system

Abstract

We provide the system. [Solution] A means of inputting personal skin information, Means for receiving and storing the aforementioned skin information, A means of using a generative model that estimates the optimal cosmetic ingredients based on the stored skin information, A means for generating a chemical structural formula based on the estimated components and designing a formulation, A means for displaying the aforementioned formulated cosmetics as a virtual try-on, A means for the user to confirm the results of the virtual try-on, 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 the modern cosmetics market, there is a problem that it is difficult to provide personalized cosmetics that completely meet individual skin types and specific needs. Many conventional cosmetics are products tailored to general skin types and may not be able to appropriately address the special skin problems and allergic reactions of individual users. Therefore, it is difficult for users to choose cosmetics that suit them, resulting in a decrease in satisfaction and an increase in skin problems.

Means for Solving the Problems

[0005] This invention solves this problem by estimating the optimal cosmetic ingredients based on an individual's skin information, generating chemical structural formulas using those ingredients, and designing formulations. Specifically, it receives and stores skin information input by the individual, and uses a generative model to estimate the optimal cosmetic ingredients from that information. Subsequently, it generates chemical structural formulas based on the estimated ingredients and designs an optimal cosmetic formulation for the user. Furthermore, this formulation is presented to the user as a virtual try-on, allowing them to check the feel of using the product in a virtual environment beforehand. This enables users to select cosmetics that are suitable for their skin, reducing the risk of skin problems. In addition, by updating the generative model based on user feedback, it becomes possible to propose cosmetics that are even more suited to individual needs.

[0006] "Personal skin information" refers to data that indicates the user's own skin condition and characteristics, and specifically includes skin type, age, allergy information, etc.

[0007] A "generative model" is an algorithm or program for estimating or generating new information based on data, and in this invention, it plays a role in estimating the optimal cosmetic ingredients.

[0008] A "chemical structural formula" is a set of symbols used to indicate the structure and composition of a chemical substance, and in this invention, it is a method of representation for concretizing estimated cosmetic ingredients.

[0009] "Formulation design" is the process of determining the specific composition and formulation of a cosmetic product based on estimated ingredients.

[0010] "Virtual try-on" is a method that allows users to check the effects of cosmetics in a virtual environment before actually using them, providing them with a simulation of how the cosmetics will look.

[0011] "User feedback" refers to users' impressions and opinions regarding the use of a product, and is data used for future product improvements and updates to generative models. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This 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] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0018] 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).

[0019] 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."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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".

[0033] This invention is a system for providing personalized cosmetics based on individual users' skin information, and at its core is a generative AI model. The generative AI model estimates the optimal cosmetic ingredients based on detailed skin information provided by the user, such as skin type, age, and allergy information.

[0034] First, users enter their skin information using a dedicated app or web interface. This information may include skin type, age, allergy information, past cosmetic usage history, and personal preferences. After entry, this information is sent from the device to the server.

[0035] The server organizes and stores the received information in a database, and then inputs its contents into a generative AI model. This generative AI model is built on a large amount of cosmetic and medical data and is used to estimate the optimal combination of ingredients. Based on the estimated ingredients, the AI ​​model generates chemical structural formulas and designs specific formulations.

[0036] Next, the server provides a function that allows users to virtually try on the designed cosmetics in a virtual environment. This function allows users to virtually check the feel of the product using a 3D model before physically handling it. The results of this virtual try-on are displayed to the user via their terminal.

[0037] Furthermore, users can provide feedback to the system, including their impressions of using the product and suggestions for improvement. This feedback is collected by the server and used to continuously improve the generated AI model and propose new products. In this way, by incorporating user opinions, it becomes possible to provide cosmetics that are more tailored to individual needs.

[0038] For example, if a woman in her 30s has dry skin and specific allergies, the AI ​​model generates a formula based on the information she inputs, estimating appropriate ingredients and creating a cosmetic product that addresses both her dry skin and allergies. By virtually trying on this cosmetic product, she can check its effects and feel before actually trying the product.

[0039] Thus, the present invention provides a platform that allows users to utilize cosmetics optimized based on their own skin information, thereby realizing a more satisfying experience.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] Users log in to a dedicated app or web interface and enter skin information such as their skin type, age, allergy information, and past cosmetic usage history. They can also enter specific concerns and beauty goals.

[0043] Step 2:

[0044] The terminal organizes the entered data, securely encrypts it, and then sends it to the server. The transmitted data is linked to the user's unique ID.

[0045] Step 3:

[0046] The server saves the received data to a database. It then prepares the saved data for input into a generating AI model for analysis.

[0047] Step 4:

[0048] The server uses a generative AI model to estimate the optimal cosmetic ingredients based on the user's skin information. This estimation utilizes past research data and information on the ingredients of commercially available cosmetics.

[0049] Step 5:

[0050] The server generates chemical structures based on estimated ingredients and designs personalized cosmetic formulations. This design is tailored to the user's unique needs.

[0051] Step 6:

[0052] The server generates a 3D model using the user's facial photograph to prepare a virtual try-on function for the designed cosmetics. Image processing technology is used to accurately capture the user's facial features.

[0053] Step 7:

[0054] The device applies the designed cosmetics to the generated 3D model and displays a virtual trial screen to the user. The user can visually check the appearance and feel of the cosmetics on the screen.

[0055] Step 8:

[0056] Users evaluate the product's suitability through a virtual trial. After the evaluation, they can decide whether to purchase the product and proceed with the purchase process.

[0057] Step 9:

[0058] The server collects user feedback and impressions and records them in a database. This feedback is used to improve the generative AI model and design future formulations.

[0059] (Example 1)

[0060] 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."

[0061] Providing optimal consumer products based on each user's individual biometric information is difficult and requires considerable time and expertise. Therefore, personalized product selection tailored to diverse needs is challenging, leading to user dissatisfaction. Furthermore, the lack of sufficient virtual trial environments means users cannot fully experience the effects of a product before trying it.

[0062] 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.

[0063] In this invention, the server includes means for receiving and recording the biometric information of individual users, means for using a generative model to estimate the optimal consumer product components based on the recorded biometric information, and means for displaying the designed consumer product as a virtual trial. This enables optimal product selection based on the user's individual needs and allows for a pre-trial experience through virtual trials.

[0064] "Individual users" refers to selected users who provide biometric information.

[0065] "Biometric information" refers to all information related to the body that is necessary for selecting consumer products, such as the skin texture, age, and allergy information of individual users.

[0066] A "generative model" refers to an automated computational method for estimating the optimal consumer product ingredients based on input data and selecting products accordingly.

[0067] "Chemical composition" refers to design information based on the molecular-level structure of the estimated components.

[0068] "Virtual trial" refers to a feature that allows users to check the usability of a designed consumer product using computer graphics or simulations, without physically trying it out.

[0069] "User feedback" refers to the collective term for feedback provided by users, including evaluations and opinions after virtual trials or product use.

[0070] "Infrastructure" refers to the electronic network and software environment for sharing information and results among users.

[0071] This invention is a system for providing optimal consumer products based on the biometric information of individual users. Embodiments thereof are shown below.

[0072] Users input their biometric information using a dedicated app or web interface. Specifically, this biometric information includes skin texture, age, and allergy information. In addition, personal preferences and past consumer product usage history can also be entered. An example of prompt text input would be: "Female, 30s, dry skin, allergies, preferred highly moisturizing creams in the past."

[0073] The terminal sends the entered biometric information to the server as a data packet. The server receives the biometric information, organizes it, and stores it in a database. A database management system is used in this process.

[0074] The server analyzes the stored information and inputs it into a generative AI model. This generative AI model is designed based on a large amount of medical and cosmetic data and estimates the optimal product ingredients from the received information. This AI model utilizes machine learning frameworks and natural language processing techniques.

[0075] Furthermore, the generation AI model generates the estimated chemical composition of the ingredients and designs a specific product formulation. To allow users to preview the feel of the designed product beforehand, the server provides a virtual trial environment. This virtual trial environment is built using 3D modeling software, allowing users to visually and interactively experience using the product.

[0076] Finally, after experiencing the virtual trial, users provide feedback on their experience and areas for improvement to the server via the app or web interface. The server records this feedback in a database, which helps in the continuous improvement of the generative AI model. This allows the generative AI model to learn from the new feedback, enabling more accurate component estimation.

[0077] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0078] Step 1:

[0079] Users enter their biometric information via a dedicated app or web interface. Input fields include skin texture, age, and allergy information, and optionally, past product usage history and preferences. This input is stored on the device in digital format and prepared for transmission.

[0080] Step 2:

[0081] The terminal packets the entered biometric information and sends it to the server via a secure communication protocol. The input data is transmitted as biometric information and received by the server as individual data entries. This creates a foundation for efficient data processing.

[0082] Step 3:

[0083] The server analyzes biometric information received from the terminal, classifies the information into the necessary categories, and stores it in the database. The entered biometric information is divided into fields, each tagged, and stored. The database management system supports this process, maintaining data reliability.

[0084] Step 4:

[0085] The server sends organized biometric information to a generating AI model. The AI ​​model analyzes the input using prompts and estimates the optimal product ingredients. This process utilizes data science techniques to structure the input data and generate meaningful output. The output is provided as a list of estimated ingredients.

[0086] Step 5:

[0087] Based on the estimated components obtained from the generating AI model, the server generates the chemical composition and designs the product. The AI ​​system considers the chemical properties of the estimated components and designs the optimal formulation. Specific product formulation information is obtained as output.

[0088] Step 6:

[0089] The server sends the designed product to a virtual trial environment, providing the user with a virtual trial experience. Here, 3D modeling software is used, allowing the user to visually confirm the product's usability. The output of the virtual trial is a 3D display rendered on the user's terminal.

[0090] Step 7:

[0091] After the virtual trial, users submit feedback on their experience and areas for improvement. This feedback is sent to the server in text format and stored in a database. This feedback is used as a dataset for improving the generative AI model, contributing to improved component estimation.

[0092] (Application Example 1)

[0093] 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."

[0094] In modern society, selecting cosmetics that take into account diverse skin types and individual allergies is a complex task for consumers. Many users lack the information to understand which cosmetics are best suited to their skin condition, making it difficult to choose cosmetics for daily use. There is a need for a system that solves this problem and efficiently suggests personalized and optimal cosmetics to individual users.

[0095] 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.

[0096] In this invention, the server includes means for inputting an individual's skin information, means for receiving and storing the skin information, and means for using a generative model that estimates the optimal cosmetic ingredients based on the stored skin information. This makes it possible to estimate the optimal cosmetic ingredients based on the individual user's skin information. In addition, users can check the feel of the suggested cosmetics in advance through virtual try-on, enabling them to make purchases based on clear judgments.

[0097] "Personal skin information" refers to individual data necessary for selecting cosmetics, such as the user's skin type, age, and allergy information.

[0098] A "generative model" is an artificial intelligence-based algorithm used to estimate appropriate cosmetic ingredients from received data.

[0099] "Methods for generating chemical structural formulas and designing formulations" refers to the process of determining the specific chemical composition based on estimated components and designing the optimal cosmetic product.

[0100] "A means of displaying as a virtual try-on" refers to a technology that allows users to view a visual image of suggested cosmetics on a digital device.

[0101] "A means of displaying and allowing users to confirm in real time" refers to a function that immediately presents the results of cosmetic selection to the user via a terminal, allowing them to check the feel and appearance of the product.

[0102] "Image processing means" refers to technology that uses devices such as smartphones and smart glasses to capture skin information in a real-world environment and analyze it as data.

[0103] The system implementing this invention enables personalized product selection by suggesting the most suitable cosmetics for each individual user and allowing them to confirm the feel of the product through virtual try-on. First, the user captures real-time images of their skin using a smartphone or smart glasses. This information is analyzed using image processing libraries such as OpenCV and TENSORFLOW® to extract characteristic skin information.

[0104] Data sent from the terminal to the server is stored and analyzed in the cloud. This data processing uses generative AI models (e.g., PyTorch and TensorFlow) to suggest optimal cosmetic ingredients based on the input data. These generative AI models utilize a large-scale cosmetics database and medical data to design individual products tailored to each user's characteristics.

[0105] The server further provides virtual try-on services through 3D models generated using Unity or Unreal Engine. Users can virtually try on suggested cosmetics in a virtual environment via their devices and check the visual effects of the products. This system also collects usage feedback, which is used for the continuous improvement of the AI ​​model.

[0106] As a concrete example of its use, a female user in her 30s could use her smartphone to scan her face, and the generating AI model could suggest a specialized moisturizing cream that is optimal for dry skin and also addresses allergies. An example of the prompt text for the generating AI model in this case would be, "Female, 30s, dry skin, glycerin allergy. Please suggest the optimal moisturizing cream ingredients." The user can virtually try on the suggested cream and check its effects beforehand, enabling a more confident purchase decision.

[0107] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0108] Step 1:

[0109] The user takes a picture of their skin using a smartphone or smart glasses. The input here is a real-time image of the skin, acquired using the device's camera. The output is analyzable skin image data.

[0110] Step 2:

[0111] The device analyzes the acquired skin image data using image processing libraries such as OpenCV and TensorFlow. In this step, skin characteristics are extracted and digital signal processing is performed. The input is skin image data, and the output is characteristic information, such as skin texture and color information.

[0112] Step 3:

[0113] Skin characteristic information is transmitted from the terminal to the server. The server receives this information and stores it in a database. The input is skin characteristic information, and the output is database update information.

