system

Abstract

We provide the system. [Solution] A means of obtaining facial images taken from users, A method for analyzing skin condition based on acquired facial images, A means of proposing the most suitable skin care products and methods to the user based on the analysis results, A means of acquiring surrounding environmental data and adjusting the proposed content, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Many people cannot accurately grasp their own skin conditions and may use incorrect skin care products. Therefore, it is difficult for people with particularly sensitive skin or complex skin problems to select appropriate products. In addition, the skin often changes due to seasonal and environmental changes, and it is difficult to appropriately adjust daily care methods. To solve these problems, a system that individually proposes optimal skin care products and methods for users is needed.

Means for Solving the Problems

[0005] This invention provides an automated system that analyzes the skin condition based on facial images acquired from a user and proposes optimal skin care products and methods according to the analysis results. The system analyzes the acquired facial images using image recognition technology to detect skin conditions such as dryness, blemishes, wrinkles, enlarged pores, and redness. Furthermore, it acquires appropriate product information from an external database and dynamically adjusts the suggestions based on surrounding environmental data, thereby providing the user with skin care advice that is suitable for the environmental conditions of the day.

[0006] "Users" refer to individuals or groups who operate the system and enjoy its services.

[0007] A "facial image" is image data of the user's face, which includes visual information necessary for analyzing the skin condition.

[0008] "Skin condition" refers to a collection of various characteristics related to the skin, such as dryness, blemishes, wrinkles, enlarged pores, and redness.

[0009] "Skin care products" refer to cosmetics or quasi-drugs used for the purpose of protecting, improving, or enhancing the appearance of the skin.

[0010] A "method" refers to a series of operations or procedures for maintaining the condition of the skin, and is a technique that exists to achieve a specific purpose.

[0011] "Environmental data" refers to information about the external environment that affects skin condition, such as temperature, humidity, and UV index. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3]It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0013] [[ID=4l]]Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

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

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

[0017] In the following embodiments, the 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, and the like.

[0018] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

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

[0022] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0029] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] This invention describes an embodiment for implementing a system that analyzes skin condition using facial images taken by a user and provides optimal skin care products and methods.

[0034] Image acquisition

[0035] User

[0036] The user uses a device with the dedicated application installed and launches the application. Within the application, they are prompted to use the camera function to take a photo of their face.

[0037] terminal

[0038] The device temporarily stores the facial image captured by the user in its own cache and automatically performs processing to optimize the image's resolution and brightness for analysis. Afterward, it sends the image to the server.

[0039] Image analysis

[0040] server

[0041] When the server receives an image, it starts analyzing it using a pre-trained deep learning model. This analysis outputs numerical data indicating the degree of dryness of the facial skin, the number of blemishes and wrinkles, the size of pores, and the degree of redness.

[0042] Skincare suggestions

[0043] server

[0044] Based on the analysis results, the server consults an internal database to select skincare products and methods suitable for the user. Product selection utilizes factors such as ingredient compatibility and past user data.

[0045] server

[0046] The server also references external weather information APIs to obtain environmental data such as current temperature, humidity, and UV index. This allows it to adjust the skincare methods provided to users based on environmental conditions.

[0047] Presentation of proposal

[0048] terminal

[0049] The device displays skincare suggestions and usage instructions received from the server in an easy-to-understand format within the application. This display includes information such as the number of times and times to use the product, and any precautions.

[0050] User

[0051] Users can review the suggested skincare plan and incorporate it into their daily routine. They can also submit feedback through the application after implementing the plan.

[0052] This format allows users to easily obtain appropriate skincare methods tailored to their ever-changing skin condition, and to enjoy personalized suggestions in real time. The system also includes a program that continuously learns from user feedback to improve the accuracy of its suggestions.

[0053] The following describes the processing flow.

[0054] Step 1:

[0055] The user launches a dedicated application and takes a photo of their face using the camera function. Once the photo is taken, they review the image and save it to their device.

[0056] Step 2:

[0057] Upon receiving an image, the terminal performs preprocessing to automatically adjust the image resolution and brightness to a state suitable for analysis. The processed image data is then sent to the server.

[0058] Step 3:

[0059] The server inputs the received facial images into a deep learning-based model to analyze the skin condition. At this stage, it outputs numerical data representing dryness, blemishes, wrinkles, enlarged pores, redness, and other factors.

[0060] Step 4:

[0061] Based on the analyzed skin condition data, the server searches its internal database for suitable skin care products and methods. It also references past user data and product ingredient information to provide optimal recommendations.

[0062] Step 5:

[0063] The server obtains current environmental data through an external weather information API. Based on information such as temperature, humidity, and UV index, it adjusts skincare methods to suit the environmental conditions.

[0064] Step 6:

[0065] The server sends a customized skincare plan to the device. The plan specifies the exact usage, frequency, timing, and precautions for each product.

[0066] Step 7:

[0067] The device displays the received skin care plan to the user. The user can review the presented plan and incorporate it into their daily care routine. Furthermore, a function is implemented to send feedback after care has been performed via the application.

[0068] (Example 1)

[0069] 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."

[0070] In recent years, there has been a growing demand for personalized skincare tailored to each user's skin condition. However, traditional methods require specialized knowledge and considerable time to accurately assess a user's skin condition and propose optimal care. Furthermore, considering environmental factors in proposals is even more difficult, and systems that provide real-time, individually tailored skincare are still not widespread.

[0071] 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.

[0072] In this invention, the server includes means for acquiring a facial image captured by the user, means for optimizing the acquired facial image for analysis using image processing technology, means for analyzing the optimized image and quantifying the skin condition as a feature, means for comparing the analysis results with internal information and proposing personalized skin care products and methods that are optimal for the user, and means for acquiring external environmental information and dynamically adjusting the proposed content. This makes it possible to provide personalized skincare suggestions in real time based on the user's skin condition and the environment at that time.

[0073] A "user" is an individual who uses the system to analyze their skin condition and receive skincare recommendations.

[0074] A "face image" is digital photographic data of a face taken by a user using the device's camera.

[0075] "Image processing technology" refers to algorithms and software used to analyze, transform, and store digital images, and is a technology used to optimize image resolution and brightness.

[0076] "Analysis" is the process of using image processing technology to numerically identify the condition of the skin from a facial image and outputting it as structured data.

[0077] "Skin condition" refers to an indicator that describes the characteristics of facial skin, and includes factors such as dryness, blemishes, wrinkles, enlarged pores, and the degree of redness.

[0078] "Personalized skin care products and methods" refers to skincare products and their usage procedures that are specifically recommended for the user based on the analysis results.

[0079] "External environmental information" refers to information such as current weather, temperature, humidity, and UV index obtained from external data sources referenced by the device.

[0080] The embodiment of this invention is based on a series of operations designed to maximize the user experience. The user first uses a device with a dedicated application installed. They launch this application and take a photograph of their face using the device's camera function. Taking the photograph under appropriate lighting conditions is recommended.

[0081] The captured facial images are temporarily stored in a cache by the device, and their resolution and brightness are optimized for analysis using image processing technology. At this stage, image processing software such as OpenCV is used. The optimized image data is then sent to a server via the network.

[0082] The server analyzes the received image data using TENSORFLOW® as a deep learning framework. This analysis quantifies the user's facial skin condition and outputs it as structured data. Specifically, it identifies factors such as skin dryness, blemishes, wrinkles, enlarged pores, and redness. These analysis results are stored in an internal database.

[0083] The server then references an internal database and past user data to suggest the most suitable, personalized skincare products and methods for the user. This process includes evaluating ingredient compatibility and effectiveness. It also uses an external weather information API to retrieve current environmental data and dynamically adjust the suggestions.

[0084] For example, if a user's skin analysis results indicate high dryness, the server will suggest a highly moisturizing cream. Furthermore, if the environmental conditions are determined to be low humidity and high UV index, the server will also recommend using sunscreen in conjunction with the cream.

[0085] An example of a prompt to input into a generative AI model is: "Please recommend the best skincare products for dry skin. The environment is 25°C, 40% humidity, and a UV index of 7."

[0086] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0087] Step 1:

[0088] The user launches a dedicated application and uses the device's camera to take a picture of their face. The input is a facial image, and the output is a digital image file temporarily stored on the device. The captured image is automatically checked for brightness and focus within the application, and if it does not meet the standards, the user is prompted to retake the picture.

[0089] Step 2:

[0090] The terminal performs image processing on the saved face image. The input is the face image captured in step 1, and the output is an image optimized for analysis. The terminal uses image processing software (e.g., OpenCV) to adjust the image resolution and remove noise. After this optimization process, the image data is ready to be sent to the server.

[0091] Step 3:

[0092] The server receives optimized facial images sent from the terminal. The input is the optimized facial image, and the output is data quantifying skin features. The server uses a deep learning framework (e.g., TensorFlow) to analyze this image and extract numerical values ​​for skin dryness, blemishes, wrinkles, enlarged pores, and redness. These individual features are then recorded in a database.

[0093] Step 4:

[0094] The server selects the most suitable skincare products and methods for the user based on the analysis results. The input is the analysis results data from step 3, and the output is a personalized skincare recommendation. The server compares this with its internal database to select products that match the user's skin condition. This selection process also takes into account the compatibility of the ingredients in the products and past user data.

[0095] Step 5:

[0096] The server retrieves current environmental data by referencing an external weather information API and adjusts the recommendations accordingly. The input is weather data for the current environment, and the output is the adjusted skincare recommendation. For example, it decides whether to enhance moisturizing or add sunscreen based on the current humidity and UV index.

[0097] Step 6:

[0098] The device displays optimal skincare suggestions received from the server to the user within the application. The input is the adjusted skincare suggestions from step 5, and the output is visually understandable information presented to the user. This information includes product usage instructions, timing, and precautions.

[0099] Step 7:

[0100] Users can incorporate the suggested skincare plan into their daily routine and send feedback on the results to the server via the application. The input is the user's feedback information, and the output is used by the server to update the data and improve accuracy. In this way, the system learns from the user's feedback and improves the accuracy of future suggestions.

[0101] (Application Example 1)

[0102] 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."

[0103] Many modern consumers desire personalized skincare recommendations based on their skin condition. However, current methods rely on limited information for skin condition analysis, resulting in limitations in the accuracy and suitability of these recommendations. Furthermore, there is a lack of effective means to present these recommendations clearly to users. Continuous learning through feedback after recommendations are also needed to improve accuracy.

[0104] 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.

[0105] In this invention, the server includes means for coordinating with a mechanical device that presents analysis results in audio and visual information, means for collecting user feedback after implementation of the proposed treatment and improving the accuracy of the analysis, and means for acquiring ambient environmental data and adjusting the proposed treatment. This makes it possible to provide users with comprehensive, personalized skin care suggestions and to improve the accuracy of the suggestions by utilizing the data after implementation.

[0106] "User" refers to an individual who wishes to use the system to analyze their skin condition and receive skincare recommendations.

[0107] A "facial image" is a digital image data of a user's face, which is used for analyzing their skin condition.

[0108] "Methods for analyzing skin condition" refer to processing methods that use facial images to detect skin health and characteristics, and generate numerical results as structured data.

[0109] "Means of proposing optimal skin care products and methods" refers to the process of selecting and providing skin care products and methods suitable for the user based on the analysis results.

[0110] "Environmental data" refers to information about external factors such as ambient temperature, humidity, and UV index, and is used to adjust skincare recommendations.

[0111] A "mechanical device that presents analysis results using audio and visual information" refers to hardware that uses audio and a display to provide information to users in order to help them intuitively understand skin care suggestions.

[0112] "Means for collecting user feedback and improving analysis accuracy" refers to methods for receiving the results of using the proposed care methods and continuously improving the system's learning model based on those results.

[0113] To implement this invention, the entire system needs to be coordinated via a terminal, a server, and mechanical devices. First, the terminal acquires a facial image from the user. To maintain high-quality input, the resolution and brightness of this image are adjusted within the terminal, and then it is transmitted to the server.

[0114] On the server, deep learning-based image recognition technology is applied to extract skin features from facial images. This process utilizes machine learning frameworks such as TensorFlow or PyTorch. The server compares the analyzed results with an internal database and further refines the recommendations by referencing external weather information. This generates a personalized skincare plan for each user.

[0115] Next, the machine communicates the generated skincare recommendations to the user through voice and visual displays. Specifically, this is achieved by home voice assistants and display-equipped devices. This provides information that is both visual and auditory, making it easier for the user to understand the recommendations.

[0116] Furthermore, after the user tries out the suggested plan, the device collects feedback from the user. This information is then sent back to the server to improve the accuracy of the suggestions and is used to help the entire system learn. Through feedback, the suggestions become increasingly accurate and personalized.

[0117] For example, on days with high humidity, the system could provide voice advice such as, "Please use less moisturizing cream today." Also, if a user reports that their blemishes have become more noticeable, the next recommendation might include a product containing more effective whitening ingredients.

[0118] Examples of prompts generated by AI include the following:

[0119] "Analyze images taken with a smartphone and suggest skincare methods suitable for an environment with 70% humidity."

[0120] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0121] Step 1:

[0122] The device acquires a facial image from the user and temporarily stores it in a cache. Here, the input is a facial image captured by the camera, and the output is an image file with adjusted resolution and brightness. The device processes and optimizes the image quality to prepare it for transmission to the server.

[0123] Step 2:

[0124] The device sends a facial image to the server. The input is an optimized facial image, and the output is a notification that the image transfer to the server is complete. This allows the server to proceed to the next analysis step.

