A method and system for monitoring and warning operating parameters of medical cosmetic equipment

Abstract

The present invention relates to the field of operational monitoring technology, and in particular to a method and system for monitoring and early warning the operational parameters of medical cosmetic equipment. The method comprises the following steps: acquiring medical cosmetic equipment data; performing a range analysis on the medical cosmetic equipment data to generate range data; integrating equipment monitoring parameters using multi-source sensors based on the range data to generate multimodal monitoring data for standard medical cosmetic equipment; and performing long-term performance degradation trend monitoring on the multimodal monitoring data for standard medical cosmetic equipment to generate long-term performance degradation trend data for key components of the equipment. Through multimodal data integration, long-term performance trend analysis, biomechanical modeling, and intelligent early warning decision optimization, the present invention improves the reliability and intelligence of operational parameter monitoring and early warning for medical cosmetic equipment.

Description

Technical Field

[0001] The present invention relates to the field of operation monitoring technology, and in particular to a method and system for monitoring and early warning of operation parameters of medical cosmetic equipment. Background Art

[0002] Early monitoring technologies for medical aesthetics devices relied primarily on simple mechanical or electrical parameter detection, failing to meet the demands of high-precision treatment. Advances in sensor technology and computer algorithms have gradually introduced real-time data acquisition and analysis capabilities, enabling detection of device power output, temperature changes, and energy distribution. However, these technologies only monitor a single parameter of device status and lack comprehensive early warning capabilities, making them incapable of addressing complex device anomalies. In recent years, the application of artificial intelligence, big data, and the Internet of Things (IoT) has provided new developments in operational parameter monitoring and early warning for medical aesthetics devices. By integrating and analyzing multi-source data using intelligent algorithms and building device operational status models, device failure trend prediction and real-time anomaly alarms can be achieved. However, current monitoring parameters for medical aesthetics devices are typically derived from a single sensor, failing to fully reflect the device's overall status and failing to fully consider the device's impact on the biomechanical properties of the skin. This results in low reliability and intelligence levels in operational parameter monitoring and early warning for medical aesthetics devices. Summary of the Invention

[0003] Based on this, it is necessary to provide a method and system for monitoring and early warning the operating parameters of medical cosmetic equipment to solve at least one of the above technical problems.

[0004] To achieve the above-mentioned purpose, a method for monitoring and early warning the operating parameters of medical cosmetic equipment is provided, the method comprising the following steps:

[0005] Step S1: Acquire medical cosmetic equipment data; perform equipment range analysis on the medical cosmetic equipment data to generate medical cosmetic equipment range data; integrate equipment monitoring parameters using multi-source sensors based on the medical cosmetic equipment range data to generate standard medical cosmetic equipment multimodal monitoring data;

[0006] Step S2: Perform long-term performance degradation trend monitoring on the multimodal monitoring data of standard medical cosmetic equipment to generate long-term performance degradation trend data of key components of the equipment; generate a first warning signal based on the long-term performance degradation trend data of key components of the equipment to obtain a first warning signal for operation monitoring; perform biomechanical modeling on the multimodal monitoring data of standard medical cosmetic equipment to generate skin stress distribution data; generate a second warning signal based on the skin stress distribution data to obtain a second warning signal for operation monitoring;

[0007] Step S3: Uploading the first operation monitoring warning signal and the second operation monitoring warning signal to the cloud platform for monitoring warning trigger frequency analysis to generate equipment monitoring warning trigger frequency data; constructing a trigger decision based on the equipment monitoring warning trigger frequency data to generate medical beauty equipment operation warning decision data;

[0008] Step S4: Evaluate the accuracy of the warning decision data for the operation of medical cosmetic equipment to generate operation monitoring warning accuracy evaluation data; adjust the warning signals of the first warning signal of operation monitoring and the second warning signal of operation monitoring based on the operation monitoring warning accuracy evaluation data to perform the operation parameter monitoring and warning optimization operation of the medical cosmetic equipment.