[0114] Step 4:

[0115] The server inputs the stored skin characteristic information into a generating AI model. The generating AI model utilizes a large amount of cosmetic data to estimate the optimal cosmetic ingredients for the user. The input consists of skin characteristic information and prompts for the AI ​​model, and the output is the estimated cosmetic ingredients.

[0116] Step 5:

[0117] The server generates chemical structural formulas based on estimated cosmetic ingredients and constructs 3D virtual models using Unity or Unreal Engine. The input is cosmetic ingredients, and the output is a 3D virtual try-on model.

[0118] Step 6:

[0119] The server sends the generated 3D virtual fitting model to the terminal. The user views this model through the terminal and performs a virtual try-on. The input is the 3D virtual fitting model, and the output is the user's fitting feedback.

[0120] Step 7:

[0121] The user enters feedback and sends it to the server. The server collects this feedback and uses it to improve the generated AI model. The input is user feedback after trying on the product, and the output is information for improving the AI ​​model.

[0122] 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.

[0123] This invention further enhances personalized cosmetic recommendations through a system incorporating an emotion engine that recognizes user emotions. This system, in addition to estimating optimal cosmetic ingredients based on the user's skin information, also considers the user's emotions, enabling more personalized cosmetic recommendations.

[0124] First, users input their skin information through an app or web interface, and also provide facial photos and videos, enabling emotion analysis. This data is securely transmitted from the device to the server.

[0125] The server inputs the received skin information into a generating AI model to estimate the optimal cosmetic ingredients. This process utilizes past training data and a market database of cosmetics. The estimated ingredients are then materialized as chemical structural formulas, and individual formulations are designed.

[0126] Furthermore, the server uses an emotion engine to analyze the user's emotional state from the submitted facial photos and video data. The emotional state is evaluated by detecting changes in facial expressions such as smiles and surprise. This evaluation serves as a criterion for determining how satisfied the user is during the virtual try-on.

[0127] The virtual try-on function applies a server-generated simulation of cosmetics to the user's 3D model and presents it to the user on their device. Based on this try-on result, the user decides whether to purchase the product or if further adjustments are needed.

[0128] The device notifies the user of the emotion engine's analysis results in real time and adjusts suggestions based on satisfaction levels. For example, if the user's reaction to the try-on results is positive, the product is recommended as is; however, if the reaction is negative, an alternative solution is presented. This adjustment is also used when updating the generative model based on user feedback data and emotion data.

[0129] For example, if a user enters information about having dry skin and expresses surprise at the fitting results, the server will re-suggest a formula containing more moisturizing ingredients. This optimizes the user experience based on their emotions.

[0130] Thus, the present invention provides a system that enables cosmetic product recommendations that take user emotions into consideration, thereby further enhancing the provision of personalized cosmetics.

[0131] The following describes the processing flow.

[0132] Step 1:

[0133] Users input information about their skin, such as skin type, age, and allergy information, using a dedicated app or web interface. They also provide facial photos and videos for the fitting experience, uploading data necessary for emotional analysis.

[0134] Step 2:

[0135] The terminal encrypts the entered data and sends it to the server according to security protocols. The transmitted data is securely stored in a database based on the user ID.

[0136] Step 3:

[0137] The server supplies the received data to a generating AI model, which estimates the optimal cosmetic ingredients for the user's skin characteristics. The AI ​​model uses a historical cosmetic database and learned patterns to generate a list of ingredients.

[0138] Step 4:

[0139] The server uses the estimated ingredient information to generate chemical structures. These chemical structures form the basis for the formulation design of individual, personalized cosmetics.

[0140] Step 5:

[0141] The server uses an emotion engine to analyze emotional data extracted from the user's facial photos and videos. The emotion engine detects microexpressions and other features to evaluate the user's emotional state.

[0142] Step 6:

[0143] The server applies the generated cosmetic formulation onto a 3D model for virtual try-on and calculates the results along with the user's emotional evaluation.

[0144] Step 7:

[0145] The device displays real-time evaluation results from an emotion engine, along with a 3D model of the cosmetics being tried on. Users can then review this and understand their emotional satisfaction level.

[0146] Step 8:

[0147] Users make product purchase decisions based on virtual try-on results and emotional evaluations. They also input feedback on the results and send it to the server.

[0148] Step 9:

[0149] The server updates its AI model using the received feedback and emotional data to improve future cosmetic recommendations. This continuous use of data enables recommendations that better match user needs.

[0150] (Example 2)

[0151] 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 device 14 as the "terminal".

[0152] Conventional cosmetic recommendation systems struggle to suggest the optimal cosmetics based on individual skin characteristics, and formulations based on specific ingredients are not sufficiently personalized. Furthermore, because they are provided without considering the user's emotional state, virtual try-on results do not necessarily improve user satisfaction. In addition, updating the generation AI model based on user feedback and adjusting the try-on results are often done manually, which is inefficient.

[0153] 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.

[0154] In this invention, the server includes means for inputting an individual's skin characteristics information, means for receiving and storing the skin characteristics information, means for using a generative AI model that estimates appropriate cosmetic materials based on the stored skin characteristics information, and means for adjusting and presenting fitting results based on the evaluated emotional state. This makes it possible to recommend personalized cosmetics that take into account individual skin characteristics and emotional states, and to provide a fitting experience that is highly satisfying to the user.

[0155] "Individual skin characteristics information" refers to data related to an individual's skin, such as skin condition and type, and information about cosmetics used.

[0156] A "generative AI model" is an artificial intelligence technology used to estimate the optimal cosmetic ingredients based on past data and market information.

[0157] "Means for generating chemical structures and designing formulations" refers to the process of calculating and designing chemical structures in order to translate estimated cosmetic ingredients into specific formulations.

[0158] "Virtual fitting" is a technology that applies generated cosmetics to a 3D model of the user and provides the results visually.

[0159] "Emotional state" refers to the psychological and emotional responses analyzed from the user's facial expressions and actions.

[0160] "Means for adjusting and presenting fitting results" refers to a method of dynamically changing the content of a virtual fitting based on the results of an analysis of the user's emotional state and presenting it to the user.

[0161] This system provides personalized cosmetic recommendations based on the user's skin characteristics and emotional state. Specifically, users input their skin information and provide facial photos and videos through an application or web interface. This data is encrypted and securely transmitted from the device to the server.

[0162] The server analyzes the received skin information and uses a generative AI model in this process. The model uses past training data and market databases to estimate the optimal cosmetic ingredients. The estimated ingredients generate chemical structures and design formulations, creating a personalized cosmetic formula for the user.

[0163] In addition, the server uses an emotion engine to analyze the submitted facial photos and videos to identify the user's emotional state. This emotion analysis is performed based on the user's facial expressions, and the results are used to adjust the virtual try-on content. The generated cosmetics are then applied to the user's 3D model using virtual try-on technology and visually displayed on the device.

[0164] The device displays the fitting results in real time and makes suggestions based on the user's emotional state. For example, if a user has dry skin and expresses surprise at the fitting results, the server will suggest a different formula containing more moisturizing ingredients based on the user's emotions and skin characteristics.

[0165] An example of a prompt message would be, "Female, 30s, dry skin, feeling surprised. Suggest the most suitable cosmetic ingredients." In this way, the system provides more personalized cosmetic recommendations based on the user's skin characteristics and emotional state.

[0166] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0167] Step 1:

[0168] Users input their skin characteristics information through an application or web interface. Specifically, they input information such as their skin condition and type, and the cosmetics they use, and also provide facial photos and videos. This input data is temporarily stored on the device and transmitted to the server via a secure communication protocol. The output is sent to the server as skin information and facial expression data.

[0169] Step 2:

[0170] The server inputs the received skin information into a generating AI model. During this process, it creates a prompt sentence, for example, "Female in her 30s, dry skin type, current emotion: surprised." Based on this prompt, the AI ​​model uses past training data and a market database to estimate appropriate cosmetic ingredients. The output is a list of estimated cosmetic ingredients.

[0171] Step 3:

[0172] The server generates chemical structures based on estimated cosmetic ingredients and designs unique formulations. Specifically, it uses chemical software to create molecular models and assembles formulations accordingly. The output is formulation design data optimized for the user.

[0173] Step 4:

[0174] The server uses the provided facial photos and videos to analyze them with an emotion engine and identify the user's emotional state. This analysis inputs collected facial expression data into an analysis algorithm to evaluate the type and intensity of emotion. The output is the user's emotional status.

[0175] Step 5:

[0176] The server applies cosmetics generated by the virtual try-on function to the user's 3D model. Based on the results of the emotional state analysis, the server adjusts the try-on to provide the user with a highly satisfying visual experience. This try-on result is displayed in real time on the terminal. The output is the adjusted virtual try-on image.

[0177] Step 6:

[0178] The user reviews the virtual fitting results and provides feedback through their device. This feedback is sent to the server. The server uses this information to update the generated AI model, improving the accuracy of future suggestions. The output is the improved suggestions based on the updated AI model.

[0179] (Application Example 2)

[0180] 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 device 14 will be referred to as the "terminal."

[0181] The problem that this invention aims to solve is to improve individual satisfaction by enabling the proposal of optimal beauty materials that take into account individual emotions and skin information, thereby meeting individual needs that were difficult to achieve with the conventional provision of uniform beauty products. Conventional beauty products have difficulty reflecting consumer emotions and real-time feedback, and as a result, it is difficult to provide an optimal customer experience. In addition, there is a problem of insufficient interaction among consumers because it is not easy to share results with others.

[0182] 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.

[0183] In this invention, the server includes means for inputting an individual's biometric information, means for using a generation algorithm that estimates the optimal beauty material based on the stored biometric information, and means for acquiring an individual's emotions and adjusting the suggested beauty materials. This makes it possible to suggest beauty materials that have been adjusted in real time through virtual fitting based on an individual's skin information and emotion analysis, thereby increasing consumer satisfaction and promoting interaction among consumers by facilitating the sharing of results with others.

[0184] "Personal biometric information" refers to physiological data specific to that individual, such as skin condition and facial expression data.

[0185] A "generative algorithm" is a computational method used to estimate the optimal beauty ingredients based on the input data.

[0186] "Beauty ingredients" refer to chemical components and products used to improve skin condition and enhance appearance.

[0187] "Chemical representation" refers to the structure of a specific chemical component and describes the details of the cosmetic material that has been designed.

[0188] "Virtual application" refers to a technology that visually simulates the usage of digitally generated beauty products.

[0189] "Individual emotions" refer to data that indicates an individual's mental state, obtained through facial expressions, voice, and other means.

[0190] "Information infrastructure" refers to an electronic platform for sharing information among a large number of users.

[0191] The system for realizing this invention provides a platform for analyzing an individual's biometric information and emotions to suggest the most suitable beauty ingredients. Specifically, it has the following configuration.

[0192] First, the user inputs biometric information using a smart device. This device is equipped with a high-precision facial recognition camera that can capture the user's skin condition and facial expressions. This data is securely transmitted to a server via the device.

[0193] The server analyzes the received biometric information and compares it with a stored database. Using a generative AI model, it estimates cosmetic materials suitable for the individual's skin condition and generates chemical representations. Furthermore, by analyzing the user's facial expression data, it recognizes emotions and adjusts the suggested products accordingly. This process utilizes software that works in conjunction with an emotion analysis engine.

[0194] Beauty material suggestions are applied to the user's 3D model using virtual fitting technology and displayed in real time on the device. Users can review the results of this virtual fitting and, if satisfied, proceed with the purchase. Furthermore, it is possible to share the results of the virtual fitting with other users through the information infrastructure. The shared information serves as a reference for other users and is reflected in the system as feedback.

[0195] As a concrete example, a user puts on smart glasses and starts a session in a virtual store. The system analyzes the user's subtle facial expressions and customizes and suggests beauty products with lifting effects. If the user shows a positive reaction after trying them on, they are guided to make a purchase.

[0196] An example of a prompt message would be, "Based on the user's emotions and skin information, generate data suggesting highly moisturizing and lifting beauty ingredients," which would be input to the AI ​​model. This enables personalized suggestions and improves the user experience.

[0197] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0198] Step 1:

[0199] Users input their biometric information using a smart device equipped with a facial recognition camera. Facial images and facial expression data are captured, and this information is transmitted to a server via the device. The input data is securely transferred via a secure protocol.

[0200] Step 2:

[0201] The server analyzes the received biometric information. Specifically, it inputs data about the skin condition into a generative AI model to estimate appropriate cosmetic ingredients. The generative AI model utilizes past training data to output a chemical expression containing the optimal ingredients. In this process, machine learning algorithms analyze the characteristics of the data and construct the chemical formulation.

[0202] Step 3:

[0203] The server analyzes the user's emotions based on their facial expression data. Using an emotion analysis engine, it determines the emotional state from changes in facial expression and adjusts the suggested beauty products based on this information. It evaluates satisfaction with the emotional input and outputs suggested results that match the user's current situation and preferences.

[0204] Step 4:

[0205] The server applies estimated cosmetic materials, based on virtual fitting technology, to the user's 3D model. The simulation results are displayed in real-time on the terminal screen. The user reviews the virtual fitting results and evaluates their level of satisfaction. Based on the user's input, the next action (purchase, re-suggestion, etc.) is determined.

