system

Abstract

We provide the system. [Solution] Means for collecting information about customers' biometrics, A means for generating a chemical structure using a generative model based on the aforementioned information, A means for testing the product in a virtual environment based on the generated chemical structure, A means for presenting the trial results in the aforementioned virtual environment to the customer, 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 persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a 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 conventional cosmetics market, there is a problem of lack of personalization by uniformly providing products that meet various consumer needs. In particular, there is a problem that personalization based on consumers' biological information is insufficient, and consumers cannot efficiently select products optimal for their skin.

Means for Solving the Problems

[0005] This invention solves the above-mentioned problems by providing a system that collects information about a customer's biological system and generates an optimal chemical structure using a generative model based on that information. Based on the generated chemical structure, it is possible to test the product in a virtual environment, and by presenting the results to the customer, personalized product selection is realized. Furthermore, a means is provided to share the generated product information with others, and by utilizing customer feedback information to improve the generative model, continuous product improvement is achieved.

[0006] "Customer biometric information" refers to individual data specific to each consumer, such as their skin type, allergies, and skin condition.

[0007] A "generative model" refers to an algorithm and computational method for automatically generating the optimal chemical structure formula based on given input data.

[0008] "Chemical structure" refers to the molecular structure of a particular cosmetic ingredient, and this structure determines the characteristics and functions of the ingredient.

[0009] A "virtual environment" refers to a simulation space reproduced on a computer, where users can try out products based on chemical structures they have generated.

[0010] "Trial results" refers to the visual and effective feedback obtained from using the product in a virtual environment.

[0011] "Means of sharing product information with others" refers to a function that allows users to view or discuss the generated personalized cosmetic data with other users via online platforms, etc.

[0012] "Feedback information" refers to the opinions and evaluations that users provide about products they have tried, and generative models and products are improved based on this feedback. [Brief explanation of the drawing]

[0013] [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]

[0014] An example of an embodiment of the system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] 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.

[0017] 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.

[0018] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0019] 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).

[0020] 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."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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".

[0034] This invention relates to a system that generates personalized cosmetics based on a customer's biological information and allows them to test the effects of these cosmetics in a virtual environment. This system is implemented through the interaction of a server, a terminal, and a user. Specific embodiments are described below.

[0035] First, the user accesses the device via an interface and enters information about their skin. This includes skin type, allergies, and specific skin concerns (e.g., dryness, sensitivity, acne, etc.). The device collects this information and sends the data to the server.

[0036] The server analyzes the received customer information and runs a generative model based on that information. The generative model includes an algorithm for generating appropriate chemical structures from the input data. The server uses this model to generate structural formulas of chemical components that meet the customer's needs. The generated chemical structures are stored in the server's internal database and compared with existing component data to verify their safety and efficacy.

[0037] Next, the server sends the generated chemical structure information to the terminal. The terminal receives this information and activates the virtual fitting system. The virtual fitting system allows the user to input their own facial data and simulate the feel of the generated cosmetics in real time. This allows the user to check the fit and visual effect of the product in a virtual environment without having to physically try it out.

[0038] Finally, users can provide their evaluation of the product they have tried through their device. This feedback information is sent back to the server and stored in a database, where it is used to further improve the accuracy of the generative model and develop new products. Furthermore, if the user wishes, they can publish information about the generated product on a platform where it can be shared with others, allowing for interaction with other users.

[0039] The following is a specific example. For instance, if a woman in her 20s with dry skin and allergies uses this system, the server will suggest moisturizing ingredients such as hyaluronic acid and ceramides, and she can try out the effects of the products in a virtual environment. This entire process makes it easier to select cosmetics that are more suitable for her.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The user uses a device to input information about their skin. This includes skin type, allergy information, and specific skin concerns. The device formats the entered information and prepares it to send the data to the server.

[0043] Step 2:

[0044] The terminal sends input information to the server. The server receives this information and begins data analysis. Specifically, it performs data analysis to assess the integrity of the information and label data related to lifestyle.

[0045] Step 3:

[0046] The server runs a generative model using the customer information it receives. The model generates the optimal chemical structure for cosmetic ingredients based on the input data. The generated chemical structure is stored in a database on the server.

[0047] Step 4:

[0048] The server compares and verifies the safety and effectiveness of the generated chemical structures with existing component data. If there are any issues with safety or effectiveness, the model is readjusted and run again.

[0049] Step 5:

[0050] The server transfers verified chemical structure information to the terminal. Based on this information, the terminal prepares the virtual fitting system.

[0051] Step 6:

[0052] The user begins a virtual try-on on the device. Based on the user's facial data, the device simulates the feel of the generated cosmetics in real time. This simulation allows the user to evaluate the appearance and intended use of the product.

[0053] Step 7:

[0054] The user reviews the results of the virtual try-on and enters their evaluation and feedback into the device. The device collects this feedback and sends it to the server.

[0055] Step 8:

[0056] The server receives feedback and stores it in the database. This data is used to improve future generative models and develop new products. Additionally, if the user wishes, they can share the generated product information through the platform.

[0057] (Example 1)

[0058] 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."

[0059] In the existing cosmetics market, there is a problem in that personalization based on individual user biometric information is not sufficiently implemented, making it difficult for users to choose products that suit their skin. Furthermore, physical samples are required to try products, and the trial process is time-consuming and costly. As a result, improving consumer satisfaction and the efficient operation of the market are hindered.

[0060] 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.

[0061] In this invention, the server includes means for receiving information about the user's biological information using an information terminal, means for transmitting the received information to a data server, and means for automatically generating the structure of a chemical substance using a model based on the information. This makes it possible to personalize cosmetics to suit the user and to quickly and efficiently provide the optimal product through trial use in a virtual environment.

[0062] An "information terminal" is a computer device used by users to input and receive biometric information.

[0063] A "data server" is a central processing unit used to store and analyze received information.

[0064] "Biological information" refers to data related to an individual's physical characteristics, such as the user's skin type, allergy information, and skin concerns.

[0065] A "generative AI model" is an artificial intelligence system that has an algorithm for automatically generating the appropriate chemical structure based on input information.

[0066] "The structure of a chemical substance" is data that represents the molecular arrangement of a compound suitable for a specific application.

[0067] A "virtual trial environment" is a computer-generated environment that allows users to simulate the feel and visual effects of cosmetics.

[0068] "Means of visual presentation" refer to display devices or software that allow users to visually confirm the results of a virtual trial.

[0069] "Communication means" refers to a network interface for exchanging generated product information with other users or external systems.

[0070] "Evaluation information" refers to data that includes opinions and feedback provided by users regarding a product.

[0071] A "storage device" is a hardware or software component used to store information for extended periods within a data server.

[0072] This shows an embodiment for carrying out the invention.

[0073] This invention embodies a system that realizes the generation and virtual trial of personalized cosmetics through interaction between a server, a terminal, and a user. Specifically, an information terminal receives information about the user's skin and transmits it to a data server. The terminal can be a general-purpose computer or mobile device, and data input is performed via a user interface.

[0074] The server functions as a data server, inputting received information into a generating AI model. This model uses state-of-the-art machine learning algorithms to automatically generate chemical structures based on the user's skin information. The generated structures are compared to an internal database to verify their safety and efficacy. The server leverages high-performance computing to perform rapid data processing.

[0075] The structural information of the generated chemical substances is transmitted to the terminal. The terminal provides a virtual trial environment, allowing the user to directly simulate the feel of using the generated cosmetics in this virtual space. The user can use the terminal's camera to capture facial data and visually confirm the effects of the cosmetics on the display.

[0076] For example, if a user enters the prompt "I have dry skin and allergies, so I would like a product with high moisturizing effects," the server will use a generative AI model to generate chemical structures containing hyaluronic acid and ceramides. Based on this information, the user can then verify the product's effectiveness in a virtual environment. This allows users to select the most suitable cosmetics for themselves without having to physically try them out.

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

[0078] Step 1:

[0079] Users input skin-related information through their device. Specifically, they fill in their skin type, allergies, and specific skin concerns in a form provided by the user interface. The entered data is appropriately formatted and sent to the data server as information packets.

[0080] Step 2:

[0081] The server receives data transmitted from the terminal and feeds it to a generating AI model. Based on the input user data, the AI ​​model generates chemical structures using a specific algorithm. During this process, data analysis is performed to obtain the optimal chemical structural formula for the user. The generated structures are stored in an internal database and compared with existing data.

[0082] Step 3:

[0083] The server transmits the generated chemical structure information to the terminal. The terminal uses the received chemical structure information to launch a virtual trial system and presents it to the user. Specifically, the terminal's camera is used to capture the user's facial data and simulate the feel of using the cosmetic in real time. As output, the trial results are displayed on the screen, which the user can visually confirm.

[0084] Step 4:

[0085] Users enter their evaluations of the products they have tried. The device collects this feedback information and sends it back to the server. The submitted evaluation data is recorded in the server's database and used to train a generative AI model. This information is used to improve existing products and develop new ones.

[0086] (Application Example 1)

[0087] 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."

[0088] To provide a system that suggests personalized cosmetics based on user characteristics and allows users to verify their effectiveness without actually trying them. Furthermore, to solve the problem of making it easier for users to select the optimal product by visually presenting the user experience in an easy-to-understand way. Additionally, to improve the accuracy of the generative model based on the acquired information, thereby improving the quality of future suggestions.

[0089] 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.

[0090] In this invention, the server includes means for collecting information about the customer's biological characteristics, means for generating a chemical structure using a generative model based on the information, means for trying out the product in a virtual environment based on the generated chemical structure, and means for performing real-time modeling using three-dimensional space to visualize the user experience during the virtual trial. This makes it possible for users to visually confirm cosmetics that are suitable for them without actually trying them.

[0091] A "customer" is an individual or group that uses a service.

[0092] "Biological information" refers to information about an individual's skin type, whether or not they have allergies, and specific skin concerns.

[0093] A "generative model" is a program that includes an algorithm for generating chemical structures from input data.

[0094] "Chemical structure" refers to information that describes the molecular structure of a specific chemical component.

[0095] A "virtual environment" is a simulation space composed of a computer-generated three-dimensional space.

[0096] "Trial use" refers to the act of virtually experiencing the effects and feel of a product.

[0097] "A method for performing real-time modeling using three-dimensional space" refers to a technology that visualizes the user's face and skin information in three dimensions and instantly displays the product's effects.

[0098] This invention provides a system that proposes personalized cosmetics to users and allows them to virtually try them out. The user first inputs information about their skin via a terminal. This information includes skin type, allergy status, and specific skin concerns, and this data is transmitted from the terminal to a server.

[0099] The server analyzes the received biometric information of the user and generates appropriate chemical structures based on a generative AI model. This model uses an algorithm built in Python and is designed to deliver high computing power on AI-enabled boards such as NVIDIA Jetson. The generated chemical structures are stored in a database on the server and compared with existing data for safety and effectiveness.

[0100] Next, the generated chemical structure information is sent to the terminal, and the virtual trial system is launched. This system uses the OpenCV library to analyze the user's facial data in real time and uses Unity 3D to visualize the feel of the cosmetic product in a three-dimensional virtual space. This process allows the user to visually experience the effects of the product without physically trying it.

[0101] Furthermore, users can provide feedback on the cosmetics they have tried and send it to the server via their device. The server stores this feedback information in a database and uses it to improve the generation model for future products. Users can also share the generated product information with others, so it also functions as a platform to facilitate communication.

[0102] For example, a woman in her 20s can use this system to be recommended cosmetics containing hyaluronic acid and ceramides best suited to her dry skin, and then try them out in a virtual environment. An example of a prompt used in this case would be: "Build a generative AI model that suggests hyaluronic acid and ceramide ingredients for a woman in her 20s with dry skin, and visualize the results." This allows users to understand the effects of the products and then make selections that meet their needs.

[0103] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0104] Step 1:

[0105] The user enters biometric information using a device. This information includes skin type, allergies, and specific skin concerns such as dryness. The device collects this data and sends it to the server via a client-side application.

[0106] Step 2:

[0107] The server receives the user's biometric information as input and runs a generative AI model. The model uses machine learning algorithms to perform data analysis to generate appropriate chemical structures from the user's data. As output, a structural formula of a chemical component suitable for the user is generated.

[0108] Step 3:

[0109] The server generates chemical structure data and sends it to the terminal. After receiving this data, the terminal starts a three-dimensional virtual simulation environment and uses OpenCV to analyze the user's facial data in real time. Using this analysis result as input, Unity 3D is used to visually model the feel of using cosmetics and display it on the screen.