[0009] By analyzing the range of action of medical cosmetic device data, this invention accurately identifies the device's operating area, ensuring that the monitored data is relevant to the device's actual operating environment and treatment area, reducing errors and providing a precise monitoring data foundation. By integrating data from multiple sensor sources, it comprehensively collects multimodal information about the device, enhancing data accuracy and comprehensiveness. Long-term performance degradation trend monitoring can promptly identify potential failure risks of key device components and generate early warning signals, facilitating intervention before problems occur and extending device lifespan. Biomechanical modeling considers the skin's response to device action, generating a secondary warning signal that reflects the device's actual impact on the patient, ensuring the safety and effectiveness of treatment. Uploading warning signals to a cloud platform enables remote monitoring and data storage, providing real-time data support for device management and maintenance. Trigger frequency analysis helps identify frequent warning signal occurrences, optimizes decision-making processes, avoids over-warnings or under-reporting, and enhances the system's intelligence. By evaluating warning accuracy, the reliability of the warning system can be verified and improved, ensuring the effectiveness and timeliness of warning signals. Adjusting warning signals based on the evaluation results can dynamically optimize the monitoring and warning system, making it better adapted to the actual operating status of the equipment, reducing false positives and missed alerts, and further improving the intelligence and precision of equipment management. Therefore, through multimodal data integration, long-term performance trend analysis, biomechanical modeling, and intelligent early warning decision optimization, this invention improves the reliability and intelligence of medical cosmetic equipment operating parameter monitoring and early warning.

[0010] Preferably, step S1 includes the following steps:

[0011] Step S11: Acquire medical beauty equipment data;

[0012] Step S12: extracting text features from the medical beauty equipment data to generate medical beauty equipment text feature data; performing text semantic analysis on the medical beauty equipment text feature data to generate medical beauty equipment text semantic analysis data;

[0013] Step S13: performing a medical beauty device scope analysis on the medical beauty device text semantic analysis data to generate medical beauty device scope data; integrating device monitoring parameters using multi-source sensors based on the medical beauty device scope data to generate medical beauty device multimodal monitoring data;

[0014] Step S14: Preprocess the multimodal monitoring data of medical cosmetic equipment to generate standard multimodal monitoring data of medical cosmetic equipment, wherein the data preprocessing includes data cleaning, data denoising, data missing value filling and data standardization.

[0015] Through steps S11 and S12, the present invention realizes the preliminary collection of medical beauty equipment data and in-depth mining at the text semantic level, which can accurately extract the core information and functional description of the equipment, and provide basic data support for subsequent analysis. The scope analysis in step S13 is combined with multi-source sensor technology, which not only improves the analytical depth of the equipment function, but also integrates the multimodal data of equipment monitoring to ensure the comprehensiveness and consistency of the data. Through the multimodal data preprocessing of S14, problems such as noise and missing values in the original data are solved, the quality of the data is ensured, and standardized multimodal monitoring data is generated, laying a reliable foundation for subsequent modeling and analysis. Through text feature extraction, semantic parsing and multimodal data processing, an intelligent process from data collection to in-depth analysis is realized, which significantly improves the accuracy and efficiency of the integration of equipment monitoring parameters. This step system has strong adaptability and can be adjusted for different types of medical beauty equipment. It is suitable for a variety of data types and monitoring needs and has high versatility.

[0016] Preferably, integrating equipment monitoring parameters through multi-source sensors based on the range data of medical cosmetic equipment includes:

[0017] Using the skin condition sensor to collect the user's real-time physiological signals within the range of the medical beauty device, the user's real-time physiological signals are obtained; the user's real-time physiological signals are conditioned to generate a real-time physiological conditioning signal;

[0018] Perform analog-to-digital conversion on the user's real-time physiological conditioning signal to generate the user's real-time physiological data; perform data change correlation analysis on the user's real-time physiological data and medical beauty equipment data to generate monitoring correlation change data; use environmental sensors to collect environmental parameters based on the monitoring correlation change data to obtain the environmental data of the medical beauty equipment;

[0019] The medical beauty equipment data, the user's real-time physiological data and the medical beauty equipment's working environment data are integrated and displayed to generate multimodal monitoring data of medical beauty equipment.