[0206] Step 5:

[0207] Users can share their virtual try-on results with other users through an information infrastructure. The server collects feedback from the shared data and aggregates the information to improve the overall system service. The shared user feedback is used to further refine the generative AI model.

[0208] In this way, it becomes possible to propose highly personalized beauty materials that utilize an individual's biometric information and emotions.

[0209] 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.

[0210] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0211] 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.

[0212] [Second Embodiment]

[0213] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0214] 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.

[0215] 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).

[0216] 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.

[0217] 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.

[0218] 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).

[0219] 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.

[0220] 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.

[0221] 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.

[0222] 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.

[0223] 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.

[0224] 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".

[0225] This invention is a system for providing personalized cosmetics based on individual users' skin information, and at its core is a generative AI model. The generative AI model estimates the optimal cosmetic ingredients based on detailed skin information provided by the user, such as skin type, age, and allergy information.

[0226] First, users enter their skin information using a dedicated app or web interface. This information may include skin type, age, allergy information, past cosmetic usage history, and personal preferences. After entry, this information is sent from the device to the server.

[0227] The server organizes and stores the received information in a database, and then inputs its contents into a generative AI model. This generative AI model is built on a large amount of cosmetic and medical data and is used to estimate the optimal combination of ingredients. Based on the estimated ingredients, the AI ​​model generates chemical structural formulas and designs specific formulations.

[0228] Next, the server provides a function that allows users to virtually try on the designed cosmetics in a virtual environment. This function allows users to virtually check the feel of the product using a 3D model before physically handling it. The results of this virtual try-on are displayed to the user via their terminal.

[0229] Furthermore, users can provide feedback to the system, including their impressions of using the product and suggestions for improvement. This feedback is collected by the server and used to continuously improve the generated AI model and propose new products. In this way, by incorporating user opinions, it becomes possible to provide cosmetics that are more tailored to individual needs.

[0230] For example, if a woman in her 30s has dry skin and specific allergies, the AI ​​model generates a formula based on the information she inputs, estimating appropriate ingredients and creating a cosmetic product that addresses both her dry skin and allergies. By virtually trying on this cosmetic product, she can check its effects and feel before actually trying the product.

[0231] Thus, the present invention provides a platform that allows users to utilize cosmetics optimized based on their own skin information, thereby realizing a more satisfying experience.

[0232] The following describes the processing flow.

[0233] Step 1:

[0234] Users log in to a dedicated app or web interface and enter skin information such as their skin type, age, allergy information, and past cosmetic usage history. They can also enter specific concerns and beauty goals.

[0235] Step 2:

[0236] The terminal organizes the entered data, securely encrypts it, and then sends it to the server. The transmitted data is linked to the user's unique ID.

[0237] Step 3:

[0238] The server saves the received data to a database. It then prepares the saved data for input into a generating AI model for analysis.

[0239] Step 4:

[0240] The server uses a generative AI model to estimate the optimal cosmetic ingredients based on the user's skin information. This estimation utilizes past research data and information on the ingredients of commercially available cosmetics.

[0241] Step 5:

[0242] The server generates chemical structural formulas based on estimated ingredients and designs personalized cosmetic formulations. This design is tailored to the user's unique needs.

[0243] Step 6:

[0244] The server generates a 3D model using the user's facial photograph to prepare a virtual try-on function for the designed cosmetics. Image processing technology is used to accurately capture the user's facial features.

[0245] Step 7:

[0246] The device applies the designed cosmetics to the generated 3D model and displays a virtual trial screen to the user. The user can visually check the appearance and feel of the cosmetics on the screen.

[0247] Step 8:

[0248] Users evaluate the product's suitability through a virtual trial. After the evaluation, they can decide whether to purchase the product and proceed with the purchase process.

[0249] Step 9:

[0250] The server collects user feedback and impressions and records them in a database. This feedback is used to improve the generative AI model and design future formulations.

[0251] (Example 1)

[0252] 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."

[0253] Providing optimal consumer products based on each user's individual biometric information is difficult and requires considerable time and expertise. Therefore, personalized product selection tailored to diverse needs is challenging, leading to user dissatisfaction. Furthermore, the lack of sufficient virtual trial environments means users cannot fully experience the effects of a product before trying it.

[0254] 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.

[0255] In this invention, the server includes means for receiving and recording the biometric information of individual users, means for using a generative model to estimate the optimal consumer product components based on the recorded biometric information, and means for displaying the designed consumer product as a virtual trial. This enables optimal product selection based on the user's individual needs and allows for a pre-trial experience through virtual trials.

[0256] "Individual users" refers to selected users who provide biometric information.

[0257] "Biometric information" refers to all information related to the body that is necessary for selecting consumer products, such as the skin texture, age, and allergy information of individual users.

[0258] A "generative model" refers to an automated computational method for estimating the optimal consumer product ingredients based on input data and selecting products accordingly.

[0259] "Chemical composition" refers to design information based on the molecular-level structure of the estimated components.

[0260] "Virtual trial" refers to a feature that allows users to check the usability of a designed consumer product using computer graphics or simulations, without physically trying it out.

[0261] "User feedback" refers to the collective term for feedback provided by users, including evaluations and opinions after virtual trials or product use.

[0262] "Infrastructure" refers to the electronic network and software environment for sharing information and results among users.

[0263] This invention is a system for providing optimal consumer products based on the biometric information of individual users. Embodiments thereof are shown below.

[0264] Users input their biometric information using a dedicated app or web interface. Specifically, this biometric information includes skin texture, age, and allergy information. In addition, personal preferences and past consumer product usage history can also be entered. An example of prompt text input would be: "Female, 30s, dry skin, allergies, preferred highly moisturizing creams in the past."

[0265] The terminal sends the entered biometric information to the server as a data packet. The server receives the biometric information, organizes it, and stores it in a database. A database management system is used in this process.

[0266] The server analyzes the stored information and inputs it into a generative AI model. This generative AI model is designed based on a large amount of medical and cosmetic data and estimates the optimal product ingredients from the received information. This AI model utilizes machine learning frameworks and natural language processing techniques.

[0267] Furthermore, the generation AI model generates the estimated chemical composition of the ingredients and designs a specific product formulation. To allow users to preview the feel of the designed product beforehand, the server provides a virtual trial environment. This virtual trial environment is built using 3D modeling software, allowing users to visually and interactively experience using the product.

[0268] Finally, after experiencing the virtual trial, users provide feedback on their experience and areas for improvement to the server via the app or web interface. The server records this feedback in a database, which helps in the continuous improvement of the generative AI model. This allows the generative AI model to learn from the new feedback, enabling more accurate component estimation.

[0269] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0270] Step 1:

[0271] Users enter their biometric information via a dedicated app or web interface. Input fields include skin texture, age, and allergy information, and optionally, past product usage history and preferences. This input is stored on the device in digital format and prepared for transmission.

[0272] Step 2:

[0273] The terminal packets the entered biometric information and sends it to the server via a secure communication protocol. The input data is transmitted as biometric information and received by the server as individual data entries. This creates a foundation for efficient data processing.

[0274] Step 3:

[0275] The server analyzes biometric information received from the terminal, classifies the information into the necessary categories, and stores it in the database. The entered biometric information is divided into fields, each tagged, and stored. The database management system supports this process, maintaining data reliability.

[0276] Step 4:

[0277] The server sends the organized biometric information to a generating AI model. The AI ​​model analyzes the input using prompts and estimates the optimal product ingredients. This process utilizes data science techniques to structure the input data and generate meaningful output. The output is provided as a list of estimated ingredients.

[0278] Step 5:

[0279] Based on the estimated components obtained from the generating AI model, the server generates a chemical composition and designs the product. The AI ​​system considers the chemical properties of the estimated components and designs the optimal formulation. Specific product formulation information is obtained as output.

[0280] Step 6:

[0281] The server sends the designed product to the virtual trial environment to provide the user with a virtual trial experience. Here, 3D modeling software is used, and the user can visually confirm the usage feeling of the product. The output of the virtual trial is a 3D display drawn on the user's terminal.

[0282] Step 7:

[0283] After the virtual trial, the user sends feedback on the usage feeling and improvement points. The feedback is sent to the server in text form and stored in the database. This feedback is used as an improved dataset for the generative AI model and is utilized for improved component estimation.

[0284] (Application Example 1)

[0285] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0286] In modern society, selecting cosmetics considering various skin types and individual allergies is complex for consumers. Many users feel difficulty in selecting daily-use cosmetics because they lack information on which cosmetics are optimal for their skin conditions. There is a demand for a system that solves this problem and efficiently proposes personalized optimal cosmetics for individual users.

[0287] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following respective means.

[0288] In this invention, the server includes means for inputting an individual's skin information, means for receiving and storing the skin information, and means for using a generative model that estimates the optimal cosmetic ingredients based on the stored skin information. This makes it possible to estimate the optimal cosmetic ingredients based on the individual user's skin information. In addition, users can check the feel of the suggested cosmetics in advance through virtual try-on, enabling them to make purchases based on clear judgments.

[0289] "Personal skin information" refers to individual data necessary for selecting cosmetics, such as the user's skin type, age, and allergy information.

[0290] A "generative model" is an artificial intelligence-based algorithm used to estimate appropriate cosmetic ingredients from received data.

[0291] "Methods for generating chemical structural formulas and designing formulations" refers to the process of determining the specific chemical composition based on estimated components and designing the optimal cosmetic product.

[0292] "A means of displaying as a virtual try-on" refers to a technology that allows users to view a visual image of suggested cosmetics on a digital device.

[0293] "A means of displaying and allowing users to confirm in real time" refers to a function that immediately presents the results of cosmetic selection to the user via a terminal, allowing them to check the feel and appearance of the product.

[0294] "Image processing means" refers to technology that uses devices such as smartphones and smart glasses to capture skin information in a real-world environment and analyze it as data.

[0295] The system implementing this invention enables personalized product selection by suggesting the most suitable cosmetics for each individual user and allowing them to confirm the feel of the products through virtual try-on. First, the user captures real-time images of their skin using a smartphone or smart glasses. This information is analyzed using image processing libraries such as OpenCV and TensorFlow to extract characteristic skin information.

[0296] Data sent from the terminal to the server is stored and analyzed in the cloud. This data processing uses generative AI models (e.g., PyTorch and TensorFlow) to suggest optimal cosmetic ingredients based on the input data. These generative AI models utilize a large-scale cosmetics database and medical data to design individual products tailored to each user's characteristics.

[0297] The server further provides virtual try-on services through 3D models generated using Unity or Unreal Engine. Users can virtually try on suggested cosmetics in a virtual environment via their devices and check the visual effects of the products. This system also collects usage feedback, which is used for the continuous improvement of the AI ​​model.

[0298] As a concrete example of its use, a female user in her 30s could use her smartphone to scan her face, and the generating AI model could suggest a specialized moisturizing cream that is optimal for dry skin and also addresses allergies. An example of the prompt text for the generating AI model in this case would be, "Female, 30s, dry skin, glycerin allergy. Please suggest the optimal moisturizing cream ingredients." The user can virtually try on the suggested cream and check its effects beforehand, enabling a more confident purchase decision.

[0299] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0300] Step 1:

[0301] The user takes a photo of their own skin using a smartphone or smart glasses. The input here is a real-time skin image, which is obtained using the terminal's camera. The output is analyzable skin image data.

[0302] Step 2:

[0303] The terminal analyzes the acquired skin image data using an image processing library such as OpenCV or TensorFlow. In this step, skin characteristics are extracted and digital signal processing is performed. The input is skin image data, and the output is characteristic information, such as skin texture and color tone information.

[0304] Step 3:

[0305] The skin characteristic information is sent from the terminal to the server. The server receives this information and saves it in the database. The input is skin characteristic information, and the output is database update information.

[0306] Step 4:

[0307] The server inputs the saved skin characteristic information into a generative AI model. The generative AI model utilizes a large amount of cosmetic data to estimate the optimal cosmetic ingredients for the user. The input is skin characteristic information and the prompt text of the AI model, and the output is the estimated cosmetic ingredients.

[0308] Step 5:

[0309] The server generates a chemical structural formula based on the estimated cosmetic ingredients and constructs a 3D virtual model using Unity or Unreal Engine. The input is cosmetic ingredients, and the output is a 3D virtual try-on model.

[0310] Step 6:

[0311] The server sends the generated 3D virtual try-on model to the terminal. The user checks this model through the terminal and performs virtual try-on. The input is the 3D virtual try-on model, and the output is the user's try-on feedback.

[0312] Step 7:

[0313] The user enters feedback and sends it to the server. The server collects this feedback and uses it to improve the generated AI model. The input is user feedback after trying on the product, and the output is information for improving the AI ​​model.

[0314] 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.

[0315] This invention further enhances personalized cosmetic recommendations through a system incorporating an emotion engine that recognizes user emotions. This system, in addition to estimating optimal cosmetic ingredients based on the user's skin information, also considers the user's emotions, enabling more personalized cosmetic recommendations.

[0316] First, users input their skin information through an app or web interface, and also provide facial photos and videos, enabling emotion analysis. This data is securely transmitted from the device to the server.

[0317] The server inputs the received skin information into a generating AI model to estimate the optimal cosmetic ingredients. This process utilizes past training data and a market database of cosmetics. The estimated ingredients are then materialized as chemical structural formulas, and individual formulations are designed.

[0318] Furthermore, the server uses an emotion engine to analyze the user's emotional state from the submitted facial photos and video data. The emotional state is evaluated by detecting changes in facial expressions such as smiles and surprise. This evaluation serves as a criterion for determining how satisfied the user is during the virtual try-on.

