Laser energy intelligent recommendation system and method for nursing equipment

Abstract

The invention provides a laser energy intelligent recommendation system and method for nursing equipment, and the system comprises an image collection module which is used for collecting the image information of a to-be-nursed part of a user; the image processing module is used for performing feature extraction on the received image information to obtain key skin features and transmitting the key skin features to the energy recommendation module; the user information acquisition module is used for acquiring and managing basic information of a user; the energy recommendation module is used for receiving the key skin characteristics and the basic information, obtaining a preliminary laser energy recommendation value matched with the user through an energy recommendation model based on the key skin characteristics and the basic information, and sending the preliminary laser energy recommendation value to the user tolerance weighting module; the user tolerance weighting module is used for querying historical nursing information of the user after receiving the initial laser energy recommendation value, and outputting a final laser energy recommendation value based on a query result; and the user module is used for providing an interactive interface for a user.

Description

Technical Field

[0001] This invention relates to the interdisciplinary fields of medical aesthetics and artificial intelligence, and in particular to a laser energy intelligent recommendation system and method for use in nursing devices. Background Technology

[0002] Laser skincare equipment is widely used in clinical practice, covering multiple treatments such as hair removal, skin whitening, freckle removal, and skin rejuvenation. The laser energy parameters used by these devices are typically set by operators based on experience and limited reference manuals. However, due to significant individual differences, relying too heavily on manual judgment has the following limitations: 1. Lack of personalized consideration in energy parameter settings may lead to poor skincare results or cause skin discomfort; 2. The experience of operators is difficult to standardize, and different physicians may recommend different energy values ​​under similar conditions; 3. User basic information (such as gender, age, treatment area, and skin type) has not been systematically utilized; 4. Before the treatment, the condition of hair / skin was not objectively analyzed using image information, and there was a lack of data-driven support.

[0003] Currently, there is no mature system that can fully integrate user image information and basic attribute data and make energy level recommendations through machine learning models. Therefore, it is of great significance to develop an intelligent system that can combine image features and user basic information to make refined laser energy recommendations. Summary of the Invention

[0004] The purpose of this invention is to provide a laser energy intelligent recommendation system and method for nursing equipment, aiming to solve the above-mentioned problems in the prior art.

[0005] This invention provides a laser energy intelligent recommendation system for nursing equipment, comprising: An image acquisition module, connected to an image processing module, is used to acquire image information of the area to be cared for by the user and transmit the image information to the image processing module. An image processing module, connected to the image acquisition module and the energy recommendation module, is used to extract features from the received image information, obtain key epidermal features, and transmit the key epidermal features to the energy recommendation module; The user information collection module is connected to the energy recommendation module and the user tolerance weighting module, and is used to collect and manage the user's basic information and transmit the basic information to the energy recommendation module and the user tolerance weighting module. An energy recommendation module, connected to the image processing module, user information collection module, and user tolerance weighting module, is used to receive the key epidermal features and the basic information, and obtain a preliminary laser energy recommendation value matching the user through an energy recommendation model based on the key epidermal features and the basic information, and send the preliminary laser energy recommendation value to the user tolerance weighting module. The user tolerance weighting module is connected to the user information collection module, energy recommendation module and user module. It is used to receive the preliminary laser energy recommendation value and then query the user's historical care information, and output the final laser energy recommendation value based on the query results. The user module, connected to the user tolerance weighting module, is used to provide users with a user-friendly operating interface and interaction interface.

[0006] This invention provides a method for intelligent laser energy recommendation for nursing devices, comprising: The image acquisition module acquires image information of the area to be treated by the user, and then transmits the image information to the image processing module. The image processing module extracts features from the received image information to obtain key epidermal features, and then transmits the key epidermal features to the energy recommendation module. The user information collection module collects and manages the user's basic information, and transmits the basic information to the energy recommendation module and the user tolerance weighting module. The energy recommendation module receives the key epidermal features and the basic information, and obtains a preliminary laser energy recommendation value that matches the user based on the key epidermal features and the basic information through the energy recommendation model. The preliminary laser energy recommendation value is then sent to the user tolerance weighting module. After receiving the preliminary recommended laser energy value, the user tolerance weighting module queries the user's historical care information and outputs the final recommended laser energy value based on the query results. The user module provides users with a user-friendly interface and interaction interface.

