system

Abstract

We provide the system. [Solution] A means for receiving image data and performing preprocessing, A method that uses a machine learning model to analyze preprocessed image data and extract skin features, A method for generating skincare product suggestions based on analyzed skin characteristic data, A means of acquiring user location and weather information and generating skincare advice tailored to the environment, A means of outputting suggested information and advice to the user, A system that controls beauty devices adapted to the characteristics of the user's skin condition, and includes means of supporting skincare in the user's living space.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Self-diagnosing the skin condition is difficult for many people, and it may take a lot of time and effort to choose an appropriate skin care product. Also, it is difficult to appropriately select a skin care method according to the usage environment and season. In addition, a comprehensive skin care advisor that takes into account a wide variety of skin types and allergies is needed.

Means for Solving the Problems

[0005] This invention provides a system that receives and preprocesses image data and analyzes skin characteristics using a machine learning model. Furthermore, it suggests skincare products based on the analysis results, acquires the user's location and weather information, and generates skincare advice tailored to the environment. By outputting the suggested products and advice to the user and utilizing the feedback as training data, the accuracy and effectiveness of skincare product selection are improved. By enabling product selection that takes into account the user's specific skin type and allergy information, comprehensive skincare support is realized.

[0006] "Image data" refers to digital information obtained from a user's smartphone or camera that shows the condition of the user's face and skin.

[0007] "Preprocessing" refers to the process of performing actions such as noise reduction, face recognition, and resizing to prepare image data for easier analysis.

[0008] A "machine learning model" is a computational model that learns from vast amounts of data and is used to recognize specific patterns or features in that data.

[0009] "Skin characteristics" refer to information obtained through analysis that indicates the condition of the skin, such as dryness, blemishes, wrinkles, enlarged pores, and redness.

[0010] "Skincare products" are beauty products such as creams and lotions used to improve the health of the skin and address specific skin problems.

[0011] "Location information" refers to data that indicates the user's current geographical location.

[0012] "Weather information" refers to data that shows the current weather conditions at a particular location, such as humidity, temperature, and UV radiation levels.

[0013] "Environment-appropriate skincare advice" refers to guidance information that indicates skincare methods and product usage suitable for specific weather conditions or seasons.

[0014] "Feedback" refers to information that shows users' opinions and impressions of the advice and product suggestions they have received.

[0015] "Skin type" is a classification of information that indicates the nature and characteristics of a user's skin, and includes categories such as dry skin and sensitive skin.

[0016] "Allergy information" refers to information indicating whether or not a user has allergies to specific ingredients or substances. [Brief explanation of the drawing]

[0017] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] 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 combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of a plurality of 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.

[0021] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0022] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0023] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0024] 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."

[0025] [First Embodiment]

[0026] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0032] 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.

[0033] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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".

[0038] This invention is a system that helps users understand their own skin condition and select appropriate skincare products and methods. The system analyzes the skin condition using facial images taken by the user and suggests optimal products and skincare methods, taking into account the environment and individual skin type.

[0039] Image capture and transmission

[0040] Users take selfies using their smartphones or cameras. They then send the images to a server via a dedicated app.

[0041] Image preprocessing

[0042] The server preprocesses the received images. This preprocessing includes noise reduction and size standardization. It also applies a face recognition algorithm to identify the facial regions necessary for analysis.

[0043] Analysis of skin characteristics

[0044] The server uses a deep learning-based machine learning model to analyze skin features based on pre-processed images. This analysis extracts multiple features such as skin dryness, blemishes, wrinkles, enlarged pores, and redness, and assigns a score to each.

[0045] Product and advice suggestions

[0046] The server generates recommendations for the most suitable skincare products for the user based on the analyzed skin characteristics. These recommendations refer to a database of commercially available products, while also taking into account the user's allergy information and survey data. Furthermore, it analyzes current weather and environmental conditions to create situation-specific skincare advice.

[0047] Submitting results and obtaining feedback

[0048] The device displays suggested products and advice, notifying the user. The user can then use this information to guide their daily skincare routine.

[0049] Users submit feedback on the suggestions through the app. This feedback will be used to improve the accuracy of future analyses.

[0050] For example, if a user uploads a photo of their face taken during the dry winter season, the server will determine that the skin is highly dry and suggest products with high moisturizing effects. Furthermore, considering the low outside temperature, it will advise on moisturizing-focused skincare methods, helping users make informed skincare choices. This system ensures that users always receive the latest and most optimal skincare information tailored to their specific skin condition.

[0051] The following describes the processing flow.

[0052] Step 1:

[0053] The user takes a selfie using their smartphone. Then, they launch a dedicated app, select the captured image file, and send it to the server.

[0054] Step 2:

[0055] The server receives image data sent by the user. It applies a noise-removing filter to the image data and extracts face regions as needed. It also resizes the images to a specific size for deep learning analysis.

[0056] Step 3:

[0057] The server inputs pre-processed images into a deep learning model. This model is a computational model that detects features such as skin dryness, blemishes, wrinkles, enlarged pores, and redness. Through analysis, it generates a numerical score for each feature.

[0058] Step 4:

[0059] The server uses the analysis results to suggest skincare products. It refers to a database of various commercially available products and selects products that match the user's skin characteristics. It also checks the ingredients in the suggested products, taking into account the allergy information registered in the user profile.

[0060] Step 5:

[0061] The server calls a weather API based on the user's location information to obtain climate data (temperature, humidity, UV index). This environmental data is then combined with analysis results to generate skincare advice.

[0062] Step 6:

[0063] The device displays a list of suggested products and skincare advice sent from the server. Users can then review this information in detail through the application and incorporate it into their skincare plan.

[0064] Step 7:

[0065] Users provide feedback on the advice and suggested products they receive using a form within the application. This feedback is incorporated into future analyses and suggestions, and is used to improve the individual user experience.

[0066] (Example 1)

[0067] 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."

[0068] Understanding one's own skin condition and choosing appropriate skincare products and methods is limited by conventional general information alone. Therefore, there is a need for more personalized skincare suggestions based on individual skin types and current environmental conditions. Furthermore, utilizing feedback on the effectiveness of suggested products and continuously improving the system is also a challenge.

[0069] 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.

[0070] In this invention, the server includes means for receiving image data and performing preprocessing such as noise reduction and size standardization; means for analyzing the preprocessed image data using a machine learning model employing deep learning to extract skin characteristics such as dryness, blemishes, wrinkles, enlarged pores, and redness; means for generating skincare product suggestions from various databases based on the analyzed skin characteristic data, taking into account specific allergy information based on the user's personal information; and means for acquiring the user's location and environmental information to generate skincare advice according to weather conditions. This enables personalized skincare suggestions based on individual skin types and environmental conditions, and also allows for continuous improvement of the system through feedback.

[0071] "Image data" refers to digital information that includes visual information of the skin surface captured by the user.

[0072] "Noise reduction" is a technique that removes unnecessary information and distortions from image data to improve the accuracy of analysis.

[0073] "Size standardization" is a process that unifies the resolution and dimensions of image data to maintain consistency in analysis.

[0074] "Preprocessing" refers to a series of processes to transform image data into a format that can be analyzed, and includes tasks such as noise reduction and facial area identification.

[0075] A "deep learning-based machine learning model" is a sophisticated computational model used to process large amounts of data, learn patterns, and analyze skin characteristics.

[0076] "Skin characteristics" refer to specific attributes of the skin being analyzed, including dryness, blemishes, wrinkles, enlarged pores, redness, etc.

[0077] "Allergy information" refers to data about hypersensitivity reactions that users exhibit to specific substances or products, and is a factor considered when proposing products.

[0078] "Environmental information" refers to data about weather conditions and other external factors in the user's area, and is used to generate skincare advice.

[0079] "Skincare product recommendations" refer to recommendations for products deemed most suitable for the user, based on analyzed skin characteristics and personal information.

[0080] "Feedback" refers to the evaluations and reactions that users provide to suggested skincare products and advice, and is data used to improve the system.

[0081] This invention is a system that helps users understand their own skin condition in detail and obtain appropriate skincare products and methods. This system mainly uses the user's terminal, a server, and a communication network to link them together.

[0082] Users capture facial images using their smartphones or cameras. After capturing, they send these images to a server via a dedicated application. Ideally, the image data should have as little noise as possible and be taken under ideal lighting conditions.

[0083] The server uses image processing libraries (e.g., OpenCV, PIL) to process the received image data, performing noise reduction and size standardization. This preprocessing makes the image suitable for analysis. Next, face recognition technology (e.g., dlib, Facenet) is used to identify the facial regions that need to be analyzed.

[0084] In the analysis stage, preprocessed image data is used to extract skin features using a generative AI model based on deep learning (e.g., TENSORFLOW®, PyTorch). This model evaluates and scores characteristics such as skin dryness, blemishes, wrinkles, enlarged pores, and redness.

[0085] Based on the analysis results, the server suggests skincare products suitable for the user's skin. This suggestion is made by referring to a database of commercially available products while also considering the user's allergy information and survey data. Furthermore, it uses OpenWeatherAPI and other tools to obtain current weather and environmental conditions, and generates skincare advice based on this information.

[0086] The device supports daily skincare by displaying suggestions and advice sent from the server and notifying the user. Furthermore, the user can send feedback on these suggestions through the application. The feedback information is stored in a database on the server and used to train the generative AI model, improving the accuracy of the system's analysis.

[0087] For example, if a user's image taken in winter is submitted, the server will detect a high dryness score and suggest products aimed at moisturizing. It will also provide skincare advice suitable for cold environments, allowing the user to implement appropriate skincare based on this information.

[0088] An example of a prompt to input into a generative AI model is: "Please suggest skincare products and advice suitable for dry skin. Also, please tell me about winter skincare methods."

[0089] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0090] Step 1:

[0091] The user takes a selfie using their smartphone or camera. This image is usually saved in JPEG or PNG format. Then, they send the image data to the server via a dedicated application. The input is the facial image data, and the output is the image data securely stored on the server. The specific actions in this step refer to everything from taking the photo to uploading the image.

[0092] Step 2:

[0093] The server begins preprocessing the received image data. Here, image processing libraries (e.g., OpenCV, PIL) are used to remove noise and standardize the image size. Furthermore, face recognition algorithms (e.g., dlib, Facenet) are used to identify the facial regions necessary for analysis. The input is the raw image data sent by the user, and the output is the preprocessed image data. This ensures that the server has data suitable for analysis.

[0094] Step 3:

[0095] The server inputs pre-processed image data into a generating AI model (e.g., TensorFlow, PyTorch) to analyze skin features. This analysis extracts features such as skin dryness, blemishes, wrinkles, enlarged pores, and redness. The input is pre-processed image data, and the output is a score for each skin feature. The specific operation involves inputting image data into the AI ​​model and receiving the analysis results.

[0096] Step 4:

[0097] The server generates recommendations for optimal skincare products based on analyzed skin characteristics. This involves referencing a product database and considering the user's allergy information and survey data. Furthermore, it uses the OpenWeatherAPI and other tools to obtain current weather and environmental conditions to generate skincare advice. Inputs are skin characteristic scores and weather data, while outputs are user-appropriate product recommendations and environment-based advice. Specific operations include database queries and data retrieval from external APIs.

[0098] Step 5:

[0099] The terminal displays skincare product suggestions and advice sent from the server to the user. The input is suggestion data from the server, and the output is a visual display of information to the user. The specific action in this step is the process of displaying information on the user interface and notifying the user.

[0100] Step 6:

[0101] Users submit feedback on the provided suggestions through a dedicated app. The input is the user's opinions and feedback data, and the output is the feedback data sent to the server. Specifically, the app records the feedback and sends it to the server via the internet.

[0102] (Application Example 1)

[0103] 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."

[0104] Traditional skincare product recommendation systems only analyze the user's skin condition and suggest products, lacking support for users to implement skincare in their daily lives. Therefore, there is a challenge in that users find it difficult to properly perform skincare based on the recommendations. In particular, in busy daily lives, there is a lack of support for carrying out the suggested care, making it difficult to obtain an effective skincare experience.

[0105] 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.

[0106] In this invention, the server includes means for receiving and pre-processing image data, means for analyzing the pre-processed image data and using a machine learning model to extract skin characteristics, and means for controlling a beauty device adapted based on the characteristics of the skin condition to support skincare in the user's living space. This makes it possible to support effective and easy skincare in the user's everyday living space.

[0107] "Image data" refers to images of a user's face taken by the user, and is used as input information for analyzing skin condition.

[0108] "Preprocessing" refers to the process of removing unwanted noise from image data and preparing it for analysis.

[0109] A "machine learning model" refers to an algorithm used to analyze data and extract specific patterns or features.

[0110] "Skin characteristics" refers to skin attribute information extracted through analysis, such as skin dryness, blemishes, wrinkles, enlarged pores, and redness.

[0111] "Skincare product recommendations" refer to selecting and presenting the most suitable skincare products to the user based on analyzed skin characteristic data.

[0112] "Location information" refers to geographical location data of the user's current location and is an element used to obtain environmental information.

[0113] "Weather information" refers to data that shows external environmental conditions such as weather and temperature in the user's area.

[0114] A "beauty device" refers to a machine that is controlled to support the user's skincare routine and assists with daily care.

[0115] "Living space" refers to the place where a user resides or engages in daily activities.

[0116] In this invention, the user takes a picture of their face using a smartphone or camera. The captured image is sent from the user's device to a server via a dedicated application. The server receives this image data and performs preprocessing using an image processing library such as OpenCV. This preprocessing includes noise reduction and size standardization.

[0117] The pre-processed images are analyzed using a machine learning platform such as TensorFlow running on the server. The machine learning model analyzes features such as skin dryness, blemishes, wrinkles, enlarged pores, and redness, and assigns a score to each.

[0118] Based on the analysis results, the server references a database of commercially available products and user profile information to generate suggestions for the most suitable skincare products. It also obtains the user's location and weather information to generate skincare advice tailored to the user's environment. The suggested information and advice are sent to the terminal and displayed to the user.

[0119] Furthermore, a consumer robot installed in the user's living space controls beauty devices based on analyzed skin characteristics, supporting the user in performing skincare in their daily life. This allows the user to use the suggested skincare products in the most optimal way, resulting in effective skincare.

[0120] For example, if the server determines that a user's skin is highly dry based on an image taken in a dry winter environment, the robot will suggest an appropriate moisturizing product and advise, "You should use this product after washing your face." By providing feedback on the results of using the suggested product, the overall analysis accuracy of the system improves, and users can receive more personalized services.

[0121] Examples of prompts to input into the generating AI model include, "Please analyze my skin characteristics and tell me the best skincare method," and "Please advise me on the best moisturizing method for winter."