[0319] The virtual try-on function applies a server-generated simulation of cosmetics to the user's 3D model and presents it to the user on their device. Based on this try-on result, the user decides whether to purchase the product or if further adjustments are needed.

[0320] The device notifies the user of the emotion engine's analysis results in real time and adjusts suggestions based on satisfaction levels. For example, if the user's reaction to the try-on results is positive, the product is recommended as is; however, if the reaction is negative, an alternative solution is presented. This adjustment is also used when updating the generative model based on user feedback data and emotion data.

[0321] For example, if a user enters information about having dry skin and expresses surprise at the fitting results, the server will re-suggest a formula containing more moisturizing ingredients. This optimizes the user experience based on their emotions.

[0322] Thus, the present invention provides a system that enables cosmetic product recommendations that take user emotions into consideration, thereby further enhancing the provision of personalized cosmetics.

[0323] The following describes the processing flow.

[0324] Step 1:

[0325] Users input information about their skin, such as skin type, age, and allergy information, using a dedicated app or web interface. They also provide facial photos and videos for the fitting experience, uploading data necessary for emotional analysis.

[0326] Step 2:

[0327] The terminal encrypts the entered data and sends it to the server according to security protocols. The transmitted data is securely stored in a database based on the user ID.

[0328] Step 3:

[0329] The server supplies the received data to a generating AI model, which estimates the optimal cosmetic ingredients for the user's skin characteristics. The AI ​​model uses a historical cosmetic database and learned patterns to generate a list of ingredients.

[0330] Step 4:

[0331] The server uses the estimated ingredient information to generate chemical structures. These chemical structures form the basis for the formulation design of individual, personalized cosmetics.

[0332] Step 5:

[0333] The server uses an emotion engine to analyze emotional data extracted from the user's facial photos and videos. The emotion engine detects microexpressions and other features to evaluate the user's emotional state.

[0334] Step 6:

[0335] The server applies the generated cosmetic formulation onto a 3D model for virtual try-on and calculates the results along with the user's emotional evaluation.

[0336] Step 7:

[0337] The device displays real-time evaluation results from an emotion engine, along with a 3D model of the cosmetics being tried on. Users can then review this and understand their emotional satisfaction level.

[0338] Step 8:

[0339] Users make product purchase decisions based on virtual try-on results and emotional evaluations. They also input feedback on the results and send it to the server.

[0340] Step 9:

[0341] The server updates its AI model using the received feedback and emotional data to improve future cosmetic recommendations. This continuous use of data enables recommendations that better match user needs.

[0342] (Example 2)

[0343] 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".

[0344] Conventional cosmetic recommendation systems struggle to suggest the optimal cosmetics based on individual skin characteristics, and formulations based on specific ingredients are not sufficiently personalized. Furthermore, because they are provided without considering the user's emotional state, virtual try-on results do not necessarily improve user satisfaction. In addition, updating the generation AI model based on user feedback and adjusting the try-on results are often done manually, which is inefficient.

[0345] 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.

[0346] In this invention, the server includes means for inputting an individual's skin characteristics information, means for receiving and storing the skin characteristics information, means for using a generative AI model that estimates appropriate cosmetic materials based on the stored skin characteristics information, and means for adjusting and presenting fitting results based on the evaluated emotional state. This makes it possible to recommend personalized cosmetics that take into account individual skin characteristics and emotional states, and to provide a fitting experience that is highly satisfying to the user.

[0347] "Individual skin characteristics information" refers to data related to an individual's skin, such as skin condition and type, and information about cosmetics used.

[0348] A "generative AI model" is an artificial intelligence technology used to estimate the optimal cosmetic ingredients based on past data and market information.

[0349] "Means for generating chemical structures and designing formulations" refers to the process of calculating and designing chemical structures in order to translate estimated cosmetic ingredients into specific formulations.

[0350] "Virtual try-on" is a technology that applies generated cosmetics to a user's 3D model and provides the results visually.

[0351] "Emotional state" refers to the psychological and emotional responses analyzed from the user's facial expressions and actions.

[0352] "Means for adjusting and presenting fitting results" refers to a method of dynamically changing the content of a virtual fitting based on the results of an analysis of the user's emotional state and presenting it to the user.

[0353] This system provides personalized cosmetic recommendations based on the user's skin characteristics and emotional state. Specifically, users input their skin information and provide facial photos and videos through an application or web interface. This data is encrypted and securely transmitted from the device to the server.

[0354] The server analyzes the received skin information and uses a generative AI model in this process. The model uses past training data and market databases to estimate the optimal cosmetic ingredients. The estimated ingredients generate chemical structures and design formulations, creating a personalized cosmetic formula for the user.

[0355] In addition, the server uses an emotion engine to analyze the submitted facial photos and videos to identify the user's emotional state. This emotion analysis is performed based on the user's facial expressions, and the results are used to adjust the virtual try-on content. The generated cosmetics are then applied to the user's 3D model using virtual try-on technology and visually displayed on the device.

[0356] The device displays the fitting results in real time and makes suggestions based on the user's emotional state. For example, if a user has dry skin and expresses surprise at the fitting results, the server will suggest a different formula containing more moisturizing ingredients based on the user's emotions and skin characteristics.

[0357] An example of a prompt message would be, "Female, 30s, dry skin, feeling surprised. Suggest the most suitable cosmetic ingredients." In this way, the system provides more personalized cosmetic recommendations based on the user's skin characteristics and emotional state.

[0358] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0359] Step 1:

[0360] Users input their skin characteristics information through an application or web interface. Specifically, they input information such as their skin condition and type, and the cosmetics they use, and also provide facial photos and videos. This input data is temporarily stored on the device and transmitted to the server via a secure communication protocol. The output is sent to the server as skin information and facial expression data.

[0361] Step 2:

[0362] The server inputs the received skin information into a generating AI model. During this process, it creates a prompt sentence, for example, "Female in her 30s, dry skin type, current emotion: surprised." Based on this prompt, the AI ​​model uses past training data and a market database to estimate appropriate cosmetic ingredients. The output is a list of estimated cosmetic ingredients.

[0363] Step 3:

[0364] The server generates chemical structures based on estimated cosmetic ingredients and designs unique formulations. Specifically, it uses chemical software to create molecular models and assembles formulations accordingly. The output is formulation design data optimized for the user.

[0365] Step 4:

[0366] The server uses the provided facial photos and videos to analyze them with an emotion engine and identify the user's emotional state. This analysis inputs collected facial expression data into an analysis algorithm to evaluate the type and intensity of emotion. The output is the user's emotional status.

[0367] Step 5:

[0368] The server applies cosmetics generated by the virtual try-on function to the user's 3D model. Based on the results of the emotional state analysis, the server adjusts the try-on to provide the user with a highly satisfying visual experience. This try-on result is displayed in real time on the terminal. The output is the adjusted virtual try-on image.

[0369] Step 6:

[0370] The user reviews the virtual fitting results and provides feedback through their device. This feedback is sent to the server. The server uses this information to update the generated AI model, improving the accuracy of future suggestions. The output is the improved suggestions based on the updated AI model.

[0371] (Application Example 2)

[0372] 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."

[0373] The problem that this invention aims to solve is to improve individual satisfaction by enabling the proposal of optimal beauty materials that take into account individual emotions and skin information, thereby meeting individual needs that were difficult to achieve with the conventional provision of uniform beauty products. Conventional beauty products have difficulty reflecting consumer emotions and real-time feedback, and as a result, it is difficult to provide an optimal customer experience. In addition, there is a problem of insufficient interaction among consumers because it is not easy to share results with others.

[0374] 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.

[0375] In this invention, the server includes means for inputting an individual's biometric information, means for using a generation algorithm that estimates the optimal beauty material based on the stored biometric information, and means for acquiring an individual's emotions and adjusting the suggested beauty materials. This makes it possible to suggest beauty materials that have been adjusted in real time through virtual fitting based on an individual's skin information and emotion analysis, thereby increasing consumer satisfaction and promoting interaction among consumers by facilitating the sharing of results with others.

[0376] "Personal biometric information" refers to physiological data specific to that individual, such as skin condition and facial expression data.

[0377] A "generative algorithm" is a computational method used to estimate the optimal beauty ingredients based on the input data.

[0378] "Beauty ingredients" refer to chemical components and products used to improve skin condition and enhance appearance.

[0379] "Chemical representation" refers to the structure of a specific chemical component and describes the details of the cosmetic material that has been designed.

[0380] "Virtual application" refers to a technology that visually simulates the usage of digitally generated beauty products.

[0381] "Individual emotions" refer to data that indicates an individual's mental state, obtained through facial expressions, voice, and other means.

[0382] "Information infrastructure" refers to an electronic platform for sharing information among a large number of users.

[0383] The system for realizing this invention provides a platform for analyzing an individual's biometric information and emotions to suggest the most suitable beauty ingredients. Specifically, it has the following configuration.

[0384] First, the user inputs biometric information using a smart device. This device is equipped with a high-precision facial recognition camera that can capture the user's skin condition and facial expressions. This data is securely transmitted to a server via the device.

[0385] The server analyzes the received biometric information and compares it with a stored database. Using a generative AI model, it estimates cosmetic materials suitable for the individual's skin condition and generates chemical representations. Furthermore, by analyzing the user's facial expression data, it recognizes emotions and adjusts the suggested products accordingly. This process utilizes software that works in conjunction with an emotion analysis engine.

[0386] Beauty material suggestions are applied to the user's 3D model using virtual fitting technology and displayed in real time on the device. Users can review the results of this virtual fitting and, if satisfied, proceed with the purchase. Furthermore, it is possible to share the results of the virtual fitting with other users through the information infrastructure. The shared information serves as a reference for other users and is reflected in the system as feedback.

[0387] As a concrete example, a user puts on smart glasses and starts a session in a virtual store. The system analyzes the user's subtle facial expressions and customizes and suggests beauty products with lifting effects. If the user shows a positive reaction after trying them on, they are guided to make a purchase.

[0388] An example of a prompt message would be, "Based on the user's emotions and skin information, generate data suggesting highly moisturizing and lifting beauty ingredients," which would be input to the AI ​​model. This enables personalized suggestions and improves the user experience.

[0389] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0390] Step 1:

[0391] Users input their biometric information using a smart device equipped with a facial recognition camera. Facial images and facial expression data are captured, and this information is transmitted to a server via the device. The input data is securely transferred via a secure protocol.

[0392] Step 2:

[0393] The server analyzes the received biometric information. Specifically, it inputs data about the skin condition into a generative AI model to estimate appropriate cosmetic ingredients. The generative AI model utilizes past training data to output a chemical expression containing the optimal ingredients. In this process, machine learning algorithms analyze the characteristics of the data and construct the chemical formulation.

[0394] Step 3:

[0395] The server analyzes the user's emotions based on their facial expression data. Using an emotion analysis engine, it determines the emotional state from changes in facial expression and adjusts the suggested beauty products based on this information. It evaluates satisfaction with the emotional input and outputs suggested results that match the user's current situation and preferences.

[0396] Step 4:

[0397] The server applies estimated cosmetic materials, based on virtual fitting technology, to the user's 3D model. The simulation results are displayed in real-time on the terminal screen. The user reviews the virtual fitting results and evaluates their level of satisfaction. Based on the user's input, the next action (purchase, re-suggestion, etc.) is determined.

[0398] Step 5:

[0399] Users can share their virtual try-on results with other users through an information infrastructure. The server collects feedback from the shared data and aggregates the information to improve the overall system service. The shared user feedback is used to further refine the generative AI model.

[0400] In this way, it becomes possible to propose highly personalized beauty materials that utilize an individual's biometric information and emotions.

[0401] 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.

[0402] 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.

[0403] 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.

[0404] [Third Embodiment]

[0405] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0406] 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.

[0407] 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).

[0408] 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.

[0409] 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.

[0410] 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).

[0411] 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.

[0412] 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.

[0413] 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.

[0414] 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.

[0415] 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.

[0416] 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".

[0417] This invention is a system for providing personalized cosmetics based on individual users' skin information, and at its core is a generative AI model. The generative AI model estimates the optimal cosmetic ingredients based on detailed skin information provided by the user, such as skin type, age, and allergy information.

[0418] First, users enter their skin information using a dedicated app or web interface. This information may include skin type, age, allergy information, past cosmetic usage history, and personal preferences. After entry, this information is sent from the device to the server.

[0419] The server organizes and stores the received information in a database, and then inputs its contents into a generative AI model. This generative AI model is built on a large amount of cosmetic and medical data and is used to estimate the optimal combination of ingredients. Based on the estimated ingredients, the AI ​​model generates chemical structural formulas and designs specific formulations.

[0420] Next, the server provides a function that allows users to virtually try on the designed cosmetics in a virtual environment. This function allows users to virtually check the feel of the product using a 3D model before physically handling it. The results of this virtual try-on are displayed to the user via their terminal.

[0421] Furthermore, users can provide feedback to the system, including their impressions of using the product and suggestions for improvement. This feedback is collected by the server and used to continuously improve the generated AI model and propose new products. In this way, by incorporating user opinions, it becomes possible to provide cosmetics that are more tailored to individual needs.