[0020] This invention uses skin condition sensors to collect user physiological signals in real time, condition them, and perform analog-to-digital conversion to generate high-precision real-time user physiological data. This process ensures the integrity and accuracy of user physiological signals, providing a reliable data foundation for personalized medical aesthetics procedures. Change correlation analysis is performed on real-time user physiological data and medical aesthetics device data to identify the specific impact of device operation on the user's physiological state and generate monitoring correlation change data. This analysis method can promptly detect anomalies or optimization points during device operation, improving monitoring accuracy and practicality. Combined with device operating environment data (such as temperature and humidity) collected by environmental sensors, device parameters are dynamically adjusted to adapt to different operating environments. This enables the device to perceive and respond to external environmental changes, improving operational safety and user experience. Medical aesthetics device data, real-time user physiological data, and operating environment data are integrated to generate multimodal monitoring data, supporting comprehensive analysis of device status and user feedback. Multimodal data integration overcomes the shortcomings of single-source monitoring and provides a more comprehensive perspective for device monitoring systems. Monitoring and correlation analysis of real-time user physiological signals support dynamic adjustment of medical aesthetics devices and enhance their real-time responsiveness.

[0021] Preferably, step S2 includes the following steps:

[0022] Step S21: extracting operating parameters of key components of a standard medical cosmetic device from multimodal monitoring data to obtain operating parameters of key components of the device, wherein the key components of the device include a laser, a radio frequency electrode, and a cooling system;

[0023] Step S22: monitoring the long-term performance degradation trend of the operating parameters of the key components of the equipment to generate long-term performance degradation trend data of the key components of the equipment; generating a first early warning signal based on the long-term performance degradation trend data of the key components of the equipment to obtain a first early warning signal for operation monitoring;

[0024] Step S23: extracting skin contact optical perception data from the multimodal monitoring data of the standard medical cosmetic equipment to obtain skin contact optical perception data;

[0025] Step S24: Perform biomechanical modeling on the skin contact optical perception data to generate skin stress distribution data; identify potential risks based on the skin stress distribution data to generate skin micro-injury prediction data; generate a second warning signal based on the skin micro-injury prediction data to obtain a second warning signal for operation monitoring.

[0026] This invention extracts operating parameters from key components, such as the laser, radiofrequency electrodes, and cooling system, providing accurate data support for the device's operating status. This helps identify potential device issues and ensures the efficient operation and stability of medical cosmetic equipment. Long-term performance degradation trend analysis of key component operating parameters identifies trends in component aging or performance degradation, providing a scientific basis for device maintenance and replacement. The generation of a first early warning signal provides timely warnings before device components fail, reducing device failure rates and avoiding potential risks to users. Optical sensing technology extracts optical parameters during contact between the user's skin and the device, enabling real-time monitoring of the user's skin condition, improving device monitoring accuracy and data richness. Biomechanical modeling of optical sensing data generates skin stress distribution data, providing a scientific basis for identifying potential skin risks. Skin micro-damage prediction data supports risk control during medical cosmetic device operation, reducing potential damage to the user's skin. A second early warning signal is generated based on this skin micro-damage prediction data, further improving the early warning mechanism. The first early warning signal focuses on the device's status, while the second focuses on user safety, establishing a multi-layered, comprehensive monitoring and early warning system. Combined with dual monitoring of the device and the user, it can quickly identify abnormal device operation and changes in the user's skin condition, significantly improving operational safety. Preemptive identification of device-induced skin damage can optimize the operation process of medical aesthetic equipment and enhance user experience and trust.

[0027] Preferably, step S22 includes the following steps:

[0028] Step S221: extracting equipment bearing operating parameters from equipment key component operating parameters to obtain equipment bearing operating data, wherein the equipment bearing operating data includes equipment bearing vibration data and equipment bearing temperature data;

[0029] Step S222: performing envelope demodulation on the equipment bearing vibration data to generate equipment bearing vibration characteristic data; performing fluctuation extraction processing on the bearing temperature data to generate equipment bearing temperature characteristic data; performing time series correlation processing on the equipment bearing vibration characteristic data and the equipment bearing temperature characteristic data to generate coupling characteristic data;

[0030] Step S223: Calculate the vibration-temperature coupling coefficient on the coupling characteristic data to generate coupling index data; perform state mapping on the coupling index data to generate equipment health assessment data; perform trend fitting on the equipment health assessment data to generate long-term performance degradation trend data of key equipment components;

[0031] Step S224: generating a first warning signal for the long-term performance degradation trend data of key components of the equipment based on a preset first signal frequency, and obtaining a first warning signal for operation monitoring.