[0122] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0123] Step 1:

[0124] The user takes a picture of their face using their smartphone camera. The captured image data is saved on the device. The user sends this image to the server via a dedicated app. The input is the user's face image, and the output is the image data received by the server.

[0125] Step 2:

[0126] The server performs preprocessing on the received image data. This preprocessing uses OpenCV to remove noise and standardize the image size. A face recognition algorithm is then applied to identify face regions within the image. The input is the received face image, and the output is the preprocessed image data.

[0127] Step 3:

[0128] The server runs a deep learning-based machine learning model using pre-processed image data to analyze skin features. This analysis extracts features such as skin dryness, blemishes, wrinkles, enlarged pores, and redness, and assigns a score to each. The input is pre-processed image data, and the output is skin feature score data.

[0129] Step 4:

[0130] The server generates skincare product recommendations based on analyzed skin characteristic data. It references a database of commercially available products and user profile information to select the most suitable skincare products and create recommendations. Inputs are skin characteristic score data and product database information, while output is skincare product recommendations.

[0131] Step 5:

[0132] The server acquires the user's location and weather information and generates skincare advice tailored to the environment. This provides the user with the optimal skincare method. The input is location and weather information, and the output is environment-based skincare advice.

[0133] Step 6:

[0134] The terminal displays suggested information and advice received from the server to the user. The user can use this as a reference for their daily skincare routine. The input is suggested information and advice from the server, and the output is the information displayed to the user.

[0135] Step 7:

[0136] Users use the suggested skincare products and send feedback about their effects to the server via the app. The server receives this feedback and uses it as training data for the system to improve the accuracy of its analysis. The input is user feedback information, and the output is the system's training data.

[0137] 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.

[0138] The present invention is a system that analyzes not only the user's skin condition but also their emotional state, and provides skincare suggestions based on this analysis. This system has a function that analyzes skin characteristics from the user's image using deep learning technology, as well as an emotion engine that recognizes the user's emotions. The following describes specific embodiments of the present invention.

[0139] Image capture and transmission

[0140] The user takes a selfie using their smartphone. The image must clearly show their entire face. They then send the image to the server via a dedicated app.

[0141] Analysis of skin characteristics and emotions

[0142] The server preprocesses the received images and analyzes skin features using a deep learning model. This analysis provides information such as skin dryness, blemishes, wrinkles, enlarged pores, and redness.

[0143] The server uses an emotion engine to simultaneously recognize emotions from the user's facial expressions. This emotion data indicates the user's current psychological state.

[0144] Product and advice suggestions

[0145] The server generates a list of optimal skincare products and advice based on skin characteristic analysis data and emotional data. If the user is experiencing stress, it will recommend products with relaxation effects, providing personalized support based on their emotions.

[0146] Furthermore, by taking into account climate data obtained from weather APIs, we can also provide skincare advice tailored to the environment.

[0147] Output of proposed information and feedback

[0148] The device displays skincare products and advice sent from the server to the user. The user can then adjust their daily skincare routine based on the information presented.

[0149] Users submit feedback to the system regarding the information and products provided. This feedback is incorporated into the system's learning database to improve the accuracy of future suggestions.

[0150] For example, if a user appears tense, the server can suggest relaxing skincare products and recommend an aromatherapy bath in the evening. In this way, the system comprehensively assesses the user's skin condition and emotions to provide the most suitable products and care methods, thereby improving the user's skincare experience.

[0151] The following describes the processing flow.

[0152] Step 1:

[0153] The user takes a picture of their face using their smartphone camera. They launch the application, select the captured image, and send it to the server.

[0154] Step 2:

[0155] The server takes in the received image data and performs preprocessing such as noise reduction and brightness adjustment. It recognizes face regions within the image and crops them as needed.

[0156] Step 3:

[0157] The server inputs the pre-processed images into a deep learning model. This model analyzes features such as skin dryness, blemishes, wrinkles, enlarged pores, and redness. The analysis results are output as numerical values ​​for each feature.

[0158] Step 4:

[0159] The server uses an emotion engine to analyze facial expressions from user images and recognize the user's emotional state. In this process, even subtle changes in facial expression are captured, and emotions such as joy, anger, and sadness are quantified.

[0160] Step 5:

[0161] The server selects the optimal skincare products based on the obtained skin characteristic data and emotional data. In this selection process, products that match the user's stress and relaxation state are prioritized.

[0162] Step 6:

[0163] The server uses a weather API to retrieve local climate data based on the user's location. This includes temperature, humidity, and UV index, and this information is used to further customize skincare advice.

[0164] Step 7:

[0165] The device displays a list of suggested skincare products and advice sent from the server to the user. The user can then incorporate this information into their daily skincare routine.

[0166] Step 8:

[0167] Users submit feedback on the products and advice provided, including their impressions and results of using them. This feedback is stored on the server as training data for the system and used to improve the accuracy of future analyses and suggestions.

[0168] (Example 2)

[0169] 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 will be referred to as the "terminal."

[0170] Conventional skincare product recommendation systems often only consider the physical characteristics of the user's skin, neglecting psychological state and environmental information, which leads to a failure to adequately address individual needs. Furthermore, there is a lack of mechanisms to effectively utilize user feedback and improve the accuracy of the system's recommendations.

[0171] 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.

[0172] In this invention, the server includes means for receiving and pre-processing image information; means for analyzing the pre-processed image information and using machine learning techniques to extract skin characteristics; means for generating skincare product suggestions based on the analyzed skin characteristics and emotional information; means for acquiring user environmental information and generating skincare advice according to external conditions; and means for acquiring feedback on the effects of the suggested skincare products and advice and utilizing it as learning information for the system. This makes it possible to provide more personalized skincare suggestions that take into account not only the user's skin characteristics but also their emotional state and external environment.

[0173] "Image information" refers to still images and videos taken by users, and is digital data that is subject to analysis.

[0174] "Preprocessing" refers to the process of transforming received image information so that it can be easily analyzed by a model. This includes processes such as resizing and noise reduction.

[0175] "Skin characteristics" refer to the physical features of the user's skin, including dryness, blemishes, wrinkles, enlarged pores, redness, etc.

[0176] "Machine learning technology" refers to algorithms and models that allow computers to learn from data and perform analysis and inference.

[0177] "Emotional information" refers to data that indicates the psychological state inferred from the user's facial expressions, and includes emotions such as joy, anger, sadness, surprise, and tension.

[0178] "Recommendations" refer to recommendations regarding skincare products and care methods provided to users based on the analysis results.

[0179] "Environmental information" refers to data that indicates external conditions based on the user's location, and includes meteorological data such as temperature, humidity, and UV index.

[0180] "Feedback" refers to a user's response to a system, such as providing suggestions, evaluations, or comments on a product.

[0181] "Learning information" refers to data that a system uses to improve the accuracy of its model's analysis based on user feedback and past data.

[0182] To implement this invention, the user, server, and terminal must each fulfill their respective roles. The user takes a selfie image using a smart device and sends this image to the server using a dedicated application. This application has the functionality to securely transmit image information using the SSL / TLS protocol.

[0183] The server preprocesses the received image information. This preprocessing includes normalization to unify image sizes and filtering to reduce noise, utilizing image processing libraries such as OpenCV. The preprocessed image information is then analyzed for skin characteristics using machine learning techniques. A deep learning model using TensorFlow is used for this analysis, automatically detecting characteristics such as skin dryness, blemishes, wrinkles, enlarged pores, and redness.

[0184] Furthermore, the server uses an emotion analysis engine to analyze emotional information, estimating emotions from the user's facial expressions. This process is crucial for understanding the user's psychological state. The analyzed emotional information and skin characteristic information are integrated, and prompts are input into a generative AI model to suggest optimal skincare products and care methods. An example of such a prompt is, "Please suggest the best nighttime skincare products for stressed skin."

[0185] The suggested information is sent from the server to the terminal and associated with the user's dedicated account. The terminal displays the received information in an easy-to-understand format, allowing the user to purchase skincare products or implement skincare methods based on that information.

[0186] Users can provide feedback on these suggestions. This feedback is sent back to the server and stored as learning information for the system, improving the accuracy of future suggestions. The server also acquires external weather information and supplements the advice with information tailored to the user's environment. This results in a customized skincare experience that meets the user's individual needs.

[0187] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0188] Step 1:

[0189] The user takes a selfie with their smart device. The captured image is sent to the server via the application. The input here is the user's image data, which the app encrypts before transferring to the server.

[0190] Step 2:

[0191] The server preprocesses the received image data. The input is the image data sent in step 1, and the output is image data in an analyzable format. In this preprocessing, the OpenCV library is used to adjust the image resolution and denoise the image.

[0192] Step 3:

[0193] The server inputs pre-processed image data into a machine learning model to analyze skin characteristics. The input is pre-processed image data, and the output provides characteristic information such as skin dryness, blemishes, wrinkles, enlarged pores, and redness. This analysis utilizes a deep learning model based on TensorFlow.

[0194] Step 4:

[0195] The server uses an emotion analysis engine to extract the user's emotional information. The input is the image data received in step 1, and the output generates emotion categories such as joy, anger, sadness, surprise, and tension. This data reflects the user's psychological state.

[0196] Step 5:

[0197] The server inputs prompt sentences into a generating AI model to produce skincare products and care advice. The inputs are skin characteristic information, emotional information, and environmental information, and the output is personalized suggestions. An example of a prompt sentence in this case is, "Please suggest the best nighttime skincare products for stressed skin."

[0198] Step 6:

[0199] The server sends the generated suggestion information to the terminal. The user can then view the suggestion information through the terminal. The input is the suggested content generated by the server, and the output provides the user with information on skincare products and advice that can be displayed to them.

[0200] Step 7:

[0201] Users provide feedback on suggested products and advice via their devices. This feedback is then sent back to the server, where the input is user feedback data and the output is the system's learned information is updated. This feedback contributes to improving the accuracy of future suggestions.

[0202] (Application Example 2)

[0203] 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".

[0204] In modern society, there is a growing demand for more personalized skincare recommendations that take into account the unique skin and emotional states of individual users. However, conventional skincare analysis systems often only analyze the user's skin condition, and fail to adequately consider emotional states in their recommendations. Furthermore, skincare recommendations that utilize environmental information are also lacking. An effective system that can solve these problems and provide individualized recommendations to users is desired.

[0205] 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.

[0206] In this invention, the server includes means for receiving and pre-processing image information; means for analyzing the pre-processed image information and using a learning model to extract skin features; means for generating skincare product suggestions based on the analyzed skin feature information and received emotional data; means for acquiring surrounding information and environmental information and generating skincare advice appropriate to the environment; means for providing suggestion information and advice to the user; and means for recognizing the user's emotional state and making skincare suggestions that take that data into consideration. This enables more personalized skincare suggestions that simultaneously consider the user's individual skin condition and emotional state.

[0207] "Image information" refers to digital data acquired through a camera device that captures the user's face and skin condition.

[0208] "Preprocessing" refers to image adjustment processes such as filtering and noise reduction performed to improve the accuracy of image information.

[0209] A "learning model" is an algorithm trained using machine learning techniques such as deep learning to analyze skin characteristics and conditions.

[0210] "Skincare product recommendations" refer to the act of listing and recommending skincare products that are considered optimal for each individual user, based on analyzed skin characteristic information and emotional data.

[0211] "Surrounding information" refers to the user's location information and surrounding environmental data, including information about the weather, humidity, and temperature of the user's environment.

[0212] "Environmental information" refers to information about external factors that may affect the skin, such as weather conditions and airborne substances in the area where the user lives.

[0213] "Emotional state" refers to the psychological or emotional state that can be inferred from the user's facial expressions and actions.

[0214] "Means of provision" refers to technical means or interfaces for visually or audibly communicating analysis results to users.

[0215] "Recognition" refers to the process of identifying and understanding the user's emotions and skin condition, and is primarily based on image analysis.

[0216] The system for realizing this invention consists of a user, a server, and a terminal. The server receives image information captured by the user using the terminal and performs preprocessing. This preprocessing includes denoising and adjusting the resolution of the images. The server analyzes the preprocessed image information using a learning model based on deep learning technology to extract skin characteristics and the user's emotional state.

[0217] The user must capture a clear image of their entire face. This allows for the extraction of skin characteristics such as dryness, blemishes, wrinkles, enlarged pores, and redness, as well as emotional data derived from their facial expressions. The server integrates this data and generates skincare product recommendations based on the analysis results. These recommendations include products that offer stress reduction and relaxation effects tailored to the analyzed emotional state.

[0218] Furthermore, the server acquires location and environmental information as surrounding information, combines it with data obtained through a weather API, and makes suggestions, including skincare advice tailored to the season and weather. The generated suggestion information and advice are provided to the user through the device.

[0219] For example, if a user uploads a photo of themselves taken with their device's camera to the system, and the analysis reveals that their skin is dry and they are under stress, the server can suggest the use of a highly moisturizing skincare cream and an aromatherapy oil that promotes relaxation. Furthermore, by using a prompt to the generative AI model such as, "Please suggest products with relaxing effects," the system can help generate more effective suggestions.

[0220] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0221] Step 1:

[0222] The user takes a picture of their face using the device's camera. The captured image must be high-resolution and clearly show the entire face. After taking the picture, this image data is sent to the server via a dedicated application. Image acquisition is crucial, as analysis cannot be performed without it. The input is high-resolution image data, and the output is a notification that the transmission to the server is complete.

[0223] Step 2:

[0224] The server performs preprocessing on the received image data, such as noise reduction and resolution adjustment. The preprocessed images have improved quality, enhancing the accuracy of subsequent analysis. The input is the received image data, and the output is the preprocessed image. Here, image processing algorithms are used to improve data quality.

[0225] Step 3:

[0226] The server analyzes pre-processed images using a deep learning model to extract skin features. This analysis yields data on skin dryness, blemishes, wrinkles, enlarged pores, redness, and other characteristics. The input is pre-processed image data, and the output is skin feature data. The model's inference engine is utilized here.

[0227] Step 4:

[0228] Simultaneously, the server uses an emotion recognition engine to analyze emotional data from the user's facial expressions. This analysis allows the server to understand the user's current psychological state. The input is pre-processed image data, and the output is emotional state data. The emotion analysis is based on facial recognition technology.

[0229] Step 5:

[0230] The server combines analyzed skin characteristic data and emotional data to generate personalized skincare product recommendations for the user. Using a generative AI model, it integrates the data based on prompt messages to determine appropriate products and advice. The input consists of skin characteristic and emotional data, while the output is a customized recommendation.

[0231] Step 6:

[0232] The server further collects surrounding environmental information via a weather API and uses this information to create skincare advice tailored to the environment. This advice indicates appropriate skincare methods based on location data such as temperature and humidity. The input is location information and weather data, and the output is environment-appropriate advice.