[0110] Step 4:

[0111] Users virtually visualize the product through a simulation environment and check its usability. They input their impressions and evaluations of the product they used as feedback and send it back to the server via their terminal. This feedback information is used to improve the AI ​​model generated in the future.

[0112] Step 5:

[0113] The server stores user feedback information received in a database. This stored data is used to improve subsequent generative model algorithms, enabling more accurate cosmetic recommendations for new users.

[0114] 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.

[0115] This invention combines a system that collects biometric information about customers and generates chemical structures based on that information with an emotion engine that recognizes user emotions, thereby enabling the provision of more personalized cosmetics. Specific embodiments are described below.

[0116] First, the user uses a device to input information about their skin. This includes skin type, allergies, and specific skin problems, and the device sends this information to the server. The server analyzes the received information and uses a generative model to generate the optimal chemical structure for that user.

[0117] Based on the generated chemical structure, the server performs a verification process and then sends the information to the terminal to create a virtual trial environment for simulating the user experience. This is where the emotion engine plays its role. While the user tries out the cosmetics generated in the virtual environment, the terminal analyzes the user's emotions in real time through cameras and biosensors.

[0118] The emotion engine analyzes the user's facial expressions, voice, and other biometric data to determine what emotions the user is experiencing. This allows for a detailed understanding of the user's reaction to the product being tested, which is then used to further refine the generative model.

[0119] As a concrete example, imagine a user virtually trying on a generated cosmetic product. The user might look in the mirror and feel happy, or show a confused expression if their expectations are not met. This emotional information is important, and the system uses it to fine-tune the cosmetic's ingredients or make new suggestions, thereby creating a product that better suits the user.

[0120] Furthermore, after users evaluate their trial results, feedback, along with emotional information, is sent to the server. This feedback is stored in a database and used to improve generative models and develop new cosmetics. A sharing function allows other users to access these trial results and emotional data and provide cross-feedback. This expands collective knowledge and further improves product quality.

[0121] The following describes the processing flow.

[0122] Step 1:

[0123] The user uses the device to input biometric information such as skin condition, allergy information, and specific beauty needs. The device collects the entered data and prepares to send it to the server.

[0124] Step 2:

[0125] The terminal sends input data to the server. The server receives this data, performs initial analysis, and inputs the labeled information into the generative model.

[0126] Step 3:

[0127] The server uses a generative model to generate the optimal chemical structure from the input data. The generated chemical structure is stored in an internal database, and safety checks are also performed.

[0128] Step 4:

[0129] The server sends verified chemical structure information to the terminal, and the terminal prepares to activate the virtual fitting simulation mode.

[0130] Step 5:

[0131] The user starts a virtual try-on on their device, and their facial expressions and emotions are analyzed in real time through cameras and sensors.

[0132] Step 6:

[0133] The emotion engine recognizes the user's emotions and collects that emotion data. The device sends this emotion information, along with the user's experience with the product being tested, to the server.

[0134] Step 7:

[0135] The server analyzes emotional data and user experience, and adjusts the generative model. It proposes new chemical structures as needed.

[0136] Step 8:

[0137] Users provide feedback based on their trial experience and emotions, and the device sends this feedback to the server. The server stores this data in a database and uses it to improve future products.

[0138] Step 9:

[0139] If a user wishes, they can upload information from their device to the platform to share their trial results and sentimental feedback with other users. The server receives this information and makes it publicly available on the platform for other users to access.

[0140] (Example 2)

[0141] 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".

[0142] Conventional personalized product recommendation systems faced the challenge of failing to achieve true customer satisfaction through mere analysis based on user information. Specifically, they required not only the ability to propose chemical structures that reflected the customer's biometric information, but also the ability to adjust the product to take into account the customer's emotions in response to the proposal. Furthermore, while effectively utilizing shared experiences and feedback from other users is crucial for improving product quality, this was not being done sufficiently.

[0143] 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.

[0144] In this invention, the server includes means for collecting information about the customer's biological characteristics, means for generating a chemical structure using a generative model based on the information, and means for testing the product in a virtual environment based on the generated chemical structure. This makes it possible to analyze the emotions the customer exhibits during use in real time and dynamically adjust the generative model based on that information. Furthermore, by sharing the trial results with other users and cross-feedback, it becomes possible to realize more highly personalized and satisfying product recommendations.

[0145] "Information about the living organism" refers to data that indicates the physical condition of an individual, including information about skin type, allergies, and specific skin problems.

[0146] A "generative model" refers to an algorithm or software used to create new chemical structures or proposals based on input data.

[0147] "Chemical structure" refers to the composition of ingredients contained in cosmetics and care products, and it has a shape that is optimized for each individual user.

[0148] A "virtual environment" refers to a simulation environment that allows users to feel as if they are actually trying out the product in question, and is usually provided via a digital device.

[0149] "Real-time emotional analysis" refers to a process that uses the user's facial expressions, voice, and biometric data to instantly analyze and determine their emotions at any given moment.

[0150] "Feedback" refers to the opinions and reactions that users provide after using a product, and it is an important source of information used to improve products and services.

[0151] "Cross-feedback" is a method of improving product quality by having multiple users share their trial results and opinions and utilize the information from each other.

[0152] To implement this invention, a system is constructed in which a server, a terminal, and a user each play their respective roles. First, the user uses the terminal to input specific information about their skin. This includes individual skin type, allergies, and skin problems. The terminal then transmits this information to the server.

[0153] The server utilizes a generative AI model to analyze the received information. The generative AI model generates the optimal chemical structure based on the user's biometric information. This process employs the aforementioned hardware configuration to execute deep learning algorithms and propose personalized product components. Specific models used here include TENSORFLOW® and PyTorch.

[0154] The generated chemical structure is verified by the server and then sent to the terminal. The terminal uses this information to create an environment where the user can virtually try out the cosmetics. In this virtual trial environment, 3D rendering software such as Unity or Unreal Engine is used to reproduce a realistic user experience.

[0155] While the user tries out the product in this virtual environment, the device uses its camera and biosensors to collect the user's facial expressions, voice, and biometric data. This data is analyzed in real time by an emotion engine. This engine implements a machine learning model because it needs to determine the user's emotional state. The results are used to gain a detailed understanding of how the user feels about the product.

[0156] For example, when a user virtually tries out the generated cosmetics, they may show a happy or disappointed expression, or a confused expression, due to disappointment. Based on the user's emotions, the system fine-tunes the chemical structure, enabling it to suggest products that are a better fit for the user.

[0157] After the trial period, users input their thoughts and opinions on the product, which are then sent to the server as feedback. This feedback is stored in a database and used to further improve the generated AI model. Furthermore, this data can be shared with other users to facilitate cross-feedback and enhance collective knowledge.

[0158] Examples of prompts include, "Please tell us about your skin type and your usual skincare routine," and "Please tell us how you felt when you tried the new cosmetic product in the virtual trial."

[0159] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0160] Step 1:

[0161] Users input information about their skin using a device. This data includes skin type, allergy information, and specific skin problems. This information is sent from the device to a server. The server uses this information to prepare for individual analysis.

[0162] Step 2:

[0163] The server inputs the received biometric information into a generating AI model for analysis. During this process, the model combines the data to generate a chemical structure optimized for the user's skin condition. The output is a customized chemical structure tailored to the user.

[0164] Step 3:

[0165] The generated chemical structure is validated by the server. Here, for the purpose of confirming safety, a database of known allergic reactions and component stability is referenced. Once validation is complete, the results are sent to the terminal.

[0166] Step 4:

[0167] The terminal receives chemical structure information sent from the server and uses it to build a virtual trial environment. This environment allows users to virtually try out cosmetics and uses a simulation engine to provide a realistic user experience. As a result, users receive visual and tactile feedback when using the product.

[0168] Step 5:

[0169] While the user tries out the product in a virtual environment, the device uses its camera and biosensors to collect data on the user's facial expressions and voice. This data is passed to an emotion engine, where it is analyzed in real time. The resulting determination of the user's emotion is then used for subsequent data processing.

[0170] Step 6:

[0171] The server receives user sentiment information and uses it to adjust the chemical structure of the generated product. Specifically, if the user's experience is unsatisfactory, it acts as data to improve the proposed components. This adjustment result is then fed back into the system as a feedback loop.

[0172] Step 7:

[0173] Users ultimately input their evaluation and feedback on the product trial and send it from their device to the server. This feedback is stored in a database and continuously used to improve the generated AI model and in product development.

[0174] Step 8:

[0175] The sharing function allows trial results and sentiment data to be shared with other users. This enables cross-feedback among users, contributing to the expansion of collective knowledge and improvement of product quality.

[0176] (Application Example 2)

[0177] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0178] In personalized cosmetic recommendations, it's necessary to consider not only the user's skin condition but also their emotional changes. However, conventional systems have struggled to accurately recognize user emotions and adjust recommendations accordingly. This can lead to product recommendations that fail to meet user expectations, making improving user satisfaction a challenge.

[0179] 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.

[0180] In this invention, the server includes means for collecting information about the customer's biological characteristics, means for generating a chemical structure using a generative model based on the information, means for trying out the product in a virtual environment based on the generated chemical structure, means for recognizing the user's emotions and analyzing the emotional information in real time, and means for adjusting product suggestions based on the analyzed emotional information. This makes it possible to suggest optimal cosmetics that meet the individual needs and emotions of each user.

[0181] "Customer biometric information" refers to biological data such as the user's skin type, allergies, and skin problems.

[0182] A "generative model" refers to an algorithm for designing and generating the optimal chemical structure based on collected biological information.

[0183] "Chemical structure" refers to the molecular structure of cosmetic ingredients proposed by the generative model.

[0184] A "virtual environment" refers to a simulation space set up for users to try out a product or service.

[0185] "Means of recognizing emotions" refers to technologies that analyze and identify emotions using data from the user's facial expressions, voice, and biosensors.

[0186] "Means of adjusting product proposals" refers to a process of dynamically optimizing product ingredients and proposal content based on emotional information.

[0187] The system implementing this invention provides a process for suggesting personalized cosmetics based on the customer's biological information.

[0188] The system first collects biometric information from the user via a terminal, such as skin type, allergies, and specific skin problems. This information is sent to a server, which uses a generative model to generate the optimal chemical structure. During this process, a generative AI model is utilized to analyze the information.

[0189] The generated chemical structures are tested by the user in a virtual environment. The terminal uses cameras and biosensors to analyze the user's emotions in real time. Emotion analysis uses data such as facial expressions and voice. The server runs an emotion engine to collect the user's emotional information and adjust product recommendations in real time based on that information.

[0190] As a concrete example, when a user tries a new moisturizing cream, a robot observes the process, and a generative AI model suggests new ingredients. If it is determined that the user's skin needs moisture, the generative AI model is prompted with the following message:

[0191] "If a user has dry skin and a strong desire to relax, what kind of cosmetics containing what ingredients would be best?"

[0192] The server stores feedback in a database and uses it, along with collected emotional data, to improve the next generative model and develop new products. This allows users to enjoy an innovative cosmetic experience tailored to their emotions and unique skin condition.

[0193] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0194] Step 1:

[0195] The device receives biometric information from the user, including skin type, allergies, and specific skin problems. The user inputs this information via a dedicated application, and the device sends this data to a server. The output is the user's biometric information received by the server.

[0196] Step 2:

[0197] The server uses a generative AI model to generate chemical structures based on the received biometric information. In this process, the collected data is fed into the generative AI model as prompts to design the optimal cosmetic ingredients. The output is the generated chemical structure.

[0198] Step 3:

[0199] The terminal constructs a virtual environment using the generated chemical structure as input, providing the user with a product trial simulation. The output is a product image of the virtual cosmetic product that the user tries out. The user tries out the product through a smart device.

[0200] Step 4:

[0201] The device uses biosensors to collect emotional data in real time, taking the user's facial expressions and voice as input during a virtual trial. The output is the analyzed emotional information.

[0202] Step 5:

[0203] The server uses the collected emotional information as input to run an emotion engine and adjust product recommendations. During data processing, the emotional data is re-inputted into a generating AI model, optimizing the chemical components as needed. The output is the adjusted product recommendation.

[0204] Step 6:

[0205] The user evaluates the trial results as input and sends the feedback from the terminal to the server. The output is feedback data. The server stores this feedback in a database and uses it to improve subsequent generative models.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] [Second Embodiment]

[0210] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0211] 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.