[0032] This invention uses multi-dimensional monitoring of the vibration and temperature of key equipment components (such as bearings) to comprehensively assess the equipment's operating status and proactively identify potential fault sources. Combining multimodal data such as vibration and temperature for time-series correlation processing and coupled analysis significantly improves the accuracy of equipment fault prediction, particularly in identifying long-term performance degradation trends. Generating timely operational health feedback from equipment health assessment data helps operations teams conduct comprehensive, real-time assessments of equipment status and ensure stable operation. Fitting analysis based on long-term performance degradation trends accurately identifies performance degradation trends in key equipment components, facilitating proactive maintenance or replacement planning and reducing repair costs. Generating a first warning signal based on preset frequency thresholds allows maintenance personnel to quickly take action based on different warning signals to prevent further escalation. Fusion analysis of vibration and temperature data enhances awareness of equipment operating status, making it particularly suitable for complex equipment environments and ensuring comprehensive and accurate equipment monitoring. Promptly identifying and remediating potential equipment failures helps maintain equipment stability and efficiency, reduces downtime, and improves overall reliability.

[0033] Preferably, step S24 includes the following steps:

[0034] Step S241: performing perception area calculation on the skin contact optical perception data to obtain the skin contact perception area; performing three-dimensional geometric reconstruction of the skin contact surface on the skin contact optical perception data based on the skin contact perception area to generate three-dimensional geometric data of the skin contact surface;

[0035] Step S242: performing skin-layer stress analysis on the three-dimensional geometric data of the skin contact surface to generate skin stress distribution data, wherein the skin-layer stress analysis includes skin surface stress analysis and skin deep layer stress analysis; performing stress extreme value screening on the skin stress distribution data to obtain skin stress distribution extreme value data;

[0036] Step S243: Potential damage identification is performed using the preset skin damage stress threshold and the skin stress distribution extreme value data. When the skin stress distribution extreme value data is greater than the preset skin damage stress threshold, stress concentration points are marked on the skin stress distribution data based on the skin stress distribution extreme value data to generate stress concentration points.

[0037] Step S244: Using the stress concentration points, the skin stress distribution extreme value data is screened for remaining extreme value points to obtain remaining skin stress distribution extreme value data; the remaining skin stress distribution extreme value data is marked as skin stress distribution extreme value data, and step S243 is repeatedly performed until the skin stress distribution extreme value data is less than or equal to a preset skin damage stress threshold, thereby generating a stress concentration area;

[0038] Step S245: Identify potential skin risks based on the three-dimensional geometric data of the skin contact surface according to the stress concentration area, and generate skin micro-injury prediction data; generate a second warning signal for the skin micro-injury prediction data based on the preset first signal frequency to obtain a second warning signal for operation monitoring.

[0039] The present invention accurately captures the skin contact surface morphology through three-dimensional geometric reconstruction of optically sensed skin contact data, providing high-precision three-dimensional data support for subsequent stress analysis and potential damage identification. By analyzing stress in both the surface and deep layers of the skin, the stress distribution of the skin under the action of medical cosmetic devices can be comprehensively assessed, identifying stress concentration areas at different levels and ensuring comprehensive attention to skin health. By screening extreme values in the skin stress distribution and marking stress concentration points, potential skin damage risks can be identified in advance, allowing for timely detection, preventing the occurrence of micro-injuries, and reducing the cumulative effects of damage. Generating a second early warning signal based on the skin micro-injury prediction data can provide timely fault warnings, prevent skin damage, and enhance users' sense of security and trust in the device. By identifying stress concentration areas, potentially high-risk areas of the skin can be accurately located, optimizing device operating parameters to ensure that excessive pressure is not applied to these areas, thereby protecting the skin from damage. By continuously looping through the steps, the system stops only when the extreme value of the stress distribution data is less than or equal to a preset threshold. The early warning strategy can be adaptively adjusted based on dynamic changes, achieving intelligent and refined risk identification and management. Through precise stress analysis and damage identification, the risk of skin damage caused by improper equipment operation is greatly reduced, and the safety and reliability of medical beauty equipment are improved.

[0040] Preferably, identifying potential skin risks based on the three-dimensional geometric data of the skin contact surface according to the stress concentration area includes:

[0041] Contact stress characteristics are extracted from stress concentration areas to obtain contact stress characteristic data. The contact stress characteristic data are divided into data sets to generate model training sets and model test sets. The model training sets are trained using a convolutional neural network algorithm to generate a skin micro-injury prediction model.