[0233] Step 7:

[0234] Ultimately, the server sends the suggested skincare products and advice to the user's device as text or audio information, which is then provided to the user by the device. Based on this output information, the user can optimize their daily skincare routine. The input is the suggested information, and the output is the completion of delivery to the user.

[0235] Step 8:

[0236] Users send their thoughts and feedback on the provided skincare information and products to the server. This feedback is used as training data for the system to improve the accuracy of future recommendations. The input is the user's feedback data, and the output is the completion of data registration in the system.

[0237] 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.

[0238] 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.

[0239] 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.

[0240] [Second Embodiment]

[0241] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0242] 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.

[0243] 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).

[0244] 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.

[0245] 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.

[0246] 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).

[0247] 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.

[0248] 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.

[0249] 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.

[0250] 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.

[0251] 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.

[0252] 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".

[0253] This invention is a system that helps users understand their own skin condition and select appropriate skincare products and methods. The system analyzes the skin condition using facial images taken by the user and suggests optimal products and skincare methods, taking into account the environment and individual skin type.

[0254] Image capture and transmission

[0255] Users take selfies using their smartphones or cameras. They then send the images to a server via a dedicated app.

[0256] Image preprocessing

[0257] The server preprocesses the received images. This preprocessing includes noise reduction and size standardization. It also applies a face recognition algorithm to identify the facial regions necessary for analysis.

[0258] Analysis of skin characteristics

[0259] The server uses a deep learning-based machine learning model to analyze skin features based on pre-processed images. This analysis extracts multiple features such as skin dryness, blemishes, wrinkles, enlarged pores, and redness, and assigns a score to each.

[0260] Product and advice suggestions

[0261] The server generates recommendations for the most suitable skincare products for the user based on the analyzed skin characteristics. These recommendations refer to a database of commercially available products, while also taking into account the user's allergy information and survey data. Furthermore, it analyzes current weather and environmental conditions to create situation-specific skincare advice.

[0262] Submitting results and obtaining feedback

[0263] The device displays suggested products and advice, notifying the user. The user can then use this information to guide their daily skincare routine.

[0264] Users submit feedback on the suggestions through the app. This feedback will be used to improve the accuracy of future analyses.

[0265] For example, if a user uploads a photo of their face taken during the dry winter season, the server will determine that the skin is highly dry and suggest products with high moisturizing effects. Furthermore, considering the low outside temperature, it will advise on moisturizing-focused skincare methods, helping users make informed skincare choices. This system ensures that users always receive the latest and most optimal skincare information tailored to their specific skin condition.

[0266] The following describes the processing flow.

[0267] Step 1:

[0268] The user takes a selfie using their smartphone. Then, they launch a dedicated app, select the captured image file, and send it to the server.

[0269] Step 2:

[0270] The server receives image data sent by the user. It applies a noise-removing filter to the image data and extracts face regions as needed. It also resizes the images to a specific size for deep learning analysis.

[0271] Step 3:

[0272] The server inputs pre-processed images into a deep learning model. This model is a computational model that detects features such as skin dryness, blemishes, wrinkles, enlarged pores, and redness. Through analysis, it generates a numerical score for each feature.

[0273] Step 4:

[0274] The server uses the analysis results to suggest skincare products. It refers to a database of various commercially available products and selects products that match the user's skin characteristics. It also checks the ingredients in the suggested products, taking into account the allergy information registered in the user profile.

[0275] Step 5:

[0276] The server calls the weather API based on the user's location information to obtain climate data (temperature, humidity, UV index). These environmental data are combined with the analysis results to generate skin care advice.

[0277] Step 6:

[0278] The terminal displays the proposed product list and skin care advice sent from the server on the screen. The user can check this information in detail through the application and incorporate it into the skin care plan.

[0279] Step 7:

[0280] The user provides feedback on the received advice and proposed products using the form within the application. This feedback is reflected in the next analysis and proposed content and is utilized to improve the individual user experience.

[0281] (Example 1)

[0282] 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".

[0283] For a user to understand their skin condition and select appropriate skin care products and methods, there are limitations with only conventional general information. Therefore, there is a need for more personalized skin care proposals based on individual skin types and current environmental conditions. Also, it is an issue to utilize the feedback on the effects of the proposed products to continuously improve the system.

[0284] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following respective means.

[0285] In this invention, the server includes means for receiving image data and performing preprocessing such as noise removal and size normalization, means for analyzing the preprocessed image data using a machine learning model based on deep learning to extract skin characteristics such as dryness, stains, wrinkles, pore opening, and redness, means for generating proposals for skin care products from various databases based on the analyzed skin characteristic data and considering specific allergy information based on the user's personal information, and means for acquiring the user's location information and environmental information and generating skin care advice according to weather conditions. This enables personalized skin care proposals based on individual skin types and environmental conditions, and also enables continuous improvement of the system through feedback.

[0286] "Image data" is digital information including visual information of the skin surface photographed by the user.

[0287] "Noise removal" is a technique for removing unnecessary information and distortion from image data to improve the accuracy of analysis.

[0288] "Size normalization" is a process for unifying the resolution and dimensions of image data to maintain consistency in analysis.

[0289] "Preprocessing" is a series of processes for processing image data into an analyzable form, including noise removal and face region identification.

[0290] "Machine learning model using deep learning" is an advanced computational model used to process a large amount of data, learn patterns, and analyze skin characteristics.

[0291] "Skin characteristics" are specific attributes including dryness, stains, wrinkles, pore opening, and redness related to the skin being analyzed.

[0292] "Allergy information" is data related to the hypersensitivity reaction shown by the user to specific substances or products, and is an element considered when making product proposals.

[0293] "Environmental information" refers to data about weather conditions and other external factors in the user's area, and is used to generate skincare advice.

[0294] "Skincare product recommendations" refer to recommendations for products deemed most suitable for the user, based on analyzed skin characteristics and personal information.

[0295] "Feedback" refers to the evaluations and reactions that users provide to suggested skincare products and advice, and is data used to improve the system.

[0296] This invention is a system that helps users understand their own skin condition in detail and obtain appropriate skincare products and methods. This system mainly uses the user's terminal, a server, and a communication network to link them together.

[0297] Users capture facial images using their smartphones or cameras. After capturing, they send these images to a server via a dedicated application. Ideally, the image data should have as little noise as possible and be taken under ideal lighting conditions.

[0298] The server uses image processing libraries (e.g., OpenCV, PIL) to process the received image data, performing noise reduction and size standardization. This preprocessing makes the image suitable for analysis. Next, face recognition technology (e.g., dlib, Facenet) is used to identify the facial regions that need to be analyzed.

[0299] In the analysis stage, preprocessed image data is used to extract skin features using a generative AI model based on deep learning (e.g., TensorFlow, PyTorch). This model evaluates and scores characteristics such as skin dryness, blemishes, wrinkles, enlarged pores, and redness.

[0300] Based on the analysis results, the server suggests skincare products suitable for the user's skin. This suggestion is made by referring to a database of commercially available products while also considering the user's allergy information and survey data. Furthermore, it uses OpenWeatherAPI and other tools to obtain current weather and environmental conditions, and generates skincare advice based on this information.

[0301] The device supports daily skincare by displaying suggestions and advice sent from the server and notifying the user. Furthermore, the user can send feedback on these suggestions through the application. The feedback information is stored in a database on the server and used to train the generative AI model, improving the accuracy of the system's analysis.

[0302] For example, if a user's image taken in winter is submitted, the server will detect a high dryness score and suggest products aimed at moisturizing. It will also provide skincare advice suitable for cold environments, allowing the user to implement appropriate skincare based on this information.

[0303] An example of a prompt to input into a generative AI model is: "Please suggest skincare products and advice suitable for dry skin. Also, please tell me about winter skincare methods."

[0304] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0305] Step 1:

[0306] The user takes a selfie using their smartphone or camera. This image is usually saved in JPEG or PNG format. Then, they send the image data to the server via a dedicated application. The input is the facial image data, and the output is the image data securely stored on the server. The specific actions in this step refer to everything from taking the photo to uploading the image.

[0307] Step 2:

[0308] The server starts preprocessing the received image data. Here, an image processing library (e.g., OpenCV, PIL) is used to remove image noise and standardize the size. Also, a face recognition algorithm (e.g., dlib, Facenet) is used to identify the face area required for analysis. The input is the raw image data sent by the user, and the output is the image data in a state where preprocessing is complete. This arranges the data suitable for analysis on the server.

[0309] Step 3:

[0310] The server inputs the preprocessed image data into a generative AI model (e.g., TensorFlow, PyTorch) to analyze skin characteristics. Through this analysis, characteristics such as skin dryness, spots, wrinkles, pore opening, and redness are extracted. The input is the preprocessed image data, and the output is the score for each skin characteristic. Specific operations include the process of inputting image data into the AI model and receiving the analysis results.

[0311] Step 4:

[0312] Based on the analyzed skin characteristics, the server generates proposals for optimal skincare products. At this time, the product database is referenced, and the user's allergy information and questionnaire data are also considered. Furthermore, current weather information and environmental conditions are obtained using OpenWeatherAPI etc. to generate skincare advice. The input is the score of skin characteristics and weather data, and the output is product proposals suitable for the user and advice based on the environment. Specific operations include database queries and data acquisition from external APIs.

[0313] Step 5:

[0314] The terminal displays skincare product suggestions and advice sent from the server to the user. The input is suggestion data from the server, and the output is a visual display of information to the user. The specific action in this step is the process of displaying information on the user interface and notifying the user.

[0315] Step 6:

[0316] Users submit feedback on the provided suggestions through a dedicated app. The input is the user's opinions and feedback data, and the output is the feedback data sent to the server. Specifically, the app records the feedback and sends it to the server via the internet.

[0317] (Application Example 1)

[0318] 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."

[0319] Traditional skincare product recommendation systems only analyze the user's skin condition and suggest products, lacking support for users to implement skincare in their daily lives. Therefore, there is a challenge in that users find it difficult to properly perform skincare based on the recommendations. In particular, in busy daily lives, there is a lack of support for carrying out the suggested care, making it difficult to obtain an effective skincare experience.

[0320] 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.

[0321] In this invention, the server includes means for receiving and pre-processing image data, means for analyzing the pre-processed image data and using a machine learning model to extract skin characteristics, and means for controlling a beauty device adapted based on the characteristics of the skin condition to support skincare in the user's living space. This makes it possible to support effective and easy skincare in the user's everyday living space.

[0322] "Image data" refers to images of a user's face taken by the user, and is used as input information for analyzing skin condition.

[0323] "Preprocessing" refers to the process of removing unwanted noise from image data and preparing it for analysis.

[0324] A "machine learning model" refers to an algorithm used to analyze data and extract specific patterns or features.

[0325] "Skin characteristics" refers to skin attribute information extracted through analysis, such as skin dryness, blemishes, wrinkles, enlarged pores, and redness.

[0326] "Skincare product recommendations" refer to selecting and presenting the most suitable skincare products to the user based on analyzed skin characteristic data.

[0327] "Location information" refers to geographical location data of the user's current location and is an element used to obtain environmental information.

[0328] "Weather information" refers to data that shows external environmental conditions such as weather and temperature in the user's area.

[0329] A "beauty device" refers to a machine that is controlled to support the user's skincare routine and assists with daily care.

[0330] "Living space" refers to the place where a user resides or engages in daily activities.

[0331] In this invention, the user takes a picture of their face using a smartphone or camera. The captured image is sent from the user's device to a server via a dedicated application. The server receives this image data and performs preprocessing using an image processing library such as OpenCV. This preprocessing includes noise reduction and size standardization.

[0332] The pre-processed images are analyzed using a machine learning platform such as TensorFlow running on the server. The machine learning model analyzes features such as skin dryness, blemishes, wrinkles, enlarged pores, and redness, and assigns a score to each.

[0333] Based on the analysis results, the server references a database of commercially available products and user profile information to generate suggestions for the most suitable skincare products. It also obtains the user's location and weather information to generate skincare advice tailored to the user's environment. The suggested information and advice are sent to the terminal and displayed to the user.

[0334] Furthermore, a consumer robot installed in the user's living space controls beauty devices based on analyzed skin characteristics, supporting the user in performing skincare in their daily life. This allows the user to use the suggested skincare products in the most optimal way, resulting in effective skincare.

[0335] For example, if the server determines that a user's skin is highly dry based on an image taken in a dry winter environment, the robot will suggest an appropriate moisturizing product and advise, "You should use this product after washing your face." By providing feedback on the results of using the suggested product, the overall analysis accuracy of the system improves, and users can receive more personalized services.

[0336] Examples of prompts to input into the generating AI model include, "Please analyze my skin characteristics and tell me the best skincare method," and "Please advise me on the best moisturizing method for winter."

[0337] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0338] Step 1:

[0339] The user takes a picture of their face using their smartphone camera. The captured image data is saved on the device. The user sends this image to the server via a dedicated app. The input is the user's face image, and the output is the image data received by the server.

[0340] Step 2:

[0341] The server performs preprocessing on the received image data. This preprocessing uses OpenCV to remove noise and standardize the image size. A face recognition algorithm is then applied to identify face regions within the image. The input is the received face image, and the output is the preprocessed image data.

[0342] Step 3:

[0343] The server runs a deep learning-based machine learning model using pre-processed image data to analyze skin features. This analysis extracts features such as skin dryness, blemishes, wrinkles, enlarged pores, and redness, and assigns a score to each. The input is pre-processed image data, and the output is skin feature score data.

[0344] Step 4:

[0345] The server generates skincare product recommendations based on analyzed skin characteristic data. It references a database of commercially available products and user profile information to select the most suitable skincare products and create recommendations. Inputs are skin characteristic score data and product database information, while output is skincare product recommendations.

[0346] Step 5:

[0347] The server acquires the user's location and weather information and generates skincare advice tailored to the environment. This provides the user with the optimal skincare method. The input is location and weather information, and the output is environment-based skincare advice.

[0348] Step 6:

[0349] The terminal displays suggested information and advice received from the server to the user. The user can use this as a reference for their daily skincare routine. The input is suggested information and advice from the server, and the output is the information displayed to the user.

[0350] Step 7:

[0351] Users use the suggested skincare products and send feedback about their effects to the server via the app. The server receives this feedback and uses it as training data for the system to improve the accuracy of its analysis. The input is user feedback information, and the output is the system's training data.

[0352] 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.

[0353] The present invention is a system that analyzes not only the user's skin condition but also their emotional state, and provides skincare suggestions based on this analysis. This system has a function that analyzes skin characteristics from the user's image using deep learning technology, as well as an emotion engine that recognizes the user's emotions. The following describes specific embodiments of the present invention.

[0354] Image capture and transmission

[0355] The user takes a selfie using their smartphone. The image must clearly show their entire face. They then send the image to the server via a dedicated app.