[0212] 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).

[0213] 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.

[0214] 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.

[0215] 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).

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] 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".

[0222] This invention relates to a system that generates personalized cosmetics based on a customer's biological information and allows them to test the effects of these cosmetics in a virtual environment. This system is implemented through the interaction of a server, a terminal, and a user. Specific embodiments are described below.

[0223] First, the user accesses the device via an interface and enters information about their skin. This includes skin type, allergies, and specific skin concerns (e.g., dryness, sensitivity, acne, etc.). The device collects this information and sends the data to the server.

[0224] The server analyzes the received customer information and runs a generative model based on that information. The generative model includes an algorithm for generating appropriate chemical structures from the input data. The server uses this model to generate structural formulas of chemical components that meet the customer's needs. The generated chemical structures are stored in the server's internal database and compared with existing component data to verify their safety and efficacy.

[0225] Next, the server sends the generated chemical structure information to the terminal. The terminal receives this information and activates the virtual fitting system. The virtual fitting system allows the user to input their own facial data and simulate the feel of the generated cosmetics in real time. This allows the user to check the fit and visual effect of the product in a virtual environment without having to physically try it out.

[0226] Finally, users can provide their evaluation of the product they have tried through their device. This feedback information is sent back to the server and stored in a database, where it is used to further improve the accuracy of the generative model and develop new products. Furthermore, if the user wishes, they can publish information about the generated product on a platform where it can be shared with others, allowing for interaction with other users.

[0227] The following is a specific example. For instance, if a woman in her 20s with dry skin and allergies uses this system, the server will suggest moisturizing ingredients such as hyaluronic acid and ceramides, and she can try out the effects of the products in a virtual environment. This entire process makes it easier to select cosmetics that are more suitable for her.

[0228] The following describes the processing flow.

[0229] Step 1:

[0230] The user uses a device to input information about their skin. This includes skin type, allergy information, and specific skin concerns. The device formats the entered information and prepares it to send the data to the server.

[0231] Step 2:

[0232] The terminal sends input information to the server. The server receives this information and begins data analysis. Specifically, it performs data analysis to assess the integrity of the information and label data related to lifestyle.

[0233] Step 3:

[0234] The server runs a generative model using the customer information it receives. The model generates the optimal chemical structure for cosmetic ingredients based on the input data. The generated chemical structure is stored in a database on the server.

[0235] Step 4:

[0236] The server compares and verifies the safety and effectiveness of the generated chemical structures with existing component data. If there are any issues with safety or effectiveness, the model is readjusted and run again.

[0237] Step 5:

[0238] The server transfers verified chemical structure information to the terminal. Based on this information, the terminal prepares the virtual fitting system.

[0239] Step 6:

[0240] The user begins a virtual try-on on the device. Based on the user's facial data, the device simulates the feel of the generated cosmetics in real time. This simulation allows the user to evaluate the appearance and intended use of the product.

[0241] Step 7:

[0242] The user reviews the results of the virtual try-on and enters their evaluation and feedback into the device. The device collects this feedback and sends it to the server.

[0243] Step 8:

[0244] The server receives feedback and stores it in the database. This data is used to improve future generative models and develop new products. Additionally, if the user wishes, they can share the generated product information through the platform.

[0245] (Example 1)

[0246] 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."

[0247] In the existing cosmetics market, there is a problem in that personalization based on individual user biometric information is not sufficiently implemented, making it difficult for users to choose products that suit their skin. Furthermore, physical samples are required to try products, and the trial process is time-consuming and costly. As a result, improving consumer satisfaction and the efficient operation of the market are hindered.

[0248] 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.

[0249] In this invention, the server includes means for receiving information about the user's biological information using an information terminal, means for transmitting the received information to a data server, and means for automatically generating the structure of a chemical substance using a model based on the information. This makes it possible to personalize cosmetics to suit the user and to quickly and efficiently provide the optimal product through trial use in a virtual environment.

[0250] An "information terminal" is a computer device used by users to input and receive biometric information.

[0251] A "data server" is a central processing unit used to store and analyze received information.

[0252] "Biological information" refers to data related to an individual's physical characteristics, such as the user's skin type, allergy information, and skin concerns.

[0253] A "generative AI model" is an artificial intelligence system that has an algorithm for automatically generating the appropriate chemical structure based on input information.

[0254] "The structure of a chemical substance" is data that represents the molecular arrangement of a compound suitable for a specific application.

[0255] A "virtual trial environment" is a computer-generated environment that allows users to simulate the feel and visual effects of cosmetics.

[0256] "Means of visual presentation" refer to display devices or software that allow users to visually confirm the results of a virtual trial.

[0257] "Communication means" refers to a network interface for exchanging generated product information with other users or external systems.

[0258] "Evaluation information" refers to data that includes opinions and feedback provided by users regarding a product.

[0259] A "storage device" is a hardware or software component used to store information for extended periods within a data server.

[0260] This shows an embodiment for carrying out the invention.

[0261] This invention embodies a system that realizes the generation and virtual trial of personalized cosmetics through interaction between a server, a terminal, and a user. Specifically, an information terminal receives information about the user's skin and transmits it to a data server. The terminal can be a general-purpose computer or mobile device, and data input is performed via a user interface.

[0262] The server functions as a data server, inputting received information into a generating AI model. This model uses state-of-the-art machine learning algorithms to automatically generate chemical structures based on the user's skin information. The generated structures are compared to an internal database to verify their safety and efficacy. The server leverages high-performance computing to perform rapid data processing.

[0263] The structural information of the generated chemical substances is transmitted to the terminal. The terminal provides a virtual trial environment, allowing the user to directly simulate the feel of using the generated cosmetics in this virtual space. The user can use the terminal's camera to capture facial data and visually confirm the effects of the cosmetics on the display.

[0264] For example, if a user enters the prompt "I have dry skin and allergies, so I would like a product with high moisturizing effects," the server will use a generative AI model to generate chemical structures containing hyaluronic acid and ceramides. Based on this information, the user can then verify the product's effectiveness in a virtual environment. This allows users to select the most suitable cosmetics for themselves without having to physically try them out.

[0265] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0266] Step 1:

[0267] Users input skin-related information through their device. Specifically, they fill in their skin type, allergies, and specific skin concerns in a form provided by the user interface. The entered data is appropriately formatted and sent to the data server as information packets.

[0268] Step 2:

[0269] The server receives data transmitted from the terminal and feeds it to a generating AI model. Based on the input user data, the AI ​​model generates chemical structures using a specific algorithm. During this process, data analysis is performed to obtain the optimal chemical structural formula for the user. The generated structures are stored in an internal database and compared with existing data.

[0270] Step 3:

[0271] The server transmits the generated chemical structure information to the terminal. The terminal uses the received chemical structure information to launch a virtual trial system and presents it to the user. Specifically, the terminal's camera is used to capture the user's facial data and simulate the feel of using the cosmetic in real time. As output, the trial results are displayed on the screen, which the user can visually confirm.

[0272] Step 4:

[0273] Users enter their evaluations of the products they have tried. The device collects this feedback information and sends it back to the server. The submitted evaluation data is recorded in the server's database and used to train a generative AI model. This information is used to improve existing products and develop new ones.

[0274] (Application Example 1)

[0275] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0276] To provide a system that proposes personalized cosmetics based on user characteristics and enables the effects to be confirmed without actual trial, and to solve the problem that by presenting the usability visually and clearly, it becomes easier for users to easily select the optimal product. Further, by improving the accuracy of the generation model based on the obtained information, the quality of future proposals is improved.

[0277] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0278] In this invention, the server includes means for collecting information related to the customer's living body, means for generating a chemical structure using a generation model based on the information, means for trying out a product in a virtual environment based on the generated chemical structure, and means for performing real-time modeling using a three-dimensional space in order to visualize the usability in virtual trial. As a result, the user can visually confirm the cosmetics suitable for himself / herself without actually trying them.

[0279] A "customer" is an individual or group that uses the service.

[0280] "Information related to the living body" is information on an individual's skin type, presence or absence of allergies, and information related to specific skin problems.

[0281] A "generation model" is a program including an algorithm for generating a chemical structure from input data.

[0282] "Chemical structure" is information indicating the molecular structure of a specific chemical component.

[0283] A "virtual environment" is a simulation space composed of a computer-generated three-dimensional space.

[0284] "Trial" is an act of virtually experiencing the effects and usability of a product.

[0285] The means of "performing real-time modeling using three-dimensional space" is a technology that visualizes in three dimensions based on information about the user's face and skin, and immediately displays the product effects.

[0286] The present invention provides a system that proposes personalized cosmetics to users and allows them to virtually try them on. First, the user inputs information about their skin via a terminal. This information includes skin type, presence or absence of allergies, and specific skin problems, and the data is transmitted from the terminal to the server.

[0287] The server analyzes the received information about the user's body and generates an appropriate chemical structure based on the generated AI model. This model is designed to use an algorithm built in Python and exhibit high computing power on an AI-compatible board such as NVIDIA Jetson. The generated chemical structure is stored in the database within the server and compared with existing data for safety and effectiveness.

[0288] Next, the generated chemical structure information is transmitted to the terminal to activate the virtual trial system. In this system, the user's face data is analyzed in real time using the OpenCV library, and the feeling of using cosmetics is visualized on a three-dimensional virtual space using Unity 3D. Through this process, the user can visually experience the effects of the product without physically trying it.

[0289] Furthermore, the user can provide feedback on the cosmetics they have tried and send it to the server via the terminal. The server accumulates this feedback information in the database and uses it to improve the generation model in subsequent times. Also, the user can share the generated product information with others, and it also functions as a platform to promote communication.

[0290] For example, a woman in her 20s can use this system to be recommended cosmetics containing hyaluronic acid and ceramides best suited to her dry skin, and then try them out in a virtual environment. An example of a prompt used in this case would be: "Build a generative AI model that suggests hyaluronic acid and ceramide ingredients for a woman in her 20s with dry skin, and visualize the results." This allows users to understand the effects of the products and then make selections that meet their needs.

[0291] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0292] Step 1:

[0293] The user enters biometric information using a device. This information includes skin type, allergies, and specific skin concerns such as dryness. The device collects this data and sends it to the server via a client-side application.

[0294] Step 2:

[0295] The server receives the user's biometric information as input and runs a generative AI model. The model uses machine learning algorithms to perform data analysis to generate appropriate chemical structures from the user's data. As output, a structural formula of a chemical component suitable for the user is generated.

[0296] Step 3:

[0297] The server generates chemical structure data and sends it to the terminal. After receiving this data, the terminal starts a three-dimensional virtual simulation environment and uses OpenCV to analyze the user's facial data in real time. Using this analysis result as input, Unity 3D is used to visually model the feel of using cosmetics and display it on the screen.

[0298] Step 4:

[0299] Users virtually visualize the product through a simulation environment and check its usability. They input their impressions and evaluations of the product they used as feedback and send it back to the server via their terminal. This feedback information is used to improve the AI ​​model generated in the future.

[0300] Step 5:

[0301] The server stores user feedback information received in a database. This stored data is used in subsequent generative model improvement algorithms, enabling more accurate cosmetic recommendations for new users.

[0302] 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.

[0303] This invention combines a system that collects biometric information about customers and generates chemical structures based on that information with an emotion engine that recognizes user emotions, thereby enabling the provision of more personalized cosmetics. Specific embodiments are described below.

[0304] First, the user uses a device to input information about their skin. This includes skin type, allergies, and specific skin problems, and the device sends this information to the server. The server analyzes the received information and uses a generative model to generate the optimal chemical structure for that user.

[0305] Based on the generated chemical structure, the server performs a verification process and then sends the information to the terminal to create a virtual trial environment for simulating the user experience. This is where the emotion engine plays its role. While the user tries out the cosmetics generated in the virtual environment, the terminal analyzes the user's emotions in real time through cameras and biosensors.

[0306] The emotion engine analyzes the user's facial expressions, voice, and other biometric data to determine what emotions the user is experiencing. This enables a detailed understanding of the user's reaction to the product under trial and is used for further adjustment of the generation model.

[0307] As a specific example, suppose a user is virtually trying out cosmetics created for them. The user may look happy when seeing themselves in the mirror or show a confused expression if the product fails to meet expectations. This emotional information is crucial, and based on it, the system can fine-tune the components of the cosmetics or make new suggestions to create products that better suit the user.