[0042] The skin micro-injury prediction pre-model is optimized and iterated using the model test set to generate a skin micro-injury prediction model; the three-dimensional geometric data of the skin contact surface is imported into the skin micro-injury prediction model to identify potential skin risks and generate skin micro-injury prediction data.

[0043] By extracting contact stress features from stress concentration areas, this method accurately captures stress information in contact areas, providing a high-quality data foundation for subsequent microdamage prediction and improving the accuracy of risk assessment. The contact stress feature data is partitioned into training and test sets, ensuring data diversity and representativeness during training, thereby enhancing the model's generalization and prediction accuracy. Using a convolutional neural network (CNN) algorithm to train the model on the training set, the powerful feature learning capabilities of deep learning are leveraged to extract potential microdamage patterns from complex stress data and generate a pre-model for skin microdamage prediction. Model optimization and iteration using the test set allows for continuous adjustment and refinement of the skin microdamage prediction model, ensuring high accuracy and reliability in practical applications and effectively avoiding false positives and false negatives. Inputting three-dimensional geometric data of the skin contact surface into the optimized skin microdamage prediction model enables real-time and accurate identification of potential skin risks, providing users with timely risk alerts and preventing skin damage. The application of the skin microdamage prediction model enables intelligent assessment of skin risks based on each user's specific circumstances, providing personalized care recommendations and treatment plans, and improving user experience and safety. Through accurate micro-damage prediction, it is possible to timely identify damage to the skin caused by device operation, avoid excessive pressure or improper use of the device, and thus improve the safety of medical cosmetic equipment.

[0044] Preferably, step S3 includes the following steps:

[0045] Step S31: integrating the first operation monitoring warning signal and the second operation monitoring warning signal to generate a medical cosmetic equipment operation monitoring warning signal;

[0046] Step S32: Upload the medical beauty equipment operation monitoring and warning signals to the cloud platform for monitoring and warning triggering, and generate equipment monitoring and warning triggering data;

[0047] Step S33: Perform trigger timing frequency analysis on the equipment monitoring and early warning trigger data to generate equipment monitoring and early warning trigger frequency data;

[0048] Step S34: construct a trigger decision for the equipment monitoring warning trigger data based on the equipment monitoring warning trigger frequency data to generate medical beauty equipment operation warning decision data.

[0049] By integrating the first and second warning signals from operational monitoring, this invention comprehensively considers the device's operating status and the risk of skin micro-injury, improving the accuracy and reliability of warning signals and avoiding false positives or missed alerts caused by a single signal. Uploading the operational monitoring warning signals of medical cosmetic devices to a cloud platform enables real-time remote monitoring and data processing of the device's status. Leveraging the cloud platform's powerful computing and storage capabilities, the device's operational status is continuously and accurately monitored and analyzed. By triggering and monitoring the device's monitoring warning signals, device anomalies or potential risks can be detected in real time and provided with immediate feedback. This triggering mechanism enhances the intelligent and adaptive capabilities of device operation. Time-series frequency analysis of device monitoring warning trigger data reveals potential device failure modes, helping maintenance teams detect anomalies earlier and take necessary remedial measures, effectively reducing the risk of equipment failure. Trigger decision-making data generated based on device monitoring warning trigger frequency data provides precise decision support, helping operators and managers make more informed preventive and maintenance decisions, thereby reducing the probability of equipment failure and safety incidents. Through trigger-series frequency analysis, the system can dynamically adjust warning strategies based on the device's actual operating conditions, achieving system self-optimization and enhancing the intelligent level of device management.

[0050] Preferably, step S4 includes the following steps:

[0051] Step S41: collecting decision feedback data on the medical cosmetic equipment operation warning decision data to obtain warning decision feedback data; performing a warning accuracy assessment on the medical cosmetic equipment operation warning decision data based on the warning decision feedback data to generate operation monitoring warning accuracy assessment data;

[0052] Step S42: Based on the operation monitoring and early warning accuracy evaluation data, the early warning signal of the operation monitoring and the second early warning signal of the operation monitoring are adjusted to perform the operation parameter monitoring and early warning optimization operation of the medical cosmetic equipment.