[0422] For example, if a woman in her 30s has dry skin and specific allergies, the AI ​​model generates a formula based on the information she inputs, estimating appropriate ingredients and creating a cosmetic product that addresses both her dry skin and allergies. By virtually trying on this cosmetic product, she can check its effects and feel before actually trying the product.

[0423] Thus, the present invention provides a platform that allows users to utilize cosmetics optimized based on their own skin information, thereby realizing a more satisfying experience.

[0424] The following describes the processing flow.

[0425] Step 1:

[0426] Users log in to a dedicated app or web interface and enter skin information such as their skin type, age, allergy information, and past cosmetic usage history. They can also enter specific concerns and beauty goals.

[0427] Step 2:

[0428] The terminal organizes the entered data, securely encrypts it, and then sends it to the server. The transmitted data is linked to the user's unique ID.

[0429] Step 3:

[0430] The server saves the received data to a database. It then prepares the saved data for input into a generating AI model for analysis.

[0431] Step 4:

[0432] The server uses a generative AI model to estimate the optimal cosmetic ingredients based on the user's skin information. This estimation utilizes past research data and information on the ingredients of commercially available cosmetics.

[0433] Step 5:

[0434] The server generates chemical structural formulas based on estimated ingredients and designs personalized cosmetic formulations. This design is tailored to the user's unique needs.

[0435] Step 6:

[0436] The server generates a 3D model using the user's facial photograph to prepare a virtual try-on function for the designed cosmetics. Image processing technology is used to accurately capture the user's facial features.

[0437] Step 7:

[0438] The device applies the designed cosmetics to the generated 3D model and displays a virtual trial screen to the user. The user can visually check the appearance and feel of the cosmetics on the screen.

[0439] Step 8:

[0440] Users evaluate the product's suitability through a virtual trial. After the evaluation, they can decide whether to purchase the product and proceed with the purchase process.

[0441] Step 9:

[0442] The server collects user feedback and impressions and records them in a database. This feedback is used to improve the generative AI model and design future formulations.

[0443] (Example 1)

[0444] 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."

[0445] Providing optimal consumer products based on each user's individual biometric information is difficult and requires considerable time and expertise. Therefore, personalized product selection tailored to diverse needs is challenging, leading to user dissatisfaction. Furthermore, the lack of sufficient virtual trial environments means users cannot fully experience the effects of a product before trying it.

[0446] 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.

[0447] In this invention, the server includes means for receiving and recording the biometric information of individual users, means for using a generative model to estimate the optimal consumer product components based on the recorded biometric information, and means for displaying the designed consumer product as a virtual trial. This enables optimal product selection based on the user's individual needs and allows for a pre-trial experience through virtual trials.

[0448] "Individual users" refers to selected users who provide biometric information.

[0449] "Biometric information" refers to all information related to the body that is necessary for selecting consumer products, such as the skin texture, age, and allergy information of individual users.

[0450] A "generative model" refers to an automated computational method for estimating the optimal consumer product ingredients based on input data and selecting products accordingly.

[0451] "Chemical composition" refers to design information based on the molecular-level structure of the estimated components.

[0452] "Virtual trial" refers to a feature that allows users to check the usability of a designed consumer product using computer graphics or simulations, without physically trying it out.

[0453] "User feedback" refers to the collective term for feedback provided by users, including evaluations and opinions after virtual trials or product use.

[0454] "Infrastructure" refers to the electronic network and software environment for sharing information and results among users.

[0455] This invention is a system for providing optimal consumer products based on the biometric information of individual users. Embodiments thereof are shown below.

[0456] Users input their biometric information using a dedicated app or web interface. Specifically, this biometric information includes skin texture, age, and allergy information. In addition, personal preferences and past consumer product usage history can also be entered. An example of prompt text input would be: "Female, 30s, dry skin, allergies, preferred highly moisturizing creams in the past."

[0457] The terminal sends the entered biometric information to the server as a data packet. The server receives the biometric information, organizes it, and stores it in a database. A database management system is used in this process.

[0458] The server analyzes the stored information and inputs it into a generative AI model. This generative AI model is designed based on a large amount of medical and cosmetic data and estimates the optimal product ingredients from the received information. This AI model utilizes machine learning frameworks and natural language processing techniques.

[0459] Furthermore, the generation AI model generates the estimated chemical composition of the ingredients and designs a specific product formulation. To allow users to preview the feel of the designed product beforehand, the server provides a virtual trial environment. This virtual trial environment is built using 3D modeling software, allowing users to visually and interactively experience using the product.

[0460] Finally, after experiencing the virtual trial, users provide feedback on their experience and areas for improvement to the server via the app or web interface. The server records this feedback in a database, which helps in the continuous improvement of the generative AI model. This allows the generative AI model to learn from the new feedback, enabling more accurate component estimation.

[0461] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0462] Step 1:

[0463] Users enter their biometric information via a dedicated app or web interface. Input fields include skin texture, age, and allergy information, and optionally, past product usage history and preferences. This input is stored on the device in digital format and prepared for transmission.

[0464] Step 2:

[0465] The terminal packets the entered biometric information and sends it to the server via a secure communication protocol. The input data is transmitted as biometric information and received by the server as individual data entries. This creates a foundation for efficient data processing.

[0466] Step 3:

[0467] The server analyzes biometric information received from the terminal, classifies the information into the necessary categories, and stores it in the database. The entered biometric information is divided into fields, each tagged, and stored. The database management system supports this process, maintaining data reliability.

[0468] Step 4:

[0469] The server sends the organized biometric information to a generating AI model. The AI ​​model analyzes the input using prompts and estimates the optimal product ingredients. This process utilizes data science techniques to structure the input data and generate meaningful output. The output is provided as a list of estimated ingredients.

[0470] Step 5:

[0471] Based on the estimated components obtained from the generating AI model, the server generates a chemical composition and designs the product. The AI ​​system considers the chemical properties of the estimated components and designs the optimal formulation. Specific product formulation information is obtained as output.

[0472] Step 6:

[0473] The server sends the designed product to a virtual trial environment, providing the user with a virtual trial experience. Here, 3D modeling software is used, allowing the user to visually confirm the product's usability. The output of the virtual trial is a 3D display rendered on the user's terminal.

[0474] Step 7:

[0475] After the virtual trial, users submit feedback on their experience and areas for improvement. This feedback is sent to the server in text format and stored in a database. This feedback is used as a dataset for improving the generative AI model, contributing to improved component estimation.

[0476] (Application Example 1)

[0477] 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."

[0478] In modern society, selecting cosmetics that take into account diverse skin types and individual allergies is a complex task for consumers. Many users lack the information to understand which cosmetics are best suited to their skin condition, making it difficult to choose cosmetics for daily use. There is a need for a system that solves this problem and efficiently suggests personalized and optimal cosmetics to individual users.

[0479] 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.

[0480] In this invention, the server includes means for inputting an individual's skin information, means for receiving and storing the skin information, and means for using a generative model that estimates the optimal cosmetic ingredients based on the stored skin information. This makes it possible to estimate the optimal cosmetic ingredients based on the individual user's skin information. In addition, users can check the feel of the suggested cosmetics in advance through virtual try-on, enabling them to make purchases based on clear judgments.

[0481] "Personal skin information" refers to individual data necessary for selecting cosmetics, such as the user's skin type, age, and allergy information.

[0482] A "generative model" is an artificial intelligence-based algorithm used to estimate appropriate cosmetic ingredients from received data.

[0483] "Methods for generating chemical structural formulas and designing formulations" refers to the process of determining the specific chemical composition based on estimated components and designing the optimal cosmetic product.

[0484] "A means of displaying as a virtual try-on" refers to a technology that allows users to view a visual image of suggested cosmetics on a digital device.

[0485] "A means of displaying and allowing users to confirm in real time" refers to a function that immediately presents the results of cosmetic selection to the user via a terminal, allowing them to check the feel and appearance of the product.

[0486] "Image processing means" refers to technology that uses devices such as smartphones and smart glasses to capture skin information in a real-world environment and analyze it as data.

[0487] The system implementing this invention enables personalized product selection by suggesting the most suitable cosmetics for each individual user and allowing them to confirm the feel of the products through virtual try-on. First, the user captures real-time images of their skin using a smartphone or smart glasses. This information is analyzed using image processing libraries such as OpenCV and TensorFlow to extract characteristic skin information.

[0488] Data sent from the terminal to the server is stored and analyzed in the cloud. This data processing uses generative AI models (e.g., PyTorch and TensorFlow) to suggest optimal cosmetic ingredients based on the input data. These generative AI models utilize a large-scale cosmetics database and medical data to design individual products tailored to each user's characteristics.

[0489] The server further provides virtual try-on services through 3D models generated using Unity or Unreal Engine. Users can virtually try on suggested cosmetics in a virtual environment via their devices and check the visual effects of the products. This system also collects usage feedback, which is used for the continuous improvement of the AI ​​model.

[0490] As a concrete example of its use, a female user in her 30s could use her smartphone to scan her face, and the generating AI model could suggest a specialized moisturizing cream that is optimal for dry skin and also addresses allergies. An example of the prompt text for the generating AI model in this case would be, "Female, 30s, dry skin, glycerin allergy. Please suggest the optimal moisturizing cream ingredients." The user can virtually try on the suggested cream and check its effects beforehand, enabling a more confident purchase decision.

[0491] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0492] Step 1:

[0493] The user takes a picture of their skin using a smartphone or smart glasses. The input here is a real-time image of the skin, acquired using the device's camera. The output is analyzable skin image data.

[0494] Step 2:

[0495] The device analyzes the acquired skin image data using image processing libraries such as OpenCV and TensorFlow. In this step, skin characteristics are extracted and digital signal processing is performed. The input is skin image data, and the output is characteristic information, such as skin texture and color information.

[0496] Step 3:

[0497] Skin characteristic information is transmitted from the terminal to the server. The server receives this information and stores it in a database. The input is skin characteristic information, and the output is database update information.

[0498] Step 4:

[0499] The server inputs the stored skin characteristic information into a generating AI model. The generating AI model utilizes a large amount of cosmetic data to estimate the optimal cosmetic ingredients for the user. The input consists of skin characteristic information and prompts for the AI ​​model, and the output is the estimated cosmetic ingredients.

[0500] Step 5:

[0501] The server generates chemical structural formulas based on estimated cosmetic ingredients and constructs 3D virtual models using Unity or Unreal Engine. The input is cosmetic ingredients, and the output is a 3D virtual try-on model.

[0502] Step 6:

[0503] The server sends the generated 3D virtual fitting model to the terminal. The user views this model through the terminal and performs a virtual try-on. The input is the 3D virtual fitting model, and the output is the user's fitting feedback.

[0504] Step 7:

[0505] The user enters feedback and sends it to the server. The server collects this feedback and uses it to improve the generated AI model. The input is user feedback after trying on the product, and the output is information for improving the AI ​​model.

[0506] 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.

[0507] This invention further enhances personalized cosmetic recommendations through a system incorporating an emotion engine that recognizes user emotions. This system, in addition to estimating optimal cosmetic ingredients based on the user's skin information, also considers the user's emotions, enabling more personalized cosmetic recommendations.

[0508] First, users input their skin information through an app or web interface, and also provide facial photos and videos, enabling emotion analysis. This data is securely transmitted from the device to the server.

[0509] The server inputs the received skin information into a generating AI model to estimate the optimal cosmetic ingredients. This process utilizes past training data and a market database of cosmetics. The estimated ingredients are then materialized as chemical structural formulas, and individual formulations are designed.

[0510] Furthermore, the server uses an emotion engine to analyze the user's emotional state from the submitted facial photos and video data. The emotional state is evaluated by detecting changes in facial expressions such as smiles and surprise. This evaluation serves as a criterion for determining how satisfied the user is during the virtual try-on.

[0511] The virtual try-on function applies a server-generated simulation of cosmetics to the user's 3D model and presents it to the user on their device. Based on this try-on result, the user decides whether to purchase the product or if further adjustments are needed.

[0512] The device notifies the user of the emotion engine's analysis results in real time and adjusts suggestions based on satisfaction levels. For example, if the user's reaction to the try-on results is positive, the product is recommended as is; however, if the reaction is negative, an alternative solution is presented. This adjustment is also used when updating the generative model based on user feedback data and emotion data.

[0513] For example, if a user enters information about having dry skin and expresses surprise at the fitting results, the server will re-suggest a formula containing more moisturizing ingredients. This optimizes the user experience based on their emotions.

[0514] Thus, the present invention provides a system that enables cosmetic product recommendations that take user emotions into consideration, thereby further enhancing the provision of personalized cosmetics.

[0515] The following describes the processing flow.

[0516] Step 1:

[0517] Users input information about their skin, such as skin type, age, and allergy information, using a dedicated app or web interface. They also provide facial photos and videos for the fitting experience, uploading data necessary for emotional analysis.

[0518] Step 2:

[0519] The terminal encrypts the entered data and sends it to the server according to security protocols. The transmitted data is securely stored in a database based on the user ID.

[0520] Step 3:

[0521] The server supplies the received data to a generating AI model, which estimates the optimal cosmetic ingredients for the user's skin characteristics. The AI ​​model uses a historical cosmetic database and learned patterns to generate a list of ingredients.

[0522] Step 4:

[0523] The server uses the estimated ingredient information to generate chemical structures. These chemical structures form the basis for the formulation design of individual, personalized cosmetics.