[0125] Step 3:

[0126] The server analyzes the facial images it receives using a deep learning model. The input is a facial image sent from the terminal, and the output is quantified data indicating skin condition. The server processes the image and quantifies skin characteristics such as blemishes, wrinkles, and dryness.

[0127] Step 4:

[0128] The server uses the analysis results to refer to an internal database and select appropriate skincare products and methods. The input is skin analysis data, and the output is a product list and care plan. The server retrieves product information best suited to the user's skin type.

[0129] Step 5:

[0130] The server references an external weather information database and adjusts the suggested skincare routine based on environmental data. Input is current temperature and humidity data, and output is the adjusted skincare plan. The server adapts the suggested routine to the environmental conditions.

[0131] Step 6:

[0132] The machine presents the proposed skincare plan to the user using audio and visual information. The input is the skincare plan received from the server, and the output is the provision of information to the user via audio and display. The machine clearly explains the plan's contents.

[0133] Step 7:

[0134] After a user completes their skincare plan, they use a device to send feedback to the system. The input is the user's usage results and feedback, and the output is feedback data sent to the server. This allows the server to improve the accuracy of subsequent analyses.

[0135] 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.

[0136] This invention provides a system that acquires a user's facial image and analyzes their skin condition and emotions based on that image. This system not only suggests the most suitable skin care products and methods for the user, but also takes their emotional state into consideration to provide more personalized suggestions.

[0137] Image acquisition and emotion recognition

[0138] User

[0139] The user installs a dedicated application on their device, launches the app, and takes a photo of their face. This captures both the facial image and facial expression data.

[0140] terminal

[0141] The device stores the acquired facial image in a temporary cache and uses an emotion recognition engine to analyze the user's emotional state. For example, it can determine whether the user is smiling or feeling stressed.

[0142] Skin condition analysis and utilization of emotional data

[0143] server

[0144] The server uses image analysis algorithms to analyze skin conditions such as dryness, blemishes, wrinkles, enlarged pores, and redness from facial images. The analysis results are stored as structured data.

[0145] server

[0146] The server optimizes the recommendations for skincare products and methods based on emotional data acquired by the emotion engine. For example, it seeks care methods that match the user's emotions, such as suggesting relaxing products when stressed or whitening products when happy.

[0147] Proposal presentation and feedback

[0148] terminal

[0149] The device displays a skin care plan and usage instructions provided by the server to the user. The plan includes information such as specific product names, usage time, frequency, and purpose.

[0150] User

[0151] Users can use the suggested plan as a reference to implement their daily care. They can also input feedback, such as usage results and impressions, within the application, which will be used to improve future suggestions.

[0152] This system integrates emotion recognition into skincare recommendations, enabling it to provide users with comprehensive support. Each module of the program is designed to adapt to dynamic changes in skin condition and emotions to enhance the user experience.

[0153] The following describes the processing flow.

[0154] Step 1:

[0155] The user launches a dedicated application and takes a photo of their face using the camera function. Along with the face image, a prompt appears to capture their facial expression, and the user faces the camera with a natural expression.

[0156] Step 2:

[0157] The device temporarily stores the captured facial image in a cache and extracts facial expression data from the image. The emotion recognition engine then activates and determines the emotional characteristics from the current facial expression. For example, it quantifies emotional states such as smiling, stern, or tense.

[0158] Step 3:

[0159] The device sends optimized facial images and emotion data to the server for analysis. This includes adjusting image resolution and removing unwanted backgrounds.

[0160] Step 4:

[0161] The server uses the received image as an analysis trigger to analyze the skin condition using a deep learning-based model. Digital processing is performed to measure dryness, the intensity of blemishes, and the depth of wrinkles.

[0162] Step 5:

[0163] The server references emotional data obtained from the emotion engine along with the analysis results. Based on this data, it selects suitable skin care products and methods from its internal database. For example, when the user is under high stress, it selects products with calming effects.

[0164] Step 6:

[0165] The server acquires external environmental data, such as temperature, humidity, and UV radiation levels, to further optimize the selected skin care plan. This environmental data is then reflected in the proposed plan.

[0166] Step 7:

[0167] The device displays an optimized skincare plan received from the server to the user. The plan includes information on how to use the products, how often to use them, and when to apply them.

[0168] Step 8:

[0169] Users review the displayed skincare plan and incorporate it into their daily routine. After completing the care, they can input their experience and feedback using the in-app feedback function, which will then be reflected in future suggestions.

[0170] (Example 2)

[0171] 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".

[0172] Current technologies that individually analyze a person's physical state and emotions and then propose lifestyle products based on that analysis have a challenge in that they cannot adequately personalize the process to improve the user's quality of life. In particular, it is difficult to propose products that take emotional states into account, making it challenging to provide proposals that meet the diverse needs of users.

[0173] 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.

[0174] In this invention, the server includes means for acquiring biometric information obtained from the user using image functions, means for analyzing the emotional state using an analysis device and generating emotional data, and means for integrating the emotional data and skin condition data and optimizing the suggested content using a generative intelligence model. This enables a comprehensive analysis of the user's biometric and emotional states, making it possible to propose more personalized and appropriate lifestyle products and methods.

[0175] "Biometric information" refers to data such as facial images and physical characteristics obtained from users.

[0176] "Personalized lifestyle products" refer to products such as skincare products and health goods that are suggested based on the specific needs and conditions of the user.

[0177] An "analysis device" refers to equipment or software used to process acquired data and analyze information such as emotions and skin condition.

[0178] "Emotional data" refers to numerical or categorical data that indicates the emotional state of a user, analyzed from their facial expressions and biometric information.

[0179] A "generative intelligence model" refers to an algorithm or program that uses artificial intelligence technology to analyze data and generate optimal suggestions.

[0180] This invention provides a system that analyzes a user's biometric information and suggests personalized lifestyle products based on their emotions and physical state. The implementation of this system is carried out using the hardware and software described below, following a specific process.

[0181] User actions:

[0182] The user begins by installing a dedicated application on their device. They then launch the application and use the device's camera to acquire biometric information, such as facial images. During this process, the app checks image quality in real time and can request the user to retake the image if necessary.

[0183] Device operation:

[0184] The device temporarily stores the acquired biometric information in its internal storage. This stored data is then transmitted to the analysis device described below. The analysis device can utilize software for analyzing emotional states, such as a general image recognition engine or machine learning algorithm.

[0185] Server operation:

[0186] The server receives biometric information transmitted from the terminal and analyzes the data using an analysis device that generates emotional data. The analysis can utilize a model to infer emotional states from facial features. Furthermore, it leverages a generative AI model to integrate the acquired emotional data and biometric data to generate optimal suggestions. These suggestions include lists of lifestyle products and care methods suitable for the user's condition. For example, if a stressful state is detected, products with relaxing effects will be recommended.

[0187] Proposal presentation:

[0188] The generated suggestions are provided to the user via a terminal. The terminal screen displays detailed information about the suggested product name and usage, which the user can review. For example, a prompt message such as, "Your facial image has been analyzed, and your skin is dry and your emotional state is stressed. Please suggest appropriate skincare products," might be output. This allows the user to take action to improve their quality of life based on the information provided.

[0189] This system configuration enables specific and personalized suggestions tailored to the user's emotional and biological state, contributing to improvements in their daily life.

[0190] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0191] Step 1:

[0192] The user launches a dedicated application and takes a facial image using the device's camera. The application assists in this process by checking image resolution and lighting conditions to ensure optimal capture. The input is a facial image acquired through the camera, and the output is high-quality facial image data.

[0193] Step 2:

[0194] The device temporarily stores the captured facial images in a cache. This storage utilizes internal storage to prepare for subsequent data analysis. The input is facial image data sent by the user, and the output is image data temporarily stored within the device.

[0195] Step 3:

[0196] The device activates an emotion analysis engine and analyzes the acquired facial image data. During this process, image recognition technology is used to characterize emotions such as smiles and stress. The input is a facial image stored in the cache, and the output is the analyzed emotion data.

[0197] Step 4:

[0198] The device sends emotion data and facial image data to the server. The data is securely transmitted via a communication protocol and prepared for further detailed analysis on the server. The input is the emotion data and facial image stored on the device, and the output is the data transfer to the server.

[0199] Step 5:

[0200] The server analyzes the skin condition based on the received data. It uses image analysis algorithms to detect skin features such as blemishes, wrinkles, and dryness. The input is a facial image sent to the server, and the output is the analysis result, including specific skin condition characteristics.

[0201] Step 6:

[0202] The server integrates emotional data and skin condition data, and uses a generative AI model to generate optimal suggestions. These suggestions include products and care methods tailored to the user's condition and are personalized by the generative AI model. The input is emotional data and skin condition data, and the output is customized suggestions.

[0203] Step 7:

[0204] The terminal receives suggestions from the server and displays them to the user. Detailed product information and usage guidelines are presented on the screen, allowing the user to use the suggestions to improve their daily life. The input is suggestion data from the server, and the output is a visualized suggestion of products and care methods for the user.

[0205] (Application Example 2)

[0206] 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".

[0207] Modern consumers struggle to choose the right skincare products from the wide variety available. Furthermore, since a consumer's emotional state and surrounding environment influence their skin condition, there is a need for product recommendations that take these factors into account. Traditional skincare product recommendations often fail to consider emotional states and surrounding environments, resulting in insufficient individualization.

[0208] 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.

[0209] In this invention, the server includes means for acquiring facial information captured from the user, means for analyzing the skin condition based on the acquired facial information, and means for identifying the emotional state of the analyzed facial information. This makes it possible to propose more personalized skin care products that take into account the user's emotional state and surrounding environment.

[0210] "Users" refers to individuals who use the skin care product recommendation system.

[0211] "Facial information" refers to data extracted from images of a user's face.

[0212] "Skin condition" refers to specific characteristics of the skin, such as dryness, blemishes, wrinkles, enlarged pores, and redness, as analyzed from facial information.

[0213] "Emotional state" refers to the user's psychological situation and mental state as determined by their facial expressions, as analyzed from facial information.

[0214] "External environmental information" refers to environmental data such as temperature, humidity, and weather present in the user's surroundings.

[0215] "Recommendation" refers to the act of recommending the most suitable skin care products and their usage methods to the user, based on the analyzed skin condition, emotional state, and external environmental information.

[0216] "Image recognition technology" refers to the technology that uses computers to extract specific information from image data and then recognize, classify, or interpret it.

[0217] "Structured data" refers to data that is organized according to a specific format and is easy for machines to interpret and analyze.

[0218] "External data storage" refers to databases or cloud storage that contain product information and can be accessed via a network.

[0219] In the system that realizes this application example, hardware such as terminals, servers, and robots work together to provide users with optimal skin care suggestions.

[0220] The device is equipped with a camera and image processing software, and has the function of capturing the user's face. This image data is temporarily stored using an image processing library such as OpenCV. Subsequently, the facial information is sent to a database and then transferred to a server for further detailed analysis.

[0221] The server utilizes machine learning models such as TensorFlow to analyze skin condition from acquired facial information. Furthermore, to understand the user's emotional state, it acquires emotional data using emotion recognition technologies such as Microsoft® Azure® Emotion API. Based on the analysis results, it then uses a generative AI model to create recommendations for appropriate skin care products and methods. If necessary, it retrieves product information from external databases to improve the quality of the recommendations.

[0222] Users can refer to the suggestions displayed on their device and incorporate them into their daily skincare routine. The suggestions include detailed information such as recommended products, usage instructions, and frequency. Users can also provide feedback, which will be incorporated into future suggestions.

[0223] As a concrete example, consider a scenario where a user casually spends a holiday morning at home using this system. If the robot captures facial information and analyzes it to determine that the skin is dry, it will recommend the use of a relaxing moisturizing cream. In addition, if it recognizes that the user's recent emotions tend to be stressful, it will suggest the use of aromatherapy products. In this way, the system comprehensively analyzes the user's internal and external state to provide optimal skincare.

[0224] An example of a prompt message for a generative AI model is: "This user's current skin condition is dry. Sentiment analysis indicates they are experiencing stress. What skincare products would you recommend?"

[0225] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0226] Step 1:

[0227] The device uses a camera to capture the user's facial information. The input is the image from the camera, and the output is the acquired facial image data. This image data is temporarily stored in memory in preparation for the next analysis process.

[0228] Step 2:

[0229] The server receives facial image data sent from the terminal. The input is facial image data from the terminal, and the output is the utilization of that data. A machine learning model is used to analyze the skin condition from this facial image data and extract specific skin characteristics such as dryness, wrinkles, and blemishes.

[0230] Step 3:

[0231] The server analyzes the emotional state using an emotion recognition API along with facial image data. The input is facial image data, and the output is the analyzed emotion data. Through emotional state recognition, information such as whether the user is currently stressed or relaxed is obtained.

[0232] Step 4:

[0233] The server generates optimal skincare suggestions using a generative AI model based on acquired skin condition and emotional state data. The input is analyzed skin and emotional data, and the output is the suggested content. This process accesses external databases and customizes suggestions by referencing various product information.

[0234] Step 5:

[0235] The terminal displays the suggestions received from the server to the user. The input is the suggestions from the server, and the output is a visual presentation of information to the user. The suggestions include specific product names, usage instructions, and frequency information.

[0236] Step 6:

[0237] Users perform their daily skincare routine based on the provided suggestions. By providing feedback, the quality of future suggestions can be improved. Input consists of the user's own actions and feedback, while output is the collection of feedback data.