[0007] This invention also provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the above-described intelligent laser energy recommendation method for nursing devices.

[0008] This invention also provides a computer-readable storage medium storing an information transmission implementation program, which, when executed by a processor, implements the steps of the above-described intelligent laser energy recommendation method for nursing devices.

[0009] The following benefits can be achieved by adopting the embodiments of the present invention: Compared with the traditional mode where laser nursing energy depends on the subjective judgment of physicians, the system proposed in the embodiments of the present invention can improve the consistency of nursing plans while ensuring safety, and provide personalized services to users and improve the efficiency of physician operations through a standardized and interpretable AI recommendation process. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in one or more embodiments of this specification or in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 This is a schematic diagram of a laser energy intelligent recommendation system for nursing equipment according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the actual operation process of the energy recommendation system according to an embodiment of the present invention; Figure 3 This is a flowchart of a laser energy intelligent recommendation method for nursing equipment according to an embodiment of the present invention. Detailed Implementation

[0012] To enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, and not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of this document.

[0013] System Implementation Examples According to embodiments of the present invention, a laser energy intelligent recommendation system for nursing equipment is provided. Figure 1 This is a schematic diagram of a laser energy intelligent recommendation system for nursing equipment according to an embodiment of the present invention, such as... Figure 1 As shown, the intelligent laser energy recommendation system for nursing equipment according to an embodiment of the present invention specifically includes: The image acquisition module 10 is connected to the image processing module and is used to acquire image information of the user's area to be cared for and transmit the image information to the image processing module. Image processing module 11, connected to the image acquisition module and the energy recommendation module, is used to extract features from the received image information, obtain key epidermal features, and transmit the key epidermal features to the energy recommendation module; The key epidermal features include hair thickness, density, color, length, skin type, skin tone, oiliness, and gloss reflectivity. The user information collection module 12 is connected to the energy recommendation module and the user tolerance weighting module, and is used to collect and manage the user's basic information and transmit the basic information to the energy recommendation module and the user tolerance weighting module. The basic information includes gender, age, nursing site, historical nursing information, and user ID; wherein, the historical nursing information includes historical nursing records and historical nursing feedback; The energy recommendation module 13 is connected to the image processing module, the user information collection module, and the user tolerance weighting module. It is used to receive the key epidermal features and the basic information, and obtain a preliminary laser energy recommendation value that matches the user through the energy recommendation model based on the key epidermal features and the basic information. The preliminary laser energy recommendation value is then sent to the user tolerance weighting module. The user tolerance weighting module 14, connected to the user information collection module, energy recommendation module, and user module, is used to receive the preliminary laser energy recommendation value, query the user's historical care information, and output the final laser energy recommendation value based on the query results. Specifically, it is used for: The system receives the preliminary recommended laser energy value, queries the user's historical nursing information based on the user ID, and if historical nursing information exists, generates the user's skin tolerance level based on the historical nursing records and feedback. The preliminary recommended laser energy value is then weighted and corrected based on the skin tolerance level, and the corrected recommended laser energy value is used as the final recommended laser energy value. If no historical nursing information exists, the preliminary recommended laser energy value will be used as the final recommended laser energy value. The preliminary recommended laser energy value and the final recommended laser energy value are both within a statistically verified safe energy range. User module 15, connected to the user tolerance weighting module, is used to provide users with a user-friendly operating interface and interaction interface; The system further includes: The physician experience transfer module is connected to the energy recommendation module, the user tolerance weighting module, and the data storage and feedback module. It provides an interactive interface for physicians, corrects the final laser energy recommendation value according to actual needs, outputs the laser energy correction value, and introduces the correction record as the energy correction offset into the energy recommendation model to construct the corresponding personalized physician model. The data storage and feedback module is connected to the image acquisition module, image processing module, user information acquisition module, energy recommendation module, user tolerance weighting module, user module, and physician experience transfer module. It is used to store the user's image information, key epidermal features, basic information, preliminary laser energy recommendation value, final laser energy recommendation value, laser energy correction value, correction record, and user nursing feedback, and to dynamically optimize the energy recommendation model based on the nursing feedback.

[0014] The following describes in detail the above-mentioned technical solutions of the present invention with reference to the specific circumstances of the intelligent laser energy recommendation system for nursing equipment in the embodiments of the present invention.