[0308] Furthermore, after the user evaluates the trial results, they are sent to the server as feedback along with the emotional information. This feedback is stored in the database and utilized for improving the generation model and developing new cosmetics. Through the sharing function, other users can access this trial result and emotional data for cross-feedback, thus expanding collective knowledge and further enhancing the product quality.

[0309] The following describes the processing flow.

[0310] Step 1:

[0311] The user uses the terminal to input information related to the body, such as skin condition, allergy information, and specific beauty needs. The terminal collects the input data and prepares to send it to the server.

[0312] Step 2:

[0313] The terminal sends the input data to the server. The server receives this data, performs initial analysis, and inputs the labeled information into the generation model.

[0314] Step 3:

[0315] The server uses a generative model to generate the optimal chemical structure from the input data. The generated chemical structure is stored in an internal database, and safety checks are also performed.

[0316] Step 4:

[0317] The server sends verified chemical structure information to the terminal, and the terminal prepares to activate the virtual fitting simulation mode.

[0318] Step 5:

[0319] The user starts a virtual try-on on their device, and their facial expressions and emotions are analyzed in real time through cameras and sensors.

[0320] Step 6:

[0321] The emotion engine recognizes the user's emotions and collects that emotion data. The device sends this emotion information, along with the user's experience with the product being tested, to the server.

[0322] Step 7:

[0323] The server analyzes emotional data and user experience, and adjusts the generative model. It proposes new chemical structures as needed.

[0324] Step 8:

[0325] Users provide feedback based on their trial experience and emotions, and the device sends this feedback to the server. The server stores this data in a database and uses it to improve future products.

[0326] Step 9:

[0327] If a user wishes, they can upload information from their device to the platform to share their trial results and sentimental feedback with other users. The server receives this information and makes it publicly available on the platform for other users to access.

[0328] (Example 2)

[0329] 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".

[0330] Conventional personalized product recommendation systems faced the challenge of failing to achieve true customer satisfaction through mere analysis based on user information. Specifically, they required not only the ability to propose chemical structures that reflected the customer's biometric information, but also the ability to adjust the product to take into account the customer's emotions in response to the proposal. Furthermore, while effectively utilizing shared experiences and feedback from other users is crucial for improving product quality, this was not being done sufficiently.

[0331] 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.

[0332] In this invention, the server includes means for collecting information about the customer's biological characteristics, means for generating a chemical structure using a generative model based on the information, and means for testing the product in a virtual environment based on the generated chemical structure. This makes it possible to analyze the emotions the customer exhibits during use in real time and dynamically adjust the generative model based on that information. Furthermore, by sharing the trial results with other users and cross-feedback, it becomes possible to realize more highly personalized and satisfying product recommendations.

[0333] "Information about the living organism" refers to data that indicates the physical condition of an individual, including information about skin type, allergies, and specific skin problems.

[0334] A "generative model" refers to an algorithm or software used to create new chemical structures or proposals based on input data.

[0335] "Chemical structure" refers to the composition of ingredients contained in cosmetics and care products, and it has a shape that is optimized for each individual user.

[0336] A "virtual environment" refers to a simulation environment that allows users to feel as if they are actually trying out the product in question, and is usually provided via a digital device.

[0337] "Real-time emotional analysis" refers to a process that uses the user's facial expressions, voice, and biometric data to instantly analyze and determine their emotions at any given moment.

[0338] "Feedback" refers to the opinions and reactions that users provide after using a product, and it is an important source of information used to improve products and services.

[0339] "Cross-feedback" is a method of improving product quality by having multiple users share their trial results and opinions and utilize the information from each other.

[0340] To implement this invention, a system is constructed in which a server, a terminal, and a user each play their respective roles. First, the user uses the terminal to input specific information about their skin. This includes individual skin type, allergies, and skin problems. The terminal then transmits this information to the server.

[0341] The server utilizes a generative AI model to analyze the received information. The generative AI model generates the optimal chemical structure based on the user's biometric information. This process employs the aforementioned hardware configuration to execute deep learning algorithms and propose personalized product components. Specific models used here include TensorFlow and PyTorch.

[0342] The generated chemical structure is verified by the server and then sent to the terminal. The terminal uses this information to create an environment where the user can virtually try out the cosmetics. In this virtual trial environment, 3D rendering software such as Unity or Unreal Engine is used to reproduce a realistic user experience.

[0343] While the user tries out the product in this virtual environment, the device uses its camera and biosensors to collect the user's facial expressions, voice, and biometric data. This data is analyzed in real time by an emotion engine. This engine implements a machine learning model because it needs to determine the user's emotional state. The results are used to gain a detailed understanding of how the user feels about the product.

[0344] For example, when a user virtually tries out the generated cosmetics, they may show a happy or disappointed expression, or a confused expression, due to disappointment. Based on the user's emotions, the system fine-tunes the chemical structure, enabling it to suggest products that are a better fit for the user.

[0345] After the trial period, users input their thoughts and opinions on the product, which are then sent to the server as feedback. This feedback is stored in a database and used to further improve the generated AI model. Furthermore, this data can be shared with other users to facilitate cross-feedback and enhance collective knowledge.

[0346] Examples of prompts include, "Please tell us about your skin type and your usual skincare routine," and "Please tell us how you felt when you tried the new cosmetic product in the virtual trial."

[0347] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0348] Step 1:

[0349] Users input information about their skin using a device. This data includes skin type, allergy information, and specific skin problems. This information is sent from the device to a server. The server uses this information to prepare for individual analysis.

[0350] Step 2:

[0351] The server inputs the received biometric information into a generating AI model for analysis. During this process, the model combines the data to generate a chemical structure optimized for the user's skin condition. The output is a customized chemical structure tailored to the user.

[0352] Step 3:

[0353] The generated chemical structure is validated by the server. Here, for the purpose of confirming safety, a database of known allergic reactions and component stability is referenced. Once validation is complete, the results are sent to the terminal.

[0354] Step 4:

[0355] The terminal receives chemical structure information sent from the server and uses it to build a virtual trial environment. This environment allows users to virtually try out cosmetics and uses a simulation engine to provide a realistic user experience. As a result, users receive visual and tactile feedback when using the product.

[0356] Step 5:

[0357] While the user tries out the product in a virtual environment, the device uses its camera and biosensors to collect data on the user's facial expressions and voice. This data is passed to an emotion engine, where it is analyzed in real time. The resulting determination of the user's emotion is then used for subsequent data processing.

[0358] Step 6:

[0359] The server receives user sentiment information and uses it to adjust the chemical structure of the generated product. Specifically, if the user's experience is unsatisfactory, it acts as data to improve the proposed components. This adjustment result is then fed back into the system as a feedback loop.

[0360] Step 7:

[0361] Users ultimately input their evaluation and feedback on the product trial and send it from their device to the server. This feedback is stored in a database and continuously used to improve the generated AI model and in product development.

[0362] Step 8:

[0363] The sharing function allows trial results and sentiment data to be shared with other users. This enables cross-feedback among users, contributing to the expansion of collective knowledge and improvement of product quality.

[0364] (Application Example 2)

[0365] 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."

[0366] In personalized cosmetic recommendations, it's necessary to consider not only the user's skin condition but also their emotional changes. However, conventional systems have struggled to accurately recognize user emotions and adjust recommendations accordingly. This can lead to product recommendations that fail to meet user expectations, making improving user satisfaction a challenge.

[0367] 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.

[0368] In this invention, the server includes means for collecting information about the customer's biological characteristics, means for generating a chemical structure using a generative model based on the information, means for trying out the product in a virtual environment based on the generated chemical structure, means for recognizing the user's emotions and analyzing the emotional information in real time, and means for adjusting product suggestions based on the analyzed emotional information. This makes it possible to suggest optimal cosmetics that meet the individual needs and emotions of each user.

[0369] "Customer biometric information" refers to biological data such as the user's skin type, allergies, and skin problems.

[0370] A "generative model" refers to an algorithm for designing and generating the optimal chemical structure based on collected biological information.

[0371] "Chemical structure" refers to the molecular structure of cosmetic ingredients proposed by the generative model.

[0372] A "virtual environment" refers to a simulation space set up for users to try out a product or service.

[0373] "Means of recognizing emotions" refers to technologies that analyze and identify emotions using data from the user's facial expressions, voice, and biosensors.

[0374] "Means of adjusting product proposals" refers to a process of dynamically optimizing product ingredients and proposal content based on emotional information.

[0375] The system implementing this invention provides a process for suggesting personalized cosmetics based on the customer's biological information.

[0376] The system first collects biometric information from the user via a terminal, such as skin type, allergies, and specific skin problems. This information is sent to a server, which uses a generative model to generate the optimal chemical structure. During this process, a generative AI model is utilized to analyze the information.

[0377] The generated chemical structures are tested by the user in a virtual environment. The terminal uses cameras and biosensors to analyze the user's emotions in real time. Emotion analysis uses data such as facial expressions and voice. The server runs an emotion engine to collect the user's emotional information and adjust product recommendations in real time based on that information.

[0378] As a concrete example, when a user tries a new moisturizing cream, a robot observes the process, and a generative AI model suggests new ingredients. If it is determined that the user's skin needs moisture, the generative AI model is prompted with the following message:

[0379] "If a user has dry skin and a strong desire to relax, what kind of cosmetics containing what ingredients would be best?"

[0380] The server stores feedback in a database and uses it, along with collected emotional data, to improve the next generative model and develop new products. This allows users to enjoy an innovative cosmetic experience tailored to their emotions and unique skin condition.

[0381] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0382] Step 1:

[0383] The device receives biometric information from the user, including skin type, allergies, and specific skin problems. The user inputs this information via a dedicated application, and the device sends this data to a server. The output is the user's biometric information received by the server.

[0384] Step 2:

[0385] The server uses a generative AI model to generate chemical structures based on the received biometric information. In this process, the collected data is fed into the generative AI model as prompts to design the optimal cosmetic ingredients. The output is the generated chemical structure.

[0386] Step 3:

[0387] The terminal constructs a virtual environment using the generated chemical structure as input, providing the user with a product trial simulation. The output is a product image of the virtual cosmetic product that the user tries out. The user tries out the product through a smart device.

[0388] Step 4:

[0389] The device uses biosensors to collect emotional data in real time, taking the user's facial expressions and voice as input during a virtual trial. The output is the analyzed emotional information.

[0390] Step 5:

[0391] The server uses the collected emotional information as input to run an emotion engine and adjust product recommendations. During data processing, the emotional data is re-inputted into a generating AI model, optimizing the chemical components as needed. The output is the adjusted product recommendation.

[0392] Step 6:

[0393] The user evaluates the trial results as input and sends the feedback from the terminal to the server. The output is feedback data. The server stores this feedback in a database and uses it to improve subsequent generative models.

[0394] 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.

[0395] 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.

[0396] 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.

[0397] [Third Embodiment]

[0398] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0399] 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.

[0400] 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).

[0401] 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.

[0402] 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.

[0403] 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).

[0404] 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.

[0405] 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.

[0406] 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.

[0407] 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.

[0408] 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.

[0409] 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".

[0410] This invention relates to a system that generates personalized cosmetics based on a customer's biological information and allows them to test the effects of these cosmetics in a virtual environment. This system is implemented through the interaction of a server, a terminal, and a user. Specific embodiments are described below.

[0411] First, the user accesses the device via an interface and enters information about their skin. This includes skin type, allergies, and specific skin concerns (e.g., dryness, sensitivity, acne, etc.). The device collects this information and sends the data to the server.

[0412] The server analyzes the received customer information and runs a generative model based on that information. The generative model includes an algorithm for generating appropriate chemical structures from the input data. The server uses this model to generate structural formulas of chemical components that meet the customer's needs. The generated chemical structures are stored in the server's internal database and compared with existing component data to verify their safety and efficacy.

[0413] Next, the server sends the generated chemical structure information to the terminal. The terminal receives this information and activates the virtual fitting system. The virtual fitting system allows the user to input their own facial data and simulate the feel of the generated cosmetics in real time. This allows the user to check the fit and visual effect of the product in a virtual environment without having to physically try it out.

[0414] Finally, users can provide their evaluation of the product they have tried through their device. This feedback information is sent back to the server and stored in a database, where it is used to further improve the accuracy of the generative model and develop new products. Furthermore, if the user wishes, they can publish information about the generated product on a platform where it can be shared with others, allowing for interaction with other users.

[0415] The following is a specific example. For instance, if a woman in her 20s with dry skin and allergies uses this system, the server will suggest moisturizing ingredients such as hyaluronic acid and ceramides, and she can try out the effects of the products in a virtual environment. This entire process makes it easier to select cosmetics that are more suitable for her.

