommends appropriate makeup products and brands based on the user's attributes (gender, age) and counseling content. This information is sent to the user's device and presented to them. Furthermore, the server uses emotion recognition to analyze the user's facial expressions and voice when they input counseling information and view images of their face after applying makeup, recognizing the user's emotions. Based on the recognized emotions, the server adjusts the makeup style and recommended products in real time.

[1502] Finally, the generated post-makeup facial image and emotion recognition information are sent to the user's device for review. The user can then review the suggested makeup products and brands, and even access the purchasing site to buy them. This entire process allows users to easily experiment with different makeup styles and, through emotion recognition, receive customized suggestions, resulting in a more satisfying makeup experience.

[1503] For example, if a user wants "natural makeup" and wants to use products from a specific brand, they would enter the following:

[1504] Example: I want natural makeup. Please suggest a lip color that suits me.

[1505] This system allows users to see how their face is being made up in real time and receive more personalized suggestions through emotion recognition. This improves user satisfaction and provides a higher level of makeup experience.

[1506] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1507] Step 1:

[1508] The user launches the camera app on their mobile device and takes an image of their face. When the user presses the capture button, the image is displayed on the device. After the user confirms and clicks the "Upload" button, the device sends the image to the server.

[1509] Specific operation: The user opens the camera app and takes a selfie of their face. After taking the picture, the image is displayed on the screen. When the user presses the upload button, the image is sent to the server.

[1510] Input: A captured image of a face.

[1511] Processing: The terminal displays the user's facial image for verification and sends it to the server.

[1512] Output: Face image uploaded to the server.

[1513] Step 2:

[1514] The device displays a makeup consultation form to the user. The user enters their ideal makeup style, preferred brands, and makeup concerns. Once the user has finished entering the information and clicks the submit button, the information is sent to the server.

[1515] Specific operation: The user enters a request such as "I want natural makeup" into a form within the app and selects their preferred brand. Once the input is complete, they click the submit button.

[1516] Input: User counseling information (makeup style, brand, concerns).

[1517] Processing: The terminal receives user input and sends it to the server.

[1518] Output: Counseling information sent to the server.

[1519] Step 3:

[1520] The server analyzes the received facial image and counseling content. First, it uses image analysis software to identify the user's facial shape, skin tone, and facial features. Then, it uses a generative AI model to generate a post-makeup facial image based on the user's preferences.

[1521] Specific operation: Image analysis software identifies the shape of the face and skin tone, and inputs this information into a generating AI model. The generating AI model then generates a post-makeup facial image based on the counseling information.

[1522] Input: User's facial image, counseling information.

[1523] Processing: Face image generation using image analysis and generative AI models.

[1524] Output: The generated image of the face after applying makeup.

[1525] Step 4:

[1526] The server recommends appropriate makeup products and brands based on the user's attributes (gender, age) and counseling content. This information is then sent to the user's device.

[1527] Specific operation: The server analyzes the user's attributes and counseling information, selects appropriate makeup products and brands, and generates recommendation information. The generated information is then sent to the user's device.

[1528] Input: User attributes, counseling information.

[1529] Processing: Selection of makeup products and brands, and generation of recommendation information.

[1530] Output: Recommendation information sent to the user's device.

[1531] Step 5:

[1532] The server uses emotion recognition to analyze the user's facial expressions and voice as they input counseling information and view images of their face after makeup application, thereby recognizing the user's emotions. Based on the recognized emotions, the server adjusts the makeup style and recommended products in real time.

[1533] Specific operation: Emotion recognition means analyze facial expressions and voice to identify the user's emotions. Based on the results, the makeup style and recommended products are adjusted.

[1534] Input: User's facial expressions and voice data.

[1535] Processing: Emotion recognition and real-time adjustment.

[1536] Output: Adjusted makeup styles and recommended products.

[1537] Step 6:

[1538] The server sends the generated post-makeup facial image and emotion recognition results to the user's device. The device displays this to the user, allowing them to see how their face will look after the make-up.

[1539] Specific operation: The server sends the generated image of the face after applying makeup and the emotion recognition results, and the terminal displays them. The user confirms the displayed information.

[1540] Input: Generated facial image, emotion recognition result.

[1541] Processing: Data transmission from server to terminal, and display on terminal.