[0015] To address the technical problems in existing laser care equipment, such as the lack of personalized energy parameter settings, reliance on human experience, ineffective integration of images and user features, and lack of feedback optimization in the recommendation mechanism, this invention proposes a laser care energy recommendation system based on machine learning, comprising the following modules: 1. Image acquisition module, used to acquire high-definition skin / hair follicle images of the area to be treated by the user; 2. Image recognition module: This module uses a deep learning model to process images and extract image features, including hair thickness, density, color, length, skin tone, and oiliness. It uses a convolutional neural network structure, including an instance segmentation network and a multi-classification network, achieving pixel-level recognition accuracy.

[0016] 3. User information collection module, used to input and manage users' basic attribute information, including gender, age, nursing site and unique identifier ID; 4. Energy Recommendation Model Module: Based on a trained machine learning model, this module takes the aforementioned image features and user information as input and outputs the most suitable laser energy recommendation parameters for the user. The energy recommendation model is one of the following: Random Forest, Support Vector Machine (SVM), XGBoost, LightGBM, or a deep neural network model, and is trained using actual clinical nursing data. The recommended value is in J / L. And it is within the statistically verified safe energy range.

[0017] 5. User tolerance weighting module, used to positively or negatively weight the recommended energy based on the user's historical care records and feedback data; this module divides users into at least 5 or 10 levels of skin tolerance and adjusts the recommended value according to the level.

[0018] 6. Physician experience transfer module, which records the correction value when physicians manually adjust the energy parameters and updates the model weights when the conditions are met, so that the recommendation results are in line with the physicians' habits; 7. Data recording and feedback module, used to store image features, user information, recommendation values, actual usage values, and feedback information, and used for model iterative training.

[0019] Preferably, the system supports offline recommendation and cloud synchronization modes, with the model update cycle being once a day or once a week, which can be automatically triggered by the device or manually initiated by the physician.

[0020] The system also includes a front-end interface for displaying recommended values ​​in real time, allowing physicians to manually modify energy parameters, and recording patients' subjective ratings.

[0021] The present invention aims to address technical problems in existing laser care equipment, such as the lack of individualization in energy parameter setting, insufficient utilization of images and basic information, and unstable recommendation mechanisms. The system proposed in this invention specifically includes: 1. Image acquisition and feature extraction module The system uses high-definition imaging equipment such as a follicle microscope to collect images of the user's treated area. Through the deployed image processing and deep learning models, the system automatically identifies key feature parameters in the images, such as hair thickness, density, distribution, color, and skin pigmentation and oiliness.

[0022] 2. User Basic Information Input Module Before providing care, the system collects basic user attribute information, including but not limited to gender, age, care area, skin type, and past care records, and assigns a unique user identifier (User ID) for historical record management and model tracking.

[0023] 3. Energy Recommendation AI Model Module The image feature vector is combined with basic user information and fed into a pre-trained machine learning recommendation model. Model types may include random forest, XGBoost, support vector machine (SVM), or multiple linear regression analysis. This model performs energy prediction based on a pre-trained dataset of physician clinical nursing parameters and outputs preliminary recommendation values.

[0024] 4. Mechanism for Physician Knowledge Transfer and Experience Integration The system has a mechanism for accumulating physicians' usage experience. In the early stages of use, the model recommends an initial energy value for users. Physicians can manually adjust this value based on the actual situation. The system records the adjustment data and subsequently updates the model weights to transfer the physicians' usage habits to the model, thereby improving the personalized accuracy of intelligent recommendations.

[0025] 5. User Individual Tolerance Weighting Module The system analyzes the energy usage and physical feedback of the same user in different care settings by recalling historical nursing records, constructs a "user tolerance level", and positively or negatively weights the recommendation results output by the model to enhance the individual adaptability of the recommendations and achieve energy calibration for users with high tolerance / low tolerance.

[0026] 6. Closed-loop data update mechanism All nursing records (recommended values, corrected values, nursing feedback) are synchronized to the cloud database for continuous optimization of the training model, realizing a closed-loop learning feedback system, and thus achieving the ability to intelligently recommend personalized energy parameters for each individual.

[0027] To make the embodiments of the present invention clearer and more explicit, the following describes the actual operation flow of the system, such as... Figure 2 As shown, a preferred embodiment is provided, which can be used by those skilled in the art to implement the present invention.