[0416] The following describes the processing flow.

[0417] Step 1:

[0418] The user uses a device to input information about their skin. This includes skin type, allergy information, and specific skin concerns. The device formats the entered information and prepares it to send the data to the server.

[0419] Step 2:

[0420] The terminal sends input information to the server. The server receives this information and begins data analysis. Specifically, it performs data analysis to assess the integrity of the information and label data related to lifestyle.

[0421] Step 3:

[0422] The server runs a generative model using the customer information it receives. The model generates the optimal chemical structure for cosmetic ingredients based on the input data. The generated chemical structure is stored in a database on the server.

[0423] Step 4:

[0424] The server compares and verifies the safety and effectiveness of the generated chemical structures with existing component data. If there are any issues with safety or effectiveness, the model is readjusted and run again.

[0425] Step 5:

[0426] The server transfers verified chemical structure information to the terminal. Based on this information, the terminal prepares the virtual fitting system.

[0427] Step 6:

[0428] The user begins a virtual try-on on the device. Based on the user's facial data, the device simulates the feel of the generated cosmetics in real time. This simulation allows the user to evaluate the appearance and intended use of the product.

[0429] Step 7:

[0430] The user reviews the results of the virtual try-on and enters their evaluation and feedback into the device. The device collects this feedback and sends it to the server.

[0431] Step 8:

[0432] The server receives feedback and stores it in the database. This data is used to improve future generative models and develop new products. Additionally, if the user wishes, they can share the generated product information through the platform.

[0433] (Example 1)

[0434] 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."

[0435] In the existing cosmetics market, there is a problem in that personalization based on individual user biometric information is not sufficiently implemented, making it difficult for users to choose products that suit their skin. Furthermore, physical samples are required to try products, and the trial process is time-consuming and costly. As a result, improving consumer satisfaction and the efficient operation of the market are hindered.

[0436] 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.

[0437] In this invention, the server includes means for receiving information about the user's biological information using an information terminal, means for transmitting the received information to a data server, and means for automatically generating the structure of a chemical substance using a model based on the information. This makes it possible to personalize cosmetics to suit the user and to quickly and efficiently provide the optimal product through trial use in a virtual environment.

[0438] An "information terminal" is a computer device used by users to input and receive biometric information.

[0439] A "data server" is a central processing unit used to store and analyze received information.

[0440] "Biological information" refers to data related to an individual's physical characteristics, such as the user's skin type, allergy information, and skin concerns.

[0441] A "generative AI model" is an artificial intelligence system that has an algorithm for automatically generating the appropriate chemical structure based on input information.

[0442] "The structure of a chemical substance" is data that represents the molecular arrangement of a compound suitable for a specific application.

[0443] A "virtual trial environment" is a computer-generated environment that allows users to simulate the feel and visual effects of cosmetics.

[0444] "Means of visual presentation" refer to display devices or software that allow users to visually confirm the results of a virtual trial.

[0445] "Communication means" refers to a network interface for exchanging generated product information with other users or external systems.

[0446] "Evaluation information" refers to data that includes opinions and feedback provided by users regarding a product.

[0447] A "storage device" is a hardware or software component used to store information for extended periods within a data server.

[0448] This shows an embodiment for carrying out the invention.

[0449] This invention embodies a system that realizes the generation and virtual trial of personalized cosmetics through interaction between a server, a terminal, and a user. Specifically, an information terminal receives information about the user's skin and transmits it to a data server. The terminal can be a general-purpose computer or mobile device, and data input is performed via a user interface.

[0450] The server functions as a data server, inputting received information into a generating AI model. This model uses state-of-the-art machine learning algorithms to automatically generate chemical structures based on the user's skin information. The generated structures are compared to an internal database to verify their safety and efficacy. The server leverages high-performance computing to perform rapid data processing.

[0451] The structural information of the generated chemical substances is transmitted to the terminal. The terminal provides a virtual trial environment, allowing the user to directly simulate the feel of using the generated cosmetics in this virtual space. The user can use the terminal's camera to capture facial data and visually confirm the effects of the cosmetics on the display.

[0452] For example, if a user enters the prompt "I have dry skin and allergies, so I would like a product with high moisturizing effects," the server will use a generative AI model to generate chemical structures containing hyaluronic acid and ceramides. Based on this information, the user can then verify the product's effectiveness in a virtual environment. This allows users to select the most suitable cosmetics for themselves without having to physically try them out.

[0453] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0454] Step 1:

[0455] Users input skin-related information through their device. Specifically, they fill in their skin type, allergies, and specific skin concerns in a form provided by the user interface. The entered data is appropriately formatted and sent to the data server as information packets.

[0456] Step 2:

[0457] The server receives data transmitted from the terminal and feeds it to a generating AI model. Based on the input user data, the AI ​​model generates chemical structures using a specific algorithm. During this process, data analysis is performed to obtain the optimal chemical structural formula for the user. The generated structures are stored in an internal database and compared with existing data.

[0458] Step 3:

[0459] The server transmits the generated chemical structure information to the terminal. The terminal uses the received chemical structure information to launch a virtual trial system and presents it to the user. Specifically, the terminal's camera is used to capture the user's facial data and simulate the feel of using the cosmetic in real time. As output, the trial results are displayed on the screen, which the user can visually confirm.

[0460] Step 4:

[0461] Users enter their evaluations of the products they have tried. The device collects this feedback information and sends it back to the server. The submitted evaluation data is recorded in the server's database and used to train a generative AI model. This information is used to improve existing products and develop new ones.

[0462] (Application Example 1)

[0463] 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."

[0464] To provide a system that suggests personalized cosmetics based on user characteristics and allows users to verify their effectiveness without actually trying them. Furthermore, to solve the problem of making it easier for users to select the optimal product by visually presenting the user experience in an easy-to-understand way. Additionally, to improve the accuracy of the generative model based on the acquired information, thereby improving the quality of future suggestions.

[0465] 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.

[0466] In this invention, the server includes means for collecting information about the customer's biological characteristics, means for generating a chemical structure using a generative model based on the information, means for trying out the product in a virtual environment based on the generated chemical structure, and means for performing real-time modeling using three-dimensional space to visualize the user experience during the virtual trial. This makes it possible for users to visually confirm cosmetics that are suitable for them without actually trying them.

[0467] A "customer" is an individual or group that uses a service.

[0468] "Biological information" refers to information about an individual's skin type, whether or not they have allergies, and specific skin concerns.

[0469] A "generative model" is a program that includes an algorithm for generating chemical structures from input data.

[0470] "Chemical structure" refers to information that describes the molecular structure of a specific chemical component.

[0471] A "virtual environment" is a simulation space composed of a computer-generated three-dimensional space.

[0472] "Trial use" refers to the act of virtually experiencing the effects and feel of a product.

[0473] "A method for performing real-time modeling using three-dimensional space" refers to a technology that visualizes the user's face and skin information in three dimensions and instantly displays the product's effects.

[0474] This invention provides a system that proposes personalized cosmetics to users and allows them to virtually try them out. The user first inputs information about their skin via a terminal. This information includes skin type, allergy status, and specific skin concerns, and this data is transmitted from the terminal to a server.

[0475] The server analyzes the received biometric information of the user and generates appropriate chemical structures based on a generative AI model. This model uses an algorithm built in Python and is designed to deliver high computing power on AI-enabled boards such as NVIDIA Jetson. The generated chemical structures are stored in a database on the server and compared with existing data for safety and effectiveness.

[0476] Next, the generated chemical structure information is sent to the terminal, and the virtual trial system is launched. This system uses the OpenCV library to analyze the user's facial data in real time and uses Unity 3D to visualize the feel of the cosmetic product in a three-dimensional virtual space. This process allows the user to visually experience the effects of the product without physically trying it.

[0477] Furthermore, users can provide feedback on the cosmetics they have tried and send it to the server via their device. The server stores this feedback information in a database and uses it to improve the generation model for future products. Users can also share the generated product information with others, so it also functions as a platform to facilitate communication.

[0478] For example, a woman in her 20s can use this system to be recommended cosmetics containing hyaluronic acid and ceramides best suited to her dry skin, and then try them out in a virtual environment. An example of a prompt used in this case would be: "Build a generative AI model that suggests hyaluronic acid and ceramide ingredients for a woman in her 20s with dry skin, and visualize the results." This allows users to understand the effects of the products and then make selections that meet their needs.

[0479] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0480] Step 1:

[0481] The user enters biometric information using a device. This information includes skin type, allergies, and specific skin concerns such as dryness. The device collects this data and sends it to the server via a client-side application.

[0482] Step 2:

[0483] The server receives the user's biometric information as input and runs a generative AI model. The model uses machine learning algorithms to perform data analysis to generate appropriate chemical structures from the user's data. As output, a structural formula of a chemical component suitable for the user is generated.

[0484] Step 3:

[0485] The server generates chemical structure data and sends it to the terminal. After receiving this data, the terminal starts a three-dimensional virtual simulation environment and uses OpenCV to analyze the user's facial data in real time. Using this analysis result as input, Unity 3D is used to visually model the feel of using cosmetics and display it on the screen.

[0486] Step 4:

[0487] Users virtually visualize the product through a simulation environment and check its usability. They input their impressions and evaluations of the product they used as feedback and send it back to the server via their terminal. This feedback information is used to improve the AI ​​model generated in the future.

[0488] Step 5:

[0489] The server stores user feedback information received in a database. This stored data is used to improve subsequent generative model algorithms, enabling more accurate cosmetic recommendations for new users.

[0490] 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.

[0491] This invention combines a system that collects biometric information about customers and generates chemical structures based on that information with an emotion engine that recognizes user emotions, thereby enabling the provision of more personalized cosmetics. Specific embodiments are described below.

[0492] First, the user uses a device to input information about their skin. This includes skin type, allergies, and specific skin problems, and the device sends this information to the server. The server analyzes the received information and uses a generative model to generate the optimal chemical structure for that user.

[0493] Based on the generated chemical structure, the server performs a verification process and then sends the information to the terminal to create a virtual trial environment for simulating the user experience. This is where the emotion engine plays its role. While the user tries out the cosmetics generated in the virtual environment, the terminal analyzes the user's emotions in real time through cameras and biosensors.

[0494] The emotion engine analyzes the user's facial expressions, voice, and other biometric data to determine what emotions the user is experiencing. This allows for a detailed understanding of the user's reaction to the product being tested, which is then used to further refine the generative model.

[0495] As a concrete example, imagine a user virtually trying on a generated cosmetic product. The user might look in the mirror and feel happy, or show a confused expression if their expectations are not met. This emotional information is important, and the system uses it to fine-tune the cosmetic's ingredients or make new suggestions, thereby creating a product that better suits the user.

[0496] Furthermore, after users evaluate their trial results, feedback, along with emotional information, is sent to the server. This feedback is stored in a database and used to improve generative models and develop new cosmetics. A sharing function allows other users to access these trial results and emotional data and provide cross-feedback. This expands collective knowledge and further improves product quality.

[0497] The following describes the processing flow.

[0498] Step 1:

[0499] The user uses the device to input biometric information such as skin condition, allergy information, and specific beauty needs. The device collects the entered data and prepares to send it to the server.

[0500] Step 2:

[0501] The terminal sends input data to the server. The server receives this data, performs initial analysis, and inputs the labeled information into the generative model.

[0502] Step 3:

[0503] The server uses a generative model to generate the optimal chemical structure from the input data. The generated chemical structure is stored in an internal database, and safety checks are also performed.

[0504] Step 4:

[0505] The server sends verified chemical structure information to the terminal, and the terminal prepares to activate the virtual fitting simulation mode.

[0506] Step 5:

[0507] The user starts a virtual try-on on their device, and their facial expressions and emotions are analyzed in real time through cameras and sensors.

[0508] Step 6:

[0509] The emotion engine recognizes the user's emotions and collects that emotion data. The device sends this emotion information, along with the user's experience with the product being tested, to the server.

[0510] Step 7:

[0511] The server analyzes emotional data and user experience, and adjusts the generative model. It proposes new chemical structures as needed.

[0512] Step 8:

[0513] Users provide feedback based on their trial experience and emotions, and the device sends this feedback to the server. The server stores this data in a database and uses it to improve future products.

[0514] Step 9:

[0515] If a user wishes, they can upload information from their device to the platform to share their trial results and sentimental feedback with other users. The server receives this information and makes it publicly available on the platform for other users to access.