[0524] Step 5:

[0525] The server uses an emotion engine to analyze emotional data extracted from the user's facial photos and videos. The emotion engine detects microexpressions and other features to evaluate the user's emotional state.

[0526] Step 6:

[0527] The server applies the generated cosmetic formulation onto a 3D model for virtual try-on and calculates the results along with the user's emotional evaluation.

[0528] Step 7:

[0529] The device displays real-time evaluation results from an emotion engine, along with a 3D model of the cosmetics being tried on. Users can then review this and understand their emotional satisfaction level.

[0530] Step 8:

[0531] Users make product purchase decisions based on virtual try-on results and emotional evaluations. They also input feedback on the results and send it to the server.

[0532] Step 9:

[0533] The server updates its AI model using the received feedback and emotional data to improve future cosmetic recommendations. This continuous use of data enables recommendations that better match user needs.

[0534] (Example 2)

[0535] 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."

[0536] Conventional cosmetic recommendation systems struggle to suggest the optimal cosmetics based on individual skin characteristics, and formulations based on specific ingredients are not sufficiently personalized. Furthermore, because they are provided without considering the user's emotional state, virtual try-on results do not necessarily improve user satisfaction. In addition, updating the generation AI model based on user feedback and adjusting the try-on results are often done manually, which is inefficient.

[0537] 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.

[0538] In this invention, the server includes means for inputting an individual's skin characteristics information, means for receiving and storing the skin characteristics information, means for using a generative AI model that estimates appropriate cosmetic materials based on the stored skin characteristics information, and means for adjusting and presenting fitting results based on the evaluated emotional state. This makes it possible to recommend personalized cosmetics that take into account individual skin characteristics and emotional states, and to provide a fitting experience that is highly satisfying to the user.

[0539] "Individual skin characteristics information" refers to data related to an individual's skin, such as skin condition and type, and information about cosmetics used.

[0540] A "generative AI model" is an artificial intelligence technology used to estimate the optimal cosmetic ingredients based on past data and market information.

[0541] "Means for generating chemical structures and designing formulations" refers to the process of calculating and designing chemical structures in order to translate estimated cosmetic ingredients into specific formulations.

[0542] "Virtual try-on" is a technology that applies generated cosmetics to a user's 3D model and provides the results visually.

[0543] "Emotional state" refers to the psychological and emotional responses analyzed from the user's facial expressions and actions.

[0544] "Means for adjusting and presenting fitting results" refers to a method of dynamically changing the content of a virtual fitting based on the results of an analysis of the user's emotional state and presenting it to the user.

[0545] This system provides personalized cosmetic recommendations based on the user's skin characteristics and emotional state. Specifically, users input their skin information and provide facial photos and videos through an application or web interface. This data is encrypted and securely transmitted from the device to the server.

[0546] The server analyzes the received skin information and uses a generative AI model in this process. The model uses past training data and market databases to estimate the optimal cosmetic ingredients. The estimated ingredients generate chemical structures and design formulations, creating a personalized cosmetic formula for the user.

[0547] In addition, the server uses an emotion engine to analyze the submitted facial photos and videos to identify the user's emotional state. This emotion analysis is performed based on the user's facial expressions, and the results are used to adjust the virtual try-on content. The generated cosmetics are then applied to the user's 3D model using virtual try-on technology and visually displayed on the device.

[0548] The device displays the fitting results in real time and makes suggestions based on the user's emotional state. For example, if a user has dry skin and expresses surprise at the fitting results, the server will suggest a different formula containing more moisturizing ingredients based on the user's emotions and skin characteristics.

[0549] An example of a prompt message would be, "Female, 30s, dry skin, feeling surprised. Suggest the most suitable cosmetic ingredients." In this way, the system provides more personalized cosmetic recommendations based on the user's skin characteristics and emotional state.

[0550] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0551] Step 1:

[0552] Users input their skin characteristics information through an application or web interface. Specifically, they input information such as their skin condition and type, and the cosmetics they use, and also provide facial photos and videos. This input data is temporarily stored on the device and transmitted to the server via a secure communication protocol. The output is sent to the server as skin information and facial expression data.

[0553] Step 2:

[0554] The server inputs the received skin information into a generating AI model. During this process, it creates a prompt sentence, for example, "Female in her 30s, dry skin type, current emotion: surprised." Based on this prompt, the AI ​​model uses past training data and a market database to estimate appropriate cosmetic ingredients. The output is a list of estimated cosmetic ingredients.

[0555] Step 3:

[0556] The server generates chemical structures based on estimated cosmetic ingredients and designs unique formulations. Specifically, it uses chemical software to create molecular models and assembles formulations accordingly. The output is formulation design data optimized for the user.

[0557] Step 4:

[0558] The server uses the provided facial photos and videos to analyze them with an emotion engine and identify the user's emotional state. This analysis inputs collected facial expression data into an analysis algorithm to evaluate the type and intensity of emotion. The output is the user's emotional status.

[0559] Step 5:

[0560] The server applies cosmetics generated by the virtual try-on function to the user's 3D model. Based on the results of the emotional state analysis, the server adjusts the try-on to provide the user with a highly satisfying visual experience. This try-on result is displayed in real time on the terminal. The output is the adjusted virtual try-on image.

[0561] Step 6:

[0562] The user reviews the virtual fitting results and provides feedback through their device. This feedback is sent to the server. The server uses this information to update the generated AI model, improving the accuracy of future suggestions. The output is the improved suggestions based on the updated AI model.

[0563] (Application Example 2)

[0564] 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."

[0565] The problem that this invention aims to solve is to improve individual satisfaction by enabling the proposal of optimal beauty materials that take into account individual emotions and skin information, thereby meeting individual needs that were difficult to achieve with the conventional provision of uniform beauty products. Conventional beauty products have difficulty reflecting consumer emotions and real-time feedback, and as a result, it is difficult to provide an optimal customer experience. In addition, there is a problem of insufficient interaction among consumers because it is not easy to share results with others.

[0566] 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.

[0567] In this invention, the server includes means for inputting an individual's biometric information, means for using a generation algorithm that estimates the optimal beauty material based on the stored biometric information, and means for acquiring an individual's emotions and adjusting the suggested beauty materials. This makes it possible to suggest beauty materials that have been adjusted in real time through virtual fitting based on an individual's skin information and emotion analysis, thereby increasing consumer satisfaction and promoting interaction among consumers by facilitating the sharing of results with others.

[0568] "Personal biometric information" refers to physiological data specific to that individual, such as skin condition and facial expression data.

[0569] A "generative algorithm" is a computational method used to estimate the optimal beauty ingredients based on the input data.

[0570] "Beauty ingredients" refer to chemical components and products used to improve skin condition and enhance appearance.

[0571] "Chemical representation" refers to the structure of a specific chemical component and describes the details of the cosmetic material that has been designed.

[0572] "Virtual application" refers to a technology that visually simulates the usage of digitally generated beauty products.

[0573] "Individual emotions" refer to data that indicates an individual's mental state, obtained through facial expressions, voice, and other means.

[0574] "Information infrastructure" refers to an electronic platform for sharing information among a large number of users.

[0575] The system for realizing this invention provides a platform for analyzing an individual's biometric information and emotions to suggest the most suitable beauty ingredients. Specifically, it has the following configuration.

[0576] First, the user inputs biometric information using a smart device. This device is equipped with a high-precision facial recognition camera that can capture the user's skin condition and facial expressions. This data is securely transmitted to a server via the device.

[0577] The server analyzes the received biometric information and compares it with a stored database. Using a generative AI model, it estimates cosmetic materials suitable for the individual's skin condition and generates chemical representations. Furthermore, by analyzing the user's facial expression data, it recognizes emotions and adjusts the suggested products accordingly. This process utilizes software that works in conjunction with an emotion analysis engine.

[0578] Beauty material suggestions are applied to the user's 3D model using virtual fitting technology and displayed in real time on the device. Users can review the results of this virtual fitting and, if satisfied, proceed with the purchase. Furthermore, it is possible to share the results of the virtual fitting with other users through the information infrastructure. The shared information serves as a reference for other users and is reflected in the system as feedback.

[0579] As a concrete example, a user puts on smart glasses and starts a session in a virtual store. The system analyzes the user's subtle facial expressions and customizes and suggests beauty products with lifting effects. If the user shows a positive reaction after trying them on, they are guided to make a purchase.

[0580] An example of a prompt message would be, "Based on the user's emotions and skin information, generate data suggesting highly moisturizing and lifting beauty ingredients," which would be input to the AI ​​model. This enables personalized suggestions and improves the user experience.

[0581] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0582] Step 1:

[0583] Users input their biometric information using a smart device equipped with a facial recognition camera. Facial images and facial expression data are captured, and this information is transmitted to a server via the device. The input data is securely transferred via a secure protocol.

[0584] Step 2:

[0585] The server analyzes the received biometric information. Specifically, it inputs data about the skin condition into a generative AI model to estimate appropriate cosmetic ingredients. The generative AI model utilizes past training data to output a chemical expression containing the optimal ingredients. In this process, machine learning algorithms analyze the characteristics of the data and construct the chemical formulation.

[0586] Step 3:

[0587] The server analyzes the user's emotions based on their facial expression data. Using an emotion analysis engine, it determines the emotional state from changes in facial expression and adjusts the suggested beauty products based on this information. It evaluates satisfaction with the emotional input and outputs suggested results that match the user's current situation and preferences.

[0588] Step 4:

[0589] The server applies estimated cosmetic materials, based on virtual fitting technology, to the user's 3D model. The simulation results are displayed in real-time on the terminal screen. The user reviews the virtual fitting results and evaluates their level of satisfaction. Based on the user's input, the next action (purchase, re-suggestion, etc.) is determined.

[0590] Step 5:

[0591] Users can share their virtual try-on results with other users through an information infrastructure. The server collects feedback from the shared data and aggregates the information to improve the overall system service. The shared user feedback is used to further refine the generative AI model.

[0592] In this way, it becomes possible to propose highly personalized beauty materials that utilize an individual's biometric information and emotions.

[0593] 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.

[0594] 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.

[0595] 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.

[0596] [Fourth Embodiment]

[0597] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0598] 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.

[0599] 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).

[0600] 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.

[0601] 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.

[0602] 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).

[0603] 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.

[0604] 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.

[0605] 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.

[0606] 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.

[0607] 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.

[0608] 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.

[0609] 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".

[0610] This invention is a system for providing personalized cosmetics based on individual users' skin information, and at its core is a generative AI model. The generative AI model estimates the optimal cosmetic ingredients based on detailed skin information provided by the user, such as skin type, age, and allergy information.

[0611] First, users enter their skin information using a dedicated app or web interface. This information may include skin type, age, allergy information, past cosmetic usage history, and personal preferences. After entry, this information is sent from the device to the server.

[0612] The server organizes and stores the received information in a database, and then inputs its contents into a generative AI model. This generative AI model is built on a large amount of cosmetic and medical data and is used to estimate the optimal combination of ingredients. Based on the estimated ingredients, the AI ​​model generates chemical structural formulas and designs specific formulations.

[0613] Next, the server provides a function that allows users to virtually try on the designed cosmetics in a virtual environment. This function allows users to virtually check the feel of the product using a 3D model before physically handling it. The results of this virtual try-on are displayed to the user via their terminal.

[0614] Furthermore, users can provide feedback to the system, including their impressions of using the product and suggestions for improvement. This feedback is collected by the server and used to continuously improve the generated AI model and propose new products. In this way, by incorporating user opinions, it becomes possible to provide cosmetics that are more tailored to individual needs.

[0615] For example, if a woman in her 30s has dry skin and specific allergies, the AI ​​model generates a formula based on the information she inputs, estimating appropriate ingredients and creating a cosmetic product that addresses both her dry skin and allergies. By virtually trying on this cosmetic product, she can check its effects and feel before actually trying the product.

[0616] Thus, the present invention provides a platform that allows users to utilize cosmetics optimized based on their own skin information, thereby realizing a more satisfying experience.

[0617] The following describes the processing flow.

[0618] Step 1:

[0619] Users log in to a dedicated app or web interface and enter skin information such as their skin type, age, allergy information, and past cosmetic usage history. They can also enter specific concerns and beauty goals.

[0620] Step 2:

[0621] The terminal organizes the entered data, securely encrypts it, and then sends it to the server. The transmitted data is linked to the user's unique ID.

[0622] Step 3:

[0623] The server saves the received data to a database. It then prepares the saved data for input into a generating AI model for analysis.

[0624] Step 4:

[0625] The server uses a generative AI model to estimate the optimal cosmetic ingredients based on the user's skin information. This estimation utilizes past research data and information on the ingredients of commercially available cosmetics.

[0626] Step 5:

[0627] The server generates chemical structural formulas based on estimated ingredients and designs personalized cosmetic formulations. This design is tailored to the user's unique needs.

[0628] Step 6:

[0629] The server generates a 3D model using the user's facial photograph to prepare a virtual try-on function for the designed cosmetics. Image processing technology is used to accurately capture the user's facial features.

[0630] Step 7:

[0631] The device applies the designed cosmetics to the generated 3D model and displays a virtual trial screen to the user. The user can visually check the appearance and feel of the cosmetics on the screen.

[0632] Step 8:

[0633] Users evaluate the product's suitability through a virtual trial. After the evaluation, they can decide whether to purchase the product and proceed with the purchase process.

[0634] Step 9:

[0635] The server collects user feedback and impressions and records them in a database. This feedback is used to improve the generative AI model and design future formulations.