[0028] 1. Physician-level AI-powered energy recommendation process architecture The laser care energy recommendation system proposed in this invention includes the following key operating steps: Step 1.1: Image Acquisition The physician uses a matching follicle microscope camera (or a professional imaging device with high-definition magnification capabilities) to photograph the area to be treated. The captured images have high clarity in hair and skin texture, and the resolution meets the requirements of AI algorithm analysis. They are then stored locally or uploaded to a server in standard image formats (such as JPEG, PNG, TIFF).

[0029] Step 1.2: Image Recognition and Feature Extraction The system invokes a deep learning image recognition model deployed locally or in the cloud to process the aforementioned images. The model can be based on structures such as Convolutional Neural Networks (CNN), U-Net, and ResNet to perform instance segmentation and feature classification of the images, automatically extracting the following parameters: Hair thickness ( ), hair density (number per unit area), hair length and color (e.g., black, brown, light), skin type (automatically graded according to Fitzpatrick standards), skin oiliness, gloss reflectance and other epidermal characteristics. All recognition results are output in the form of feature vectors for subsequent energy recommendation algorithms to use.

[0030] Step 1.3: Basic Information Fusion and Energy Recommendation The system front-end inputs basic user information, including gender, age, treated area, nursing history, and user ID. The image feature vector is then integrated with the user's basic attributes and used as input features to feed into the trained machine learning recommendation model.

[0031] The model can use supervised learning algorithms such as Random Forest, Support Vector Machine (SVM), XGBoost, and Decision Tree Regression. The model is pre-trained with large-scale clinical operation data before leaving the factory and outputs recommended laser care energy values ​​(unit: J / cm²) to ensure that effective energy settings are provided within a safe range.

[0032] Step 1.4: Physician Manual Feedback and Model Knowledge Update Mechanism The recommended energy parameters are initial values ​​(the default factory settings are relatively conservative). Users can view the recommended values ​​on the front-end page and choose whether to adopt them. If "Use recommended value" is selected, the system will directly call the parameter to control the laser output; if the physician believes that the recommended value is too low or too high, the parameter can be manually fine-tuned, and the system will record the adjustment behavior and compare it with the original recommended value and archive it; for each nursing process, the system will write complete data such as image data, user information, recommended value, actual usage value, and user feedback into the local database and upload it to the cloud data center for long-term accumulation.

[0033] Step 1.5: Physician Habit Model Learning After a physician has used the device for a period of time, the system may prompt whether to perform a "knowledge weight update" operation. Once confirmed, the system will extract the energy correction offset used by the physician under specific images / user information from historical data and automatically fine-tune the weight parameters in the recommendation model to form a "personalized physician model". Thereafter, when the same physician operates on the same type of image again, the recommended value will prioritize reflecting his past usage habits and further align with his diagnosis and treatment logic.

[0034] Step 1.6: User Tolerance Weighting Mechanism Before each care session, the system will look up the user's care history in the database based on the user ID: If there is no historical data, the system will directly recommend based on the current model; If a historical record exists, the system will calculate the "surface tolerance index" based on past nursing energy values ​​and user feedback. The index can be further divided into several levels, with lower energy values ​​for users with low tolerance; The final output is a recommended energy value that has been adjusted with personalized weighting to ensure both safety and comfort.

[0035] Through the above process, this embodiment of the invention realizes a preliminary AI recommendation based on images and attributes, and integrates a closed-loop structure of physician feedback updates and user sensation group correction, thereby constructing an "individualized" intelligent energy recommendation system.

[0036] 2. System Implementation Technical Details 2.1 Image Recognition Algorithm Implementation 2.1.1 Application of Multi-Classification + Instance Segmentation Algorithm Combination Use pre-trained convolutional neural networks (such as ResNet34, EfficientNet, YOLO, etc.) to identify hair / skin texture features in images; At the same time, it combines instance segmentation algorithms such as U-Net or Mask-RCNN to accurately separate hair regions and improve the accuracy of density and morphology extraction. The model is trained using a combination of publicly available image datasets and enterprise-built datasets to enhance its generalization ability. The output structured features include more than 10 indicators such as coarseness, concentration, skin tone, and oiliness.