[0516] (Example 2)

[0517] 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."

[0518] Conventional personalized product recommendation systems faced the challenge of failing to achieve true customer satisfaction through mere analysis based on user information. Specifically, they required not only the ability to propose chemical structures that reflected the customer's biometric information, but also the ability to adjust the product to take into account the customer's emotions in response to the proposal. Furthermore, while effectively utilizing shared experiences and feedback from other users is crucial for improving product quality, this was not being done sufficiently.

[0519] 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.

[0520] In this invention, the server includes means for collecting information about the customer's biological characteristics, means for generating a chemical structure using a generative model based on the information, and means for testing the product in a virtual environment based on the generated chemical structure. This makes it possible to analyze the emotions the customer exhibits during use in real time and dynamically adjust the generative model based on that information. Furthermore, by sharing the trial results with other users and cross-feedback, it becomes possible to realize more highly personalized and satisfying product recommendations.

[0521] "Information about the living organism" refers to data that indicates the physical condition of an individual, including information about skin type, allergies, and specific skin problems.

[0522] A "generative model" refers to an algorithm or software used to create new chemical structures or proposals based on input data.

[0523] "Chemical structure" refers to the composition of ingredients contained in cosmetics and care products, and it has a shape that is optimized for each individual user.

[0524] A "virtual environment" refers to a simulation environment that allows users to feel as if they are actually trying out the product in question, and is usually provided via a digital device.

[0525] "Real-time emotional analysis" refers to a process that uses the user's facial expressions, voice, and biometric data to instantly analyze and determine their emotions at any given moment.

[0526] "Feedback" refers to the opinions and reactions that users provide after using a product, and it is an important source of information used to improve products and services.

[0527] "Cross-feedback" is a method of improving product quality by having multiple users share their trial results and opinions and utilize the information from each other.

[0528] To implement this invention, a system is constructed in which a server, a terminal, and a user each play their respective roles. First, the user uses the terminal to input specific information about their skin. This includes individual skin type, allergies, and skin problems. The terminal then transmits this information to the server.

[0529] The server utilizes a generative AI model to analyze the received information. The generative AI model generates the optimal chemical structure based on the user's biometric information. This process employs the aforementioned hardware configuration to execute deep learning algorithms and propose personalized product components. Specific models used here include TensorFlow and PyTorch.

[0530] The generated chemical structure is verified by the server and then sent to the terminal. The terminal uses this information to create an environment where the user can virtually try out the cosmetics. In this virtual trial environment, 3D rendering software such as Unity or Unreal Engine is used to reproduce a realistic user experience.

[0531] While the user tries out the product in this virtual environment, the device uses its camera and biosensors to collect the user's facial expressions, voice, and biometric data. This data is analyzed in real time by an emotion engine. This engine implements a machine learning model because it needs to determine the user's emotional state. The results are used to gain a detailed understanding of how the user feels about the product.

[0532] For example, when a user virtually tries out the generated cosmetics, they may show a happy or disappointed expression, or a confused expression, due to disappointment. Based on the user's emotions, the system fine-tunes the chemical structure, enabling it to suggest products that are a better fit for the user.

[0533] After the trial period, users input their thoughts and opinions on the product, which are then sent to the server as feedback. This feedback is stored in a database and used to further improve the generated AI model. Furthermore, this data can be shared with other users to facilitate cross-feedback and enhance collective knowledge.

[0534] Examples of prompts include, "Please tell us about your skin type and your usual skincare routine," and "Please tell us how you felt when you tried the new cosmetic product in the virtual trial."

[0535] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0536] Step 1:

[0537] Users input information about their skin using a device. This data includes skin type, allergy information, and specific skin problems. This information is sent from the device to a server. The server uses this information to prepare for individual analysis.

[0538] Step 2:

[0539] The server inputs the received biometric information into a generating AI model for analysis. During this process, the model combines the data to generate a chemical structure optimized for the user's skin condition. The output is a customized chemical structure tailored to the user.

[0540] Step 3:

[0541] The generated chemical structure is validated by the server. Here, for the purpose of confirming safety, a database of known allergic reactions and component stability is referenced. Once validation is complete, the results are sent to the terminal.

[0542] Step 4:

[0543] The terminal receives chemical structure information sent from the server and uses it to build a virtual trial environment. This environment allows users to virtually try out cosmetics and uses a simulation engine to provide a realistic user experience. As a result, users receive visual and tactile feedback when using the product.

[0544] Step 5:

[0545] While the user tries out the product in a virtual environment, the device uses its camera and biosensors to collect data on the user's facial expressions and voice. This data is passed to an emotion engine, where it is analyzed in real time. The resulting determination of the user's emotion is then used for subsequent data processing.

[0546] Step 6:

[0547] The server receives user sentiment information and uses it to adjust the chemical structure of the generated product. Specifically, if the user's experience is unsatisfactory, it acts as data to improve the proposed components. This adjustment result is then fed back into the system as a feedback loop.

[0548] Step 7:

[0549] Users ultimately input their evaluation and feedback on the product trial and send it from their device to the server. This feedback is stored in a database and continuously used to improve the generated AI model and in product development.

[0550] Step 8:

[0551] The sharing function allows trial results and sentiment data to be shared with other users. This enables cross-feedback among users, contributing to the expansion of collective knowledge and improvement of product quality.

[0552] (Application Example 2)

[0553] 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."

[0554] In personalized cosmetic recommendations, it's necessary to consider not only the user's skin condition but also their emotional changes. However, conventional systems have struggled to accurately recognize user emotions and adjust recommendations accordingly. This can lead to product recommendations that fail to meet user expectations, making improving user satisfaction a challenge.

[0555] 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.

[0556] In this invention, the server includes means for collecting information about the customer's biological characteristics, means for generating a chemical structure using a generative model based on the information, means for trying out the product in a virtual environment based on the generated chemical structure, means for recognizing the user's emotions and analyzing the emotional information in real time, and means for adjusting product suggestions based on the analyzed emotional information. This makes it possible to suggest optimal cosmetics that meet the individual needs and emotions of each user.

[0557] "Customer biometric information" refers to biological data such as the user's skin type, allergies, and skin problems.

[0558] A "generative model" refers to an algorithm for designing and generating the optimal chemical structure based on collected biological information.

[0559] "Chemical structure" refers to the molecular structure of cosmetic ingredients proposed by the generative model.

[0560] A "virtual environment" refers to a simulation space set up for users to try out a product or service.

[0561] "Means of recognizing emotions" refers to technologies that analyze and identify emotions using data from the user's facial expressions, voice, and biosensors.

[0562] "Means of adjusting product proposals" refers to a process of dynamically optimizing product ingredients and proposal content based on emotional information.

[0563] The system implementing this invention provides a process for suggesting personalized cosmetics based on the customer's biological information.

[0564] The system first collects biometric information from the user via a terminal, such as skin type, allergies, and specific skin problems. This information is sent to a server, which uses a generative model to generate the optimal chemical structure. During this process, a generative AI model is utilized to analyze the information.

[0565] The generated chemical structures are tested by the user in a virtual environment. The terminal uses cameras and biosensors to analyze the user's emotions in real time. Emotion analysis uses data such as facial expressions and voice. The server runs an emotion engine to collect the user's emotional information and adjust product recommendations in real time based on that information.

[0566] As a concrete example, when a user tries a new moisturizing cream, a robot observes the process, and a generative AI model suggests new ingredients. If it is determined that the user's skin needs moisture, the generative AI model is prompted with the following message:

[0567] "If a user has dry skin and a strong desire to relax, what kind of cosmetics containing what ingredients would be best?"

[0568] The server stores feedback in a database and uses it, along with collected emotional data, to improve the next generative model and develop new products. This allows users to enjoy an innovative cosmetic experience tailored to their emotions and unique skin condition.

[0569] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0570] Step 1:

[0571] The device receives biometric information from the user, including skin type, allergies, and specific skin problems. The user inputs this information via a dedicated application, and the device sends this data to a server. The output is the user's biometric information received by the server.

[0572] Step 2:

[0573] The server uses a generative AI model to generate chemical structures based on the received biometric information. In this process, the collected data is fed into the generative AI model as prompts to design the optimal cosmetic ingredients. The output is the generated chemical structure.

[0574] Step 3:

[0575] The terminal constructs a virtual environment using the generated chemical structure as input, providing the user with a product trial simulation. The output is a product image of the virtual cosmetic product that the user tries out. The user tries out the product through a smart device.

[0576] Step 4:

[0577] The device uses biosensors to collect emotional data in real time, taking the user's facial expressions and voice as input during a virtual trial. The output is the analyzed emotional information.

[0578] Step 5:

[0579] The server uses the collected emotional information as input to run an emotion engine and adjust product recommendations. During data processing, the emotional data is re-inputted into a generating AI model, optimizing the chemical components as needed. The output is the adjusted product recommendation.

[0580] Step 6:

[0581] The user evaluates the trial results as input and sends the feedback from the terminal to the server. The output is feedback data. The server stores this feedback in a database and uses it to improve subsequent generative models.

[0582] 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.

[0583] 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.

[0584] 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.

[0585] [Fourth Embodiment]

[0586] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0587] 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.

[0588] 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).

[0589] 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.

[0590] 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.

[0591] 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).

[0592] 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.

[0593] 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.

[0594] 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.

[0595] 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.

[0596] 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.

[0597] 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.

[0598] 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".

[0599] This invention relates to a system that generates personalized cosmetics based on a customer's biological information and allows them to test the effects of these cosmetics in a virtual environment. This system is implemented through the interaction of a server, a terminal, and a user. Specific embodiments are described below.

[0600] First, the user accesses the device via an interface and enters information about their skin. This includes skin type, allergies, and specific skin concerns (e.g., dryness, sensitivity, acne, etc.). The device collects this information and sends the data to the server.

[0601] The server analyzes the received customer information and runs a generative model based on that information. The generative model includes an algorithm for generating appropriate chemical structures from the input data. The server uses this model to generate structural formulas of chemical components that meet the customer's needs. The generated chemical structures are stored in the server's internal database and compared with existing component data to verify their safety and efficacy.

[0602] Next, the server sends the generated chemical structure information to the terminal. The terminal receives this information and activates the virtual fitting system. The virtual fitting system allows the user to input their own facial data and simulate the feel of the generated cosmetics in real time. This allows the user to check the fit and visual effect of the product in a virtual environment without having to physically try it out.

[0603] Finally, users can provide their evaluation of the product they have tried through their device. This feedback information is sent back to the server and stored in a database, where it is used to further improve the accuracy of the generative model and develop new products. Furthermore, if the user wishes, they can publish information about the generated product on a platform where it can be shared with others, allowing for interaction with other users.

[0604] The following is a specific example. For instance, if a woman in her 20s with dry skin and allergies uses this system, the server will suggest moisturizing ingredients such as hyaluronic acid and ceramides, and she can try out the effects of the products in a virtual environment. This entire process makes it easier to select cosmetics that are more suitable for her.

[0605] The following describes the processing flow.

[0606] Step 1:

[0607] The user uses a device to input information about their skin. This includes skin type, allergy information, and specific skin concerns. The device formats the entered information and prepares it to send the data to the server.

[0608] Step 2:

[0609] The terminal sends input information to the server. The server receives this information and begins data analysis. Specifically, it performs data analysis to assess the integrity of the information and label data related to lifestyle.

[0610] Step 3:

[0611] The server runs a generative model using the customer information it receives. The model generates the optimal chemical structure for cosmetic ingredients based on the input data. The generated chemical structure is stored in a database on the server.

[0612] Step 4:

[0613] The server compares and verifies the safety and effectiveness of the generated chemical structures with existing component data. If there are any issues with safety or effectiveness, the model is readjusted and run again.

[0614] Step 5:

[0615] The server transfers verified chemical structure information to the terminal. Based on this information, the terminal prepares the virtual fitting system.

[0616] Step 6:

[0617] The user begins a virtual try-on on the device. Based on the user's facial data, the device simulates the feel of the generated cosmetics in real time. This simulation allows the user to evaluate the appearance and intended use of the product.

[0618] Step 7:

[0619] The user reviews the results of the virtual try-on and enters their evaluation and feedback into the device. The device collects this feedback and sends it to the server.

[0620] Step 8:

[0621] The server receives feedback and stores it in the database. This data is used to improve future generative models and develop new products. Additionally, if the user wishes, they can share the generated product information through the platform.