[0053] By collecting early warning decision feedback data and evaluating the accuracy of medical cosmetic equipment's operational early warning decision data based on this data, the present invention enables dynamic optimization of the early warning system, ensuring continuous improvement and enhancing its accuracy, while reducing false alarms and missed alerts. The collection and evaluation of early warning decision feedback data helps the equipment monitoring system better adapt to changes in the actual operating environment, thereby enhancing the system's flexibility and relevance and improving monitoring effectiveness. By utilizing early warning accuracy evaluation data, the system can promptly adjust early warning strategies based on actual feedback, thereby optimizing early warning signals for operational monitoring in real time and improving the accuracy and response speed of equipment monitoring. Through this continuously optimized early warning mechanism, medical cosmetic equipment can respond more promptly to potential risks, effectively preventing equipment failures or safety incidents, thereby ensuring the safety of users and equipment. Based on the evaluation and optimization of feedback data, the system achieves more intelligent early warning operations, not only automatically detecting and predicting equipment anomalies but also self-adjusting according to operational conditions, gradually improving the overall intelligence level of the equipment. By adjusting early warning signals based on early warning accuracy evaluation data, early warning system parameters can be optimized based on actual operational conditions, ensuring that each monitoring task of the equipment is performed optimally, improving the stability and efficiency of equipment operation. Accurate early warning signal adjustments can provide reliable data support for equipment operators and managers, helping them to more accurately diagnose problems and develop response strategies, thereby improving decision-making efficiency in equipment maintenance and troubleshooting.

[0054] In this specification, a medical cosmetic device operating parameter monitoring and early warning system is provided, which is used to execute the above-mentioned medical cosmetic device operating parameter monitoring and early warning method. The medical cosmetic device operating parameter monitoring and early warning system includes:

[0055] The data fusion module is used to obtain medical beauty equipment data; perform equipment range analysis on the medical beauty equipment data to generate medical beauty equipment range data; integrate equipment monitoring parameters through multi-source sensors based on the medical beauty equipment range data to generate standard medical beauty equipment multimodal monitoring data;

[0056] The monitoring and early warning module is used to monitor the long-term performance degradation trend of the multimodal monitoring data of standard medical cosmetic equipment and generate long-term performance degradation trend data of key equipment components; generate a first early warning signal based on the long-term performance degradation trend data of key equipment components to obtain a first early warning signal for operation monitoring; perform biomechanical modeling on the multimodal monitoring data of standard medical cosmetic equipment to generate skin stress distribution data; and generate a second early warning signal based on the skin stress distribution data to obtain a second early warning signal for operation monitoring;

[0057] The early warning prediction module is used to upload the first early warning signal of operation monitoring and the second early warning signal of operation monitoring to the cloud platform for monitoring and early warning trigger frequency analysis, and generate equipment monitoring and early warning trigger frequency data; based on the equipment monitoring and early warning trigger frequency data, trigger decision construction is carried out to generate medical beauty equipment operation early warning decision data;

[0058] The early warning optimization module is used to evaluate the early warning accuracy of the medical beauty equipment operation early warning decision data and generate operation monitoring early warning accuracy evaluation data; based on the operation monitoring early warning accuracy evaluation data, the early warning signal of the operation monitoring first early warning signal and the operation monitoring second early warning signal are adjusted to perform the operation parameter monitoring and early warning optimization operation of the medical beauty equipment.

[0059] The beneficial effects of the present invention lie in that, through multi-source sensor integration and device range analysis, the data fusion module can comprehensively and accurately collect device operating data, ensuring that all important device parameters are monitored. This multimodal data fusion provides a reliable foundation for subsequent analysis, improves data accuracy and comprehensiveness, and avoids bias caused by single sensor data. By monitoring long-term performance degradation trends and biomechanical modeling, potential device failure risks can be predicted in advance. A second warning signal is generated based on skin stress distribution to ensure that device operation matches patient skin reactions, minimizing operational risks. The generated warning signal provides important early warning information for device maintenance, effectively extending the device's service life and ensuring the stability of treatment effects. By uploading warning signals to a cloud platform and performing trigger frequency analysis, the module can provide real-time monitoring of device operating status and optimize the warning system based on trigger frequency, avoiding over-warning and under-reporting, thereby enhancing the intelligence level of warning. In addition, the trigger decision-making structure can dynamically adjust the device's monitoring strategy, ensuring the flexibility and adaptability of the warning system and improving device management efficiency. By evaluating and adjusting the accuracy of warnings, the accuracy and reliability of the warning system are further improved. Optimizing early warning signals based on evaluation results dynamically adapts to the device's actual operating status, reducing the likelihood of false alarms and missed alerts, and ensuring operational safety and the stability of treatment outcomes. This early warning optimization process empowers the entire system with continuous optimization and self-adjustment capabilities, enhancing the intelligence and efficiency of medical cosmetic equipment. Therefore, through multimodal data integration, long-term performance trend analysis, biomechanical modeling, and intelligent early warning decision optimization, this invention improves the reliability and intelligence of medical cosmetic equipment operating parameter monitoring and early warning systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 A schematic flow chart of the steps of a method for monitoring and early warning the operating parameters of medical cosmetic equipment;