[0037] 2.1.2 Recommendation Algorithm Model Structure and Input Feature Composition Input features: Image recognition output (e.g., hair_density, skin_tone_level), user attributes (age, sex, site); Output objective: Optimal recommended energy value (continuous variable); Model structures can be XGBoost (structured data optimization), SVM (high accuracy with small sample sizes), or Random Forest (to prevent overfitting). All models are pre-trained on real clinical datasets and validated by expert annotations before the devices leave the factory.

[0038] 2.1.3 User-level personalized recommendation mechanism After each recommendation, the system will automatically check the database to determine if the user has any nursing records. If applicable, analyze the user's historical energy values ​​and actual nursing feedback to model the user's "feeling level". The recommended value is adjusted (weighted) within a weight range of ±10% according to the level, thereby outputting the final energy value. This process realizes the adaptive optimization of the recommendation results to the individual user's response, reflecting personalized precision control.

[0039] Method Implementation Examples According to embodiments of the present invention, a method for intelligent laser energy recommendation for nursing devices is provided. Figure 3This is a flowchart of a laser energy intelligent recommendation method for nursing equipment according to an embodiment of the present invention, such as... Figure 3 As shown, the intelligent laser energy recommendation method for nursing devices according to an embodiment of the present invention specifically includes: Step S301: Acquire image information of the user's area to be cared for through the image acquisition module, and transmit the image information to the image processing module; Step S302: The image processing module extracts features from the received image information to obtain key epidermal features, and transmits the key epidermal features to the energy recommendation module. The key epidermal features include hair thickness, density, color, length, skin type, skin tone, oiliness, and gloss reflectivity. Step S303: Collect and manage the user's basic information through the user information collection module, and transmit the basic information to the energy recommendation module and the user tolerance weighting module; The basic information includes gender, age, nursing site, historical nursing information, and user ID; wherein, the historical nursing information includes historical nursing records and historical nursing feedback; Step S304: Receive the key epidermal features and the basic information through the energy recommendation module, and obtain a preliminary laser energy recommendation value matching the user based on the key epidermal features and the basic information through the energy recommendation model, and send the preliminary laser energy recommendation value to the user tolerance weighting module. Step S305 involves the user tolerance weighting module querying the user's historical care information after receiving the preliminary recommended laser energy value, and outputting the final recommended laser energy value based on the query results. Specifically, this includes: The preliminary recommended laser energy value is received through the user tolerance weighting module. The user's historical nursing information is queried according to the user ID. If historical nursing information exists, the user's skin tolerance level is generated based on the historical nursing records and feedback. The preliminary recommended laser energy value is weighted and corrected based on the skin tolerance level, and the corrected recommended laser energy value is used as the final recommended laser energy value. If no historical nursing information exists, the preliminary recommended laser energy value will be used as the final recommended laser energy value. The preliminary recommended laser energy value and the final recommended laser energy value are both within a statistically verified safe energy range. Step S306: Provide users with a user-friendly interface and interaction interface through the user module; The method further includes: The physician experience transfer module provides an interactive interface for physicians, which corrects the final recommended laser energy value according to actual needs, outputs the corrected laser energy value, and introduces the correction record as the energy correction offset into the energy recommendation model to build a corresponding personalized physician model. The data storage and feedback module stores the user's image information, key epidermal features, basic information, preliminary laser energy recommendation value, final laser energy recommendation value, laser energy correction value, correction record, and user nursing feedback, and dynamically optimizes the energy recommendation model based on the nursing feedback. The following describes in detail the above-mentioned technical solutions of the present invention with reference to the specific details of the intelligent laser energy recommendation method for nursing equipment in the embodiments of the present invention.

[0040] This invention proposes a machine learning-based method for recommending laser care energy, comprising the following steps: 1. Use an image acquisition device to capture images of the area to be treated on the user's body; 2. Perform deep learning processing on the image to extract image features, including hair thickness, density, color, and skin tone. 3. Collect basic user attribute information, including gender, age, and treatment area, and generate a unique user identifier; 4. Input image features and user information into a trained machine learning recommendation model, and output laser care energy value; 5. If the user has a history of care, the recommended value will be positively or negatively weighted based on the user's feedback level. 6. Provide recommended values ​​to physicians as a nursing reference. Physicians can choose to adopt the values ​​or manually adjust the parameters. 7. Write the recommended values, actual usage values, and user feedback information into the database and use them for subsequent model training and updates.