[0622] (Example 1)

[0623] 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".

[0624] In the existing cosmetics market, there is a problem in that personalization based on individual user biometric information is not sufficiently implemented, making it difficult for users to choose products that suit their skin. Furthermore, physical samples are required to try products, and the trial process is time-consuming and costly. As a result, improving consumer satisfaction and the efficient operation of the market are hindered.

[0625] 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.

[0626] In this invention, the server includes means for receiving information about the user's biological information using an information terminal, means for transmitting the received information to a data server, and means for automatically generating the structure of a chemical substance using a model based on the information. This makes it possible to personalize cosmetics to suit the user and to quickly and efficiently provide the optimal product through trial use in a virtual environment.

[0627] An "information terminal" is a computer device used by users to input and receive biometric information.

[0628] A "data server" is a central processing unit used to store and analyze received information.

[0629] "Biological information" refers to data related to an individual's physical characteristics, such as the user's skin type, allergy information, and skin concerns.

[0630] A "generative AI model" is an artificial intelligence system that has an algorithm for automatically generating the appropriate chemical structure based on input information.

[0631] "The structure of a chemical substance" is data that represents the molecular arrangement of a compound suitable for a specific application.

[0632] A "virtual trial environment" is a computer-generated environment that allows users to simulate the feel and visual effects of cosmetics.

[0633] "Means of visual presentation" refer to display devices or software that allow users to visually confirm the results of a virtual trial.

[0634] "Communication means" refers to a network interface for exchanging generated product information with other users or external systems.

[0635] "Evaluation information" refers to data that includes opinions and feedback provided by users regarding a product.

[0636] A "storage device" is a hardware or software component used to store information for extended periods within a data server.

[0637] This shows an embodiment for carrying out the invention.

[0638] This invention embodies a system that realizes the generation and virtual trial of personalized cosmetics through interaction between a server, a terminal, and a user. Specifically, an information terminal receives information about the user's skin and transmits it to a data server. The terminal can be a general-purpose computer or mobile device, and data input is performed via a user interface.

[0639] The server functions as a data server, inputting received information into a generating AI model. This model uses state-of-the-art machine learning algorithms to automatically generate chemical structures based on the user's skin information. The generated structures are compared to an internal database to verify their safety and efficacy. The server leverages high-performance computing to perform rapid data processing.

[0640] The structural information of the generated chemical substances is transmitted to the terminal. The terminal provides a virtual trial environment, allowing the user to directly simulate the feel of using the generated cosmetics in this virtual space. The user can use the terminal's camera to capture facial data and visually confirm the effects of the cosmetics on the display.

[0641] For example, if a user enters the prompt "I have dry skin and allergies, so I would like a product with high moisturizing effects," the server will use a generative AI model to generate chemical structures containing hyaluronic acid and ceramides. Based on this information, the user can then verify the product's effectiveness in a virtual environment. This allows users to select the most suitable cosmetics for themselves without having to physically try them out.

[0642] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0643] Step 1:

[0644] Users input skin-related information through their device. Specifically, they fill in their skin type, allergies, and specific skin concerns in a form provided by the user interface. The entered data is appropriately formatted and sent to the data server as information packets.

[0645] Step 2:

[0646] The server receives data transmitted from the terminal and feeds it to a generating AI model. Based on the input user data, the AI ​​model generates chemical structures using a specific algorithm. During this process, data analysis is performed to obtain the optimal chemical structural formula for the user. The generated structures are stored in an internal database and compared with existing data.

[0647] Step 3:

[0648] The server transmits the generated chemical structure information to the terminal. The terminal uses the received chemical structure information to launch a virtual trial system and presents it to the user. Specifically, the terminal's camera is used to capture the user's facial data and simulate the feel of using the cosmetic in real time. As output, the trial results are displayed on the screen, which the user can visually confirm.

[0649] Step 4:

[0650] Users enter their evaluations of the products they have tried. The device collects this feedback information and sends it back to the server. The submitted evaluation data is recorded in the server's database and used to train a generative AI model. This information is used to improve existing products and develop new ones.

[0651] (Application Example 1)

[0652] 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".

[0653] To provide a system that suggests personalized cosmetics based on user characteristics and allows users to verify their effectiveness without actually trying them. Furthermore, to solve the problem of making it easier for users to select the optimal product by visually presenting the user experience in an easy-to-understand way. Additionally, to improve the accuracy of the generative model based on the acquired information, thereby improving the quality of future suggestions.

[0654] 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.

[0655] In this invention, the server includes means for collecting information about the customer's biological characteristics, means for generating a chemical structure using a generative model based on the information, means for trying out the product in a virtual environment based on the generated chemical structure, and means for performing real-time modeling using three-dimensional space to visualize the user experience during the virtual trial. This makes it possible for users to visually confirm cosmetics that are suitable for them without actually trying them.

[0656] A "customer" is an individual or group that uses a service.

[0657] "Biological information" refers to information about an individual's skin type, whether or not they have allergies, and specific skin concerns.

[0658] A "generative model" is a program that includes an algorithm for generating chemical structures from input data.

[0659] "Chemical structure" refers to information that describes the molecular structure of a specific chemical component.

[0660] A "virtual environment" is a simulation space composed of a computer-generated three-dimensional space.

[0661] "Trial use" refers to the act of virtually experiencing the effects and feel of a product.

[0662] "A method for performing real-time modeling using three-dimensional space" refers to a technology that visualizes the user's face and skin information in three dimensions and instantly displays the product's effects.

[0663] This invention provides a system that proposes personalized cosmetics to users and allows them to virtually try them out. The user first inputs information about their skin via a terminal. This information includes skin type, allergy status, and specific skin concerns, and this data is transmitted from the terminal to a server.

[0664] The server analyzes the received biometric information of the user and generates appropriate chemical structures based on a generative AI model. This model uses an algorithm built in Python and is designed to deliver high computing power on AI-enabled boards such as NVIDIA Jetson. The generated chemical structures are stored in a database on the server and compared with existing data for safety and effectiveness.

[0665] Next, the generated chemical structure information is sent to the terminal, and the virtual trial system is launched. This system uses the OpenCV library to analyze the user's facial data in real time and uses Unity 3D to visualize the feel of the cosmetic product in a three-dimensional virtual space. This process allows the user to visually experience the effects of the product without physically trying it.

[0666] Furthermore, users can provide feedback on the cosmetics they have tried and send it to the server via their device. The server stores this feedback information in a database and uses it to improve the generation model for future products. Users can also share the generated product information with others, so it also functions as a platform to facilitate communication.

[0667] For example, a woman in her 20s can use this system to be recommended cosmetics containing hyaluronic acid and ceramides best suited to her dry skin, and then try them out in a virtual environment. An example of a prompt used in this case would be: "Build a generative AI model that suggests hyaluronic acid and ceramide ingredients for a woman in her 20s with dry skin, and visualize the results." This allows users to understand the effects of the products and then make selections that meet their needs.

[0668] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0669] Step 1:

[0670] The user enters biometric information using a device. This information includes skin type, allergies, and specific skin concerns such as dryness. The device collects this data and sends it to the server via a client-side application.

[0671] Step 2:

[0672] The server receives the user's biometric information as input and runs a generative AI model. The model uses machine learning algorithms to perform data analysis to generate appropriate chemical structures from the user's data. As output, a structural formula of a chemical component suitable for the user is generated.

[0673] Step 3:

[0674] The server generates chemical structure data and sends it to the terminal. After receiving this data, the terminal starts a three-dimensional virtual simulation environment and uses OpenCV to analyze the user's facial data in real time. Using this analysis result as input, Unity 3D is used to visually model the feel of using cosmetics and display it on the screen.

[0675] Step 4:

[0676] Users virtually visualize the product through a simulation environment and check its usability. They input their impressions and evaluations of the product they used as feedback and send it back to the server via their terminal. This feedback information is used to improve the AI ​​model generated in the future.

[0677] Step 5:

[0678] The server stores user feedback information received in a database. This stored data is used to improve subsequent generative model algorithms, enabling more accurate cosmetic recommendations for new users.

[0679] 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.

[0680] This invention combines a system that collects biometric information about customers and generates chemical structures based on that information with an emotion engine that recognizes user emotions, thereby enabling the provision of more personalized cosmetics. Specific embodiments are described below.

[0681] First, the user uses a device to input information about their skin. This includes skin type, allergies, and specific skin problems, and the device sends this information to the server. The server analyzes the received information and uses a generative model to generate the optimal chemical structure for that user.

[0682] Based on the generated chemical structure, the server performs a verification process and then sends the information to the terminal to create a virtual trial environment for simulating the user experience. This is where the emotion engine plays its role. While the user tries out the cosmetics generated in the virtual environment, the terminal analyzes the user's emotions in real time through cameras and biosensors.

[0683] The emotion engine analyzes the user's facial expressions, voice, and other biometric data to determine what emotions the user is experiencing. This allows for a detailed understanding of the user's reaction to the product being tested, which is then used to further refine the generative model.

[0684] As a concrete example, imagine a user virtually trying on a generated cosmetic product. The user might look in the mirror and feel happy, or show a confused expression if their expectations are not met. This emotional information is important, and the system uses it to fine-tune the cosmetic's ingredients or make new suggestions, thereby creating a product that better suits the user.

[0685] Furthermore, after users evaluate their trial results, feedback, along with emotional information, is sent to the server. This feedback is stored in a database and used to improve generative models and develop new cosmetics. A sharing function allows other users to access these trial results and emotional data and provide cross-feedback. This expands collective knowledge and further improves product quality.

[0686] The following describes the processing flow.

[0687] Step 1:

[0688] The user uses the device to input biometric information such as skin condition, allergy information, and specific beauty needs. The device collects the entered data and prepares to send it to the server.

[0689] Step 2:

[0690] The terminal sends input data to the server. The server receives this data, performs initial analysis, and inputs the labeled information into the generative model.

[0691] Step 3:

[0692] The server uses a generative model to generate the optimal chemical structure from the input data. The generated chemical structure is stored in an internal database, and safety checks are also performed.

[0693] Step 4:

[0694] The server sends verified chemical structure information to the terminal, and the terminal prepares to activate the virtual fitting simulation mode.

[0695] Step 5:

[0696] The user starts a virtual try-on on their device, and their facial expressions and emotions are analyzed in real time through cameras and sensors.

[0697] Step 6:

[0698] The emotion engine recognizes the user's emotions and collects that emotion data. The device sends this emotion information, along with the user's experience with the product being tested, to the server.

[0699] Step 7:

[0700] The server analyzes emotional data and user experience, and adjusts the generative model. It proposes new chemical structures as needed.

[0701] Step 8:

[0702] Users provide feedback based on their trial experience and emotions, and the device sends this feedback to the server. The server stores this data in a database and uses it to improve future products.

[0703] Step 9:

[0704] If a user wishes, they can upload information from their device to the platform to share their trial results and sentimental feedback with other users. The server receives this information and makes it publicly available on the platform for other users to access.

[0705] (Example 2)

[0706] 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".

[0707] Conventional personalized product recommendation systems faced the challenge of failing to achieve true customer satisfaction through mere analysis based on user information. Specifically, they required not only the ability to propose chemical structures that reflected the customer's biometric information, but also the ability to adjust the product to take into account the customer's emotions in response to the proposal. Furthermore, while effectively utilizing shared experiences and feedback from other users is crucial for improving product quality, this was not being done sufficiently.

[0708] 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.

[0709] In this invention, the server includes means for collecting information about the customer's biological characteristics, means for generating a chemical structure using a generative model based on the information, and means for testing the product in a virtual environment based on the generated chemical structure. This makes it possible to analyze the emotions the customer exhibits during use in real time and dynamically adjust the generative model based on that information. Furthermore, by sharing the trial results with other users and cross-feedback, it becomes possible to realize more highly personalized and satisfying product recommendations.

[0710] "Information about the living organism" refers to data that indicates the physical condition of an individual, including information about skin type, allergies, and specific skin problems.

[0711] A "generative model" refers to an algorithm or software used to create new chemical structures or proposals based on input data.

[0712] "Chemical structure" refers to the composition of ingredients contained in cosmetics and care products, and it has a shape that is optimized for each individual user.

[0713] A "virtual environment" refers to a simulation environment that allows users to feel as if they are actually trying out the product in question, and is usually provided via a digital device.

[0714] "Real-time emotional analysis" refers to a process that uses the user's facial expressions, voice, and biometric data to instantly analyze and determine their emotions at any given moment.