[0356] Analysis of skin characteristics and emotions

[0357] The server preprocesses the received images and analyzes skin features using a deep learning model. This analysis provides information such as skin dryness, blemishes, wrinkles, enlarged pores, and redness.

[0358] The server uses an emotion engine to simultaneously recognize emotions from the user's facial expressions. This emotion data indicates the user's current psychological state.

[0359] Product and advice suggestions

[0360] The server generates a list of optimal skincare products and advice based on skin characteristic analysis data and emotional data. If the user is experiencing stress, it will recommend products with relaxation effects, providing personalized support based on their emotions.

[0361] Furthermore, by taking into account climate data obtained from weather APIs, we can also provide skincare advice tailored to the environment.

[0362] Output of proposed information and feedback

[0363] The device displays skincare products and advice sent from the server to the user. The user can then adjust their daily skincare routine based on the information presented.

[0364] Users submit feedback to the system regarding the information and products provided. This feedback is incorporated into the system's learning database to improve the accuracy of future suggestions.

[0365] For example, if a user appears tense, the server can suggest relaxing skincare products and recommend an aromatherapy bath in the evening. In this way, the system comprehensively assesses the user's skin condition and emotions to provide the most suitable products and care methods, thereby improving the user's skincare experience.

[0366] The following describes the processing flow.

[0367] Step 1:

[0368] The user takes a picture of their face using their smartphone camera. They launch the application, select the captured image, and send it to the server.

[0369] Step 2:

[0370] The server takes in the received image data and performs preprocessing such as noise reduction and brightness adjustment. It recognizes face regions within the image and crops them as needed.

[0371] Step 3:

[0372] The server inputs the pre-processed images into a deep learning model. This model analyzes features such as skin dryness, blemishes, wrinkles, enlarged pores, and redness. The analysis results are output as numerical values ​​for each feature.

[0373] Step 4:

[0374] The server uses an emotion engine to analyze facial expressions from user images and recognize the user's emotional state. In this process, even subtle changes in facial expression are captured, and emotions such as joy, anger, and sadness are quantified.

[0375] Step 5:

[0376] The server selects the optimal skincare products based on the obtained skin characteristic data and emotional data. In this selection process, products that match the user's stress and relaxation state are prioritized.

[0377] Step 6:

[0378] The server uses a weather API to retrieve local climate data based on the user's location. This includes temperature, humidity, and UV index, and this information is used to further customize skincare advice.

[0379] Step 7:

[0380] The device displays a list of suggested skincare products and advice sent from the server to the user. The user can then incorporate this information into their daily skincare routine.

[0381] Step 8:

[0382] Users submit feedback on the products and advice provided, including their impressions and results of using them. This feedback is stored on the server as training data for the system and used to improve the accuracy of future analyses and suggestions.

[0383] (Example 2)

[0384] 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".

[0385] Conventional skincare product recommendation systems often only consider the physical characteristics of the user's skin, neglecting psychological state and environmental information, which leads to a failure to adequately address individual needs. Furthermore, there is a lack of mechanisms to effectively utilize user feedback and improve the accuracy of the system's recommendations.

[0386] 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.

[0387] In this invention, the server includes means for receiving and pre-processing image information; means for analyzing the pre-processed image information and using machine learning techniques to extract skin characteristics; means for generating skincare product suggestions based on the analyzed skin characteristics and emotional information; means for acquiring user environmental information and generating skincare advice according to external conditions; and means for acquiring feedback on the effects of the suggested skincare products and advice and utilizing it as learning information for the system. This makes it possible to provide more personalized skincare suggestions that take into account not only the user's skin characteristics but also their emotional state and external environment.

[0388] "Image information" refers to still images and videos taken by users, and is digital data that is subject to analysis.

[0389] "Preprocessing" refers to the process of transforming received image information so that it can be easily analyzed by a model. This includes processes such as resizing and noise reduction.

[0390] "Skin characteristics" refer to the physical features of the user's skin, including dryness, blemishes, wrinkles, enlarged pores, redness, etc.

[0391] "Machine learning technology" refers to algorithms and models that allow computers to learn from data and perform analysis and inference.

[0392] "Emotional information" refers to data that indicates the psychological state inferred from the user's facial expressions, and includes emotions such as joy, anger, sadness, surprise, and tension.

[0393] "Recommendations" refer to recommendations regarding skincare products and care methods provided to users based on the analysis results.

[0394] "Environmental information" refers to data that indicates external conditions based on the user's location, and includes meteorological data such as temperature, humidity, and UV index.

[0395] "Feedback" refers to a user's response to a system, such as providing suggestions, evaluations, or comments on a product.

[0396] "Learning information" refers to data that a system uses to improve the accuracy of its model's analysis based on user feedback and past data.

[0397] To implement this invention, the user, server, and terminal must each fulfill their respective roles. The user takes a selfie image using a smart device and sends this image to the server using a dedicated application. This application has the functionality to securely transmit image information using the SSL / TLS protocol.

[0398] The server preprocesses the received image information. This preprocessing includes normalization to unify image sizes and filtering to reduce noise, utilizing image processing libraries such as OpenCV. The preprocessed image information is then analyzed for skin characteristics using machine learning techniques. A deep learning model using TensorFlow is used for this analysis, automatically detecting characteristics such as skin dryness, blemishes, wrinkles, enlarged pores, and redness.

[0399] Furthermore, the server uses an emotion analysis engine to analyze emotional information, estimating emotions from the user's facial expressions. This process is crucial for understanding the user's psychological state. The analyzed emotional information and skin characteristic information are integrated, and prompts are input into a generative AI model to suggest optimal skincare products and care methods. An example of such a prompt is, "Please suggest the best nighttime skincare products for stressed skin."

[0400] The suggested information is sent from the server to the terminal and associated with the user's dedicated account. The terminal displays the received information in an easy-to-understand format, allowing the user to purchase skincare products or implement skincare methods based on that information.

[0401] Users can provide feedback on these suggestions. This feedback is sent back to the server and stored as learning information for the system, improving the accuracy of future suggestions. The server also acquires external weather information and supplements the advice with information tailored to the user's environment. This results in a customized skincare experience that meets the user's individual needs.

[0402] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0403] Step 1:

[0404] The user takes a selfie with their smart device. The captured image is sent to the server via the application. The input here is the user's image data, which the app encrypts before transferring to the server.

[0405] Step 2:

[0406] The server preprocesses the received image data. The input is the image data sent in step 1, and the output is image data in an analyzable format. In this preprocessing, the OpenCV library is used to adjust the image resolution and denoise the image.

[0407] Step 3:

[0408] The server inputs pre-processed image data into a machine learning model to analyze skin characteristics. The input is pre-processed image data, and the output provides characteristic information such as skin dryness, blemishes, wrinkles, enlarged pores, and redness. This analysis utilizes a deep learning model based on TensorFlow.

[0409] Step 4:

[0410] The server uses an emotion analysis engine to extract the user's emotional information. The input is the image data received in step 1, and the output generates emotion categories such as joy, anger, sadness, surprise, and tension. This data reflects the user's psychological state.

[0411] Step 5:

[0412] The server inputs prompt sentences into a generating AI model to produce skincare products and care advice. The inputs are skin characteristic information, emotional information, and environmental information, and the output is personalized suggestions. An example of a prompt sentence in this case is, "Please suggest the best nighttime skincare products for stressed skin."

[0413] Step 6:

[0414] The server sends the generated suggestion information to the terminal. The user can then view the suggestion information through the terminal. The input is the suggested content generated by the server, and the output provides the user with information on skincare products and advice that can be displayed to them.

[0415] Step 7:

[0416] Users provide feedback on suggested products and advice via their devices. This feedback is then sent back to the server, where the input is user feedback data and the output is the system's learned information is updated. This feedback contributes to improving the accuracy of future suggestions.

[0417] (Application Example 2)

[0418] 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".

[0419] In modern society, there is a growing demand for more personalized skincare recommendations that take into account the unique skin and emotional states of individual users. However, conventional skincare analysis systems often only analyze the user's skin condition, and fail to adequately consider emotional states in their recommendations. Furthermore, skincare recommendations that utilize environmental information are also lacking. An effective system that can solve these problems and provide individualized recommendations to users is desired.

[0420] 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.

[0421] In this invention, the server includes means for receiving and pre-processing image information; means for analyzing the pre-processed image information and using a learning model to extract skin features; means for generating skincare product suggestions based on the analyzed skin feature information and received emotional data; means for acquiring surrounding information and environmental information and generating skincare advice appropriate to the environment; means for providing suggestion information and advice to the user; and means for recognizing the user's emotional state and making skincare suggestions that take that data into consideration. This enables more personalized skincare suggestions that simultaneously consider the user's individual skin condition and emotional state.

[0422] "Image information" refers to digital data acquired through a camera device that captures the user's face and skin condition.

[0423] "Preprocessing" refers to image adjustment processes such as filtering and noise reduction performed to improve the accuracy of image information.

[0424] A "learning model" is an algorithm trained using machine learning techniques such as deep learning to analyze skin characteristics and conditions.

[0425] "Skincare product recommendations" refer to the act of listing and recommending skincare products that are considered optimal for each individual user, based on analyzed skin characteristic information and emotional data.

[0426] "Surrounding information" refers to the user's location information and surrounding environmental data, including information about the weather, humidity, and temperature of the user's environment.

[0427] "Environmental information" refers to information about external factors that may affect the skin, such as weather conditions and airborne substances in the area where the user lives.

[0428] "Emotional state" refers to the psychological or emotional state that can be inferred from the user's facial expressions and actions.

[0429] "Means of provision" refers to technical means or interfaces for visually or audibly communicating analysis results to users.

[0430] "Recognition" refers to the process of identifying and understanding the user's emotions and skin condition, and is primarily based on image analysis.

[0431] The system for realizing this invention consists of a user, a server, and a terminal. The server receives image information captured by the user using the terminal and performs preprocessing. This preprocessing includes denoising and adjusting the resolution of the images. The server analyzes the preprocessed image information using a learning model based on deep learning technology to extract skin characteristics and the user's emotional state.

[0432] The user must capture a clear image of their entire face. This allows for the extraction of skin characteristics such as dryness, blemishes, wrinkles, enlarged pores, and redness, as well as emotional data derived from their facial expressions. The server integrates this data and generates skincare product recommendations based on the analysis results. These recommendations include products that offer stress reduction and relaxation effects tailored to the analyzed emotional state.

[0433] Furthermore, the server acquires location and environmental information as surrounding information, combines it with data obtained through a weather API, and makes suggestions, including skincare advice tailored to the season and weather. The generated suggestion information and advice are provided to the user through the device.

[0434] For example, if a user uploads a photo of themselves taken with their device's camera to the system, and the analysis reveals that their skin is dry and they are under stress, the server can suggest the use of a highly moisturizing skincare cream and an aromatherapy oil that promotes relaxation. Furthermore, by using a prompt to the generative AI model such as, "Please suggest products with relaxing effects," the system can help generate more effective suggestions.

[0435] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0436] Step 1:

[0437] The user takes a picture of their face using the device's camera. The captured image must be high-resolution and clearly show the entire face. After taking the picture, this image data is sent to the server via a dedicated application. Image acquisition is crucial, as analysis cannot be performed without it. The input is high-resolution image data, and the output is a notification that the transmission to the server is complete.

[0438] Step 2:

[0439] The server performs preprocessing on the received image data, such as noise reduction and resolution adjustment. The preprocessed images have improved quality, enhancing the accuracy of subsequent analysis. The input is the received image data, and the output is the preprocessed image. Here, image processing algorithms are used to improve data quality.

[0440] Step 3:

[0441] The server analyzes pre-processed images using a deep learning model to extract skin features. This analysis yields data on skin dryness, blemishes, wrinkles, enlarged pores, redness, and other characteristics. The input is pre-processed image data, and the output is skin feature data. The model's inference engine is utilized here.

[0442] Step 4:

[0443] Simultaneously, the server uses an emotion recognition engine to analyze emotional data from the user's facial expressions. This analysis allows the server to understand the user's current psychological state. The input is pre-processed image data, and the output is emotional state data. The emotion analysis is based on facial recognition technology.

[0444] Step 5:

[0445] The server combines analyzed skin characteristic data and emotional data to generate personalized skincare product recommendations for the user. Using a generative AI model, it integrates the data based on prompt messages to determine appropriate products and advice. The input consists of skin characteristic and emotional data, while the output is a customized recommendation.

[0446] Step 6:

[0447] The server further collects surrounding environmental information via a weather API and uses this information to create skincare advice tailored to the environment. This advice indicates appropriate skincare methods based on location data such as temperature and humidity. The input is location information and weather data, and the output is environment-appropriate advice.

[0448] Step 7:

[0449] Ultimately, the server sends the suggested skincare products and advice to the user's device as text or audio information, which is then provided to the user by the device. Based on this output information, the user can optimize their daily skincare routine. The input is the suggested information, and the output is the completion of delivery to the user.

[0450] Step 8:

[0451] Users send their thoughts and feedback on the provided skincare information and products to the server. This feedback is used as training data for the system to improve the accuracy of future recommendations. The input is the user's feedback data, and the output is the completion of data registration in the system.

[0452] 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.

[0453] 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.

[0454] 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.

[0455] [Third Embodiment]

[0456] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0457] 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.

[0458] 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).

[0459] 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.

[0460] 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.

[0461] 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).

[0462] 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.

[0463] 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.

[0464] 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.

[0465] 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.

[0466] 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.

[0467] 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".

[0468] This invention is a system that helps users understand their own skin condition and select appropriate skincare products and methods. The system analyzes the skin condition using facial images taken by the user and suggests optimal products and skincare methods, taking into account the environment and individual skin type.

[0469] Image capture and transmission

[0470] Users take selfies using their smartphones or cameras. They then send the images to a server via a dedicated app.

[0471] Image preprocessing

[0472] The server preprocesses the received images. This preprocessing includes noise reduction and size standardization. It also applies a face recognition algorithm to identify the facial regions necessary for analysis.

[0473] Analysis of skin characteristics

[0474] The server uses a deep learning-based machine learning model to analyze skin features based on pre-processed images. This analysis extracts multiple features such as skin dryness, blemishes, wrinkles, enlarged pores, and redness, and assigns a score to each.

[0475] Product and advice suggestions

[0476] The server generates recommendations for the most suitable skincare products for the user based on the analyzed skin characteristics. These recommendations refer to a database of commercially available products, while also taking into account the user's allergy information and survey data. Furthermore, it analyzes current weather and environmental conditions to create situation-specific skincare advice.

[0477] Submitting results and obtaining feedback

[0478] The device displays suggested products and advice, notifying the user. The user can then use this information to guide their daily skincare routine.