[0041] The image processing model uses a series of deep learning network structures to identify hair and skin regions; the user's body sensation level is divided into at least five levels, based on the user's feedback evaluation or thermal score after care; the model's recommended value is initially set to factory settings and supports updating the model's knowledge weights based on physician usage data; the model training samples are derived from multi-center clinical datasets, and cross-validation is used to ensure that the output value is within the expected safe range.

[0042] In summary, the laser care energy recommendation system and method based on machine learning proposed in this invention have the following beneficial effects: 1. Energy recommendation accuracy significantly improved This invention integrates user image features (such as hair thickness, density, skin color, etc.) with basic information (gender, age, location, etc.) and uses a trained machine learning model to perform energy recommendation, replacing the traditional experience-based manual setting method, and significantly improving the scientific nature and individualized adaptation capability of energy setting.

[0043] 2. Intelligent decision-making mechanism for personalized nursing care The system has a built-in user tolerance grading mechanism that uses historical nursing data and sensory responses for weighted correction to achieve personalized energy adjustment recommendations. This enhances adaptability to individual differences and effectively avoids discomfort, inefficiency, or damage caused by insufficient or excessive energy.

[0044] 3. Reduce reliance on physician experience and improve consistency and operational efficiency. Compared to the traditional model where laser care energy relies on the physician's subjective judgment, the system proposed in this embodiment of the invention improves the consistency of care plans, shortens the learning time for novice physicians, and increases operational efficiency through a standardized and interpretable AI recommendation process, while ensuring safety.

[0045] 4. Achieve experience transfer and continuous knowledge optimization The system proposed in this invention allows physicians to manually adjust parameters to train and update the model during use. The system precipitates physician experience into structured data and automatically transfers it to subsequent recommendations through weight optimization, achieving "experience standardization and model self-learning".

[0046] 5. Establish a closed-loop feedback and data-driven nursing optimization system. All nursing records (including recommended parameters, adjustment history, and user feedback) will be synchronized to the database, forming a closed-loop data chain. This will provide high-quality, real-world data support for future model iterations and establish a data-driven path for medical optimization.

[0047] 6. Possesses good economic value and promising prospects for promotion. The system boasts a highly versatile architecture, making it compatible with various laser care devices and facilitating integration and widespread adoption. AI-assisted operation reduces reliance on senior physicians, enabling the equipment to be used in primary care settings or beauty clinics, lowering training costs, and improving equipment utilization and patient satisfaction.

[0048] 7. User experience and security have been significantly enhanced. Before nursing care, the system intelligently recommends appropriate energy levels based on images and databases, effectively reducing the risks of burns, pain, and inefficiency, improving the user nursing experience, enhancing patient engagement and trust, and demonstrating significant social benefits.

[0049] Device Example 1 This invention provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, performs the steps described in the method embodiment.

[0050] Device Example 2 This invention provides a computer-readable storage medium storing an information transmission implementation program, which, when executed by a processor, performs the steps described in the method embodiment.

[0051] The computer-readable storage media described in this embodiment include, but are not limited to, ROM, RAM, disk, or optical disk.

[0052] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A laser energy intelligent recommendation system for nursing equipment, characterized in that... include: An image acquisition module, connected to an image processing module, is used to acquire image information of the area to be cared for by the user and transmit the image information to the image processing module. An image processing module, connected to the image acquisition module and the energy recommendation module, is used to extract features from the received image information, obtain key epidermal features, and transmit the key epidermal features to the energy recommendation module; The user information collection module is connected to the energy recommendation module and the user tolerance weighting module, and is used to collect and manage the user's basic information and transmit the basic information to the energy recommendation module and the user tolerance weighting module. An energy recommendation module, connected to the image processing module, user information collection module, and user tolerance weighting module, is used to receive the key epidermal features and the basic information, and obtain a preliminary laser energy recommendation value matching the user through an energy recommendation model based on the key epidermal features and the basic information, and send the preliminary laser energy recommendation value to the user tolerance weighting module. The user tolerance weighting module is connected to the user information collection module, energy recommendation module and user module. It is used to receive the preliminary laser energy recommendation value and then query the user's historical care information, and output the final laser energy recommendation value based on the query results. The user module, connected to the user tolerance weighting module, is used to provide users with a user-friendly operating interface and interaction interface.