[0715] "Feedback" refers to the opinions and reactions that users provide after using a product, and it is an important source of information used to improve products and services.

[0716] "Cross-feedback" is a method of improving product quality by having multiple users share their trial results and opinions and utilize the information from each other.

[0717] To implement this invention, a system is constructed in which a server, a terminal, and a user each play their respective roles. First, the user uses the terminal to input specific information about their skin. This includes individual skin type, allergies, and skin problems. The terminal then transmits this information to the server.

[0718] The server utilizes a generative AI model to analyze the received information. The generative AI model generates the optimal chemical structure based on the user's biometric information. This process employs the aforementioned hardware configuration to execute deep learning algorithms and propose personalized product components. Specific models used here include TensorFlow and PyTorch.

[0719] The generated chemical structure is verified by the server and then sent to the terminal. The terminal uses this information to create an environment where the user can virtually try out the cosmetics. In this virtual trial environment, 3D rendering software such as Unity or Unreal Engine is used to reproduce a realistic user experience.

[0720] While the user tries out the product in this virtual environment, the device uses its camera and biosensors to collect the user's facial expressions, voice, and biometric data. This data is analyzed in real time by an emotion engine. This engine implements a machine learning model because it needs to determine the user's emotional state. The results are used to gain a detailed understanding of how the user feels about the product.

[0721] For example, when a user virtually tries out the generated cosmetics, they may show a happy or disappointed expression, or a confused expression, due to disappointment. Based on the user's emotions, the system fine-tunes the chemical structure, enabling it to suggest products that are a better fit for the user.

[0722] After the trial period, users input their thoughts and opinions on the product, which are then sent to the server as feedback. This feedback is stored in a database and used to further improve the generated AI model. Furthermore, this data can be shared with other users to facilitate cross-feedback and enhance collective knowledge.

[0723] Examples of prompts include, "Please tell us about your skin type and your usual skincare routine," and "Please tell us how you felt when you tried the new cosmetic product in the virtual trial."

[0724] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0725] Step 1:

[0726] Users input information about their skin using a device. This data includes skin type, allergy information, and specific skin problems. This information is sent from the device to a server. The server uses this information to prepare for individual analysis.

[0727] Step 2:

[0728] The server inputs the received biometric information into a generating AI model for analysis. During this process, the model combines the data to generate a chemical structure optimized for the user's skin condition. The output is a customized chemical structure tailored to the user.

[0729] Step 3:

[0730] The generated chemical structure is validated by the server. Here, for the purpose of confirming safety, a database of known allergic reactions and component stability is referenced. Once validation is complete, the results are sent to the terminal.

[0731] Step 4:

[0732] The terminal receives chemical structure information sent from the server and uses it to build a virtual trial environment. This environment allows users to virtually try out cosmetics and uses a simulation engine to provide a realistic user experience. As a result, users receive visual and tactile feedback when using the product.

[0733] Step 5:

[0734] While the user tries out the product in a virtual environment, the device uses its camera and biosensors to collect data on the user's facial expressions and voice. This data is passed to an emotion engine, where it is analyzed in real time. The resulting determination of the user's emotion is then used for subsequent data processing.

[0735] Step 6:

[0736] The server receives user sentiment information and uses it to adjust the chemical structure of the generated product. Specifically, if the user's experience is unsatisfactory, it acts as data to improve the proposed components. This adjustment result is then fed back into the system as a feedback loop.

[0737] Step 7:

[0738] Users ultimately input their evaluation and feedback on the product trial and send it from their device to the server. This feedback is stored in a database and continuously used to improve the generated AI model and in product development.

[0739] Step 8:

[0740] The sharing function allows trial results and sentiment data to be shared with other users. This enables cross-feedback among users, contributing to the expansion of collective knowledge and improvement of product quality.

[0741] (Application Example 2)

[0742] 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".

[0743] In personalized cosmetic recommendations, it's necessary to consider not only the user's skin condition but also their emotional changes. However, conventional systems have struggled to accurately recognize user emotions and adjust recommendations accordingly. This can lead to product recommendations that fail to meet user expectations, making improving user satisfaction a challenge.

[0744] 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.

[0745] In this invention, the server includes means for collecting information about the customer's biological characteristics, means for generating a chemical structure using a generative model based on the information, means for trying out the product in a virtual environment based on the generated chemical structure, means for recognizing the user's emotions and analyzing the emotional information in real time, and means for adjusting product suggestions based on the analyzed emotional information. This makes it possible to suggest optimal cosmetics that meet the individual needs and emotions of each user.

[0746] "Customer biometric information" refers to biological data such as the user's skin type, allergies, and skin problems.

[0747] A "generative model" refers to an algorithm for designing and generating the optimal chemical structure based on collected biological information.

[0748] "Chemical structure" refers to the molecular structure of cosmetic ingredients proposed by the generative model.

[0749] A "virtual environment" refers to a simulation space set up for users to try out a product or service.

[0750] "Means of recognizing emotions" refers to technologies that analyze and identify emotions using data from the user's facial expressions, voice, and biosensors.

[0751] "Means of adjusting product proposals" refers to a process of dynamically optimizing product ingredients and proposal content based on emotional information.

[0752] The system implementing this invention provides a process for suggesting personalized cosmetics based on the customer's biological information.

[0753] The system first collects biometric information from the user via a terminal, such as skin type, allergies, and specific skin problems. This information is sent to a server, which uses a generative model to generate the optimal chemical structure. During this process, a generative AI model is utilized to analyze the information.

[0754] The generated chemical structures are tested by the user in a virtual environment. The terminal uses cameras and biosensors to analyze the user's emotions in real time. Emotion analysis uses data such as facial expressions and voice. The server runs an emotion engine to collect the user's emotional information and adjust product recommendations in real time based on that information.

[0755] As a concrete example, when a user tries a new moisturizing cream, a robot observes the process, and a generative AI model suggests new ingredients. If it is determined that the user's skin needs moisture, the generative AI model is prompted with the following message:

[0756] "If a user has dry skin and a strong desire to relax, what kind of cosmetics containing what ingredients would be best?"

[0757] The server stores feedback in a database and uses it, along with collected emotional data, to improve the next generative model and develop new products. This allows users to enjoy an innovative cosmetic experience tailored to their emotions and unique skin condition.

[0758] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0759] Step 1:

[0760] The device receives biometric information from the user, including skin type, allergies, and specific skin problems. The user inputs this information via a dedicated application, and the device sends this data to a server. The output is the user's biometric information received by the server.

[0761] Step 2:

[0762] The server uses a generative AI model to generate chemical structures based on the received biometric information. In this process, the collected data is fed into the generative AI model as prompts to design the optimal cosmetic ingredients. The output is the generated chemical structure.

[0763] Step 3:

[0764] The terminal constructs a virtual environment using the generated chemical structure as input, providing the user with a product trial simulation. The output is a product image of the virtual cosmetic product that the user tries out. The user tries out the product through a smart device.

[0765] Step 4:

[0766] The device uses biosensors to collect emotional data in real time, taking the user's facial expressions and voice as input during a virtual trial. The output is the analyzed emotional information.

[0767] Step 5:

[0768] The server uses the collected emotional information as input to run an emotion engine and adjust product recommendations. During data processing, the emotional data is re-inputted into a generating AI model, optimizing the chemical components as needed. The output is the adjusted product recommendation.

[0769] Step 6:

[0770] The user evaluates the trial results as input and sends the feedback from the terminal to the server. The output is feedback data. The server stores this feedback in a database and uses it to improve subsequent generative models.

[0771] 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.

[0772] 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.

[0773] 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 robot 414.

[0774] 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.

[0775] 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.

[0776] 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.

[0777] 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.

[0778] 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.

[0779] 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."

[0780] 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.

[0781] 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.

[0782] 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.

[0783] 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.

[0784] 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.

[0785] 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.

[0786] 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.

[0787] 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.

[0788] 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.

[0789] 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.

[0790] 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.

[0791] 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.

[0792] The following is further disclosed regarding the embodiments described above.

[0793] (Claim 1)

[0794] Means for collecting information about customers' biometrics,

[0795] A means for generating a chemical structure using a generative model based on the aforementioned information,

[0796] A means for testing the product in a virtual environment based on the generated chemical structure,

[0797] A means for presenting the trial results in the aforementioned virtual environment to the customer,

[0798] A system that includes this.

[0799] (Claim 2)

[0800] The system according to claim 1, comprising means for sharing personalized product information with others based on the generated chemical structure.

[0801] (Claim 3)

[0802] The system according to claim 1, further comprising means for collecting the aforementioned customer feedback information, storing it in a database, and using it to improve subsequent generative models.

[0803] "Example 1"

[0804] (Claim 1)

[0805] A means of receiving biometric information of a user using an information terminal,

[0806] Means for transmitting the received information to a data server,

[0807] Based on the aforementioned information, a means for automatically generating the structure of a chemical substance using a model,

[0808] A means of storing the structure of the generated chemical substances in a database and comparing their safety and effectiveness,

[0809] A means for simulating the user experience of the product in a virtual trial environment using the structure of the generated chemical substance,

[0810] A means for visually presenting the results of the virtual trial to the user,

[0811] A system that includes this.

[0812] (Claim 2)

[0813] The system according to claim 1, further comprising communication means for sharing product information tailored to the user with other users based on the structure of the generated chemical substance.

[0814] (Claim 3)

[0815] The system according to claim 1, further comprising means for collecting evaluation information from users and storing the evaluation information in a storage device within a data server in order to utilize it for improving the generated AI model.

[0816] "Application Example 1"

[0817] (Claim 1)

[0818] Means for collecting information about customers' biometrics,

[0819] A means for generating a chemical structure using a generative model based on the aforementioned information,

[0820] A means for testing the product in a virtual environment based on the generated chemical structure,

[0821] A means for presenting the trial results in the aforementioned virtual environment to the customer,

[0822] To visualize the user experience during virtual trials, we have a method for performing real-time modeling using three-dimensional space,

[0823] A system that includes this.

[0824] (Claim 2)

[0825] The system according to claim 1, comprising means for sharing personalized product information with others based on the generated chemical structure.

[0826] (Claim 3)

[0827] The system according to claim 1, further comprising means for collecting the aforementioned customer feedback information, storing it in a database, and using it to improve subsequent generative models.

[0828] "Example 2 of combining an emotion engine"

[0829] (Claim 1)

[0830] Means for collecting information about customers' biometrics,

[0831] A means for generating a chemical structure using a generative model based on the aforementioned information,

[0832] A means for testing the product in a virtual environment based on the generated chemical structure,

[0833] A means for analyzing customer emotions in real time during the trial in the aforementioned virtual environment,

[0834] A means for adjusting the generative model based on the aforementioned trial results and emotional data,

[0835] A means for presenting the trial results in the aforementioned virtual environment to the customer,

[0836] A system that includes this.

[0837] (Claim 2)

[0838] The system according to claim 1, comprising means for sharing personalized product information with others based on the generated chemical structure.

[0839] (Claim 3)

[0840] The system according to claim 1, further comprising means for collecting customer feedback information and sentiment data, storing them in a database, and using them to improve subsequent generative models.

[0841] "Application example 2 when combining with an emotional engine"

[0842] (Claim 1)

[0843] Means for collecting information about customers' biometrics,

[0844] A means for generating a chemical structure using a generative model based on the aforementioned information,

[0845] A means for testing the product in a virtual environment based on the generated chemical structure,

[0846] A means for presenting the trial results in the aforementioned virtual environment to the customer,

[0847] A means to recognize user emotions and analyze that emotional information in real time,

[0848] A means for adjusting product proposals based on the analyzed emotional information,

[0849] A system that includes this.

[0850] (Claim 2)

[0851] The system according to claim 1, comprising means for sharing personalized product information with others based on the generated chemical structure.

[0852] (Claim 3)

[0853] The system according to claim 1, further comprising means for collecting the aforementioned customer feedback information, storing it in a database, and using it to improve subsequent generative models. [Explanation of symbols]

[0854] 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. Means for collecting information about customers' biometrics, A means for generating a chemical structure using a generative model based on the aforementioned information, A means for testing the product in a virtual environment based on the generated chemical structure, A means for presenting the trial results in the aforementioned virtual environment to the customer, A system that includes this.

2. The system according to claim 1, further comprising means for sharing personalized product information with others based on the generated chemical structure.

3. The system according to claim 1, further comprising means for collecting customer feedback information, storing it in a database, and using it to improve subsequent generative models.

Images