[0479] Users submit feedback on the suggestions through the app. This feedback will be used to improve the accuracy of future analyses.

[0480] For example, if a user uploads a photo of their face taken during the dry winter season, the server will determine that the skin is highly dry and suggest products with high moisturizing effects. Furthermore, considering the low outside temperature, it will advise on moisturizing-focused skincare methods, helping users make informed skincare choices. This system ensures that users always receive the latest and most optimal skincare information tailored to their specific skin condition.

[0481] The following describes the processing flow.

[0482] Step 1:

[0483] The user takes a selfie using their smartphone. Then, they launch a dedicated app, select the captured image file, and send it to the server.

[0484] Step 2:

[0485] The server receives image data sent by the user. It applies a noise-removing filter to the image data and extracts face regions as needed. It also resizes the images to a specific size for deep learning analysis.

[0486] Step 3:

[0487] The server inputs pre-processed images into a deep learning model. This model is a computational model that detects features such as skin dryness, blemishes, wrinkles, enlarged pores, and redness. Through analysis, it generates a numerical score for each feature.

[0488] Step 4:

[0489] The server uses the analysis results to suggest skincare products. It refers to a database of various commercially available products and selects products that match the user's skin characteristics. It also checks the ingredients in the suggested products, taking into account the allergy information registered in the user profile.

[0490] Step 5:

[0491] The server calls a weather API based on the user's location information to obtain climate data (temperature, humidity, UV index). This environmental data is then combined with analysis results to generate skincare advice.

[0492] Step 6:

[0493] The device displays a list of suggested products and skincare advice sent from the server. Users can then review this information in detail through the application and incorporate it into their skincare plan.

[0494] Step 7:

[0495] Users provide feedback on the advice and suggested products they receive using a form within the application. This feedback is incorporated into future analyses and suggestions, and is used to improve the individual user experience.

[0496] (Example 1)

[0497] 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."

[0498] Understanding one's own skin condition and choosing appropriate skincare products and methods is limited by conventional general information alone. Therefore, there is a need for more personalized skincare suggestions based on individual skin types and current environmental conditions. Furthermore, utilizing feedback on the effectiveness of suggested products and continuously improving the system is also a challenge.

[0499] 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.

[0500] In this invention, the server includes means for receiving image data and performing preprocessing such as noise reduction and size standardization; means for analyzing the preprocessed image data using a machine learning model employing deep learning to extract skin characteristics such as dryness, blemishes, wrinkles, enlarged pores, and redness; means for generating skincare product suggestions from various databases based on the analyzed skin characteristic data, taking into account specific allergy information based on the user's personal information; and means for acquiring the user's location and environmental information to generate skincare advice according to weather conditions. This enables personalized skincare suggestions based on individual skin types and environmental conditions, and also allows for continuous improvement of the system through feedback.

[0501] "Image data" refers to digital information that includes visual information of the skin surface captured by the user.

[0502] "Noise reduction" is a technique that removes unnecessary information and distortions from image data to improve the accuracy of analysis.

[0503] "Size standardization" is a process that unifies the resolution and dimensions of image data to maintain consistency in analysis.

[0504] "Preprocessing" refers to a series of processes to transform image data into a format that can be analyzed, and includes tasks such as noise reduction and facial area identification.

[0505] A "deep learning-based machine learning model" is a sophisticated computational model used to process large amounts of data, learn patterns, and analyze skin characteristics.

[0506] "Skin characteristics" refer to specific attributes of the skin being analyzed, including dryness, blemishes, wrinkles, enlarged pores, redness, etc.

[0507] "Allergy information" refers to data about hypersensitivity reactions that users exhibit to specific substances or products, and is a factor considered when proposing products.

[0508] "Environmental information" refers to data about weather conditions and other external factors in the user's area, and is used to generate skincare advice.

[0509] "Skincare product recommendations" refer to recommendations for products deemed most suitable for the user, based on analyzed skin characteristics and personal information.

[0510] "Feedback" refers to the evaluations and reactions that users provide to suggested skincare products and advice, and is data used to improve the system.

[0511] This invention is a system that helps users understand their own skin condition in detail and obtain appropriate skincare products and methods. This system mainly uses the user's terminal, a server, and a communication network to link them together.

[0512] Users capture facial images using their smartphones or cameras. After capturing, they send these images to a server via a dedicated application. Ideally, the image data should have as little noise as possible and be taken under ideal lighting conditions.

[0513] The server uses image processing libraries (e.g., OpenCV, PIL) to process the received image data, performing noise reduction and size standardization. This preprocessing makes the image suitable for analysis. Next, face recognition technology (e.g., dlib, Facenet) is used to identify the facial regions that need to be analyzed.

[0514] In the analysis stage, preprocessed image data is used to extract skin features using a generative AI model based on deep learning (e.g., TensorFlow, PyTorch). This model evaluates and scores characteristics such as skin dryness, blemishes, wrinkles, enlarged pores, and redness.

[0515] Based on the analysis results, the server suggests skincare products suitable for the user's skin. This suggestion is made by referring to a database of commercially available products while also considering the user's allergy information and survey data. Furthermore, it uses OpenWeatherAPI and other tools to obtain current weather and environmental conditions, and generates skincare advice based on this information.

[0516] The device supports daily skincare by displaying suggestions and advice sent from the server and notifying the user. Furthermore, the user can send feedback on these suggestions through the application. The feedback information is stored in a database on the server and used to train the generative AI model, improving the accuracy of the system's analysis.

[0517] For example, if a user's image taken in winter is submitted, the server will detect a high dryness score and suggest products aimed at moisturizing. It will also provide skincare advice suitable for cold environments, allowing the user to implement appropriate skincare based on this information.

[0518] An example of a prompt to input into a generative AI model is: "Please suggest skincare products and advice suitable for dry skin. Also, please tell me about winter skincare methods."

[0519] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0520] Step 1:

[0521] The user takes a selfie using their smartphone or camera. This image is usually saved in JPEG or PNG format. Then, they send the image data to the server via a dedicated application. The input is the facial image data, and the output is the image data securely stored on the server. The specific actions in this step refer to everything from taking the photo to uploading the image.

[0522] Step 2:

[0523] The server begins preprocessing the received image data. Here, image processing libraries (e.g., OpenCV, PIL) are used to remove noise and standardize the image size. Furthermore, face recognition algorithms (e.g., dlib, Facenet) are used to identify the facial regions necessary for analysis. The input is the raw image data sent by the user, and the output is the preprocessed image data. This ensures that the server has data suitable for analysis.

[0524] Step 3:

[0525] The server inputs pre-processed image data into a generating AI model (e.g., TensorFlow, PyTorch) to analyze skin features. This analysis extracts features such as skin dryness, blemishes, wrinkles, enlarged pores, and redness. The input is pre-processed image data, and the output is a score for each skin feature. The specific operation involves inputting image data into the AI ​​model and receiving the analysis results.

[0526] Step 4:

[0527] The server generates recommendations for optimal skincare products based on analyzed skin characteristics. This involves referencing a product database and considering the user's allergy information and survey data. Furthermore, it uses the OpenWeatherAPI and other tools to obtain current weather and environmental conditions to generate skincare advice. Inputs are skin characteristic scores and weather data, while outputs are user-appropriate product recommendations and environment-based advice. Specific operations include database queries and data retrieval from external APIs.

[0528] Step 5:

[0529] The terminal displays skincare product suggestions and advice sent from the server to the user. The input is suggestion data from the server, and the output is a visual display of information to the user. The specific action in this step is the process of displaying information on the user interface and notifying the user.

[0530] Step 6:

[0531] Users submit feedback on the provided suggestions through a dedicated app. The input is the user's opinions and feedback data, and the output is the feedback data sent to the server. Specifically, the app records the feedback and sends it to the server via the internet.

[0532] (Application Example 1)

[0533] 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."

[0534] Traditional skincare product recommendation systems only analyze the user's skin condition and suggest products, lacking support for users to implement skincare in their daily lives. Therefore, there is a challenge in that users find it difficult to properly perform skincare based on the recommendations. In particular, in busy daily lives, there is a lack of support for carrying out the suggested care, making it difficult to obtain an effective skincare experience.

[0535] 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.

[0536] In this invention, the server includes means for receiving and pre-processing image data, means for analyzing the pre-processed image data and using a machine learning model to extract skin characteristics, and means for controlling a beauty device adapted based on the characteristics of the skin condition to support skincare in the user's living space. This makes it possible to support effective and easy skincare in the user's everyday living space.

[0537] "Image data" refers to images of a user's face taken by the user, and is used as input information for analyzing skin condition.

[0538] "Preprocessing" refers to the process of removing unwanted noise from image data and preparing it for analysis.

[0539] A "machine learning model" refers to an algorithm used to analyze data and extract specific patterns or features.

[0540] "Skin characteristics" refers to skin attribute information extracted through analysis, such as skin dryness, blemishes, wrinkles, enlarged pores, and redness.

[0541] "Skincare product recommendations" refer to selecting and presenting the most suitable skincare products to the user based on analyzed skin characteristic data.

[0542] "Location information" refers to geographical location data of the user's current location and is an element used to obtain environmental information.

[0543] "Weather information" refers to data that shows external environmental conditions such as weather and temperature in the user's area.

[0544] A "beauty device" refers to a machine that is controlled to support the user's skincare routine and assists with daily care.

[0545] "Living space" refers to the place where a user resides or engages in daily activities.

[0546] In this invention, the user takes a picture of their face using a smartphone or camera. The captured image is sent from the user's device to a server via a dedicated application. The server receives this image data and performs preprocessing using an image processing library such as OpenCV. This preprocessing includes noise reduction and size standardization.

[0547] The pre-processed images are analyzed using a machine learning platform such as TensorFlow running on the server. The machine learning model analyzes features such as skin dryness, blemishes, wrinkles, enlarged pores, and redness, and assigns a score to each.

[0548] Based on the analysis results, the server references a database of commercially available products and user profile information to generate suggestions for the most suitable skincare products. It also obtains the user's location and weather information to generate skincare advice tailored to the user's environment. The suggested information and advice are sent to the terminal and displayed to the user.

[0549] Furthermore, a consumer robot installed in the user's living space controls beauty devices based on analyzed skin characteristics, supporting the user in performing skincare in their daily life. This allows the user to use the suggested skincare products in the most optimal way, resulting in effective skincare.

[0550] For example, if the server determines that a user's skin is highly dry based on an image taken in a dry winter environment, the robot will suggest an appropriate moisturizing product and advise, "You should use this product after washing your face." By providing feedback on the results of using the suggested product, the overall analysis accuracy of the system improves, and users can receive more personalized services.

[0551] Examples of prompts to input into the generating AI model include, "Please analyze my skin characteristics and tell me the best skincare method," and "Please advise me on the best moisturizing method for winter."

[0552] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0553] Step 1:

[0554] The user takes a picture of their face using their smartphone camera. The captured image data is saved on the device. The user sends this image to the server via a dedicated app. The input is the user's face image, and the output is the image data received by the server.

[0555] Step 2:

[0556] The server performs preprocessing on the received image data. This preprocessing uses OpenCV to remove noise and standardize the image size. A face recognition algorithm is then applied to identify face regions within the image. The input is the received face image, and the output is the preprocessed image data.

[0557] Step 3:

[0558] The server runs a deep learning-based machine learning model using pre-processed image data to analyze skin features. This analysis extracts features such as skin dryness, blemishes, wrinkles, enlarged pores, and redness, and assigns a score to each. The input is pre-processed image data, and the output is skin feature score data.

[0559] Step 4:

[0560] The server generates skincare product recommendations based on analyzed skin characteristic data. It references a database of commercially available products and user profile information to select the most suitable skincare products and create recommendations. Inputs are skin characteristic score data and product database information, while output is skincare product recommendations.

[0561] Step 5:

[0562] The server acquires the user's location and weather information and generates skincare advice tailored to the environment. This provides the user with the optimal skincare method. The input is location and weather information, and the output is environment-based skincare advice.

[0563] Step 6:

[0564] The terminal displays suggested information and advice received from the server to the user. The user can use this as a reference for their daily skincare routine. The input is suggested information and advice from the server, and the output is the information displayed to the user.

[0565] Step 7:

[0566] Users use the suggested skincare products and send feedback about their effects to the server via the app. The server receives this feedback and uses it as training data for the system to improve the accuracy of its analysis. The input is user feedback information, and the output is the system's training data.

[0567] 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.

[0568] The present invention is a system that analyzes not only the user's skin condition but also their emotional state, and provides skincare suggestions based on this analysis. This system has a function that analyzes skin characteristics from the user's image using deep learning technology, as well as an emotion engine that recognizes the user's emotions. The following describes specific embodiments of the present invention.

[0569] Image capture and transmission

[0570] The user takes a selfie using their smartphone. The image must clearly show their entire face. They then send the image to the server via a dedicated app.

[0571] Analysis of skin characteristics and emotions

[0572] The server preprocesses the received images and analyzes skin features using a deep learning model. This analysis provides information such as skin dryness, blemishes, wrinkles, enlarged pores, and redness.

[0573] The server uses an emotion engine to simultaneously recognize emotions from the user's facial expressions. This emotion data indicates the user's current psychological state.

[0574] Product and advice suggestions

[0575] The server generates a list of optimal skincare products and advice based on skin characteristic analysis data and emotional data. If the user is experiencing stress, it will recommend products with relaxation effects, providing personalized support based on their emotions.

[0576] Furthermore, by taking into account climate data obtained from weather APIs, we can also provide skincare advice tailored to the environment.

[0577] Output of proposed information and feedback

[0578] The device displays skincare products and advice sent from the server to the user. The user can then adjust their daily skincare routine based on the information presented.

[0579] Users submit feedback to the system regarding the information and products provided. This feedback is incorporated into the system's learning database to improve the accuracy of future suggestions.

[0580] For example, if a user appears tense, the server can suggest relaxing skincare products and recommend an aromatherapy bath in the evening. In this way, the system comprehensively assesses the user's skin condition and emotions to provide the most suitable products and care methods, thereby improving the user's skincare experience.

[0581] The following describes the processing flow.

[0582] Step 1:

[0583] The user takes a picture of their face using their smartphone camera. They launch the application, select the captured image, and send it to the server.

[0584] Step 2:

[0585] The server takes in the received image data and performs preprocessing such as noise reduction and brightness adjustment. It recognizes face regions within the image and crops them as needed.

[0586] Step 3:

[0587] The server inputs the pre-processed images into a deep learning model. This model analyzes features such as skin dryness, blemishes, wrinkles, enlarged pores, and redness. The analysis results are output as numerical values ​​for each feature.