2. The system according to claim 1, characterized in that, The system further includes: The physician experience transfer module is connected to the energy recommendation module, the user tolerance weighting module, and the data storage and feedback module. It provides an interactive interface for physicians, corrects the final laser energy recommendation value according to actual needs, outputs the laser energy correction value, and introduces the correction record as the energy correction offset into the energy recommendation model to construct the corresponding personalized physician model. The data storage and feedback module is connected to the image acquisition module, image processing module, user information acquisition module, energy recommendation module, user tolerance weighting module, user module, and physician experience transfer module. It is used to store the user's image information, key epidermal features, basic information, preliminary laser energy recommendation value, final laser energy recommendation value, laser energy correction value, correction record, and user nursing feedback, and to dynamically optimize the energy recommendation model based on the nursing feedback.

3. The system according to claim 1, characterized in that, The key epidermal features include hair thickness, density, color, length, skin type, skin tone, oiliness, and gloss reflectivity; The basic information includes gender, age, nursing site, historical nursing information, and user ID; The historical nursing information includes historical nursing records and historical nursing feedback.

4. The system according to claim 3, characterized in that, The user tolerance weighting module is specifically used for: The system receives the preliminary recommended laser energy value, queries the user's historical nursing information based on the user ID, and if historical nursing information exists, generates the user's skin tolerance level based on the historical nursing records and feedback. The preliminary recommended laser energy value is then weighted and corrected based on the skin tolerance level, and the corrected recommended laser energy value is used as the final recommended laser energy value. If no historical nursing information exists, the preliminary recommended laser energy value will be used as the final recommended laser energy value. The preliminary recommended laser energy value and the final recommended laser energy value are both within a statistically verified safe energy range.

5. A method for intelligently recommending laser energy for nursing equipment, characterized in that... include: The image acquisition module acquires image information of the area to be treated by the user, and then transmits the image information to the image processing module. The image processing module extracts features from the received image information to obtain key epidermal features, and then transmits the key epidermal features to the energy recommendation module. The user information collection module collects and manages the user's basic information, and transmits the basic information to the energy recommendation module and the user tolerance weighting module. The energy recommendation module receives the key epidermal features and the basic information, and obtains a preliminary laser energy recommendation value that matches the user based on the key epidermal features and the basic information through the energy recommendation model. The preliminary laser energy recommendation value is then sent to the user tolerance weighting module. After receiving the preliminary recommended laser energy value, the user tolerance weighting module queries the user's historical care information and outputs the final recommended laser energy value based on the query results. The user module provides users with a user-friendly interface and interaction interface.

6. The method according to claim 5, characterized in that, The method further includes: The physician experience transfer module provides an interactive interface for physicians, which corrects the final recommended laser energy value according to actual needs, outputs the corrected laser energy value, and introduces the correction record as the energy correction offset into the energy recommendation model to build a corresponding personalized physician model. The data storage and feedback module stores the user's image information, key epidermal features, basic information, preliminary laser energy recommendation value, final laser energy recommendation value, laser energy correction value, correction record, and user nursing feedback, and dynamically optimizes the energy recommendation model based on the nursing feedback.

7. The method according to claim 5, characterized in that, The key epidermal features include hair thickness, density, color, length, skin type, skin tone, oiliness, and gloss reflectivity; The basic information includes gender, age, nursing site, historical nursing information, and user ID; The historical nursing information includes historical nursing records and historical nursing feedback.

8. The method according to claim 7, characterized in that, After receiving the preliminary recommended laser energy value, the user tolerance weighting module queries the user's historical care information and outputs the final recommended laser energy value based on the query results. Specifically, this includes: The preliminary recommended laser energy value is received through the user tolerance weighting module. The user's historical nursing information is queried according to the user ID. If historical nursing information exists, the user's skin tolerance level is generated based on the historical nursing records and feedback. The preliminary recommended laser energy value is weighted and corrected based on the skin tolerance level, and the corrected recommended laser energy value is used as the final recommended laser energy value. If no historical nursing information exists, the preliminary recommended laser energy value will be used as the final recommended laser energy value. The preliminary recommended laser energy value and the final recommended laser energy value are both within a statistically verified safe energy range.

9. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the intelligent laser energy recommendation method for a care device as described in any one of claims 5-8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores an implementation program for information transmission, which, when executed by a processor, implements the steps of the intelligent laser energy recommendation method for a nursing device as described in any one of claims 5-8.

Images