[1542] Output: The post-makeup facial image and emotion recognition results displayed on the user's device.

[1543] Step 7:

[1544] Users review the presented makeup products and brands, and if necessary, access the purchasing site to buy the items.

[1545] Specific actions: The user clicks on a link to a presented lip color or other product, accesses the online store, and completes the purchase process.

[1546] Input: Recommended makeup products and brand information.

[1547] Process: The user checks the product and accesses the online store.

[1548] Output: Purchased makeup products.

[1549] (Application Example 2)

[1550] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1551] In modern brick-and-mortar stores, providing personalized makeup experiences tailored to customers' emotions and preferences is challenging. Furthermore, limited means of visualizing the results beforehand make improving customer satisfaction difficult. Additionally, there's a lack of systems that allow customers to easily select the most suitable makeup products and brands on the spot.

[1552] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1553] In this invention, the server includes an image acquisition means, a generation means, a presentation means, an emotion recognition means, a real-time processing means, and a decision-making means. This enables personalized makeup suggestions and product recommendations through the acquisition of a user's facial image, generation of a post-makeup facial image, emotion recognition, and real-time analysis.

[1554] "Image acquisition means" refers to a means for a user to acquire an image of their own face using the camera of a smart device.

[1555] The "generation method" is a means of generating a post-makeup facial image based on a generative model for analyzing facial shape and skin tone.

[1556] "Presentation means" refers to a means of visually displaying the generated post-makeup facial image and analysis results to the user.

[1557] "Emotion recognition means" refers to a means of recognizing the user's emotions and adjusting makeup suggestions based on the results of that recognition.

[1558] The "real-time processing method" is a means of analyzing the user's satisfaction level and reaction in real time when they check their face image after applying makeup, and providing the optimal makeup style.

[1559] "Decision-making means" refers to methods for recommending the most suitable makeup products and brands to a user based on data from emotion recognition means and real-time processing means.

[1560] A "server" is a computer system used to process image data and analysis results, and to execute generative models and emotion recognition algorithms.

[1561] Embodiments of the present invention will be described in detail below.

[1562] System Configuration

[1563] This system includes the following means: image acquisition means, generation means, presentation means, emotion recognition means, real-time processing means, and decision-making means. The entire system consists of the user's smart device and a server that processes the data.

[1564] Image acquisition method

[1565] The user takes a picture of their face using the camera on a smart device (e.g., a smartphone). This image is acquired by the "image acquisition means" and sent to the server.

[1566] generation means

[1567] The server applies a generative AI model to the received facial image to analyze its shape and skin tone. Based on the analysis results, it generates a post-makeup facial image that reflects the user's desired makeup style. Machine learning frameworks such as TensorFlow and Keras are used for this generation process.

[1568] Presentation means

[1569] The generated image of the face after applying makeup is displayed on the user's smart device via a presentation mechanism. This allows the user to see the results of the makeup in real time.

[1570] emotion recognition means

[1571] The server uses emotion recognition engines such as DeepFace to analyze the user's emotions when they view their face image after applying makeup. This makes it possible to suggest makeup looks that match the user's satisfaction level and preferences.

[1572] Real-time processing means

[1573] The server analyzes the user's facial expressions and reactions in real time as they view their post-makeup facial image. Image processing libraries such as OpenCV are used for this process. The analysis results are immediately fed back and reflected in the generative model.

[1574] decision making means

[1575] Based on data obtained from emotion recognition and real-time processing systems, the server makes decisions. Specifically, it recommends the most suitable makeup products and brands to the user and provides that information to the user through a presentation system.

[1576] Explanation of specific examples

[1577] For example, a user takes a photo of their face using a smart device installed in a physical store. The image is sent to a server, where a generative model analyzes it. A new image of the user's face with natural makeup applied is then generated and displayed on the user's smart device. Furthermore, the user's facial expressions are analyzed, and if they are highly satisfied, specific makeup products or brands are recommended.

[1578] Example of a prompt

[1579] "Enter the user's face image and generate a post-makeup image. If the user's emotion is 'happy,' apply a natural makeup style."

[1580] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1581] Step 1:

[1582] The user uses the camera on their smart device to capture an image of their face.