[0238] 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.

[0239] 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.

[0240] 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.

[0241] [Second Embodiment]

[0242] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0243] 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.

[0244] 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).

[0245] 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.

[0246] 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.

[0247] 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).

[0248] 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.

[0249] 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.

[0250] 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.

[0251] 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.

[0252] 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.

[0253] 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".

[0254] This invention describes an embodiment for implementing a system that analyzes skin condition using facial images taken by a user and provides optimal skin care products and methods.

[0255] Image acquisition

[0256] User

[0257] The user uses a device with the dedicated application installed and launches the application. Within the application, they are prompted to use the camera function to take a photo of their face.

[0258] terminal

[0259] The device temporarily stores the facial image captured by the user in its own cache and automatically performs processing to optimize the image's resolution and brightness for analysis. Afterward, it sends the image to the server.

[0260] Image analysis

[0261] server

[0262] When the server receives an image, it starts analyzing it using a pre-trained deep learning model. This analysis outputs numerical data indicating the degree of dryness of the facial skin, the number of blemishes and wrinkles, the size of pores, and the degree of redness.

[0263] Skincare suggestions

[0264] server

[0265] Based on the analysis results, the server consults an internal database to select skincare products and methods suitable for the user. Product selection utilizes factors such as ingredient compatibility and past user data.

[0266] server

[0267] The server also references external weather information APIs to obtain environmental data such as current temperature, humidity, and UV index. This allows it to adjust the skincare methods provided to users based on environmental conditions.

[0268] Presentation of proposal

[0269] terminal

[0270] The device displays skincare suggestions and usage instructions received from the server in an easy-to-understand format within the application. This display includes information such as the number of times and times to use the product, and any precautions.

[0271] User

[0272] Users can review the suggested skincare plan and incorporate it into their daily routine. They can also submit feedback through the application after implementing the plan.

[0273] This format allows users to easily obtain appropriate skincare methods tailored to their ever-changing skin condition, and to enjoy personalized suggestions in real time. The system also includes a program that continuously learns from user feedback to improve the accuracy of its suggestions.

[0274] The following describes the processing flow.

[0275] Step 1:

[0276] The user launches a dedicated application and takes a photo of their face using the camera function. Once the photo is taken, they review the image and save it to their device.

[0277] Step 2:

[0278] Upon receiving an image, the terminal performs preprocessing to automatically adjust the image resolution and brightness to a state suitable for analysis. The processed image data is then sent to the server.

[0279] Step 3:

[0280] The server inputs the received facial images into a deep learning-based model to analyze the skin condition. At this stage, it outputs numerical data representing dryness, blemishes, wrinkles, enlarged pores, redness, and other factors.

[0281] Step 4:

[0282] Based on the analyzed skin condition data, the server searches its internal database for suitable skin care products and methods. It also references past user data and product ingredient information to provide optimal recommendations.

[0283] Step 5:

[0284] The server obtains current environmental data through an external weather information API. Based on information such as temperature, humidity, and UV index, it adjusts the skin care method according to the environmental conditions.

[0285] Step 6:

[0286] The server sends the adjusted skin care plan to the terminal. The plan specifies the specific usage method, frequency, time zone, precautions, etc. of the product.

[0287] Step 7:

[0288] The terminal displays the received skin care plan to the user. The user can check the presented plan and incorporate it into daily care. Furthermore, a function to send feedback after care via the application is implemented.

[0289] (Example 1)

[0290] Next, Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0291] In recent years, the demand for personalized skin care according to the user's skin condition has been increasing. However, with conventional methods, it requires specialized knowledge and a lot of time to accurately recognize the user's skin condition and provide the optimal care proposal. In addition, it is even more difficult to consider environmental factors, and systems that provide individually suitable skin care in real time are hardly widespread.

[0292] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0293] In this invention, the server includes means for acquiring a facial image captured by the user, means for optimizing the acquired facial image for analysis using image processing technology, means for analyzing the optimized image and quantifying the skin condition as a feature, means for comparing the analysis results with internal information and proposing personalized skin care products and methods that are optimal for the user, and means for acquiring external environmental information and dynamically adjusting the proposed content. This makes it possible to provide personalized skincare suggestions in real time based on the user's skin condition and the environment at that time.

[0294] A "user" is an individual who uses the system to analyze their skin condition and receive skincare recommendations.

[0295] A "face image" is digital photographic data of a face taken by a user using the device's camera.

[0296] "Image processing technology" refers to algorithms and software used to analyze, transform, and store digital images, and is a technology used to optimize image resolution and brightness.

[0297] "Analysis" is the process of using image processing technology to numerically identify the condition of the skin from a facial image and outputting it as structured data.

[0298] "Skin condition" refers to an indicator that describes the characteristics of facial skin, and includes factors such as dryness, blemishes, wrinkles, enlarged pores, and the degree of redness.

[0299] "Personalized skin care products and methods" refers to skincare products and their usage procedures that are specifically recommended for the user based on the analysis results.

[0300] "External environmental information" refers to information such as current weather, temperature, humidity, and UV index obtained from external data sources referenced by the device.

[0301] The embodiment of this invention is based on a series of operations designed to maximize the user experience. The user first uses a device with a dedicated application installed. They launch this application and take a photograph of their face using the device's camera function. Taking the photograph under appropriate lighting conditions is recommended.

[0302] The captured facial images are temporarily stored in a cache by the device, and their resolution and brightness are optimized for analysis using image processing technology. At this stage, image processing software such as OpenCV is used. The optimized image data is then sent to a server via the network.

[0303] The server analyzes the received image data using TensorFlow as a deep learning framework. This analysis allows the server to quantify the user's facial skin condition and output it as structured data. Specifically, it identifies factors such as skin dryness, blemishes, wrinkles, enlarged pores, and redness. These analysis results are stored in an internal database.

[0304] The server then references an internal database and past user data to suggest the most suitable, personalized skincare products and methods for the user. This process includes evaluating ingredient compatibility and effectiveness. It also uses an external weather information API to retrieve current environmental data and dynamically adjust the suggestions.

[0305] For example, if a user's skin analysis results indicate high dryness, the server will suggest a highly moisturizing cream. Furthermore, if the environmental conditions are determined to be low humidity and high UV index, the server will also recommend using sunscreen in conjunction with the cream.

[0306] An example of a prompt to input into a generative AI model is: "Please recommend the best skincare products for dry skin. The environment is 25°C, 40% humidity, and a UV index of 7."

[0307] The flow of the specific process in Example 1 will be described with reference to FIG. 11.

[0308] Step 1:

[0309] The user launches a dedicated application and uses the camera function of the terminal to take a picture of their face. The input is a face image, and the output is a digital image file temporarily saved on the terminal. The captured image is automatically checked for brightness and focus within the application, and if it does not meet the criteria, it is set to prompt re - shooting.

[0310] Step 2:

[0311] The terminal performs image processing on the saved face image. The input is the face image captured in Step 1, and the output is an image optimized for analysis. The terminal uses image - processing software (e.g., OpenCV) to adjust the resolution of the image and remove noise. After this optimization process, the image data is ready to be sent to the server.

[0312] Step 3:

[0313] The server receives the optimized face image sent from the terminal. The input is the optimized face image, and the output is data that quantifies the characteristics of the skin. The server uses a deep - learning framework (e.g., TensorFlow) to analyze this image and extract the dryness, spots, wrinkles, pore expansion, and degree of redness of the skin as numerical values. As a result, individual characteristics are recorded in the database.

[0314] Step 4:

[0315] Based on the analysis results, the server selects the most suitable skin - care products and methods for the user. The input is the analysis result data from Step 3, and the output is an individualized skin - care proposal. The server checks against an internal database and selects products suitable for the user's skin condition. In this selection process, the compatibility of the ingredients contained in the products and past user data are also taken into consideration.

[0316] Step 5:

[0317] The server retrieves current environmental data by referencing an external weather information API and adjusts the recommendations accordingly. The input is weather data for the current environment, and the output is the adjusted skincare recommendation. For example, it decides whether to enhance moisturizing or add sunscreen based on the current humidity and UV index.

[0318] Step 6:

[0319] The device displays optimal skincare suggestions received from the server to the user within the application. The input is the adjusted skincare suggestions from step 5, and the output is visually understandable information presented to the user. This information includes product usage instructions, timing, and precautions.

[0320] Step 7:

[0321] Users can incorporate the suggested skincare plan into their daily routine and send feedback on the results to the server via the application. The input is the user's feedback information, and the output is used by the server to update the data and improve accuracy. In this way, the system learns from the user's feedback and improves the accuracy of future suggestions.

[0322] (Application Example 1)

[0323] 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."

[0324] Many modern consumers desire personalized skincare recommendations based on their skin condition. However, current methods rely on limited information for skin condition analysis, resulting in limitations in the accuracy and suitability of these recommendations. Furthermore, there is a lack of effective means to present these recommendations clearly to users. Continuous learning through feedback after recommendations are also needed to improve accuracy.

[0325] 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.

[0326] In this invention, the server includes means for coordinating with a mechanical device that presents analysis results in audio and visual information, means for collecting user feedback after implementation of the proposed treatment and improving the accuracy of the analysis, and means for acquiring ambient environmental data and adjusting the proposed treatment. This makes it possible to provide users with comprehensive, personalized skin care suggestions and to improve the accuracy of the suggestions by utilizing the data after implementation.

[0327] "User" refers to an individual who wishes to use the system to analyze their skin condition and receive skincare recommendations.

[0328] A "facial image" is a digital image data of a user's face, which is used for analyzing their skin condition.

[0329] "Methods for analyzing skin condition" refer to processing methods that use facial images to detect skin health and characteristics, and generate numerical results as structured data.

[0330] "Means of proposing optimal skin care products and methods" refers to the process of selecting and providing skin care products and methods suitable for the user based on the analysis results.

[0331] "Environmental data" refers to information about external factors such as ambient temperature, humidity, and UV index, and is used to adjust skincare recommendations.

[0332] A "mechanical device that presents analysis results using audio and visual information" refers to hardware that uses audio and a display to provide information to users in order to help them intuitively understand skin care suggestions.

[0333] "Means for collecting user feedback and improving analysis accuracy" refers to methods for receiving the results of using the proposed care methods and continuously improving the system's learning model based on those results.

[0334] To implement this invention, the entire system needs to be coordinated via a terminal, a server, and mechanical devices. First, the terminal acquires a facial image from the user. To maintain high-quality input, the resolution and brightness of this image are adjusted within the terminal, and then it is transmitted to the server.

[0335] On the server, deep learning-based image recognition technology is applied to extract skin features from facial images. This process utilizes machine learning frameworks such as TensorFlow or PyTorch. The server compares the analyzed results with an internal database and further refines the recommendations by referencing external weather information. This generates a personalized skincare plan for each user.

[0336] Next, the machine communicates the generated skincare recommendations to the user through voice and visual displays. Specifically, this is achieved by home voice assistants and display-equipped devices. This provides information that is both visual and auditory, making it easier for the user to understand the recommendations.

[0337] Furthermore, after the user tries out the suggested plan, the device collects feedback from the user. This information is then sent back to the server to improve the accuracy of the suggestions and is used to help the entire system learn. Through feedback, the suggestions become increasingly accurate and personalized.

[0338] For example, on days with high humidity, the system could provide voice advice such as, "Please use less moisturizing cream today." Also, if a user reports that their blemishes have become more noticeable, the next recommendation might include a product containing more effective whitening ingredients.

[0339] Examples of prompts generated by AI include the following:

[0340] "Analyze images taken with a smartphone and suggest skincare methods suitable for an environment with 70% humidity."

[0341] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0342] Step 1:

[0343] The device acquires a facial image from the user and temporarily stores it in a cache. Here, the input is a facial image captured by the camera, and the output is an image file with adjusted resolution and brightness. The device processes and optimizes the image quality to prepare it for transmission to the server.

[0344] Step 2:

[0345] The device sends a facial image to the server. The input is an optimized facial image, and the output is a notification that the image transfer to the server is complete. This allows the server to proceed to the next analysis step.

[0346] Step 3:

[0347] The server analyzes the facial images it receives using a deep learning model. The input is a facial image sent from the terminal, and the output is quantified data indicating skin condition. The server processes the image and quantifies skin characteristics such as blemishes, wrinkles, and dryness.

[0348] Step 4:

[0349] The server uses the analysis results to refer to an internal database and select appropriate skincare products and methods. The input is skin analysis data, and the output is a product list and care plan. The server retrieves product information best suited to the user's skin type.

[0350] Step 5:

[0351] The server references an external weather information database and adjusts the suggested skincare routine based on environmental data. Input is current temperature and humidity data, and output is the adjusted skincare plan. The server adapts the suggested routine to the environmental conditions.

[0352] Step 6:

[0353] The machine presents the proposed skincare plan to the user using audio and visual information. The input is the skincare plan received from the server, and the output is the provision of information to the user via audio and display. The machine clearly explains the plan's contents.

[0354] Step 7:

[0355] After a user completes their skincare plan, they use a device to send feedback to the system. The input is the user's usage results and feedback, and the output is feedback data sent to the server. This allows the server to improve the accuracy of subsequent analyses.

[0356] 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.

[0357] This invention provides a system that acquires a user's facial image and analyzes their skin condition and emotions based on that image. This system not only suggests the most suitable skin care products and methods for the user, but also takes their emotional state into consideration to provide more personalized suggestions.