[0636] (Example 1)

[0637] 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".

[0638] Providing optimal consumer products based on each user's individual biometric information is difficult and requires considerable time and expertise. Therefore, personalized product selection tailored to diverse needs is challenging, leading to user dissatisfaction. Furthermore, the lack of sufficient virtual trial environments means users cannot fully experience the effects of a product before trying it.

[0639] 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.

[0640] In this invention, the server includes means for receiving and recording the biometric information of individual users, means for using a generative model to estimate the optimal consumer product components based on the recorded biometric information, and means for displaying the designed consumer product as a virtual trial. This enables optimal product selection based on the user's individual needs and allows for a pre-trial experience through virtual trials.

[0641] "Individual users" refers to selected users who provide biometric information.

[0642] "Biometric information" refers to all information related to the body that is necessary for selecting consumer products, such as the skin texture, age, and allergy information of individual users.

[0643] A "generative model" refers to an automated computational method for estimating the optimal consumer product ingredients based on input data and selecting products accordingly.

[0644] "Chemical composition" refers to design information based on the molecular-level structure of the estimated components.

[0645] "Virtual trial" refers to a feature that allows users to check the usability of a designed consumer product using computer graphics or simulations, without physically trying it out.

[0646] "User feedback" refers to the collective term for feedback provided by users, including evaluations and opinions after virtual trials or product use.

[0647] "Infrastructure" refers to the electronic network and software environment for sharing information and results among users.

[0648] This invention is a system for providing optimal consumer products based on the biometric information of individual users. Embodiments thereof are shown below.

[0649] Users input their biometric information using a dedicated app or web interface. Specifically, this biometric information includes skin texture, age, and allergy information. In addition, personal preferences and past consumer product usage history can also be entered. An example of prompt text input would be: "Female, 30s, dry skin, allergies, preferred highly moisturizing creams in the past."

[0650] The terminal sends the entered biometric information to the server as a data packet. The server receives the biometric information, organizes it, and stores it in a database. A database management system is used in this process.

[0651] The server analyzes the stored information and inputs it into a generative AI model. This generative AI model is designed based on a large amount of medical and cosmetic data and estimates the optimal product ingredients from the received information. This AI model utilizes machine learning frameworks and natural language processing techniques.

[0652] Furthermore, the generation AI model generates the estimated chemical composition of the ingredients and designs a specific product formulation. To allow users to preview the feel of the designed product beforehand, the server provides a virtual trial environment. This virtual trial environment is built using 3D modeling software, allowing users to visually and interactively experience using the product.

[0653] Finally, after experiencing the virtual trial, users provide feedback on their experience and areas for improvement to the server via the app or web interface. The server records this feedback in a database, which helps in the continuous improvement of the generative AI model. This allows the generative AI model to learn from the new feedback, enabling more accurate component estimation.

[0654] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0655] Step 1:

[0656] Users enter their biometric information via a dedicated app or web interface. Input fields include skin texture, age, and allergy information, and optionally, past product usage history and preferences. This input is stored on the device in digital format and prepared for transmission.

[0657] Step 2:

[0658] The terminal packets the entered biometric information and sends it to the server via a secure communication protocol. The input data is transmitted as biometric information and received by the server as individual data entries. This creates a foundation for efficient data processing.

[0659] Step 3:

[0660] The server analyzes biometric information received from the terminal, classifies the information into the necessary categories, and stores it in the database. The entered biometric information is divided into fields, each tagged, and stored. The database management system supports this process, maintaining data reliability.

[0661] Step 4:

[0662] The server sends the organized biometric information to a generating AI model. The AI ​​model analyzes the input using prompts and estimates the optimal product ingredients. This process utilizes data science techniques to structure the input data and generate meaningful output. The output is provided as a list of estimated ingredients.

[0663] Step 5:

[0664] Based on the estimated components obtained from the generating AI model, the server generates a chemical composition and designs the product. The AI ​​system considers the chemical properties of the estimated components and designs the optimal formulation. Specific product formulation information is obtained as output.

[0665] Step 6:

[0666] The server sends the designed product to a virtual trial environment, providing the user with a virtual trial experience. Here, 3D modeling software is used, allowing the user to visually confirm the product's usability. The output of the virtual trial is a 3D display rendered on the user's terminal.

[0667] Step 7:

[0668] After the virtual trial, users submit feedback on their experience and areas for improvement. This feedback is sent to the server in text format and stored in a database. This feedback is used as a dataset for improving the generative AI model, contributing to improved component estimation.

[0669] (Application Example 1)

[0670] 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".

[0671] In modern society, selecting cosmetics that take into account diverse skin types and individual allergies is a complex task for consumers. Many users lack the information to understand which cosmetics are best suited to their skin condition, making it difficult to choose cosmetics for daily use. There is a need for a system that solves this problem and efficiently suggests personalized and optimal cosmetics to individual users.

[0672] 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.

[0673] In this invention, the server includes means for inputting an individual's skin information, means for receiving and storing the skin information, and means for using a generative model that estimates the optimal cosmetic ingredients based on the stored skin information. This makes it possible to estimate the optimal cosmetic ingredients based on the individual user's skin information. In addition, users can check the feel of the suggested cosmetics in advance through virtual try-on, enabling them to make purchases based on clear judgments.

[0674] "Personal skin information" refers to individual data necessary for selecting cosmetics, such as the user's skin type, age, and allergy information.

[0675] A "generative model" is an artificial intelligence-based algorithm used to estimate appropriate cosmetic ingredients from received data.

[0676] "Methods for generating chemical structural formulas and designing formulations" refers to the process of determining the specific chemical composition based on estimated components and designing the optimal cosmetic product.

[0677] "A means of displaying as a virtual try-on" refers to a technology that allows users to view a visual image of suggested cosmetics on a digital device.

[0678] "A means of displaying and allowing users to confirm in real time" refers to a function that immediately presents the results of cosmetic selection to the user via a terminal, allowing them to check the feel and appearance of the product.

[0679] "Image processing means" refers to technology that uses devices such as smartphones and smart glasses to capture skin information in a real-world environment and analyze it as data.

[0680] The system implementing this invention enables personalized product selection by suggesting the most suitable cosmetics for each individual user and allowing them to confirm the feel of the products through virtual try-on. First, the user captures real-time images of their skin using a smartphone or smart glasses. This information is analyzed using image processing libraries such as OpenCV and TensorFlow to extract characteristic skin information.

[0681] Data sent from the terminal to the server is stored and analyzed in the cloud. This data processing uses generative AI models (e.g., PyTorch and TensorFlow) to suggest optimal cosmetic ingredients based on the input data. These generative AI models utilize a large-scale cosmetics database and medical data to design individual products tailored to each user's characteristics.

[0682] The server further provides virtual try-on services through 3D models generated using Unity or Unreal Engine. Users can virtually try on suggested cosmetics in a virtual environment via their devices and check the visual effects of the products. This system also collects usage feedback, which is used for the continuous improvement of the AI ​​model.

[0683] As a concrete example of its use, a female user in her 30s could use her smartphone to scan her face, and the generating AI model could suggest a specialized moisturizing cream that is optimal for dry skin and also addresses allergies. An example of the prompt text for the generating AI model in this case would be, "Female, 30s, dry skin, glycerin allergy. Please suggest the optimal moisturizing cream ingredients." The user can virtually try on the suggested cream and check its effects beforehand, enabling a more confident purchase decision.

[0684] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0685] Step 1:

[0686] The user takes a picture of their skin using a smartphone or smart glasses. The input here is a real-time image of the skin, acquired using the device's camera. The output is analyzable skin image data.

[0687] Step 2:

[0688] The device analyzes the acquired skin image data using image processing libraries such as OpenCV and TensorFlow. In this step, skin characteristics are extracted and digital signal processing is performed. The input is skin image data, and the output is characteristic information, such as skin texture and color information.

[0689] Step 3:

[0690] Skin characteristic information is transmitted from the terminal to the server. The server receives this information and stores it in a database. The input is skin characteristic information, and the output is database update information.

[0691] Step 4:

[0692] The server inputs the stored skin characteristic information into a generating AI model. The generating AI model utilizes a large amount of cosmetic data to estimate the optimal cosmetic ingredients for the user. The input consists of skin characteristic information and prompts for the AI ​​model, and the output is the estimated cosmetic ingredients.

[0693] Step 5:

[0694] The server generates chemical structural formulas based on estimated cosmetic ingredients and constructs 3D virtual models using Unity or Unreal Engine. The input is cosmetic ingredients, and the output is a 3D virtual try-on model.

[0695] Step 6:

[0696] The server sends the generated 3D virtual fitting model to the terminal. The user views this model through the terminal and performs a virtual try-on. The input is the 3D virtual fitting model, and the output is the user's fitting feedback.

[0697] Step 7:

[0698] The user enters feedback and sends it to the server. The server collects this feedback and uses it to improve the generated AI model. The input is user feedback after trying on the product, and the output is information for improving the AI ​​model.

[0699] 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.

[0700] This invention further enhances personalized cosmetic recommendations through a system incorporating an emotion engine that recognizes user emotions. This system, in addition to estimating optimal cosmetic ingredients based on the user's skin information, also considers the user's emotions, enabling more personalized cosmetic recommendations.

[0701] First, users input their skin information through an app or web interface, and also provide facial photos and videos, enabling emotion analysis. This data is securely transmitted from the device to the server.

[0702] The server inputs the received skin information into a generating AI model to estimate the optimal cosmetic ingredients. This process utilizes past training data and a market database of cosmetics. The estimated ingredients are then materialized as chemical structural formulas, and individual formulations are designed.

[0703] Furthermore, the server uses an emotion engine to analyze the user's emotional state from the submitted facial photos and video data. The emotional state is evaluated by detecting changes in facial expressions such as smiles and surprise. This evaluation serves as a criterion for determining how satisfied the user is during the virtual try-on.

[0704] The virtual try-on function applies a server-generated simulation of cosmetics to the user's 3D model and presents it to the user on their device. Based on this try-on result, the user decides whether to purchase the product or if further adjustments are needed.

[0705] The device notifies the user of the emotion engine's analysis results in real time and adjusts suggestions based on satisfaction levels. For example, if the user's reaction to the try-on results is positive, the product is recommended as is; however, if the reaction is negative, an alternative solution is presented. This adjustment is also used when updating the generative model based on user feedback data and emotion data.

[0706] For example, if a user enters information about having dry skin and expresses surprise at the fitting results, the server will re-suggest a formula containing more moisturizing ingredients. This optimizes the user experience based on their emotions.

[0707] Thus, the present invention provides a system that enables cosmetic product recommendations that take user emotions into consideration, thereby further enhancing the provision of personalized cosmetics.

[0708] The following describes the processing flow.

[0709] Step 1:

[0710] Users input information about their skin, such as skin type, age, and allergy information, using a dedicated app or web interface. They also provide facial photos and videos for the fitting experience, uploading data necessary for emotional analysis.

[0711] Step 2:

[0712] The terminal encrypts the entered data and sends it to the server according to security protocols. The transmitted data is securely stored in a database based on the user ID.

[0713] Step 3:

[0714] The server supplies the received data to a generating AI model, which estimates the optimal cosmetic ingredients for the user's skin characteristics. The AI ​​model uses a historical cosmetic database and learned patterns to generate a list of ingredients.

[0715] Step 4:

[0716] The server uses the estimated ingredient information to generate chemical structures. These chemical structures form the basis for the formulation design of individual, personalized cosmetics.

[0717] Step 5:

[0718] The server uses an emotion engine to analyze emotional data extracted from the user's facial photos and videos. The emotion engine detects microexpressions and other features to evaluate the user's emotional state.

[0719] Step 6:

[0720] The server applies the generated cosmetic formulation onto a 3D model for virtual try-on and calculates the results along with the user's emotional evaluation.

[0721] Step 7:

[0722] The device displays real-time evaluation results from an emotion engine, along with a 3D model of the cosmetics being tried on. Users can then review this and understand their emotional satisfaction level.

[0723] Step 8:

[0724] Users make product purchase decisions based on virtual try-on results and emotional evaluations. They also input feedback on the results and send it to the server.

[0725] Step 9:

[0726] The server updates its AI model using the received feedback and emotional data to improve future cosmetic recommendations. This continuous use of data enables recommendations that better match user needs.

[0727] (Example 2)

[0728] 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".

[0729] Conventional cosmetic recommendation systems struggle to suggest the optimal cosmetics based on individual skin characteristics, and formulations based on specific ingredients are not sufficiently personalized. Furthermore, because they are provided without considering the user's emotional state, virtual try-on results do not necessarily improve user satisfaction. In addition, updating the generation AI model based on user feedback and adjusting the try-on results are often done manually, which is inefficient.

[0730] 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.

[0731] In this invention, the server includes means for inputting an individual's skin characteristics information, means for receiving and storing the skin characteristics information, means for using a generative AI model that estimates appropriate cosmetic materials based on the stored skin characteristics information, and means for adjusting and presenting fitting results based on the evaluated emotional state. This makes it possible to recommend personalized cosmetics that take into account individual skin characteristics and emotional states, and to provide a fitting experience that is highly satisfying to the user.

[0732] "Individual skin characteristics information" refers to data related to an individual's skin, such as skin condition and type, and information about cosmetics used.

[0733] A "generative AI model" is an artificial intelligence technology used to estimate the optimal cosmetic ingredients based on past data and market information.