[1583] Input: Face image taken from the user's smart device

[1584] Output: Acquired facial image

[1585] Specific operation: The user launches the smartphone's camera app and takes a selfie of their face. The captured image is then saved to the device.

[1586] Step 2:

[1587] The acquired facial images are uploaded to the server.

[1588] Input: Face image saved on the device

[1589] Output: Face image transferred to the server

[1590] Specific operation: When the user clicks the "Upload" button within the application, the device sends the acquired facial image to the server.

[1591] Step 3:

[1592] The server receives the transmitted facial image and uses a generating AI model to analyze the facial shape and skin tone.

[1593] Input: Face image sent to the server

[1594] Output: Analysis results (face shape, skin tone)

[1595] Specific operation: The server receives a facial image, runs a generative AI model using TensorFlow or Keras, and extracts and analyzes the facial shape and skin tone.

[1596] Step 4:

[1597] The generation method generates a post-makeup facial image based on the analysis results.

[1598] Input: Analysis results of facial shape and skin tone

[1599] Output: Face image after makeup application

[1600] Specific operation: The server uses the analysis results to generate a facial image after applying the user's desired makeup style.

[1601] Step 5:

[1602] The generated, post-makeup facial image is displayed to the user using a presentation device.

[1603] Input: Face image after makeup

[1604] Output: Face image after makeup application displayed on the user's terminal

[1605] Specific operation: The server sends the generated facial image to the user's smart device, and that image is displayed within the application.

[1606] Step 6:

[1607] Using emotion recognition technology, the system recognizes the emotions a user experiences when reviewing their face image after applying makeup.

[1608] Input: User's facial expression data

[1609] Output: User sentiment analysis results

[1610] Specific operation: The user's facial expressions when viewing the generated makeup-applied face image are captured by the smart device's camera, and emotions are analyzed using an emotion recognition engine such as DeepFace.

[1611] Step 7:

[1612] Real-time processing capabilities allow for real-time analysis of user satisfaction and reactions.

[1613] Input: User reaction data and sentiment analysis results

[1614] Output: Reaction analysis results

[1615] Specific operation: Capture and analyze in real time the user's satisfaction level and reactions to a presented image of their face after applying makeup.

[1616] Step 8:

[1617] Based on data from emotion recognition and real-time processing methods, the system uses decision-making mechanisms to recommend the most suitable makeup products and brands to the user.

[1618] Input: Emotion recognition results, reaction analysis results

[1619] Output: Recommended makeup products and brand information

[1620] Specific operation: Based on the emotion recognition results and reaction analysis results, the server determines the most suitable makeup products and brands for the user, and sends that information to the user's terminal for display.

[1621] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1622] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1623] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1624] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1625] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1626] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1627] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1628] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1629] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1630] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1631] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1632] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1633] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1634] 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.

[1635] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1636] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1637] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1638] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1639] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1640] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1641] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1642] The following is further disclosed regarding the embodiments described above.

[1643] (Claim 1)

[1644] Image acquisition method,

[1645] means of generation,

[1646] means of presentation,

[1647] A system that includes this.

[1648] (Claim 2)

[1649] The system according to claim 1, wherein the image acquisition means is a means for a user to acquire an image of their own face with the camera of a smart device, and the means is a means for processing the face image acquired by the image acquisition means.

[1650] (Claim 3)

[1651] The system according to claim 1, wherein the generation means is a means for generating a post-makeup face image based on a generation model for analyzing the shape of the face and the skin tone.

[1652] (Claim 4)

[1653] The system according to claim 1, wherein the presentation means is a means for displaying the post-makeup face image generated by the generation means on the user's smart device, and is a means for providing information related to the makeup.

[1654] (Claim 5)

[1655] Furthermore, the system according to claim 1 is characterized by including a decision-making mechanism for recommending makeup products and brands based on the user's attributes and counseling content.

[1656] (Claim 6)

[1657] The system according to claim 5, wherein the decision-making means is a means for generating a recommended list of makeup products based on the user's attributes and providing a link to a purchasing site, and also includes means for tracking the user's behavior.

[1658] (Claim 7)

[1659] Furthermore, the system according to claim 1 is characterized by comprising means for providing targeted advertising and special offers, and means for improving the marketing strategy by analyzing the user's behavioral data.