[0358] Image acquisition and emotion recognition

[0359] User

[0360] The user installs a dedicated application on their device, launches the app, and takes a photo of their face. This captures both the facial image and facial expression data.

[0361] terminal

[0362] The device stores the acquired facial image in a temporary cache and uses an emotion recognition engine to analyze the user's emotional state. For example, it can determine whether the user is smiling or feeling stressed.

[0363] Skin condition analysis and utilization of emotional data

[0364] server

[0365] The server uses image analysis algorithms to analyze skin conditions such as dryness, blemishes, wrinkles, enlarged pores, and redness from facial images. The analysis results are stored as structured data.

[0366] server

[0367] The server optimizes the recommendations for skincare products and methods based on emotional data acquired by the emotion engine. For example, it seeks care methods that match the user's emotions, such as suggesting relaxing products when stressed or whitening products when happy.

[0368] Proposal presentation and feedback

[0369] terminal

[0370] The device displays a skin care plan and usage instructions provided by the server to the user. The plan includes information such as specific product names, usage time, frequency, and purpose.

[0371] User

[0372] Users can use the suggested plan as a reference to implement their daily care. They can also input feedback, such as usage results and impressions, within the application, which will be used to improve future suggestions.

[0373] This system integrates emotion recognition into skincare recommendations, enabling it to provide users with comprehensive support. Each module of the program is designed to adapt to dynamic changes in skin condition and emotions to enhance the user experience.

[0374] The following describes the processing flow.

[0375] Step 1:

[0376] The user launches a dedicated application and takes a photo of their face using the camera function. Along with the face image, a prompt appears to capture their facial expression, and the user faces the camera with a natural expression.

[0377] Step 2:

[0378] The device temporarily stores the captured facial image in a cache and extracts facial expression data from the image. The emotion recognition engine then activates and determines the emotional characteristics from the current facial expression. For example, it quantifies emotional states such as smiling, stern, or tense.

[0379] Step 3:

[0380] The device sends optimized facial images and emotion data to the server for analysis. This includes adjusting image resolution and removing unwanted backgrounds.

[0381] Step 4:

[0382] The server uses the received image as an analysis trigger to analyze the skin condition using a deep learning-based model. Digital processing is performed to measure dryness, the intensity of blemishes, and the depth of wrinkles.

[0383] Step 5:

[0384] The server references emotional data obtained from the emotion engine along with the analysis results. Based on this data, it selects suitable skin care products and methods from its internal database. For example, when the user is under high stress, it selects products with calming effects.

[0385] Step 6:

[0386] The server acquires external environmental data, such as temperature, humidity, and UV radiation levels, to further optimize the selected skin care plan. This environmental data is then reflected in the proposed plan.

[0387] Step 7:

[0388] The device displays an optimized skincare plan received from the server to the user. The plan includes information on how to use the products, how often to use them, and when to apply them.

[0389] Step 8:

[0390] Users review the displayed skincare plan and incorporate it into their daily routine. After completing the care, they can input their experience and feedback using the in-app feedback function, which will then be reflected in future suggestions.

[0391] (Example 2)

[0392] 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".

[0393] Current technologies that individually analyze a person's physical state and emotions and then propose lifestyle products based on that analysis have a challenge in that they cannot adequately personalize the process to improve the user's quality of life. In particular, it is difficult to propose products that take emotional states into account, making it challenging to provide proposals that meet the diverse needs of users.

[0394] 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.

[0395] In this invention, the server includes means for acquiring biometric information obtained from the user using image functions, means for analyzing the emotional state using an analysis device and generating emotional data, and means for integrating the emotional data and skin condition data and optimizing the suggested content using a generative intelligence model. This enables a comprehensive analysis of the user's biometric and emotional states, making it possible to propose more personalized and appropriate lifestyle products and methods.

[0396] "Biometric information" refers to data such as facial images and physical characteristics obtained from users.

[0397] "Personalized lifestyle products" refer to products such as skincare products and health goods that are suggested based on the specific needs and conditions of the user.

[0398] An "analysis device" refers to equipment or software used to process acquired data and analyze information such as emotions and skin condition.

[0399] "Emotional data" refers to numerical or categorical data that indicates the emotional state of a user, analyzed from their facial expressions and biometric information.

[0400] A "generative intelligence model" refers to an algorithm or program that uses artificial intelligence technology to analyze data and generate optimal suggestions.

[0401] This invention provides a system that analyzes a user's biometric information and suggests personalized lifestyle products based on their emotions and physical state. The implementation of this system is carried out using the hardware and software described below, following a specific process.

[0402] User actions:

[0403] The user begins by installing a dedicated application on their device. They then launch the application and use the device's camera to acquire biometric information, such as facial images. During this process, the app checks image quality in real time and can request the user to retake the image if necessary.

[0404] Device operation:

[0405] The device temporarily stores the acquired biometric information in its internal storage. This stored data is then transmitted to the analysis device described below. The analysis device can utilize software for analyzing emotional states, such as a general image recognition engine or machine learning algorithm.

[0406] Server operation:

[0407] The server receives biometric information transmitted from the terminal and analyzes the data using an analysis device that generates emotional data. The analysis can utilize a model to infer emotional states from facial features. Furthermore, it leverages a generative AI model to integrate the acquired emotional data and biometric data to generate optimal suggestions. These suggestions include lists of lifestyle products and care methods suitable for the user's condition. For example, if a stressful state is detected, products with relaxing effects will be recommended.

[0408] Proposal presentation:

[0409] The generated suggestions are provided to the user via a terminal. The terminal screen displays detailed information about the suggested product name and usage, which the user can review. For example, a prompt message such as, "Your facial image has been analyzed, and your skin is dry and your emotional state is stressed. Please suggest appropriate skincare products," might be output. This allows the user to take action to improve their quality of life based on the information provided.

[0410] This system configuration enables specific and personalized suggestions tailored to the user's emotional and biological state, contributing to improvements in their daily life.

[0411] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0412] Step 1:

[0413] The user launches a dedicated application and takes a facial image using the device's camera. The application assists in this process by checking image resolution and lighting conditions to ensure optimal capture. The input is a facial image acquired through the camera, and the output is high-quality facial image data.

[0414] Step 2:

[0415] The device temporarily stores the captured facial images in a cache. This storage utilizes internal storage to prepare for subsequent data analysis. The input is facial image data sent by the user, and the output is image data temporarily stored within the device.

[0416] Step 3:

[0417] The device activates an emotion analysis engine and analyzes the acquired facial image data. During this process, image recognition technology is used to characterize emotions such as smiles and stress. The input is a facial image stored in the cache, and the output is the analyzed emotion data.

[0418] Step 4:

[0419] The device sends emotion data and facial image data to the server. The data is securely transmitted via a communication protocol and prepared for further detailed analysis on the server. The input is the emotion data and facial image stored on the device, and the output is the data transfer to the server.

[0420] Step 5:

[0421] The server analyzes the skin condition based on the received data. It uses image analysis algorithms to detect skin features such as blemishes, wrinkles, and dryness. The input is a facial image sent to the server, and the output is the analysis result, including specific skin condition characteristics.

[0422] Step 6:

[0423] The server integrates emotional data and skin condition data, and uses a generative AI model to generate optimal suggestions. These suggestions include products and care methods tailored to the user's condition and are personalized by the generative AI model. The input is emotional data and skin condition data, and the output is customized suggestions.

[0424] Step 7:

[0425] The terminal receives suggestions from the server and displays them to the user. Detailed product information and usage guidelines are presented on the screen, allowing the user to use the suggestions to improve their daily life. The input is suggestion data from the server, and the output is a visualized suggestion of products and care methods for the user.

[0426] (Application Example 2)

[0427] 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 as the "terminal".

[0428] Modern consumers struggle to choose the right skincare products from the wide variety available. Furthermore, since a consumer's emotional state and surrounding environment influence their skin condition, there is a need for product recommendations that take these factors into account. Traditional skincare product recommendations often fail to consider emotional states and surrounding environments, resulting in insufficient individualization.

[0429] 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.

[0430] In this invention, the server includes means for acquiring facial information captured from the user, means for analyzing the skin condition based on the acquired facial information, and means for identifying the emotional state of the analyzed facial information. This makes it possible to propose more personalized skin care products that take into account the user's emotional state and surrounding environment.

[0431] "Users" refers to individuals who use the skin care product recommendation system.

[0432] "Facial information" refers to data extracted from images of a user's face.

[0433] "Skin condition" refers to specific characteristics of the skin, such as dryness, blemishes, wrinkles, enlarged pores, and redness, as analyzed from facial information.

[0434] "Emotional state" refers to the user's psychological situation and mental state as determined by their facial expressions, as analyzed from facial information.

[0435] "External environmental information" refers to environmental data such as temperature, humidity, and weather present in the user's surroundings.

[0436] "Recommendation" refers to the act of recommending the most suitable skin care products and their usage methods to the user, based on the analyzed skin condition, emotional state, and external environmental information.

[0437] "Image recognition technology" refers to the technology that uses computers to extract specific information from image data and then recognize, classify, or interpret it.

[0438] "Structured data" refers to data that is organized according to a specific format and is easy for machines to interpret and analyze.

[0439] "External data storage" refers to databases or cloud storage that contain product information and can be accessed via a network.

[0440] In the system that realizes this application example, hardware such as terminals, servers, and robots work together to provide users with optimal skin care suggestions.

[0441] The device is equipped with a camera and image processing software, and has the function of capturing the user's face. This image data is temporarily stored using an image processing library such as OpenCV. Subsequently, the facial information is sent to a database and then transferred to a server for further detailed analysis.

[0442] The server utilizes machine learning models such as TensorFlow to analyze skin condition from acquired facial information. Furthermore, it acquires emotional data by using emotion recognition technologies such as Microsoft Azure Emotion API to understand the user's emotional state. Based on the analysis results, it then uses a generative AI model to create recommendations for appropriate skin care products and methods. If necessary, it retrieves product information from external databases to improve the quality of the recommendations.

[0443] Users can refer to the suggestions displayed on their device and incorporate them into their daily skincare routine. The suggestions include detailed information such as recommended products, usage instructions, and frequency. Users can also provide feedback, which will be incorporated into future suggestions.

[0444] As a concrete example, consider a scenario where a user casually spends a holiday morning at home using this system. If the robot captures facial information and analyzes it to determine that the skin is dry, it will recommend the use of a relaxing moisturizing cream. In addition, if it recognizes that the user's recent emotions tend to be stressful, it will suggest the use of aromatherapy products. In this way, the system comprehensively analyzes the user's internal and external state to provide optimal skincare.

[0445] An example of a prompt message for a generative AI model is: "This user's current skin condition is dry. Sentiment analysis indicates they are experiencing stress. What skincare products would you recommend?"

[0446] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0447] Step 1:

[0448] The device uses a camera to capture the user's facial information. The input is the image from the camera, and the output is the acquired facial image data. This image data is temporarily stored in memory in preparation for the next analysis process.

[0449] Step 2:

[0450] The server receives facial image data sent from the terminal. The input is facial image data from the terminal, and the output is the utilization of that data. A machine learning model is used to analyze the skin condition from this facial image data and extract specific skin characteristics such as dryness, wrinkles, and blemishes.

[0451] Step 3:

[0452] The server analyzes the emotional state using an emotion recognition API along with facial image data. The input is facial image data, and the output is the analyzed emotion data. Through emotional state recognition, information such as whether the user is currently stressed or relaxed is obtained.

[0453] Step 4:

[0454] The server generates optimal skincare suggestions using a generative AI model based on acquired skin condition and emotional state data. The input is analyzed skin and emotional data, and the output is the suggested content. This process accesses external databases and customizes suggestions by referencing various product information.

[0455] Step 5:

[0456] The terminal displays the suggestions received from the server to the user. The input is the suggestions from the server, and the output is a visual presentation of information to the user. The suggestions include specific product names, usage instructions, and frequency information.

[0457] Step 6:

[0458] Users perform their daily skincare routine based on the provided suggestions. By providing feedback, the quality of future suggestions can be improved. Input consists of the user's own actions and feedback, while output is the collection of feedback data.

[0459] 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.

[0460] 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.

[0461] 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.

[0462] [Third Embodiment]

[0463] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0464] 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.

[0465] 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).

[0466] 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.

[0467] 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.

[0468] 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).

[0469] 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.

[0470] 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.

[0471] 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.

[0472] 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.

[0473] 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.

[0474] 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".

[0475] This invention describes an embodiment for implementing a system that analyzes skin condition using facial images taken by a user and provides optimal skin care products and methods.

[0476] Image acquisition

[0477] User

[0478] The user uses a device with the dedicated application installed and launches the application. Within the application, they are prompted to use the camera function to take a photo of their face.

[0479] terminal

[0480] The device temporarily stores the facial image captured by the user in its own cache and automatically performs processing to optimize the image's resolution and brightness for analysis. Afterward, it sends the image to the server.

[0481] Image analysis

[0482] server

[0483] When the server receives an image, it starts analyzing it using a pre-trained deep learning model. This analysis outputs numerical data indicating the degree of dryness of the facial skin, the number of blemishes and wrinkles, the size of pores, and the degree of redness.

[0484] Skincare suggestions

[0485] server

[0486] Based on the analysis results, the server consults an internal database to select skincare products and methods suitable for the user. Product selection utilizes factors such as ingredient compatibility and past user data.