[0061] Figure 2 for Figure 1 Detailed implementation steps of step S2 in FIG.

[0062] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0063] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0064] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. It is obvious that the embodiments described are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts are within the scope of protection of the present invention.

[0065] In addition, the accompanying drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. Identical reference numerals in the figures denote identical or similar parts, and thus repetitive descriptions thereof will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor and / or microcontroller approaches.

[0066] It should be understood that although the terms "first," "second," and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are used solely to distinguish one element from another. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element, without departing from the scope of the exemplary embodiments. The term "and / or" as used herein includes any and all combinations of one or more of the listed associated items.

[0067] To achieve this, please refer to Figures 1 to 3 A method for monitoring and early warning the operating parameters of medical cosmetic equipment comprises the following steps:

[0068] Step S1: Acquire medical cosmetic equipment data; perform equipment range analysis on the medical cosmetic equipment data to generate medical cosmetic equipment range data; integrate equipment monitoring parameters using multi-source sensors based on the medical cosmetic equipment range data to generate standard medical cosmetic equipment multimodal monitoring data;

[0069] Step S2: Perform long-term performance degradation trend monitoring on the multimodal monitoring data of standard medical cosmetic equipment to generate long-term performance degradation trend data of key components of the equipment; generate a first warning signal based on the long-term performance degradation trend data of key components of the equipment to obtain a first warning signal for operation monitoring; perform biomechanical modeling on the multimodal monitoring data of standard medical cosmetic equipment to generate skin stress distribution data; generate a second warning signal based on the skin stress distribution data to obtain a second warning signal for operation monitoring;

[0070] Step S3: Uploading the first operation monitoring warning signal and the second operation monitoring warning signal to the cloud platform for monitoring warning trigger frequency analysis to generate equipment monitoring warning trigger frequency data; constructing a trigger decision based on the equipment monitoring warning trigger frequency data to generate medical beauty equipment operation warning decision data;

[0071] Step S4: Evaluate the accuracy of the warning decision data for the operation of medical cosmetic equipment to generate operation monitoring warning accuracy evaluation data; adjust the warning signals of the first warning signal of operation monitoring and the second warning signal of operation monitoring based on the operation monitoring warning accuracy evaluation data to perform the operation parameter monitoring and warning optimization operation of the medical cosmetic equipment.

[0072] In the embodiment of the present invention, reference Figure 1 FIG. 1 is a flow chart showing the steps of a method for monitoring and warning the operating parameters of a medical cosmetic device according to the present invention. In this example, the method for monitoring and warning the operating parameters of a medical cosmetic device includes the following steps:

[0073] Step S1: Acquire medical cosmetic equipment data; perform equipment range analysis on the medical cosmetic equipment data to generate medical cosmetic equipment range data; integrate equipment monitoring parameters using multi-source sensors based on the medical cosmetic equipment range data to generate standard medical cosmetic equipment multimodal monitoring data;