[1660] "Example 1"

[1661] (Claim 1)

[1662] Image acquisition method,

[1663] means of generation,

[1664] means of presentation,

[1665] Data transmission means,

[1666] Analytical methods,

[1667] Recommendation methods,

[1668] means of providing advertising,

[1669] A system that includes this.

[1670] (Claim 2)

[1671] The system according to claim 1, wherein the image acquisition means is a means for a user to acquire an image of their own face with a computer camera, and the face image acquired by the image acquisition means is transmitted to a server by a data transmission means.

[1672] (Claim 3)

[1673] The system according to claim 1, wherein the generation means is a means for generating a post-makeup face image based on a generation AI model for analyzing the shape of the face and the skin tone.

[1674] "Application Example 1"

[1675] (Claim 1)

[1676] Image acquisition method,

[1677] means of generation,

[1678] means of presentation,

[1679] Recommendation methods,

[1680] means of providing advertising,

[1681] A system that includes this.

[1682] (Claim 2)

[1683] The system according to claim 1, wherein the image acquisition means is a means by which a user acquires an image of their own face using the imaging device of a mobile communication device, and the means is a means for processing the face image acquired by the image acquisition means.

[1684] (Claim 3)

[1685] The system according to claim 1, wherein the generation means is a means for generating a post-makeup face image based on a generation AI model for analyzing the shape of the face and the skin tone.

[1686] "Example 2 of combining an emotion engine"

[1687] (Claim 1)

[1688] Image acquisition method,

[1689] means of generation,

[1690] means of presentation,

[1691] Means of recognizing emotions,

[1692] Decision-making tools,

[1693] A system that includes this.

[1694] (Claim 2)

[1695] The system according to claim 1, wherein the image acquisition means is a means for a user to acquire an image of their own face using the camera of a mobile information terminal, and the means is for processing the face image acquired by the image acquisition means.

[1696] (Claim 3)

[1697] The system according to claim 1, wherein the generation means is a means for generating a post-makeup facial image based on a generation AI model for analyzing the shape of the face and the skin tone.

[1698] "Application example 2 when combining with an emotional engine"

[1699] (Claim 1)

[1700] Image acquisition method,

[1701] means of generation,

[1702] means of presentation,

[1703] Means of recognizing emotions,

[1704] Real-time processing means,

[1705] Decision-making tools,

[1706] A system that includes this.

[1707] (Claim 2)

[1708] The system according to claim 1, wherein the image acquisition means is a means for a user to acquire an image of their own face with the camera of a smart device, and the means is a means for processing the face image acquired by the image acquisition means.

[1709] (Claim 3)

[1710] The system according to claim 1, wherein the generation means is a means for generating a post-makeup face image based on a generation model for analyzing the shape of the face and the skin tone.

[1711] (Claim 4)

[1712] The system according to claim 1, wherein the emotion recognition means is a means for recognizing the user's emotions and adjusting the makeup suggestion based on the recognition result.

[1713] (Claim 5)

[1714] The system according to claim 1, wherein the real-time processing means analyzes the user's satisfaction level and reaction in real time when they check the face image after applying makeup, and provides the optimal makeup style.

[1715] (Claim 6)

[1716] The system according to claim 1, wherein the decision-making means is a means for recommending the most suitable makeup products and brands to the user based on data from the emotion recognition means and the real-time processing means. [Explanation of symbols]

[1717] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means by which a user acquires an image of their own face using the camera of a smart device, and an image acquisition means for processing the acquired face image, A generation means for generating a post-makeup facial image based on a generative model for analyzing facial shape and skin tone, A means for displaying the face image after makeup application, generated by the generation means, on the user's smart device, and a presentation means for providing information related to the makeup, A system that includes this.

2. Furthermore, the system according to claim 1 is characterized by including a decision-making means for recommending makeup products and brands based on the user's attributes and counseling content.

3. The system according to claim 2, wherein the decision-making means is a means for generating a recommended list of makeup products based on the user's attributes and providing a link to a purchasing site, and also includes means for tracking the user's behavior.

4. Furthermore, the system according to claim 1 is characterized by comprising means for providing targeted advertising and special offers, and means for improving the marketing strategy by analyzing the user's behavioral data.

Images