[0588] Step 4:

[0589] The server uses an emotion engine to analyze facial expressions from user images and recognize the user's emotional state. In this process, even subtle changes in facial expression are captured, and emotions such as joy, anger, and sadness are quantified.

[0590] Step 5:

[0591] The server selects the optimal skincare products based on the obtained skin characteristic data and emotional data. In this selection process, products that match the user's stress and relaxation state are prioritized.

[0592] Step 6:

[0593] The server uses a weather API to retrieve local climate data based on the user's location. This includes temperature, humidity, and UV index, and this information is used to further customize skincare advice.

[0594] Step 7:

[0595] The device displays a list of suggested skincare products and advice sent from the server to the user. The user can then incorporate this information into their daily skincare routine.

[0596] Step 8:

[0597] Users submit feedback on the products and advice provided, including their impressions and results of using them. This feedback is stored on the server as training data for the system and used to improve the accuracy of future analyses and suggestions.

[0598] (Example 2)

[0599] 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."

[0600] Conventional skincare product recommendation systems often only consider the physical characteristics of the user's skin, neglecting psychological state and environmental information, which leads to a failure to adequately address individual needs. Furthermore, there is a lack of mechanisms to effectively utilize user feedback and improve the accuracy of the system's recommendations.

[0601] 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.

[0602] In this invention, the server includes means for receiving and pre-processing image information; means for analyzing the pre-processed image information and using machine learning techniques to extract skin characteristics; means for generating skincare product suggestions based on the analyzed skin characteristics and emotional information; means for acquiring user environmental information and generating skincare advice according to external conditions; and means for acquiring feedback on the effects of the suggested skincare products and advice and utilizing it as learning information for the system. This makes it possible to provide more personalized skincare suggestions that take into account not only the user's skin characteristics but also their emotional state and external environment.

[0603] "Image information" refers to still images and videos taken by users, and is digital data that is subject to analysis.

[0604] "Preprocessing" refers to the process of transforming received image information so that it can be easily analyzed by a model. This includes processes such as resizing and noise reduction.

[0605] "Skin characteristics" refer to the physical features of the user's skin, including dryness, blemishes, wrinkles, enlarged pores, redness, etc.

[0606] "Machine learning technology" refers to algorithms and models that allow computers to learn from data and perform analysis and inference.

[0607] "Emotional information" refers to data that indicates the psychological state inferred from the user's facial expressions, and includes emotions such as joy, anger, sadness, surprise, and tension.

[0608] "Recommendations" refer to recommendations regarding skincare products and care methods provided to users based on the analysis results.

[0609] "Environmental information" refers to data that indicates external conditions based on the user's location, and includes meteorological data such as temperature, humidity, and UV index.

[0610] "Feedback" refers to a user's response to a system, such as providing suggestions, evaluations, or comments on a product.

[0611] "Learning information" refers to data that a system uses to improve the accuracy of its model's analysis based on user feedback and past data.

[0612] To implement this invention, the user, server, and terminal must each fulfill their respective roles. The user takes a selfie image using a smart device and sends this image to the server using a dedicated application. This application has the functionality to securely transmit image information using the SSL / TLS protocol.

[0613] The server preprocesses the received image information. This preprocessing includes normalization to unify image sizes and filtering to reduce noise, utilizing image processing libraries such as OpenCV. The preprocessed image information is then analyzed for skin characteristics using machine learning techniques. A deep learning model using TensorFlow is used for this analysis, automatically detecting characteristics such as skin dryness, blemishes, wrinkles, enlarged pores, and redness.

[0614] Furthermore, the server uses an emotion analysis engine to analyze emotional information, estimating emotions from the user's facial expressions. This process is crucial for understanding the user's psychological state. The analyzed emotional information and skin characteristic information are integrated, and prompts are input into a generative AI model to suggest optimal skincare products and care methods. An example of such a prompt is, "Please suggest the best nighttime skincare products for stressed skin."

[0615] The suggested information is sent from the server to the terminal and associated with the user's dedicated account. The terminal displays the received information in an easy-to-understand format, allowing the user to purchase skincare products or implement skincare methods based on that information.

[0616] Users can provide feedback on these suggestions. This feedback is sent back to the server and stored as learning information for the system, improving the accuracy of future suggestions. The server also acquires external weather information and supplements the advice with information tailored to the user's environment. This results in a customized skincare experience that meets the user's individual needs.

[0617] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0618] Step 1:

[0619] The user takes a selfie with their smart device. The captured image is sent to the server via the application. The input here is the user's image data, which the app encrypts before transferring to the server.

[0620] Step 2:

[0621] The server preprocesses the received image data. The input is the image data sent in step 1, and the output is image data in an analyzable format. In this preprocessing, the OpenCV library is used to adjust the image resolution and denoise the image.

[0622] Step 3:

[0623] The server inputs pre-processed image data into a machine learning model to analyze skin characteristics. The input is pre-processed image data, and the output provides characteristic information such as skin dryness, blemishes, wrinkles, enlarged pores, and redness. This analysis utilizes a deep learning model based on TensorFlow.

[0624] Step 4:

[0625] The server uses an emotion analysis engine to extract the user's emotional information. The input is the image data received in step 1, and the output generates emotion categories such as joy, anger, sadness, surprise, and tension. This data reflects the user's psychological state.

[0626] Step 5:

[0627] The server inputs prompt sentences into a generating AI model to produce skincare products and care advice. The inputs are skin characteristic information, emotional information, and environmental information, and the output is personalized suggestions. An example of a prompt sentence in this case is, "Please suggest the best nighttime skincare products for stressed skin."

[0628] Step 6:

[0629] The server sends the generated suggestion information to the terminal. The user can then view the suggestion information through the terminal. The input is the suggested content generated by the server, and the output provides the user with information on skincare products and advice that can be displayed to them.

[0630] Step 7:

[0631] Users provide feedback on suggested products and advice via their devices. This feedback is then sent back to the server, where the input is user feedback data and the output is the system's learned information is updated. This feedback contributes to improving the accuracy of future suggestions.

[0632] (Application Example 2)

[0633] 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."

[0634] In modern society, there is a growing demand for more personalized skincare recommendations that take into account the unique skin and emotional states of individual users. However, conventional skincare analysis systems often only analyze the user's skin condition, and fail to adequately consider emotional states in their recommendations. Furthermore, skincare recommendations that utilize environmental information are also lacking. An effective system that can solve these problems and provide individualized recommendations to users is desired.

[0635] 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.

[0636] In this invention, the server includes means for receiving and pre-processing image information; means for analyzing the pre-processed image information and using a learning model to extract skin features; means for generating skincare product suggestions based on the analyzed skin feature information and received emotional data; means for acquiring surrounding information and environmental information and generating skincare advice appropriate to the environment; means for providing suggestion information and advice to the user; and means for recognizing the user's emotional state and making skincare suggestions that take that data into consideration. This enables more personalized skincare suggestions that simultaneously consider the user's individual skin condition and emotional state.

[0637] "Image information" refers to digital data acquired through a camera device that captures the user's face and skin condition.

[0638] "Preprocessing" refers to image adjustment processes such as filtering and noise reduction performed to improve the accuracy of image information.

[0639] A "learning model" is an algorithm trained using machine learning techniques such as deep learning to analyze skin characteristics and conditions.

[0640] "Skincare product recommendations" refer to the act of listing and recommending skincare products that are considered optimal for each individual user, based on analyzed skin characteristic information and emotional data.

[0641] "Surrounding information" refers to the user's location information and surrounding environmental data, including information about the weather, humidity, and temperature of the user's environment.

[0642] "Environmental information" refers to information about external factors that may affect the skin, such as weather conditions and airborne substances in the area where the user lives.

[0643] "Emotional state" refers to the psychological or emotional state that can be inferred from the user's facial expressions and actions.

[0644] "Means of provision" refers to technical means or interfaces for visually or audibly communicating analysis results to users.

[0645] "Recognition" refers to the process of identifying and understanding the user's emotions and skin condition, and is primarily based on image analysis.

[0646] The system for realizing this invention consists of a user, a server, and a terminal. The server receives image information captured by the user using the terminal and performs preprocessing. This preprocessing includes denoising and adjusting the resolution of the images. The server analyzes the preprocessed image information using a learning model based on deep learning technology to extract skin characteristics and the user's emotional state.

[0647] The user must capture a clear image of their entire face. This allows for the extraction of skin characteristics such as dryness, blemishes, wrinkles, enlarged pores, and redness, as well as emotional data derived from their facial expressions. The server integrates this data and generates skincare product recommendations based on the analysis results. These recommendations include products that offer stress reduction and relaxation effects tailored to the analyzed emotional state.

[0648] Furthermore, the server acquires location and environmental information as surrounding information, combines it with data obtained through a weather API, and makes suggestions, including skincare advice tailored to the season and weather. The generated suggestion information and advice are provided to the user through the device.

[0649] For example, if a user uploads a photo of themselves taken with their device's camera to the system, and the analysis reveals that their skin is dry and they are under stress, the server can suggest the use of a highly moisturizing skincare cream and an aromatherapy oil that promotes relaxation. Furthermore, by using a prompt to the generative AI model such as, "Please suggest products with relaxing effects," the system can help generate more effective suggestions.

[0650] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0651] Step 1:

[0652] The user takes a picture of their face using the device's camera. The captured image must be high-resolution and clearly show the entire face. After taking the picture, this image data is sent to the server via a dedicated application. Image acquisition is crucial, as analysis cannot be performed without it. The input is high-resolution image data, and the output is a notification that the transmission to the server is complete.

[0653] Step 2:

[0654] The server performs preprocessing on the received image data, such as noise reduction and resolution adjustment. The preprocessed images have improved quality, enhancing the accuracy of subsequent analysis. The input is the received image data, and the output is the preprocessed image. Here, image processing algorithms are used to improve data quality.

[0655] Step 3:

[0656] The server analyzes pre-processed images using a deep learning model to extract skin features. This analysis yields data on skin dryness, blemishes, wrinkles, enlarged pores, redness, and other characteristics. The input is pre-processed image data, and the output is skin feature data. The model's inference engine is utilized here.

[0657] Step 4:

[0658] Simultaneously, the server uses an emotion recognition engine to analyze emotional data from the user's facial expressions. This analysis allows the server to understand the user's current psychological state. The input is pre-processed image data, and the output is emotional state data. The emotion analysis is based on facial recognition technology.

[0659] Step 5:

[0660] The server combines analyzed skin characteristic data and emotional data to generate personalized skincare product recommendations for the user. Using a generative AI model, it integrates the data based on prompt messages to determine appropriate products and advice. The input consists of skin characteristic and emotional data, while the output is a customized recommendation.

[0661] Step 6:

[0662] The server further collects surrounding environmental information via a weather API and uses this information to create skincare advice tailored to the environment. This advice indicates appropriate skincare methods based on location data such as temperature and humidity. The input is location information and weather data, and the output is environment-appropriate advice.

[0663] Step 7:

[0664] Ultimately, the server sends the suggested skincare products and advice to the user's device as text or audio information, which is then provided to the user by the device. Based on this output information, the user can optimize their daily skincare routine. The input is the suggested information, and the output is the completion of delivery to the user.

[0665] Step 8:

[0666] Users send their thoughts and feedback on the provided skincare information and products to the server. This feedback is used as training data for the system to improve the accuracy of future recommendations. The input is the user's feedback data, and the output is the completion of data registration in the system.

[0667] 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.

[0668] 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.

[0669] 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.

[0670] [Fourth Embodiment]

[0671] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0672] 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.

[0673] 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).

[0674] 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.

[0675] 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.

[0676] 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).

[0677] 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.

[0678] 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.

[0679] 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.

[0680] 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.

[0681] 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.

[0682] 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.

[0683] 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".

[0684] This invention is a system that helps users understand their own skin condition and select appropriate skincare products and methods. The system analyzes the skin condition using facial images taken by the user and suggests optimal products and skincare methods, taking into account the environment and individual skin type.

[0685] Image capture and transmission

[0686] Users take selfies using their smartphones or cameras. They then send the images to a server via a dedicated app.

[0687] Image preprocessing

[0688] The server preprocesses the received images. This preprocessing includes noise reduction and size standardization. It also applies a face recognition algorithm to identify the facial regions necessary for analysis.

[0689] Analysis of skin characteristics

[0690] The server uses a deep learning-based machine learning model to analyze skin features based on pre-processed images. This analysis extracts multiple features such as skin dryness, blemishes, wrinkles, enlarged pores, and redness, and assigns a score to each.

[0691] Product and advice suggestions

[0692] The server generates recommendations for the most suitable skincare products for the user based on the analyzed skin characteristics. These recommendations refer to a database of commercially available products, while also taking into account the user's allergy information and survey data. Furthermore, it analyzes current weather and environmental conditions to create situation-specific skincare advice.

[0693] Submitting results and obtaining feedback

[0694] The device displays suggested products and advice, notifying the user. The user can then use this information to guide their daily skincare routine.

[0695] Users submit feedback on the suggestions through the app. This feedback will be used to improve the accuracy of future analyses.

[0696] For example, if a user uploads a photo of their face taken during the dry winter season, the server will determine that the skin is highly dry and suggest products with high moisturizing effects. Furthermore, considering the low outside temperature, it will advise on moisturizing-focused skincare methods, helping users make informed skincare choices. This system ensures that users always receive the latest and most optimal skincare information tailored to their specific skin condition.

[0697] The following describes the processing flow.

[0698] Step 1:

[0699] The user takes a selfie using their smartphone. Then, they launch a dedicated app, select the captured image file, and send it to the server.

[0700] Step 2:

[0701] The server receives image data sent by the user. It applies a noise-removing filter to the image data and extracts face regions as needed. It also resizes the images to a specific size for deep learning analysis.

[0702] Step 3:

[0703] The server inputs pre-processed images into a deep learning model. This model is a computational model that detects features such as skin dryness, blemishes, wrinkles, enlarged pores, and redness. Through analysis, it generates a numerical score for each feature.

[0704] Step 4:

[0705] The server uses the analysis results to suggest skincare products. It refers to a database of various commercially available products and selects products that match the user's skin characteristics. It also checks the ingredients in the suggested products, taking into account the allergy information registered in the user profile.

[0706] Step 5:

[0707] The server calls a weather API based on the user's location information to obtain climate data (temperature, humidity, UV index). This environmental data is then combined with analysis results to generate skincare advice.

[0708] Step 6:

[0709] The device displays a list of suggested products and skincare advice sent from the server. Users can then review this information in detail through the application and incorporate it into their skincare plan.

[0710] Step 7:

[0711] Users provide feedback on the advice and suggested products they receive using a form within the application. This feedback is incorporated into future analyses and suggestions, and is used to improve the individual user experience.

[0712] (Example 1)

[0713] 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".