[0487] server

[0488] The server also references external weather information APIs to obtain environmental data such as current temperature, humidity, and UV index. This allows it to adjust the skincare methods provided to users based on environmental conditions.

[0489] Presentation of proposal

[0490] terminal

[0491] The device displays skincare suggestions and usage instructions received from the server in an easy-to-understand format within the application. This display includes information such as the number of times and times to use the product, and any precautions.

[0492] User

[0493] Users can review the suggested skincare plan and incorporate it into their daily routine. They can also submit feedback through the application after implementing the plan.

[0494] This format allows users to easily obtain appropriate skincare methods tailored to their ever-changing skin condition, and to enjoy personalized suggestions in real time. The system also includes a program that continuously learns from user feedback to improve the accuracy of its suggestions.

[0495] The following describes the processing flow.

[0496] Step 1:

[0497] The user launches a dedicated application and takes a photo of their face using the camera function. Once the photo is taken, they review the image and save it to their device.

[0498] Step 2:

[0499] Upon receiving an image, the terminal performs preprocessing to automatically adjust the image resolution and brightness to a state suitable for analysis. The processed image data is then sent to the server.

[0500] Step 3:

[0501] The server inputs the received facial images into a deep learning-based model to analyze the skin condition. At this stage, it outputs numerical data representing dryness, blemishes, wrinkles, enlarged pores, redness, and other factors.

[0502] Step 4:

[0503] Based on the analyzed skin condition data, the server searches its internal database for suitable skin care products and methods. It also references past user data and product ingredient information to provide optimal recommendations.

[0504] Step 5:

[0505] The server obtains current environmental data through an external weather information API. Based on information such as temperature, humidity, and UV index, it adjusts skincare methods to suit the environmental conditions.

[0506] Step 6:

[0507] The server sends a customized skincare plan to the device. The plan specifies the exact usage, frequency, timing, and precautions for each product.

[0508] Step 7:

[0509] The device displays the received skin care plan to the user. The user can review the presented plan and incorporate it into their daily care routine. Furthermore, a function is implemented to send feedback after care has been performed via the application.

[0510] (Example 1)

[0511] 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."

[0512] In recent years, there has been a growing demand for personalized skincare tailored to each user's skin condition. However, traditional methods require specialized knowledge and considerable time to accurately assess a user's skin condition and propose optimal care. Furthermore, considering environmental factors in proposals is even more difficult, and systems that provide real-time, individually tailored skincare are still not widespread.

[0513] 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.

[0514] In this invention, the server includes means for acquiring a facial image captured by the user, means for optimizing the acquired facial image for analysis using image processing technology, means for analyzing the optimized image and quantifying the skin condition as a feature, means for comparing the analysis results with internal information and proposing personalized skin care products and methods that are optimal for the user, and means for acquiring external environmental information and dynamically adjusting the proposed content. This makes it possible to provide personalized skincare suggestions in real time based on the user's skin condition and the environment at that time.

[0515] A "user" is an individual who uses the system to analyze their skin condition and receive skincare recommendations.

[0516] A "face image" is digital photographic data of a face taken by a user using the device's camera.

[0517] "Image processing technology" refers to algorithms and software used to analyze, transform, and store digital images, and is a technology used to optimize image resolution and brightness.

[0518] "Analysis" is the process of using image processing technology to numerically identify the condition of the skin from a facial image and outputting it as structured data.

[0519] "Skin condition" refers to an indicator that describes the characteristics of facial skin, and includes factors such as dryness, blemishes, wrinkles, enlarged pores, and the degree of redness.

[0520] "Personalized skin care products and methods" refers to skincare products and their usage procedures that are specifically recommended for the user based on the analysis results.

[0521] "External environmental information" refers to information such as current weather, temperature, humidity, and UV index obtained from external data sources referenced by the device.

[0522] The embodiment of this invention is based on a series of operations designed to maximize the user experience. The user first uses a device with a dedicated application installed. They launch this application and take a photograph of their face using the device's camera function. Taking the photograph under appropriate lighting conditions is recommended.

[0523] The captured facial images are temporarily stored in a cache by the device, and their resolution and brightness are optimized for analysis using image processing technology. At this stage, image processing software such as OpenCV is used. The optimized image data is then sent to a server via the network.

[0524] The server analyzes the received image data using TensorFlow as a deep learning framework. This analysis allows the server to quantify the user's facial skin condition and output it as structured data. Specifically, it identifies factors such as skin dryness, blemishes, wrinkles, enlarged pores, and redness. These analysis results are stored in an internal database.

[0525] The server then references an internal database and past user data to suggest the most suitable, personalized skincare products and methods for the user. This process includes evaluating ingredient compatibility and effectiveness. It also uses an external weather information API to retrieve current environmental data and dynamically adjust the suggestions.

[0526] For example, if a user's skin analysis results indicate high dryness, the server will suggest a highly moisturizing cream. Furthermore, if the environmental conditions are determined to be low humidity and high UV index, the server will also recommend using sunscreen in conjunction with the cream.

[0527] An example of a prompt to input into a generative AI model is: "Please recommend the best skincare products for dry skin. The environment is 25°C, 40% humidity, and a UV index of 7."

[0528] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0529] Step 1:

[0530] The user launches a dedicated application and uses the device's camera to take a picture of their face. The input is a facial image, and the output is a digital image file temporarily stored on the device. The captured image is automatically checked for brightness and focus within the application, and if it does not meet the standards, the user is prompted to retake the picture.

[0531] Step 2:

[0532] The terminal performs image processing on the saved face image. The input is the face image captured in step 1, and the output is an image optimized for analysis. The terminal uses image processing software (e.g., OpenCV) to adjust the image resolution and remove noise. After this optimization process, the image data is ready to be sent to the server.

[0533] Step 3:

[0534] The server receives optimized facial images sent from the terminal. The input is the optimized facial image, and the output is data quantifying skin features. The server uses a deep learning framework (e.g., TensorFlow) to analyze this image and extract numerical values ​​for skin dryness, blemishes, wrinkles, enlarged pores, and redness. These individual features are then recorded in a database.

[0535] Step 4:

[0536] The server selects the most suitable skincare products and methods for the user based on the analysis results. The input is the analysis results data from step 3, and the output is a personalized skincare recommendation. The server compares this with its internal database to select products that match the user's skin condition. This selection process also takes into account the compatibility of the ingredients in the products and past user data.

[0537] Step 5:

[0538] The server retrieves current environmental data by referencing an external weather information API and adjusts the recommendations accordingly. The input is weather data for the current environment, and the output is the adjusted skincare recommendation. For example, it decides whether to enhance moisturizing or add sunscreen based on the current humidity and UV index.

[0539] Step 6:

[0540] The device displays optimal skincare suggestions received from the server to the user within the application. The input is the adjusted skincare suggestions from step 5, and the output is visually understandable information presented to the user. This information includes product usage instructions, timing, and precautions.

[0541] Step 7:

[0542] Users can incorporate the suggested skincare plan into their daily routine and send feedback on the results to the server via the application. The input is the user's feedback information, and the output is used by the server to update the data and improve accuracy. In this way, the system learns from the user's feedback and improves the accuracy of future suggestions.

[0543] (Application Example 1)

[0544] 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."

[0545] Many modern consumers desire personalized skincare recommendations based on their skin condition. However, current methods rely on limited information for skin condition analysis, resulting in limitations in the accuracy and suitability of these recommendations. Furthermore, there is a lack of effective means to present these recommendations clearly to users. Continuous learning through feedback after recommendations are also needed to improve accuracy.

[0546] 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.

[0547] In this invention, the server includes means for coordinating with a mechanical device that presents analysis results in audio and visual information, means for collecting user feedback after implementation of the proposed treatment and improving the accuracy of the analysis, and means for acquiring ambient environmental data and adjusting the proposed treatment. This makes it possible to provide users with comprehensive, personalized skin care suggestions and to improve the accuracy of the suggestions by utilizing the data after implementation.

[0548] "User" refers to an individual who wishes to use the system to analyze their skin condition and receive skincare recommendations.

[0549] A "facial image" is a digital image data of a user's face, which is used for analyzing their skin condition.

[0550] "Methods for analyzing skin condition" refer to processing methods that use facial images to detect skin health and characteristics, and generate numerical results as structured data.

[0551] "Means of proposing optimal skin care products and methods" refers to the process of selecting and providing skin care products and methods suitable for the user based on the analysis results.

[0552] "Environmental data" refers to information about external factors such as ambient temperature, humidity, and UV index, and is used to adjust skincare recommendations.

[0553] A "mechanical device that presents analysis results using audio and visual information" refers to hardware that uses audio and a display to provide information to users in order to help them intuitively understand skin care suggestions.

[0554] "Means for collecting user feedback and improving analysis accuracy" refers to methods for receiving the results of using the proposed care methods and continuously improving the system's learning model based on those results.

[0555] To implement this invention, the entire system needs to be coordinated via a terminal, a server, and mechanical devices. First, the terminal acquires a facial image from the user. To maintain high-quality input, the resolution and brightness of this image are adjusted within the terminal, and then it is transmitted to the server.

[0556] On the server, deep learning-based image recognition technology is applied to extract skin features from facial images. This process utilizes machine learning frameworks such as TensorFlow or PyTorch. The server compares the analyzed results with an internal database and further refines the recommendations by referencing external weather information. This generates a personalized skincare plan for each user.

[0557] Next, the machine communicates the generated skincare recommendations to the user through voice and visual displays. Specifically, this is achieved by home voice assistants and display-equipped devices. This provides information that is both visual and auditory, making it easier for the user to understand the recommendations.

[0558] Furthermore, after the user tries out the suggested plan, the device collects feedback from the user. This information is then sent back to the server to improve the accuracy of the suggestions and is used to help the entire system learn. Through feedback, the suggestions become increasingly accurate and personalized.

[0559] For example, on days with high humidity, the system could provide voice advice such as, "Please use less moisturizing cream today." Also, if a user reports that their blemishes have become more noticeable, the next recommendation might include a product containing more effective whitening ingredients.

[0560] Examples of prompts generated by AI include the following:

[0561] "Analyze images taken with a smartphone and suggest skincare methods suitable for an environment with 70% humidity."

[0562] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0563] Step 1:

[0564] The device acquires a facial image from the user and temporarily stores it in a cache. Here, the input is a facial image captured by the camera, and the output is an image file with adjusted resolution and brightness. The device processes and optimizes the image quality to prepare it for transmission to the server.

[0565] Step 2:

[0566] The device sends a facial image to the server. The input is an optimized facial image, and the output is a notification that the image transfer to the server is complete. This allows the server to proceed to the next analysis step.

[0567] Step 3:

[0568] The server analyzes the facial images it receives using a deep learning model. The input is a facial image sent from the terminal, and the output is quantified data indicating skin condition. The server processes the image and quantifies skin characteristics such as blemishes, wrinkles, and dryness.

[0569] Step 4:

[0570] The server uses the analysis results to refer to an internal database and select appropriate skincare products and methods. The input is skin analysis data, and the output is a product list and care plan. The server retrieves product information best suited to the user's skin type.

[0571] Step 5:

[0572] The server references an external weather information database and adjusts the suggested skincare routine based on environmental data. Input is current temperature and humidity data, and output is the adjusted skincare plan. The server adapts the suggested routine to the environmental conditions.

[0573] Step 6:

[0574] The machine presents the proposed skincare plan to the user using audio and visual information. The input is the skincare plan received from the server, and the output is the provision of information to the user via audio and display. The machine clearly explains the plan's contents.

[0575] Step 7:

[0576] After a user completes their skincare plan, they use a device to send feedback to the system. The input is the user's usage results and feedback, and the output is feedback data sent to the server. This allows the server to improve the accuracy of subsequent analyses.

[0577] 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.

[0578] This invention provides a system that acquires a user's facial image and analyzes their skin condition and emotions based on that image. This system not only suggests the most suitable skin care products and methods for the user, but also takes their emotional state into consideration to provide more personalized suggestions.

[0579] Image acquisition and emotion recognition

[0580] User

[0581] The user installs a dedicated application on their device, launches the app, and takes a photo of their face. This captures both the facial image and facial expression data.

[0582] terminal

[0583] The device stores the acquired facial image in a temporary cache and uses an emotion recognition engine to analyze the user's emotional state. For example, it can determine whether the user is smiling or feeling stressed.

[0584] Skin condition analysis and utilization of emotional data

[0585] server

[0586] The server uses image analysis algorithms to analyze skin conditions such as dryness, blemishes, wrinkles, enlarged pores, and redness from facial images. The analysis results are stored as structured data.

[0587] server

[0588] The server optimizes the recommendations for skincare products and methods based on emotional data acquired by the emotion engine. For example, it seeks care methods that match the user's emotions, such as suggesting relaxing products when stressed or whitening products when happy.

[0589] Proposal presentation and feedback

[0590] terminal

[0591] The device displays a skin care plan and usage instructions provided by the server to the user. The plan includes information such as specific product names, usage time, frequency, and purpose.

[0592] User

[0593] Users can use the suggested plan as a reference to implement their daily care. They can also input feedback, such as usage results and impressions, within the application, which will be used to improve future suggestions.

[0594] This system integrates emotion recognition into skincare recommendations, enabling it to provide users with comprehensive support. Each module of the program is designed to adapt to dynamic changes in skin condition and emotions to enhance the user experience.

[0595] The following describes the processing flow.

[0596] Step 1:

[0597] The user launches a dedicated application and takes a photo of their face using the camera function. Along with the face image, a prompt appears to capture their facial expression, and the user faces the camera with a natural expression.