[0734] "Means for generating chemical structures and designing formulations" refers to the process of calculating and designing chemical structures in order to translate estimated cosmetic ingredients into specific formulations.

[0735] "Virtual try-on" is a technology that applies generated cosmetics to a user's 3D model and provides the results visually.

[0736] "Emotional state" refers to the psychological and emotional responses analyzed from the user's facial expressions and actions.

[0737] "Means for adjusting and presenting fitting results" refers to a method of dynamically changing the content of a virtual fitting based on the results of an analysis of the user's emotional state and presenting it to the user.

[0738] This system provides personalized cosmetic recommendations based on the user's skin characteristics and emotional state. Specifically, users input their skin information and provide facial photos and videos through an application or web interface. This data is encrypted and securely transmitted from the device to the server.

[0739] The server analyzes the received skin information and uses a generative AI model in this process. The model uses past training data and market databases to estimate the optimal cosmetic ingredients. The estimated ingredients generate chemical structures and design formulations, creating a personalized cosmetic formula for the user.

[0740] In addition, the server uses an emotion engine to analyze the submitted facial photos and videos to identify the user's emotional state. This emotion analysis is performed based on the user's facial expressions, and the results are used to adjust the virtual try-on content. The generated cosmetics are then applied to the user's 3D model using virtual try-on technology and visually displayed on the device.

[0741] The device displays the fitting results in real time and makes suggestions based on the user's emotional state. For example, if a user has dry skin and expresses surprise at the fitting results, the server will suggest a different formula containing more moisturizing ingredients based on the user's emotions and skin characteristics.

[0742] An example of a prompt message would be, "Female, 30s, dry skin, feeling surprised. Suggest the most suitable cosmetic ingredients." In this way, the system provides more personalized cosmetic recommendations based on the user's skin characteristics and emotional state.

[0743] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0744] Step 1:

[0745] Users input their skin characteristics information through an application or web interface. Specifically, they input information such as their skin condition and type, and the cosmetics they use, and also provide facial photos and videos. This input data is temporarily stored on the device and transmitted to the server via a secure communication protocol. The output is sent to the server as skin information and facial expression data.

[0746] Step 2:

[0747] The server inputs the received skin information into a generating AI model. During this process, it creates a prompt sentence, for example, "Female in her 30s, dry skin type, current emotion: surprised." Based on this prompt, the AI ​​model uses past training data and a market database to estimate appropriate cosmetic ingredients. The output is a list of estimated cosmetic ingredients.

[0748] Step 3:

[0749] The server generates chemical structures based on estimated cosmetic ingredients and designs unique formulations. Specifically, it uses chemical software to create molecular models and assembles formulations accordingly. The output is formulation design data optimized for the user.

[0750] Step 4:

[0751] The server uses the provided facial photos and videos to analyze them with an emotion engine and identify the user's emotional state. This analysis inputs collected facial expression data into an analysis algorithm to evaluate the type and intensity of emotion. The output is the user's emotional status.

[0752] Step 5:

[0753] The server applies cosmetics generated by the virtual try-on function to the user's 3D model. Based on the results of the emotional state analysis, the server adjusts the try-on to provide the user with a highly satisfying visual experience. This try-on result is displayed in real time on the terminal. The output is the adjusted virtual try-on image.

[0754] Step 6:

[0755] The user reviews the virtual fitting results and provides feedback through their device. This feedback is sent to the server. The server uses this information to update the generated AI model, improving the accuracy of future suggestions. The output is the improved suggestions based on the updated AI model.

[0756] (Application Example 2)

[0757] 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".

[0758] The problem that this invention aims to solve is to improve individual satisfaction by enabling the proposal of optimal beauty materials that take into account individual emotions and skin information, thereby meeting individual needs that were difficult to achieve with the conventional provision of uniform beauty products. Conventional beauty products have difficulty reflecting consumer emotions and real-time feedback, and as a result, it is difficult to provide an optimal customer experience. In addition, there is a problem of insufficient interaction among consumers because it is not easy to share results with others.

[0759] 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.

[0760] In this invention, the server includes means for inputting an individual's biometric information, means for using a generation algorithm that estimates the optimal beauty material based on the stored biometric information, and means for acquiring an individual's emotions and adjusting the suggested beauty materials. This makes it possible to suggest beauty materials that have been adjusted in real time through virtual fitting based on an individual's skin information and emotion analysis, thereby increasing consumer satisfaction and promoting interaction among consumers by facilitating the sharing of results with others.

[0761] "Personal biometric information" refers to physiological data specific to that individual, such as skin condition and facial expression data.

[0762] A "generative algorithm" is a computational method used to estimate the optimal beauty ingredients based on the input data.

[0763] "Beauty ingredients" refer to chemical components and products used to improve skin condition and enhance appearance.

[0764] "Chemical representation" refers to the structure of a specific chemical component and describes the details of the cosmetic material that has been designed.

[0765] "Virtual application" refers to a technology that visually simulates the usage of digitally generated beauty products.

[0766] "Individual emotions" refer to data that indicates an individual's mental state, obtained through facial expressions, voice, and other means.

[0767] "Information infrastructure" refers to an electronic platform for sharing information among a large number of users.

[0768] The system for realizing this invention provides a platform for analyzing an individual's biometric information and emotions to suggest the most suitable beauty ingredients. Specifically, it has the following configuration.

[0769] First, the user inputs biometric information using a smart device. This device is equipped with a high-precision facial recognition camera that can capture the user's skin condition and facial expressions. This data is securely transmitted to a server via the device.

[0770] The server analyzes the received biometric information and compares it with a stored database. Using a generative AI model, it estimates cosmetic materials suitable for the individual's skin condition and generates chemical representations. Furthermore, by analyzing the user's facial expression data, it recognizes emotions and adjusts the suggested products accordingly. This process utilizes software that works in conjunction with an emotion analysis engine.

[0771] Beauty material suggestions are applied to the user's 3D model using virtual fitting technology and displayed in real time on the device. Users can review the results of this virtual fitting and, if satisfied, proceed with the purchase. Furthermore, it is possible to share the results of the virtual fitting with other users through the information infrastructure. The shared information serves as a reference for other users and is reflected in the system as feedback.

[0772] As a concrete example, a user puts on smart glasses and starts a session in a virtual store. The system analyzes the user's subtle facial expressions and customizes and suggests beauty products with lifting effects. If the user shows a positive reaction after trying them on, they are guided to make a purchase.

[0773] An example of a prompt message would be, "Based on the user's emotions and skin information, generate data suggesting highly moisturizing and lifting beauty ingredients," which would be input to the AI ​​model. This enables personalized suggestions and improves the user experience.

[0774] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0775] Step 1:

[0776] Users input their biometric information using a smart device equipped with a facial recognition camera. Facial images and facial expression data are captured, and this information is transmitted to a server via the device. The input data is securely transferred via a secure protocol.

[0777] Step 2:

[0778] The server analyzes the received biometric information. Specifically, it inputs data about the skin condition into a generative AI model to estimate appropriate cosmetic ingredients. The generative AI model utilizes past training data to output a chemical expression containing the optimal ingredients. In this process, machine learning algorithms analyze the characteristics of the data and construct the chemical formulation.

[0779] Step 3:

[0780] The server analyzes the user's emotions based on their facial expression data. Using an emotion analysis engine, it determines the emotional state from changes in facial expression and adjusts the suggested beauty products based on this information. It evaluates satisfaction with the emotional input and outputs suggested results that match the user's current situation and preferences.

[0781] Step 4:

[0782] The server applies estimated cosmetic materials, based on virtual fitting technology, to the user's 3D model. The simulation results are displayed in real-time on the terminal screen. The user reviews the virtual fitting results and evaluates their level of satisfaction. Based on the user's input, the next action (purchase, re-suggestion, etc.) is determined.

[0783] Step 5:

[0784] Users can share their virtual try-on results with other users through an information infrastructure. The server collects feedback from the shared data and aggregates the information to improve the overall system service. The shared user feedback is used to further refine the generative AI model.

[0785] In this way, it becomes possible to propose highly personalized beauty materials that utilize an individual's biometric information and emotions.

[0786] 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.

[0787] 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.

[0788] 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.

[0789] 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.

[0790] 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.

[0791] 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.

[0792] 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.

[0793] 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.

[0794] 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."

[0795] 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.

[0796] 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.

[0797] 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.

[0798] 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.

[0799] 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.

[0800] 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.

[0801] 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.

[0802] 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.

[0803] 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.

[0804] 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.

[0805] 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.

[0806] 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 as being incorporated by reference.

[0807] The following is further disclosed regarding the embodiments described above.

[0808] (Claim 1)

[0809] A means of inputting personal skin information,

[0810] Means for receiving and storing the aforementioned skin information,

[0811] A means of using a generative model that estimates the optimal cosmetic ingredients based on the stored skin information,

[0812] A means for generating a chemical structural formula based on the estimated components and designing a formulation,

[0813] A means for displaying the aforementioned formulated cosmetics as a virtual try-on,

[0814] A means for the user to confirm the results of the virtual try-on,

[0815] A system that includes this.

[0816] (Claim 2)

[0817] The system according to claim 1, further comprising means for receiving user feedback and updating the generative model.

[0818] (Claim 3)

[0819] The system according to claim 1, further comprising means for providing a platform for sharing the results of the virtual try-on with other users.

[0820] "Example 1"

[0821] (Claim 1)

[0822] A means of inputting biometric information of individual users,

[0823] The means for receiving and recording the aforementioned biological information,

[0824] A means of using a generative model that estimates the optimal ingredients of a consumer product based on the recorded biological information,

[0825] A means for generating a chemical composition based on the estimated components and designing a product,

[0826] A means for displaying the consumer product designed as a virtual trial,

[0827] A means for the user to verify the results of the virtual trial,

[0828] A system that includes this.

[0829] (Claim 2)

[0830] The system according to claim 1, further comprising means for receiving user return information and updating the generation model.

[0831] (Claim 3)

[0832] The system according to claim 1, further comprising means for providing a platform for sharing the results of the virtual trial with other users.

[0833] "Application Example 1"

[0834] (Claim 1)

[0835] A means of inputting personal skin information,

[0836] Means for receiving and storing the aforementioned skin information,

[0837] A means of using a generative model that estimates the optimal cosmetic ingredients based on the stored skin information,

[0838] A means for generating a chemical structural formula based on the estimated components and designing a formulation,

[0839] A means for displaying the aforementioned formulated cosmetics as a virtual try-on,

[0840] A means for displaying the results of the virtual fitting in real time and allowing the user to confirm them,

[0841] Image processing means for acquiring skin information in a real environment,

[0842] A system that includes this.

[0843] (Claim 2)

[0844] The system according to claim 1, further comprising means for receiving user feedback and updating the generative model.

[0845] (Claim 3)

[0846] The system according to claim 1, further comprising means for providing a platform for sharing the results of the virtual try-on with other users.

[0847] "Example 2 of combining an emotion engine"

[0848] (Claim 1)

[0849] A means of inputting personal skin characteristic information,

[0850] Means for receiving and storing the aforementioned skin characteristic information,

[0851] A means of using a generative AI model that estimates appropriate cosmetic materials based on the stored skin characteristic information,

[0852] A means for generating a chemical structure and designing a formulation based on the estimated materials,

[0853] A means for displaying the aforementioned formulated cosmetics as a virtual try-on,

[0854] A means for receiving the results of the virtual fitting,

[0855] A method for analyzing facial expression data to evaluate the user's emotional state,

[0856] A method for adjusting and presenting fitting results based on the evaluated emotional state,

[0857] A system that includes this.

[0858] (Claim 2)

[0859] The system according to claim 1, further comprising means for receiving user emotional evaluations and feedback and updating the generating AI model.

[0860] (Claim 3)

[0861] The system according to claim 1, further comprising means for providing a platform for sharing the results of the virtual try-on and emotional evaluation with other consumers.

[0862] "Application example 2 when combining with an emotional engine"

[0863] (Claim 1)

[0864] A means of inputting personal biometric information,

[0865] Means for receiving and storing the aforementioned biological information,

[0866] A means of using a generation algorithm that estimates the optimal beauty material based on the stored biological information,

[0867] A means for generating a chemical representation and designing based on the estimated material,

[0868] A means for presenting the aforementioned designed cosmetic material as a virtual attachment,

[0869] A means for an individual to confirm the results of the virtual fitting,

[0870] A means for acquiring an individual's emotions and adjusting the proposed beauty materials,

[0871] A system that includes this.

[0872] (Claim 2)

[0873] The system according to claim 1, further comprising means for receiving feedback based on individual emotions and updating the generation algorithm.

[0874] (Claim 3)

[0875] The system according to claim 1, further comprising means for providing an information infrastructure for sharing the results of the virtual fitting with other users. [Explanation of Symbols]

[0876] 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 of inputting personal skin information, Means for receiving and storing the aforementioned skin information, A means of using a generative model that estimates the optimal cosmetic ingredients based on the stored skin information, A means for generating a chemical structural formula based on the estimated components and designing a formulation, A means for displaying the aforementioned formulated cosmetics as a virtual try-on, A means for the user to confirm the results of the virtual try-on, A system that includes this.

2. The system according to claim 1, further comprising means for receiving user feedback and updating the generation model.

3. The system according to claim 1, further comprising means for providing a platform for sharing the results of the virtual try-on with other users.

Images