[0714] Understanding one's own skin condition and choosing appropriate skincare products and methods is limited by conventional general information alone. Therefore, there is a need for more personalized skincare suggestions based on individual skin types and current environmental conditions. Furthermore, utilizing feedback on the effectiveness of suggested products and continuously improving the system is also a challenge.

[0715] 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.

[0716] In this invention, the server includes means for receiving image data and performing preprocessing such as noise reduction and size standardization; means for analyzing the preprocessed image data using a machine learning model employing deep learning to extract skin characteristics such as dryness, blemishes, wrinkles, enlarged pores, and redness; means for generating skincare product suggestions from various databases based on the analyzed skin characteristic data, taking into account specific allergy information based on the user's personal information; and means for acquiring the user's location and environmental information to generate skincare advice according to weather conditions. This enables personalized skincare suggestions based on individual skin types and environmental conditions, and also allows for continuous improvement of the system through feedback.

[0717] "Image data" refers to digital information that includes visual information of the skin surface captured by the user.

[0718] "Noise reduction" is a technique that removes unnecessary information and distortions from image data to improve the accuracy of analysis.

[0719] "Size standardization" is a process that unifies the resolution and dimensions of image data to maintain consistency in analysis.

[0720] "Preprocessing" refers to a series of processes to transform image data into a format that can be analyzed, and includes tasks such as noise reduction and facial area identification.

[0721] A "deep learning-based machine learning model" is a sophisticated computational model used to process large amounts of data, learn patterns, and analyze skin characteristics.

[0722] "Skin characteristics" refer to specific attributes of the skin being analyzed, including dryness, blemishes, wrinkles, enlarged pores, redness, etc.

[0723] "Allergy information" refers to data about hypersensitivity reactions that users exhibit to specific substances or products, and is a factor considered when proposing products.

[0724] "Environmental information" refers to data about weather conditions and other external factors in the user's area, and is used to generate skincare advice.

[0725] "Skincare product recommendations" refer to recommendations for products deemed most suitable for the user, based on analyzed skin characteristics and personal information.

[0726] "Feedback" refers to the evaluations and reactions that users provide to suggested skincare products and advice, and is data used to improve the system.

[0727] This invention is a system that helps users understand their own skin condition in detail and obtain appropriate skincare products and methods. This system mainly uses the user's terminal, a server, and a communication network to link them together.

[0728] Users capture facial images using their smartphones or cameras. After capturing, they send these images to a server via a dedicated application. Ideally, the image data should have as little noise as possible and be taken under ideal lighting conditions.

[0729] The server uses image processing libraries (e.g., OpenCV, PIL) to process the received image data, performing noise reduction and size standardization. This preprocessing makes the image suitable for analysis. Next, face recognition technology (e.g., dlib, Facenet) is used to identify the facial regions that need to be analyzed.

[0730] In the analysis stage, preprocessed image data is used to extract skin features using a generative AI model based on deep learning (e.g., TensorFlow, PyTorch). This model evaluates and scores characteristics such as skin dryness, blemishes, wrinkles, enlarged pores, and redness.

[0731] Based on the analysis results, the server suggests skincare products suitable for the user's skin. This suggestion is made by referring to a database of commercially available products while also considering the user's allergy information and survey data. Furthermore, it uses OpenWeatherAPI and other tools to obtain current weather and environmental conditions, and generates skincare advice based on this information.

[0732] The device supports daily skincare by displaying suggestions and advice sent from the server and notifying the user. Furthermore, the user can send feedback on these suggestions through the application. The feedback information is stored in a database on the server and used to train the generative AI model, improving the accuracy of the system's analysis.

[0733] For example, if a user's image taken in winter is submitted, the server will detect a high dryness score and suggest products aimed at moisturizing. It will also provide skincare advice suitable for cold environments, allowing the user to implement appropriate skincare based on this information.

[0734] An example of a prompt to input into a generative AI model is: "Please suggest skincare products and advice suitable for dry skin. Also, please tell me about winter skincare methods."

[0735] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0736] Step 1:

[0737] The user takes a selfie using their smartphone or camera. This image is usually saved in JPEG or PNG format. Then, they send the image data to the server via a dedicated application. The input is the facial image data, and the output is the image data securely stored on the server. The specific actions in this step refer to everything from taking the photo to uploading the image.

[0738] Step 2:

[0739] The server begins preprocessing the received image data. Here, image processing libraries (e.g., OpenCV, PIL) are used to remove noise and standardize the image size. Furthermore, face recognition algorithms (e.g., dlib, Facenet) are used to identify the facial regions necessary for analysis. The input is the raw image data sent by the user, and the output is the preprocessed image data. This ensures that the server has data suitable for analysis.

[0740] Step 3:

[0741] The server inputs pre-processed image data into a generating AI model (e.g., TensorFlow, PyTorch) to analyze skin features. This analysis extracts features such as skin dryness, blemishes, wrinkles, enlarged pores, and redness. The input is pre-processed image data, and the output is a score for each skin feature. The specific operation involves inputting image data into the AI ​​model and receiving the analysis results.

[0742] Step 4:

[0743] The server generates recommendations for optimal skincare products based on analyzed skin characteristics. This involves referencing a product database and considering the user's allergy information and survey data. Furthermore, it uses the OpenWeatherAPI and other tools to obtain current weather and environmental conditions to generate skincare advice. Inputs are skin characteristic scores and weather data, while outputs are user-appropriate product recommendations and environment-based advice. Specific operations include database queries and data retrieval from external APIs.

[0744] Step 5:

[0745] The terminal displays skincare product suggestions and advice sent from the server to the user. The input is suggestion data from the server, and the output is a visual display of information to the user. The specific action in this step is the process of displaying information on the user interface and notifying the user.

[0746] Step 6:

[0747] Users submit feedback on the provided suggestions through a dedicated app. The input is the user's opinions and feedback data, and the output is the feedback data sent to the server. Specifically, the app records the feedback and sends it to the server via the internet.

[0748] (Application Example 1)

[0749] 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".

[0750] Traditional skincare product recommendation systems only analyze the user's skin condition and suggest products, lacking support for users to implement skincare in their daily lives. Therefore, there is a challenge in that users find it difficult to properly perform skincare based on the recommendations. In particular, in busy daily lives, there is a lack of support for carrying out the suggested care, making it difficult to obtain an effective skincare experience.

[0751] 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.

[0752] In this invention, the server includes means for receiving and pre-processing image data, means for analyzing the pre-processed image data and using a machine learning model to extract skin characteristics, and means for controlling a beauty device adapted based on the characteristics of the skin condition to support skincare in the user's living space. This makes it possible to support effective and easy skincare in the user's everyday living space.

[0753] "Image data" refers to images of a user's face taken by the user, and is used as input information for analyzing skin condition.

[0754] "Preprocessing" refers to the process of removing unwanted noise from image data and preparing it for analysis.

[0755] A "machine learning model" refers to an algorithm used to analyze data and extract specific patterns or features.

[0756] "Skin characteristics" refers to skin attribute information extracted through analysis, such as skin dryness, blemishes, wrinkles, enlarged pores, and redness.

[0757] "Skincare product recommendations" refer to selecting and presenting the most suitable skincare products to the user based on analyzed skin characteristic data.

[0758] "Location information" refers to geographical location data of the user's current location and is an element used to obtain environmental information.

[0759] "Weather information" refers to data that shows external environmental conditions such as weather and temperature in the user's area.

[0760] A "beauty device" refers to a machine that is controlled to support the user's skincare routine and assists with daily care.

[0761] "Living space" refers to the place where a user resides or engages in daily activities.

[0762] In this invention, the user takes a picture of their face using a smartphone or camera. The captured image is sent from the user's device to a server via a dedicated application. The server receives this image data and performs preprocessing using an image processing library such as OpenCV. This preprocessing includes noise reduction and size standardization.

[0763] The pre-processed images are analyzed using a machine learning platform such as TensorFlow running on the server. The machine learning model analyzes features such as skin dryness, blemishes, wrinkles, enlarged pores, and redness, and assigns a score to each.

[0764] Based on the analysis results, the server references a database of commercially available products and user profile information to generate suggestions for the most suitable skincare products. It also obtains the user's location and weather information to generate skincare advice tailored to the user's environment. The suggested information and advice are sent to the terminal and displayed to the user.

[0765] Furthermore, a consumer robot installed in the user's living space controls beauty devices based on analyzed skin characteristics, supporting the user in performing skincare in their daily life. This allows the user to use the suggested skincare products in the most optimal way, resulting in effective skincare.

[0766] For example, if the server determines that a user's skin is highly dry based on an image taken in a dry winter environment, the robot will suggest an appropriate moisturizing product and advise, "You should use this product after washing your face." By providing feedback on the results of using the suggested product, the overall analysis accuracy of the system improves, and users can receive more personalized services.

[0767] Examples of prompts to input into the generating AI model include, "Please analyze my skin characteristics and tell me the best skincare method," and "Please advise me on the best moisturizing method for winter."

[0768] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0769] Step 1:

[0770] The user takes a picture of their face using their smartphone camera. The captured image data is saved on the device. The user sends this image to the server via a dedicated app. The input is the user's face image, and the output is the image data received by the server.

[0771] Step 2:

[0772] The server performs preprocessing on the received image data. This preprocessing uses OpenCV to remove noise and standardize the image size. A face recognition algorithm is then applied to identify face regions within the image. The input is the received face image, and the output is the preprocessed image data.

[0773] Step 3:

[0774] The server runs a deep learning-based machine learning model using pre-processed image data to analyze skin features. This analysis extracts features such as skin dryness, blemishes, wrinkles, enlarged pores, and redness, and assigns a score to each. The input is pre-processed image data, and the output is skin feature score data.

[0775] Step 4:

[0776] The server generates skincare product recommendations based on analyzed skin characteristic data. It references a database of commercially available products and user profile information to select the most suitable skincare products and create recommendations. Inputs are skin characteristic score data and product database information, while output is skincare product recommendations.

[0777] Step 5:

[0778] The server acquires the user's location and weather information and generates skincare advice tailored to the environment. This provides the user with the optimal skincare method. The input is location and weather information, and the output is environment-based skincare advice.

[0779] Step 6:

[0780] The terminal displays suggested information and advice received from the server to the user. The user can use this as a reference for their daily skincare routine. The input is suggested information and advice from the server, and the output is the information displayed to the user.

[0781] Step 7:

[0782] Users use the suggested skincare products and send feedback about their effects to the server via the app. The server receives this feedback and uses it as training data for the system to improve the accuracy of its analysis. The input is user feedback information, and the output is the system's training data.

[0783] 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.

[0784] The present invention is a system that analyzes not only the user's skin condition but also their emotional state, and provides skincare suggestions based on this analysis. This system has a function that analyzes skin characteristics from the user's image using deep learning technology, as well as an emotion engine that recognizes the user's emotions. The following describes specific embodiments of the present invention.

[0785] Image capture and transmission

[0786] The user takes a selfie using their smartphone. The image must clearly show their entire face. They then send the image to the server via a dedicated app.

[0787] Analysis of skin characteristics and emotions

[0788] The server preprocesses the received images and analyzes skin features using a deep learning model. This analysis provides information such as skin dryness, blemishes, wrinkles, enlarged pores, and redness.

[0789] The server uses an emotion engine to simultaneously recognize emotions from the user's facial expressions. This emotion data indicates the user's current psychological state.

[0790] Product and advice suggestions

[0791] The server generates a list of optimal skincare products and advice based on skin characteristic analysis data and emotional data. If the user is experiencing stress, it will recommend products with relaxation effects, providing personalized support based on their emotions.

[0792] Furthermore, by taking into account climate data obtained from weather APIs, we can also provide skincare advice tailored to the environment.

[0793] Output of proposed information and feedback

[0794] The device displays skincare products and advice sent from the server to the user. The user can then adjust their daily skincare routine based on the information presented.

[0795] Users submit feedback to the system regarding the information and products provided. This feedback is incorporated into the system's learning database to improve the accuracy of future suggestions.

[0796] For example, if a user appears tense, the server can suggest relaxing skincare products and recommend an aromatherapy bath in the evening. In this way, the system comprehensively assesses the user's skin condition and emotions to provide the most suitable products and care methods, thereby improving the user's skincare experience.

[0797] The following describes the processing flow.

[0798] Step 1:

[0799] The user takes a picture of their face using their smartphone camera. They launch the application, select the captured image, and send it to the server.

[0800] Step 2:

[0801] The server takes in the received image data and performs preprocessing such as noise reduction and brightness adjustment. It recognizes face regions within the image and crops them as needed.

[0802] Step 3:

[0803] The server inputs the pre-processed images into a deep learning model. This model analyzes features such as skin dryness, blemishes, wrinkles, enlarged pores, and redness. The analysis results are output as numerical values ​​for each feature.

[0804] Step 4:

[0805] The server uses an emotion engine to analyze facial expressions from user images and recognize the user's emotional state. In this process, even subtle changes in facial expression are captured, and emotions such as joy, anger, and sadness are quantified.

[0806] Step 5:

[0807] The server selects the optimal skincare products based on the obtained skin characteristic data and emotional data. In this selection process, products that match the user's stress and relaxation state are prioritized.

[0808] Step 6:

[0809] The server uses a weather API to retrieve local climate data based on the user's location. This includes temperature, humidity, and UV index, and this information is used to further customize skincare advice.

[0810] Step 7:

[0811] The device displays a list of suggested skincare products and advice sent from the server to the user. The user can then incorporate this information into their daily skincare routine.

[0812] Step 8:

[0813] Users submit feedback on the products and advice provided, including their impressions and results of using them. This feedback is stored on the server as training data for the system and used to improve the accuracy of future analyses and suggestions.

[0814] (Example 2)

[0815] 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".

[0816] Conventional skincare product recommendation systems often only consider the physical characteristics of the user's skin, neglecting psychological state and environmental information, which leads to a failure to adequately address individual needs. Furthermore, there is a lack of mechanisms to effectively utilize user feedback and improve the accuracy of the system's recommendations.

[0817] 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.

[0818] In this invention, the server includes means for receiving and pre-processing image information; means for analyzing the pre-processed image information and using machine learning techniques to extract skin characteristics; means for generating skincare product suggestions based on the analyzed skin characteristics and emotional information; means for acquiring user environmental information and generating skincare advice according to external conditions; and means for acquiring feedback on the effects of the suggested skincare products and advice and utilizing it as learning information for the system. This makes it possible to provide more personalized skincare suggestions that take into account not only the user's skin characteristics but also their emotional state and external environment.

[0819] "Image information" refers to still images and videos taken by users, and is digital data that is subject to analysis.

[0820] "Preprocessing" refers to the process of transforming received image information so that it can be easily analyzed by a model. This includes processes such as resizing and noise reduction.