[0598] Step 2:

[0599] The device temporarily stores the captured facial image in a cache and extracts facial expression data from the image. The emotion recognition engine then activates and determines the emotional characteristics from the current facial expression. For example, it quantifies emotional states such as smiling, stern, or tense.

[0600] Step 3:

[0601] The device sends optimized facial images and emotion data to the server for analysis. This includes adjusting image resolution and removing unwanted backgrounds.

[0602] Step 4:

[0603] The server uses the received image as an analysis trigger to analyze the skin condition using a deep learning-based model. Digital processing is performed to measure dryness, the intensity of blemishes, and the depth of wrinkles.

[0604] Step 5:

[0605] The server references emotional data obtained from the emotion engine along with the analysis results. Based on this data, it selects suitable skin care products and methods from its internal database. For example, when the user is under high stress, it selects products with calming effects.

[0606] Step 6:

[0607] The server acquires external environmental data, such as temperature, humidity, and UV radiation levels, to further optimize the selected skin care plan. This environmental data is then reflected in the proposed plan.

[0608] Step 7:

[0609] The device displays an optimized skincare plan received from the server to the user. The plan includes information on how to use the products, how often to use them, and when to apply them.

[0610] Step 8:

[0611] Users review the displayed skincare plan and incorporate it into their daily routine. After completing the care, they can input their experience and feedback using the in-app feedback function, which will then be reflected in future suggestions.

[0612] (Example 2)

[0613] 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."

[0614] Current technologies that individually analyze a person's physical state and emotions and then propose lifestyle products based on that analysis have a challenge in that they cannot adequately personalize the process to improve the user's quality of life. In particular, it is difficult to propose products that take emotional states into account, making it challenging to provide proposals that meet the diverse needs of users.

[0615] 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.

[0616] In this invention, the server includes means for acquiring biometric information obtained from the user using image functions, means for analyzing the emotional state using an analysis device and generating emotional data, and means for integrating the emotional data and skin condition data and optimizing the suggested content using a generative intelligence model. This enables a comprehensive analysis of the user's biometric and emotional states, making it possible to propose more personalized and appropriate lifestyle products and methods.

[0617] "Biometric information" refers to data such as facial images and physical characteristics obtained from users.

[0618] "Personalized lifestyle products" refer to products such as skincare products and health goods that are suggested based on the specific needs and conditions of the user.

[0619] An "analysis device" refers to equipment or software used to process acquired data and analyze information such as emotions and skin condition.

[0620] "Emotional data" refers to numerical or categorical data that indicates the emotional state of a user, analyzed from their facial expressions and biometric information.

[0621] A "generative intelligence model" refers to an algorithm or program that uses artificial intelligence technology to analyze data and generate optimal suggestions.

[0622] This invention provides a system that analyzes a user's biometric information and suggests personalized lifestyle products based on their emotions and physical state. The implementation of this system is carried out using the hardware and software described below, following a specific process.

[0623] User actions:

[0624] The user begins by installing a dedicated application on their device. They then launch the application and use the device's camera to acquire biometric information, such as facial images. During this process, the app checks image quality in real time and can request the user to retake the image if necessary.

[0625] Device operation:

[0626] The device temporarily stores the acquired biometric information in its internal storage. This stored data is then transmitted to the analysis device described below. The analysis device can utilize software for analyzing emotional states, such as a general image recognition engine or machine learning algorithm.

[0627] Server operation:

[0628] The server receives biometric information transmitted from the terminal and analyzes the data using an analysis device that generates emotional data. The analysis can utilize a model to infer emotional states from facial features. Furthermore, it leverages a generative AI model to integrate the acquired emotional data and biometric data to generate optimal suggestions. These suggestions include lists of lifestyle products and care methods suitable for the user's condition. For example, if a stressful state is detected, products with relaxing effects will be recommended.

[0629] Proposal presentation:

[0630] The generated suggestions are provided to the user via a terminal. The terminal screen displays detailed information about the suggested product name and usage, which the user can review. For example, a prompt message such as, "Your facial image has been analyzed, and your skin is dry and your emotional state is stressed. Please suggest appropriate skincare products," might be output. This allows the user to take action to improve their quality of life based on the information provided.

[0631] This system configuration enables specific and personalized suggestions tailored to the user's emotional and biological state, contributing to improvements in their daily life.

[0632] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0633] Step 1:

[0634] The user launches a dedicated application and takes a facial image using the device's camera. The application assists in this process by checking image resolution and lighting conditions to ensure optimal capture. The input is a facial image acquired through the camera, and the output is high-quality facial image data.

[0635] Step 2:

[0636] The device temporarily stores the captured facial images in a cache. This storage utilizes internal storage to prepare for subsequent data analysis. The input is facial image data sent by the user, and the output is image data temporarily stored within the device.

[0637] Step 3:

[0638] The device activates an emotion analysis engine and analyzes the acquired facial image data. During this process, image recognition technology is used to characterize emotions such as smiles and stress. The input is a facial image stored in the cache, and the output is the analyzed emotion data.

[0639] Step 4:

[0640] The device sends emotion data and facial image data to the server. The data is securely transmitted via a communication protocol and prepared for further detailed analysis on the server. The input is the emotion data and facial image stored on the device, and the output is the data transfer to the server.

[0641] Step 5:

[0642] The server analyzes the skin condition based on the received data. It uses image analysis algorithms to detect skin features such as blemishes, wrinkles, and dryness. The input is a facial image sent to the server, and the output is the analysis result, including specific skin condition characteristics.

[0643] Step 6:

[0644] The server integrates emotional data and skin condition data, and uses a generative AI model to generate optimal suggestions. These suggestions include products and care methods tailored to the user's condition and are personalized by the generative AI model. The input is emotional data and skin condition data, and the output is customized suggestions.

[0645] Step 7:

[0646] The terminal receives suggestions from the server and displays them to the user. Detailed product information and usage guidelines are presented on the screen, allowing the user to use the suggestions to improve their daily life. The input is suggestion data from the server, and the output is a visualized suggestion of products and care methods for the user.

[0647] (Application Example 2)

[0648] 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."

[0649] Modern consumers struggle to choose the right skincare products from the wide variety available. Furthermore, since a consumer's emotional state and surrounding environment influence their skin condition, there is a need for product recommendations that take these factors into account. Traditional skincare product recommendations often fail to consider emotional states and surrounding environments, resulting in insufficient individualization.

[0650] 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.

[0651] In this invention, the server includes means for acquiring facial information captured from the user, means for analyzing the skin condition based on the acquired facial information, and means for identifying the emotional state of the analyzed facial information. This makes it possible to propose more personalized skin care products that take into account the user's emotional state and surrounding environment.

[0652] "Users" refers to individuals who use the skin care product recommendation system.

[0653] "Facial information" refers to data extracted from images of a user's face.

[0654] "Skin condition" refers to specific characteristics of the skin, such as dryness, blemishes, wrinkles, enlarged pores, and redness, as analyzed from facial information.

[0655] "Emotional state" refers to the user's psychological situation and mental state as determined by their facial expressions, as analyzed from facial information.

[0656] "External environmental information" refers to environmental data such as temperature, humidity, and weather present in the user's surroundings.

[0657] "Recommendation" refers to the act of recommending the most suitable skin care products and their usage methods to the user, based on the analyzed skin condition, emotional state, and external environmental information.

[0658] "Image recognition technology" refers to the technology that uses computers to extract specific information from image data and then recognize, classify, or interpret it.

[0659] "Structured data" refers to data that is organized according to a specific format and is easy for machines to interpret and analyze.

[0660] "External data storage" refers to databases or cloud storage that contain product information and can be accessed via a network.

[0661] In the system that realizes this application example, hardware such as terminals, servers, and robots work together to provide users with optimal skin care suggestions.

[0662] The device is equipped with a camera and image processing software, and has the function of capturing the user's face. This image data is temporarily stored using an image processing library such as OpenCV. Subsequently, the facial information is sent to a database and then transferred to a server for further detailed analysis.

[0663] The server utilizes machine learning models such as TensorFlow to analyze skin condition from acquired facial information. Furthermore, it acquires emotional data by using emotion recognition technologies such as Microsoft Azure Emotion API to understand the user's emotional state. Based on the analysis results, it then uses a generative AI model to create recommendations for appropriate skin care products and methods. If necessary, it retrieves product information from external databases to improve the quality of the recommendations.

[0664] Users can refer to the suggestions displayed on their device and incorporate them into their daily skincare routine. The suggestions include detailed information such as recommended products, usage instructions, and frequency. Users can also provide feedback, which will be incorporated into future suggestions.

[0665] As a concrete example, consider a scenario where a user casually spends a holiday morning at home using this system. If the robot captures facial information and analyzes it to determine that the skin is dry, it will recommend the use of a relaxing moisturizing cream. In addition, if it recognizes that the user's recent emotions tend to be stressful, it will suggest the use of aromatherapy products. In this way, the system comprehensively analyzes the user's internal and external state to provide optimal skincare.

[0666] An example of a prompt message for a generative AI model is: "This user's current skin condition is dry. Sentiment analysis indicates they are experiencing stress. What skincare products would you recommend?"

[0667] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0668] Step 1:

[0669] The device uses a camera to capture the user's facial information. The input is the image from the camera, and the output is the acquired facial image data. This image data is temporarily stored in memory in preparation for the next analysis process.

[0670] Step 2:

[0671] The server receives facial image data sent from the terminal. The input is facial image data from the terminal, and the output is the utilization of that data. A machine learning model is used to analyze the skin condition from this facial image data and extract specific skin characteristics such as dryness, wrinkles, and blemishes.

[0672] Step 3:

[0673] The server analyzes the emotional state using an emotion recognition API along with facial image data. The input is facial image data, and the output is the analyzed emotion data. Through emotional state recognition, information such as whether the user is currently stressed or relaxed is obtained.

[0674] Step 4:

[0675] The server generates optimal skincare suggestions using a generative AI model based on acquired skin condition and emotional state data. The input is analyzed skin and emotional data, and the output is the suggested content. This process accesses external databases and customizes suggestions by referencing various product information.

[0676] Step 5:

[0677] The terminal displays the suggestions received from the server to the user. The input is the suggestions from the server, and the output is a visual presentation of information to the user. The suggestions include specific product names, usage instructions, and frequency information.

[0678] Step 6:

[0679] Users perform their daily skincare routine based on the provided suggestions. By providing feedback, the quality of future suggestions can be improved. Input consists of the user's own actions and feedback, while output is the collection of feedback data.

[0680] 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.

[0681] 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.

[0682] 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.

[0683] [Fourth Embodiment]

[0684] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0685] 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.

[0686] 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).

[0687] 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.

[0688] 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.

[0689] 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).

[0690] 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.

[0691] 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.

[0692] 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.

[0693] 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.

[0694] 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.

[0695] 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.

[0696] 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".

[0697] This invention describes an embodiment for implementing a system that analyzes skin condition using facial images taken by a user and provides optimal skin care products and methods.

[0698] Image acquisition

[0699] User

[0700] The user uses a device with the dedicated application installed and launches the application. Within the application, they are prompted to use the camera function to take a photo of their face.

[0701] terminal

[0702] The device temporarily stores the facial image captured by the user in its own cache and automatically performs processing to optimize the image's resolution and brightness for analysis. Afterward, it sends the image to the server.

[0703] Image analysis

[0704] server

[0705] When the server receives an image, it starts analyzing it using a pre-trained deep learning model. This analysis outputs numerical data indicating the degree of dryness of the facial skin, the number of blemishes and wrinkles, the size of pores, and the degree of redness.

[0706] Skincare suggestions

[0707] server

[0708] Based on the analysis results, the server consults an internal database to select skincare products and methods suitable for the user. Product selection utilizes factors such as ingredient compatibility and past user data.

[0709] server

[0710] The server also references external weather information APIs to obtain environmental data such as current temperature, humidity, and UV index. This allows it to adjust the skincare methods provided to users based on environmental conditions.

[0711] Presentation of proposal

[0712] terminal

[0713] The device displays skincare suggestions and usage instructions received from the server in an easy-to-understand format within the application. This display includes information such as the number of times and times to use the product, and any precautions.

[0714] User

[0715] Users can review the suggested skincare plan and incorporate it into their daily routine. They can also submit feedback through the application after implementing the plan.

[0716] This format allows users to easily obtain appropriate skincare methods tailored to their ever-changing skin condition, and to enjoy personalized suggestions in real time. The system also includes a program that continuously learns from user feedback to improve the accuracy of its suggestions.

[0717] The following describes the processing flow.

[0718] Step 1:

[0719] The user launches a dedicated application and takes a photo of their face using the camera function. Once the photo is taken, they review the image and save it to their device.

[0720] Step 2:

[0721] Upon receiving an image, the terminal performs preprocessing to automatically adjust the image resolution and brightness to a state suitable for analysis. The processed image data is then sent to the server.

[0722] Step 3:

[0723] The server inputs the received facial images into a deep learning-based model to analyze the skin condition. At this stage, it outputs numerical data representing dryness, blemishes, wrinkles, enlarged pores, redness, and other factors.

[0724] Step 4:

[0725] Based on the analyzed skin condition data, the server searches its internal database for suitable skin care products and methods. It also references past user data and product ingredient information to provide optimal recommendations.

[0726] Step 5:

[0727] The server obtains current environmental data through an external weather information API. Based on information such as temperature, humidity, and UV index, it adjusts skincare methods to suit the environmental conditions.