[0821] "Skin characteristics" refer to the physical features of the user's skin, including dryness, blemishes, wrinkles, enlarged pores, redness, etc.

[0822] "Machine learning technology" refers to algorithms and models that allow computers to learn from data and perform analysis and inference.

[0823] "Emotional information" refers to data that indicates the psychological state inferred from the user's facial expressions, and includes emotions such as joy, anger, sadness, surprise, and tension.

[0824] "Recommendations" refer to recommendations regarding skincare products and care methods provided to users based on the analysis results.

[0825] "Environmental information" refers to data that indicates external conditions based on the user's location, and includes meteorological data such as temperature, humidity, and UV index.

[0826] "Feedback" refers to a user's response to a system, such as providing suggestions, evaluations, or comments on a product.

[0827] "Learning information" refers to data that a system uses to improve the accuracy of its model's analysis based on user feedback and past data.

[0828] To implement this invention, the user, server, and terminal must each fulfill their respective roles. The user takes a selfie image using a smart device and sends this image to the server using a dedicated application. This application has the functionality to securely transmit image information using the SSL / TLS protocol.

[0829] The server preprocesses the received image information. This preprocessing includes normalization to unify image sizes and filtering to reduce noise, utilizing image processing libraries such as OpenCV. The preprocessed image information is then analyzed for skin characteristics using machine learning techniques. A deep learning model using TensorFlow is used for this analysis, automatically detecting characteristics such as skin dryness, blemishes, wrinkles, enlarged pores, and redness.

[0830] Furthermore, the server uses an emotion analysis engine to analyze emotional information, estimating emotions from the user's facial expressions. This process is crucial for understanding the user's psychological state. The analyzed emotional information and skin characteristic information are integrated, and prompts are input into a generative AI model to suggest optimal skincare products and care methods. An example of such a prompt is, "Please suggest the best nighttime skincare products for stressed skin."

[0831] The suggested information is sent from the server to the terminal and associated with the user's dedicated account. The terminal displays the received information in an easy-to-understand format, allowing the user to purchase skincare products or implement skincare methods based on that information.

[0832] Users can provide feedback on these suggestions. This feedback is sent back to the server and stored as learning information for the system, improving the accuracy of future suggestions. The server also acquires external weather information and supplements the advice with information tailored to the user's environment. This results in a customized skincare experience that meets the user's individual needs.

[0833] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0834] Step 1:

[0835] The user takes a selfie with their smart device. The captured image is sent to the server via the application. The input here is the user's image data, which the app encrypts before transferring to the server.

[0836] Step 2:

[0837] The server preprocesses the received image data. The input is the image data sent in step 1, and the output is image data in an analyzable format. In this preprocessing, the OpenCV library is used to adjust the image resolution and denoise the image.

[0838] Step 3:

[0839] The server inputs pre-processed image data into a machine learning model to analyze skin characteristics. The input is pre-processed image data, and the output provides characteristic information such as skin dryness, blemishes, wrinkles, enlarged pores, and redness. This analysis utilizes a deep learning model based on TensorFlow.

[0840] Step 4:

[0841] The server uses an emotion analysis engine to extract the user's emotional information. The input is the image data received in step 1, and the output generates emotion categories such as joy, anger, sadness, surprise, and tension. This data reflects the user's psychological state.

[0842] Step 5:

[0843] The server inputs prompt sentences into a generating AI model to produce skincare products and care advice. The inputs are skin characteristic information, emotional information, and environmental information, and the output is personalized suggestions. An example of a prompt sentence in this case is, "Please suggest the best nighttime skincare products for stressed skin."

[0844] Step 6:

[0845] The server sends the generated suggestion information to the terminal. The user can then view the suggestion information through the terminal. The input is the suggested content generated by the server, and the output provides the user with information on skincare products and advice that can be displayed to them.

[0846] Step 7:

[0847] Users provide feedback on suggested products and advice via their devices. This feedback is then sent back to the server, where the input is user feedback data and the output is the system's learned information is updated. This feedback contributes to improving the accuracy of future suggestions.

[0848] (Application Example 2)

[0849] 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".

[0850] In modern society, there is a growing demand for more personalized skincare recommendations that take into account the unique skin and emotional states of individual users. However, conventional skincare analysis systems often only analyze the user's skin condition, and fail to adequately consider emotional states in their recommendations. Furthermore, skincare recommendations that utilize environmental information are also lacking. An effective system that can solve these problems and provide individualized recommendations to users is desired.

[0851] 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.

[0852] In this invention, the server includes means for receiving and pre-processing image information; means for analyzing the pre-processed image information and using a learning model to extract skin features; means for generating skincare product suggestions based on the analyzed skin feature information and received emotional data; means for acquiring surrounding information and environmental information and generating skincare advice appropriate to the environment; means for providing suggestion information and advice to the user; and means for recognizing the user's emotional state and making skincare suggestions that take that data into consideration. This enables more personalized skincare suggestions that simultaneously consider the user's individual skin condition and emotional state.

[0853] "Image information" refers to digital data acquired through a camera device that captures the user's face and skin condition.

[0854] "Preprocessing" refers to image adjustment processes such as filtering and noise reduction performed to improve the accuracy of image information.

[0855] A "learning model" is an algorithm trained using machine learning techniques such as deep learning to analyze skin characteristics and conditions.

[0856] "Skincare product recommendations" refer to the act of listing and recommending skincare products that are considered optimal for each individual user, based on analyzed skin characteristic information and emotional data.

[0857] "Surrounding information" refers to the user's location information and surrounding environmental data, including information about the weather, humidity, and temperature of the user's environment.

[0858] "Environmental information" refers to information about external factors that may affect the skin, such as weather conditions and airborne substances in the area where the user lives.

[0859] "Emotional state" refers to the psychological or emotional state that can be inferred from the user's facial expressions and actions.

[0860] "Means of provision" refers to technical means or interfaces for visually or audibly communicating analysis results to users.

[0861] "Recognition" refers to the process of identifying and understanding the user's emotions and skin condition, and is primarily based on image analysis.

[0862] The system for realizing this invention consists of a user, a server, and a terminal. The server receives image information captured by the user using the terminal and performs preprocessing. This preprocessing includes denoising and adjusting the resolution of the images. The server analyzes the preprocessed image information using a learning model based on deep learning technology to extract skin characteristics and the user's emotional state.

[0863] The user must capture a clear image of their entire face. This allows for the extraction of skin characteristics such as dryness, blemishes, wrinkles, enlarged pores, and redness, as well as emotional data derived from their facial expressions. The server integrates this data and generates skincare product recommendations based on the analysis results. These recommendations include products that offer stress reduction and relaxation effects tailored to the analyzed emotional state.

[0864] Furthermore, the server acquires location and environmental information as surrounding information, combines it with data obtained through a weather API, and makes suggestions, including skincare advice tailored to the season and weather. The generated suggestion information and advice are provided to the user through the device.

[0865] For example, if a user uploads a photo of themselves taken with their device's camera to the system, and the analysis reveals that their skin is dry and they are under stress, the server can suggest the use of a highly moisturizing skincare cream and an aromatherapy oil that promotes relaxation. Furthermore, by using a prompt to the generative AI model such as, "Please suggest products with relaxing effects," the system can help generate more effective suggestions.

[0866] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0867] Step 1:

[0868] The user takes a picture of their face using the device's camera. The captured image must be high-resolution and clearly show the entire face. After taking the picture, this image data is sent to the server via a dedicated application. Image acquisition is crucial, as analysis cannot be performed without it. The input is high-resolution image data, and the output is a notification that the transmission to the server is complete.

[0869] Step 2:

[0870] The server performs preprocessing on the received image data, such as noise reduction and resolution adjustment. The preprocessed images have improved quality, enhancing the accuracy of subsequent analysis. The input is the received image data, and the output is the preprocessed image. Here, image processing algorithms are used to improve data quality.

[0871] Step 3:

[0872] The server analyzes pre-processed images using a deep learning model to extract skin features. This analysis yields data on skin dryness, blemishes, wrinkles, enlarged pores, redness, and other characteristics. The input is pre-processed image data, and the output is skin feature data. The model's inference engine is utilized here.

[0873] Step 4:

[0874] Simultaneously, the server uses an emotion recognition engine to analyze emotional data from the user's facial expressions. This analysis allows the server to understand the user's current psychological state. The input is pre-processed image data, and the output is emotional state data. The emotion analysis is based on facial recognition technology.

[0875] Step 5:

[0876] The server combines analyzed skin characteristic data and emotional data to generate personalized skincare product recommendations for the user. Using a generative AI model, it integrates the data based on prompt messages to determine appropriate products and advice. The input consists of skin characteristic and emotional data, while the output is a customized recommendation.

[0877] Step 6:

[0878] The server further collects surrounding environmental information via a weather API and uses this information to create skincare advice tailored to the environment. This advice indicates appropriate skincare methods based on location data such as temperature and humidity. The input is location information and weather data, and the output is environment-appropriate advice.

[0879] Step 7:

[0880] Ultimately, the server sends the suggested skincare products and advice to the user's device as text or audio information, which is then provided to the user by the device. Based on this output information, the user can optimize their daily skincare routine. The input is the suggested information, and the output is the completion of delivery to the user.

[0881] Step 8:

[0882] Users send their thoughts and feedback on the provided skincare information and products to the server. This feedback is used as training data for the system to improve the accuracy of future recommendations. The input is the user's feedback data, and the output is the completion of data registration in the system.

[0883] 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.

[0884] 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.

[0885] 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.

[0886] 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.

[0887] 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.

[0888] 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.

[0889] 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.

[0890] 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.

[0891] 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."

[0892] 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.

[0893] 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.

[0894] 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.

[0895] 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.

[0896] 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.

[0897] 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.

[0898] 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.

[0899] 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.

[0900] 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.

[0901] 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.

[0902] 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.

[0903] 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.

[0904] The following is further disclosed regarding the embodiments described above.

[0905] (Claim 1)

[0906] A means for receiving image data and performing preprocessing,

[0907] A method that uses a machine learning model to analyze preprocessed image data and extract skin features,

[0908] A method for generating skincare product suggestions based on analyzed skin characteristic data,

[0909] A means of acquiring user location and weather information and generating skincare advice tailored to the environment,

[0910] A system that includes means for outputting suggested information and advice to the user.

[0911] (Claim 2)

[0912] The system according to claim 1, which obtains feedback on the effectiveness of a proposed skincare product and uses it as training data for the system.

[0913] (Claim 3)

[0914] The system according to claim 1, which takes allergy information into consideration when suggesting products suitable for a specific skin type based on analyzed skin characteristics.

[0915] "Example 1"

[0916] (Claim 1)

[0917] A means for receiving image data and performing preprocessing such as noise reduction and size standardization,

[0918] A method for analyzing pre-processed image data using a machine learning model employing deep learning to extract skin characteristics such as dryness, blemishes, wrinkles, enlarged pores, and redness,

[0919] Based on analyzed skin characteristic data, the system generates skincare product suggestions from various databases, taking into account specific allergy information based on the user's personal information.

[0920] A means for acquiring the user's location and environmental information and generating skincare advice according to weather conditions,

[0921] A system including means for outputting suggested skincare product information and skincare advice to a user terminal.

[0922] (Claim 2)

[0923] The system according to claim 1, which obtains feedback from users regarding the effectiveness of proposed skincare products and uses it as training data for the system's generated AI model to improve the accuracy of the analysis.

[0924] (Claim 3)

[0925] The system according to claim 1, which, when suggesting products suitable for a specific skin type based on analyzed skin characteristics, takes into account the user's allergy information within the system when selecting products.

[0926] "Application Example 1"

[0927] (Claim 1)

[0928] A means for receiving image data and performing preprocessing,

[0929] A method that uses a machine learning model to analyze preprocessed image data and extract skin features,

[0930] A method for generating skincare product suggestions based on analyzed skin characteristic data,

[0931] A means of acquiring user location and weather information and generating skincare advice tailored to the environment,

[0932] A means of outputting suggested information and advice to the user,

[0933] A system that controls beauty devices adapted to the characteristics of the user's skin condition, and includes means of supporting skincare in the user's living space.

[0934] (Claim 2)

[0935] The system according to claim 1, which obtains feedback on the effectiveness of a proposed skincare product and uses it as training data for the system.

[0936] (Claim 3)

[0937] The system according to claim 1, which takes allergy information into consideration when suggesting products suitable for a specific skin type based on analyzed skin characteristics.

[0938] "Example 2 of combining an emotion engine"

[0939] (Claim 1)

[0940] A means for receiving and pre-processing image information,

[0941] A method that uses machine learning techniques to analyze pre-processed image information and extract skin characteristics,

[0942] A means for generating skincare product suggestions based on analyzed skin characteristic information and emotional information,

[0943] A means for acquiring user environmental information and generating skincare advice according to external conditions,

[0944] A system that includes means for outputting suggested information and advice to the user.

[0945] (Claim 2)

[0946] The system according to claim 1, which obtains feedback on the effectiveness and advice of proposed skincare products and utilizes it as learning information for the system.

[0947] (Claim 3)

[0948] The system according to claim 1, which takes into account the user's health status information when suggesting products suitable for a specific skin type based on analyzed skin characteristics and emotional state.

[0949] "Application example 2 when combining with an emotional engine"

[0950] (Claim 1)

[0951] A means for receiving and pre-processing image information,

[0952] A method that uses a learning model to analyze pre-processed image information and extract skin features,

[0953] A means of generating skincare product suggestions based on analyzed skin characteristic information and received emotional data,

[0954] A means for acquiring surrounding information and environmental information and generating skincare advice tailored to the environment,

[0955] Means of providing users with suggested information and advice,

[0956] A system that recognizes the user's emotional state and provides skincare recommendations that take that data into consideration.

[0957] (Claim 2)

[0958] The system according to claim 1, which obtains user feedback on the effectiveness of a proposed skincare product and utilizes it as learning information for the system.

[0959] (Claim 3)

[0960] The system according to claim 1, which takes health status information into consideration when suggesting products suitable for a specific skin type based on analyzed skin characteristics and emotions. [Explanation of Symbols]

[0961] 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 for receiving image data and performing preprocessing, A method that uses a machine learning model to analyze preprocessed image data and extract skin features, A method for generating skincare product suggestions based on analyzed skin characteristic data, A means of acquiring user location and weather information and generating skincare advice tailored to the environment, A means of outputting suggested information and advice to the user, A system that controls beauty devices adapted to the characteristics of the user's skin condition, and includes means of supporting skincare in the user's living space.

2. The system according to claim 1, which obtains feedback on the effectiveness of a proposed skincare product and uses it as training data for the system.

3. The system according to claim 1, which takes allergy information into consideration when suggesting products suitable for a specific skin type based on analyzed skin characteristics.

Images