[0728] Step 6:

[0729] The server sends a customized skincare plan to the device. The plan specifies the exact usage, frequency, timing, and precautions for each product.

[0730] Step 7:

[0731] The device displays the received skin care plan to the user. The user can review the presented plan and incorporate it into their daily care routine. Furthermore, a function is implemented to send feedback after care has been performed via the application.

[0732] (Example 1)

[0733] 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".

[0734] In recent years, there has been a growing demand for personalized skincare tailored to each user's skin condition. However, traditional methods require specialized knowledge and considerable time to accurately assess a user's skin condition and propose optimal care. Furthermore, considering environmental factors in proposals is even more difficult, and systems that provide real-time, individually tailored skincare are still not widespread.

[0735] 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.

[0736] In this invention, the server includes means for acquiring a facial image captured by the user, means for optimizing the acquired facial image for analysis using image processing technology, means for analyzing the optimized image and quantifying the skin condition as a feature, means for comparing the analysis results with internal information and proposing personalized skin care products and methods that are optimal for the user, and means for acquiring external environmental information and dynamically adjusting the proposed content. This makes it possible to provide personalized skincare suggestions in real time based on the user's skin condition and the environment at that time.

[0737] A "user" is an individual who uses the system to analyze their skin condition and receive skincare recommendations.

[0738] A "face image" is digital photographic data of a face taken by a user using the device's camera.

[0739] "Image processing technology" refers to algorithms and software used to analyze, transform, and store digital images, and is a technology used to optimize image resolution and brightness.

[0740] "Analysis" is the process of using image processing technology to numerically identify the condition of the skin from a facial image and outputting it as structured data.

[0741] "Skin condition" refers to an indicator that describes the characteristics of facial skin, and includes factors such as dryness, blemishes, wrinkles, enlarged pores, and the degree of redness.

[0742] "Personalized skin care products and methods" refers to skincare products and their usage procedures that are specifically recommended for the user based on the analysis results.

[0743] "External environmental information" refers to information such as current weather, temperature, humidity, and UV index obtained from external data sources referenced by the device.

[0744] The embodiment of this invention is based on a series of operations designed to maximize the user experience. The user first uses a device with a dedicated application installed. They launch this application and take a photograph of their face using the device's camera function. Taking the photograph under appropriate lighting conditions is recommended.

[0745] The captured facial images are temporarily stored in a cache by the device, and their resolution and brightness are optimized for analysis using image processing technology. At this stage, image processing software such as OpenCV is used. The optimized image data is then sent to a server via the network.

[0746] The server analyzes the received image data using TensorFlow as a deep learning framework. This analysis allows the server to quantify the user's facial skin condition and output it as structured data. Specifically, it identifies factors such as skin dryness, blemishes, wrinkles, enlarged pores, and redness. These analysis results are stored in an internal database.

[0747] The server then references an internal database and past user data to suggest the most suitable, personalized skincare products and methods for the user. This process includes evaluating ingredient compatibility and effectiveness. It also uses an external weather information API to retrieve current environmental data and dynamically adjust the suggestions.

[0748] For example, if a user's skin analysis results indicate high dryness, the server will suggest a highly moisturizing cream. Furthermore, if the environmental conditions are determined to be low humidity and high UV index, the server will also recommend using sunscreen in conjunction with the cream.

[0749] An example of a prompt to input into a generative AI model is: "Please recommend the best skincare products for dry skin. The environment is 25°C, 40% humidity, and a UV index of 7."

[0750] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0751] Step 1:

[0752] The user launches a dedicated application and uses the device's camera to take a picture of their face. The input is a facial image, and the output is a digital image file temporarily stored on the device. The captured image is automatically checked for brightness and focus within the application, and if it does not meet the standards, the user is prompted to retake the picture.

[0753] Step 2:

[0754] The terminal performs image processing on the saved face image. The input is the face image captured in step 1, and the output is an image optimized for analysis. The terminal uses image processing software (e.g., OpenCV) to adjust the image resolution and remove noise. After this optimization process, the image data is ready to be sent to the server.

[0755] Step 3:

[0756] The server receives optimized facial images sent from the terminal. The input is the optimized facial image, and the output is data quantifying skin features. The server uses a deep learning framework (e.g., TensorFlow) to analyze this image and extract numerical values ​​for skin dryness, blemishes, wrinkles, enlarged pores, and redness. These individual features are then recorded in a database.

[0757] Step 4:

[0758] The server selects the most suitable skincare products and methods for the user based on the analysis results. The input is the analysis results data from step 3, and the output is a personalized skincare recommendation. The server compares this with its internal database to select products that match the user's skin condition. This selection process also takes into account the compatibility of the ingredients in the products and past user data.

[0759] Step 5:

[0760] The server retrieves current environmental data by referencing an external weather information API and adjusts the recommendations accordingly. The input is weather data for the current environment, and the output is the adjusted skincare recommendation. For example, it decides whether to enhance moisturizing or add sunscreen based on the current humidity and UV index.

[0761] Step 6:

[0762] The device displays optimal skincare suggestions received from the server to the user within the application. The input is the adjusted skincare suggestions from step 5, and the output is visually understandable information presented to the user. This information includes product usage instructions, timing, and precautions.

[0763] Step 7:

[0764] Users can incorporate the suggested skincare plan into their daily routine and send feedback on the results to the server via the application. The input is the user's feedback information, and the output is used by the server to update the data and improve accuracy. In this way, the system learns from the user's feedback and improves the accuracy of future suggestions.

[0765] (Application Example 1)

[0766] 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".

[0767] Many modern consumers desire personalized skincare recommendations based on their skin condition. However, current methods rely on limited information for skin condition analysis, resulting in limitations in the accuracy and suitability of these recommendations. Furthermore, there is a lack of effective means to present these recommendations clearly to users. Continuous learning through feedback after recommendations are also needed to improve accuracy.

[0768] 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.

[0769] In this invention, the server includes means for coordinating with a mechanical device that presents analysis results in audio and visual information, means for collecting user feedback after implementation of the proposed treatment and improving the accuracy of the analysis, and means for acquiring ambient environmental data and adjusting the proposed treatment. This makes it possible to provide users with comprehensive, personalized skin care suggestions and to improve the accuracy of the suggestions by utilizing the data after implementation.

[0770] "User" refers to an individual who wishes to use the system to analyze their skin condition and receive skincare recommendations.

[0771] A "facial image" is a digital image data of a user's face, which is used for analyzing their skin condition.

[0772] "Methods for analyzing skin condition" refer to processing methods that use facial images to detect skin health and characteristics, and generate numerical results as structured data.

[0773] "Means of proposing optimal skin care products and methods" refers to the process of selecting and providing skin care products and methods suitable for the user based on the analysis results.

[0774] "Environmental data" refers to information about external factors such as ambient temperature, humidity, and UV index, and is used to adjust skincare recommendations.

[0775] A "mechanical device that presents analysis results using audio and visual information" refers to hardware that uses audio and a display to provide information to users in order to help them intuitively understand skin care suggestions.

[0776] "Means for collecting user feedback and improving analysis accuracy" refers to methods for receiving the results of using the proposed care methods and continuously improving the system's learning model based on those results.

[0777] To implement this invention, the entire system needs to be coordinated via a terminal, a server, and mechanical devices. First, the terminal acquires a facial image from the user. To maintain high-quality input, the resolution and brightness of this image are adjusted within the terminal, and then it is transmitted to the server.

[0778] On the server, deep learning-based image recognition technology is applied to extract skin features from facial images. This process utilizes machine learning frameworks such as TensorFlow or PyTorch. The server compares the analyzed results with an internal database and further refines the recommendations by referencing external weather information. This generates a personalized skincare plan for each user.

[0779] Next, the machine communicates the generated skincare recommendations to the user through voice and visual displays. Specifically, this is achieved by home voice assistants and display-equipped devices. This provides information that is both visual and auditory, making it easier for the user to understand the recommendations.

[0780] Furthermore, after the user tries out the suggested plan, the device collects feedback from the user. This information is then sent back to the server to improve the accuracy of the suggestions and is used to help the entire system learn. Through feedback, the suggestions become increasingly accurate and personalized.

[0781] For example, on days with high humidity, the system could provide voice advice such as, "Please use less moisturizing cream today." Also, if a user reports that their blemishes have become more noticeable, the next recommendation might include a product containing more effective whitening ingredients.

[0782] Examples of prompts generated by AI include the following:

[0783] "Analyze images taken with a smartphone and suggest skincare methods suitable for an environment with 70% humidity."

[0784] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0785] Step 1:

[0786] The device acquires a facial image from the user and temporarily stores it in a cache. Here, the input is a facial image captured by the camera, and the output is an image file with adjusted resolution and brightness. The device processes and optimizes the image quality to prepare it for transmission to the server.

[0787] Step 2:

[0788] The device sends a facial image to the server. The input is an optimized facial image, and the output is a notification that the image transfer to the server is complete. This allows the server to proceed to the next analysis step.

[0789] Step 3:

[0790] The server analyzes the facial images it receives using a deep learning model. The input is a facial image sent from the terminal, and the output is quantified data indicating skin condition. The server processes the image and quantifies skin characteristics such as blemishes, wrinkles, and dryness.

[0791] Step 4:

[0792] The server uses the analysis results to refer to an internal database and select appropriate skincare products and methods. The input is skin analysis data, and the output is a product list and care plan. The server retrieves product information best suited to the user's skin type.

[0793] Step 5:

[0794] The server references an external weather information database and adjusts the suggested skincare routine based on environmental data. Input is current temperature and humidity data, and output is the adjusted skincare plan. The server adapts the suggested routine to the environmental conditions.

[0795] Step 6:

[0796] The machine presents the proposed skincare plan to the user using audio and visual information. The input is the skincare plan received from the server, and the output is the provision of information to the user via audio and display. The machine clearly explains the plan's contents.

[0797] Step 7:

[0798] After a user completes their skincare plan, they use a device to send feedback to the system. The input is the user's usage results and feedback, and the output is feedback data sent to the server. This allows the server to improve the accuracy of subsequent analyses.

[0799] 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.

[0800] This invention provides a system that acquires a user's facial image and analyzes their skin condition and emotions based on that image. This system not only suggests the most suitable skin care products and methods for the user, but also takes their emotional state into consideration to provide more personalized suggestions.

[0801] Image acquisition and emotion recognition

[0802] User

[0803] The user installs a dedicated application on their device, launches the app, and takes a photo of their face. This captures both the facial image and facial expression data.

[0804] terminal

[0805] The device stores the acquired facial image in a temporary cache and uses an emotion recognition engine to analyze the user's emotional state. For example, it can determine whether the user is smiling or feeling stressed.

[0806] Skin condition analysis and utilization of emotional data

[0807] server

[0808] The server uses image analysis algorithms to analyze skin conditions such as dryness, blemishes, wrinkles, enlarged pores, and redness from facial images. The analysis results are stored as structured data.

[0809] server

[0810] The server optimizes the recommendations for skincare products and methods based on emotional data acquired by the emotion engine. For example, it seeks care methods that match the user's emotions, such as suggesting relaxing products when stressed or whitening products when happy.

[0811] Proposal presentation and feedback

[0812] terminal

[0813] The device displays a skin care plan and usage instructions provided by the server to the user. The plan includes information such as specific product names, usage time, frequency, and purpose.

[0814] User

[0815] Users can use the suggested plan as a reference to implement their daily care. They can also input feedback, such as usage results and impressions, within the application, which will be used to improve future suggestions.

[0816] This system integrates emotion recognition into skincare recommendations, enabling it to provide users with comprehensive support. Each module of the program is designed to adapt to dynamic changes in skin condition and emotions to enhance the user experience.

[0817] The following describes the processing flow.

[0818] Step 1:

[0819] The user launches a dedicated application and takes a photo of their face using the camera function. Along with the face image, a prompt appears to capture their facial expression, and the user faces the camera with a natural expression.

[0820] Step 2:

[0821] The device temporarily stores the captured facial image in a cache and extracts facial expression data from the image. The emotion recognition engine then activates and determines the emotional characteristics from the current facial expression. For example, it quantifies emotional states such as smiling, stern, or tense.

[0822] Step 3:

[0823] The device sends optimized facial images and emotion data to the server for analysis. This includes adjusting image resolution and removing unwanted backgrounds.

[0824] Step 4:

[0825] The server uses the received image as an analysis trigger to analyze the skin condition using a deep learning-based model. Digital processing is performed to measure dryness, the intensity of blemishes, and the depth of wrinkles.

[0826] Step 5:

[0827] The server references emotional data obtained from the emotion engine along with the analysis results. Based on this data, it selects suitable skin care products and methods from its internal database. For example, when the user is under high stress, it selects products with calming effects.

[0828] Step 6:

[0829] The server acquires external environmental data, such as temperature, humidity, and UV radiation levels, to further optimize the selected skin care plan. This environmental data is then reflected in the proposed plan.

[0830] Step 7:

[0831] The device displays an optimized skincare plan received from the server to the user. The plan includes information on how to use the products, how often to use them, and when to apply them.

[0832] Step 8:

[0833] Users review the displayed skincare plan and incorporate it into their daily routine. After completing the care, they can input their experience and feedback using the in-app feedback function, which will then be reflected in future suggestions.

[0834] (Example 2)

[0835] 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".

[0836] Current technologies that individually analyze a person's physical state and emotions and then propose lifestyle products based on that analysis have a challenge in that they cannot adequately personalize the process to improve the user's quality of life. In particular, it is difficult to propose products that take emotional states into account, making it challenging to provide proposals that meet the diverse needs of users.

[0837] 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.

[0838] In this invention, the server includes means for acquiring biometric information obtained from the user using image functions, means for analyzing the emotional state using an analysis device and generating emotional data, and means for integrating the emotional data and skin condition data and optimizing the suggested content using a generative intelligence model. This enables a comprehensive analysis of the user's biometric and emotional states, making it possible to propose more personalized and appropriate lifestyle products and methods.

[0839] "Biometric information" refers to data such as facial images and physical characteristics obtained from users.

[0840] "Personalized lifestyle products" refer to products such as skincare products and health goods that are suggested based on the specific needs and conditions of the user.

[0841] An "analysis device" refers to equipment or software used to process acquired data and analyze information such as emotions and skin condition.

[0842] "Emotional data" refers to numerical or categorical data that indicates the emotional state of a user, analyzed from their facial expressions and biometric information.

[0843] A "generative intelligence model" refers to an algorithm or program that uses artificial intelligence technology to analyze data and generate optimal suggestions.

[0844] This invention provides a system that analyzes a user's biometric information and suggests personalized lifestyle products based on their emotions and physical state. The implementation of this system is carried out using the hardware and software described below, following a specific process.

[0845] User actions:

[0846] The user begins by installing a dedicated application on their device. They then launch the application and use the device's camera to acquire biometric information, such as facial images. During this process, the app checks image quality in real time and can request the user to retake the image if necessary.

[0847] Device operation:

[0848] The device temporarily stores the acquired biometric information in its internal storage. This stored data is then transmitted to the analysis device described below. The analysis device can utilize software for analyzing emotional states, such as a general image recognition engine or machine learning algorithm.

[0849] Server operation:

[0850] The server receives biometric information transmitted from the terminal and analyzes the data using an analysis device that generates emotional data. The analysis can utilize a model to infer emotional states from facial features. Furthermore, it leverages a generative AI model to integrate the acquired emotional data and biometric data to generate optimal suggestions. These suggestions include lists of lifestyle products and care methods suitable for the user's condition. For example, if a stressful state is detected, products with relaxing effects will be recommended.

[0851] Proposal presentation:

[0852] The generated suggestions are provided to the user via a terminal. The terminal screen displays detailed information about the suggested product name and usage, which the user can review. For example, a prompt message such as, "Your facial image has been analyzed, and your skin is dry and your emotional state is stressed. Please suggest appropriate skincare products," might be output. This allows the user to take action to improve their quality of life based on the information provided.

[0853] This system configuration enables specific and personalized suggestions tailored to the user's emotional and biological state, contributing to improvements in their daily life.

[0854] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0855] Step 1:

[0856] The user launches a dedicated application and takes a facial image using the device's camera. The application assists in this process by checking image resolution and lighting conditions to ensure optimal capture. The input is a facial image acquired through the camera, and the output is high-quality facial image data.

[0857] Step 2:

[0858] The device temporarily stores the captured facial images in a cache. This storage utilizes internal storage to prepare for subsequent data analysis. The input is facial image data sent by the user, and the output is image data temporarily stored within the device.

[0859] Step 3:

[0860] The device activates an emotion analysis engine and analyzes the acquired facial image data. During this process, image recognition technology is used to characterize emotions such as smiles and stress. The input is a facial image stored in the cache, and the output is the analyzed emotion data.

[0861] Step 4:

[0862] The device sends emotion data and facial image data to the server. The data is securely transmitted via a communication protocol and prepared for further detailed analysis on the server. The input is the emotion data and facial image stored on the device, and the output is the data transfer to the server.

[0863] Step 5:

[0864] The server analyzes the skin condition based on the received data. It uses image analysis algorithms to detect skin features such as blemishes, wrinkles, and dryness. The input is a facial image sent to the server, and the output is the analysis result, including specific skin condition characteristics.

[0865] Step 6:

[0866] The server integrates emotional data and skin condition data, and uses a generative AI model to generate optimal suggestions. These suggestions include products and care methods tailored to the user's condition and are personalized by the generative AI model. The input is emotional data and skin condition data, and the output is customized suggestions.

[0867] Step 7:

[0868] The terminal receives suggestions from the server and displays them to the user. Detailed product information and usage guidelines are presented on the screen, allowing the user to use the suggestions to improve their daily life. The input is suggestion data from the server, and the output is a visualized suggestion of products and care methods for the user.

[0869] (Application Example 2)

[0870] 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".

[0871] Modern consumers struggle to choose the right skincare products from the wide variety available. Furthermore, since a consumer's emotional state and surrounding environment influence their skin condition, there is a need for product recommendations that take these factors into account. Traditional skincare product recommendations often fail to consider emotional states and surrounding environments, resulting in insufficient individualization.

[0872] 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.

[0873] In this invention, the server includes means for acquiring facial information captured from the user, means for analyzing the skin condition based on the acquired facial information, and means for identifying the emotional state of the analyzed facial information. This makes it possible to propose more personalized skin care products that take into account the user's emotional state and surrounding environment.

[0874] "Users" refers to individuals who use the skin care product recommendation system.

[0875] "Facial information" refers to data extracted from images of a user's face.

[0876] "Skin condition" refers to specific characteristics of the skin, such as dryness, blemishes, wrinkles, enlarged pores, and redness, as analyzed from facial information.

[0877] "Emotional state" refers to the user's psychological situation and mental state as determined by their facial expressions, as analyzed from facial information.

[0878] "External environmental information" refers to environmental data such as temperature, humidity, and weather present in the user's surroundings.

[0879] "Recommendation" refers to the act of recommending the most suitable skin care products and their usage methods to the user, based on the analyzed skin condition, emotional state, and external environmental information.

[0880] "Image recognition technology" refers to the technology that uses computers to extract specific information from image data and then recognize, classify, or interpret it.

[0881] "Structured data" refers to data that is organized according to a specific format and is easy for machines to interpret and analyze.

[0882] "External data storage" refers to databases or cloud storage that contain product information and can be accessed via a network.

[0883] In the system that realizes this application example, hardware such as terminals, servers, and robots work together to provide users with optimal skin care suggestions.

[0884] The device is equipped with a camera and image processing software, and has the function of capturing the user's face. This image data is temporarily stored using an image processing library such as OpenCV. Subsequently, the facial information is sent to a database and then transferred to a server for further detailed analysis.

[0885] The server utilizes machine learning models such as TensorFlow to analyze skin condition from acquired facial information. Furthermore, it acquires emotional data by using emotion recognition technologies such as Microsoft Azure Emotion API to understand the user's emotional state. Based on the analysis results, it then uses a generative AI model to create recommendations for appropriate skin care products and methods. If necessary, it retrieves product information from external databases to improve the quality of the recommendations.

[0886] Users can refer to the suggestions displayed on their device and incorporate them into their daily skincare routine. The suggestions include detailed information such as recommended products, usage instructions, and frequency. Users can also provide feedback, which will be incorporated into future suggestions.

[0887] As a concrete example, consider a scenario where a user casually spends a holiday morning at home using this system. If the robot captures facial information and analyzes it to determine that the skin is dry, it will recommend the use of a relaxing moisturizing cream. In addition, if it recognizes that the user's recent emotions tend to be stressful, it will suggest the use of aromatherapy products. In this way, the system comprehensively analyzes the user's internal and external state to provide optimal skincare.

[0888] An example of a prompt message for a generative AI model is: "This user's current skin condition is dry. Sentiment analysis indicates they are experiencing stress. What skincare products would you recommend?"

[0889] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0890] Step 1:

[0891] The device uses a camera to capture the user's facial information. The input is the image from the camera, and the output is the acquired facial image data. This image data is temporarily stored in memory in preparation for the next analysis process.

[0892] Step 2:

[0893] The server receives facial image data sent from the terminal. The input is facial image data from the terminal, and the output is the utilization of that data. A machine learning model is used to analyze the skin condition from this facial image data and extract specific skin characteristics such as dryness, wrinkles, and blemishes.

[0894] Step 3:

[0895] The server analyzes the emotional state using an emotion recognition API along with facial image data. The input is facial image data, and the output is the analyzed emotion data. Through emotional state recognition, information such as whether the user is currently stressed or relaxed is obtained.

[0896] Step 4:

[0897] The server generates optimal skincare suggestions using a generative AI model based on acquired skin condition and emotional state data. The input is analyzed skin and emotional data, and the output is the suggested content. This process accesses external databases and customizes suggestions by referencing various product information.

[0898] Step 5:

[0899] The terminal displays the suggestions received from the server to the user. The input is the suggestions from the server, and the output is a visual presentation of information to the user. The suggestions include specific product names, usage instructions, and frequency information.

[0900] Step 6:

[0901] Users perform their daily skincare routine based on the provided suggestions. By providing feedback, the quality of future suggestions can be improved. Input consists of the user's own actions and feedback, while output is the collection of feedback data.

[0902] 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.

[0903] 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.

[0904] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0905] 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.

[0906] 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.

[0907] 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.

[0908] 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.

[0909] 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.

[0910] 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."

[0911] 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.

[0912] 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.

[0913] 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.

[0914] 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.

[0915] 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.

[0916] 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.

[0917] 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.

[0918] 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.

[0919] 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.

[0920] 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.

[0921] 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.

[0922] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0923] The following is further disclosed regarding the embodiments described above.

[0924] (Claim 1)

[0925] A means of obtaining facial images taken from users,

[0926] A method for analyzing skin condition based on acquired facial images,

[0927] A means of proposing the most suitable skin care products and methods to the user based on the analysis results,

[0928] A means of acquiring surrounding environmental data and adjusting the proposed content,

[0929] A system that includes this.

[0930] (Claim 2)

[0931] The system according to claim 1, which detects skin features using image recognition technology and generates analysis results as structured data.

[0932] (Claim 3)

[0933] The system according to claim 1, which refers to an external database and obtains appropriate product information based on the analysis results.

[0934] "Example 1"

[0935] (Claim 1)

[0936] A means of obtaining facial images taken from users,

[0937] A means of optimizing the analysis using image processing technology based on the acquired facial images,

[0938] A means of analyzing optimized images and quantifying skin condition as a feature,

[0939] A means of comparing analysis results with internal information to propose personalized skin care products and methods that are optimal for the user,

[0940] A means of acquiring external environmental information and dynamically adjusting the proposed content,

[0941] A system that includes this.

[0942] (Claim 2)

[0943] The system according to claim 1, which uses a machine learning algorithm to detect skin characteristics with high accuracy and outputs the analysis results as structured data.

[0944] (Claim 3)

[0945] The system according to claim 1, which refers to an internal database and an external information source to select the most suitable product information based on the user's environment.

[0946] "Application Example 1"

[0947] (Claim 1)

[0948] A means of obtaining facial images taken from users,

[0949] A method for analyzing skin condition based on acquired facial images,

[0950] A means of proposing the most suitable skin care products and methods to the user based on the analysis results,

[0951] A means of acquiring surrounding environmental data and adjusting the proposed content,

[0952] A means of coordinating with a machine that presents analysis results using audio and visual information,

[0953] A means to collect user feedback after the implementation of the proposal and improve the accuracy of the analysis,

[0954] A system that includes this.

[0955] (Claim 2)

[0956] The system according to claim 1, which detects skin features using image recognition technology and generates analysis results as structured data.

[0957] (Claim 3)

[0958] The system according to claim 1, which refers to an external database and obtains appropriate product information based on the analysis results.

[0959] "Example 2 of combining an emotion engine"

[0960] (Claim 1)

[0961] A means of acquiring biometric information obtained from users using image functions,

[0962] A means of proposing personalized lifestyle products and methods based on acquired biometric information,

[0963] A means for analyzing emotional states using an analysis device and generating emotional data,

[0964] A means for integrating the aforementioned emotional data and skin condition data and optimizing the proposed content using a generative intelligence model,

[0965] A system that includes this.

[0966] (Claim 2)

[0967] The system according to claim 1, which uses machine learning technology to detect biological features and generates analysis results as structured information.

[0968] (Claim 3)

[0969] The system according to claim 1, which refers to a knowledge base and obtains appropriate product information based on the analysis results.

[0970] "Application example 2 when combining with an emotional engine"

[0971] (Claim 1)

[0972] A means of obtaining facial information captured from a user,

[0973] A method for analyzing skin condition based on acquired facial information,

[0974] A means for identifying the emotional state of analyzed facial information,

[0975] A means of suggesting the most suitable skin care products and methods to the user based on the identified emotional state and skin condition,

[0976] A means of acquiring external environmental information and adjusting the proposed content,

[0977] A system that includes this.

[0978] (Claim 2)

[0979] The system according to claim 1, which detects skin features using image recognition technology and generates analysis results as structured data.

[0980] (Claim 3)

[0981] The system according to claim 1, which refers to an external data storage and obtains appropriate product information based on the analysis results. [Explanation of symbols]

[0982] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of obtaining facial images taken from users, A method for analyzing skin condition based on acquired facial images, A means of proposing the most suitable skin care products and methods to the user based on the analysis results, A means of acquiring surrounding environmental data and adjusting the proposed content, A system that includes this.

2. The system according to claim 1, which detects skin features using image recognition technology and generates analysis results as structured data.

3. The system according to claim 1, which refers to an external database and obtains appropriate product information based on the analysis results.

Images