[0074] In this embodiment of the present invention, medical aesthetic device data is collected through embedded sensors, device control systems, and external monitoring systems. Key data includes, but is not limited to: device operating data: including parameters such as laser power, RF current, temperature, pressure, and vibration; device control data: operating instructions issued by the control system, device on / off status, and operating mode; and device environmental data: including temperature, humidity, and electromagnetic field strength in the device's surroundings. Data is collected in real time through a sensor network (such as temperature sensors, pressure sensors, and optical sensors). A data recording module (such as a PLC system or embedded microcontroller) digitally stores the device's operating parameters, control commands, and environmental change data and uploads them to a cloud platform. The collected medical aesthetic device data undergoes preliminary cleaning to remove noise and outliers and standardize the data format. Physical modeling is performed using the propagation characteristics of the signals emitted by the device (such as laser and RF signals) combined with the device's operating parameters (such as power and frequency) to infer the spatial distribution of the device's range of action. Actual data from the device's sensors, such as laser irradiation point and RF electrode temperature, is used to adjust model parameters and ensure accuracy. Combining device parameters with biomedical knowledge, the device's range of action is determined, identifying the skin layer, depth, and impact area. This includes determining the contact area between the device and the skin's surface. By calculating the device's energy conduction and signal attenuation, the device's deeper impact is inferred, and the device's range of action data is output. Based on this range data, multi-source sensors are used to collect additional physiological parameters, further enhancing the device's monitoring capabilities and generating standard multimodal monitoring data for medical aesthetic devices. These sensors include skin temperature sensors, heart rate sensors, and sweat gland sensors, which collect real-time user physiological data and provide physiological feedback on the device's effects. Sensors such as temperature and humidity sensors, radiation detection sensors, and electromagnetic field sensors monitor the device's operating environment to ensure it operates within appropriate conditions. Vibration sensors, power sensors, and current sensors monitor the device's operating status to ensure stability and safety. Data from different sensors is fused and processed. A time synchronization algorithm is used to ensure temporal consistency between sensor data, and data interpolation and smoothing algorithms are used to optimize data from different sensors to enable fusion under the same standard. Using data integration methods, the range data of medical cosmetic equipment, user physiological data, environmental data and equipment status data are comprehensively processed to form a multi-dimensional monitoring data set.

[0075] Step S2: Perform long-term performance degradation trend monitoring on the multimodal monitoring data of standard medical cosmetic equipment to generate long-term performance degradation trend data of key components of the equipment; generate a first warning signal based on the long-term performance degradation trend data of key components of the equipment to obtain a first warning signal for operation monitoring; perform biomechanical modeling on the multimodal monitoring data of standard medical cosmetic equipment to generate skin stress distribution data; generate a second warning signal based on the skin stress distribution data to obtain a second warning signal for operation monitoring;

[0076] In this embodiment of the present invention, real-time operating data of key components (such as motors, heaters, and sensors) is recorded by collecting multimodal monitoring data from the device, including sensor data such as temperature, pressure, current, and vibration. The collected data is then de-noised and standardized to eliminate interference from external environmental factors and ensure data accuracy. Based on the analysis results, long-term performance degradation trend data for key components of the device is generated, reflecting the operating status and degradation rate of each component. Performance degradation thresholds for each key component are set based on device design standards and historical operating data. When the performance degradation rate of a component exceeds the set threshold, a first warning signal is generated, indicating that the device is at risk of failure or requires maintenance. Different levels of warning signals (e.g., low, medium, and high) are generated based on the failure risk of different components. Finite element analysis (FEA) or other biomechanical modeling methods are used to construct a stress-strain model of the skin based on the device's operating mode and monitoring data. Multimodal data such as pressure and temperature are collected during actual device use and input into the biomechanical model to simulate the stress distribution on the skin under the action of the device. Based on the simulation results, skin stress distribution data is generated, reflecting the pressure distribution and stress variations in different areas, as well as the risk of skin damage. A safety threshold for skin stress is set based on the skin's physiological tolerance. When the stress applied by the device on the skin exceeds the safety threshold, a second warning signal is generated, indicating that the device is causing skin damage or excessive stress. Depending on the severity of the stress distribution, different levels of warning signals are generated to facilitate timely adjustment of device parameters or cessation of use.

[0077] Step S3: Uploading the first operation monitoring warning signal and the second operation monitoring warning signal to the cloud platform for monitoring warning trigger frequency analysis to generate equipment monitoring warning trigger frequency data; constructing a trigger decision based on the equipment monitoring warning trigger frequency data to generate medical beauty equipment operation warning decision data;

[0078] In this embodiment of the present invention, a first warning signal (a warning signal indicating performance degradation of a key device component) and a second warning signal (a warning signal indicating excessive skin stress) are uploaded to a cloud platform via a secure data transmission protocol (such as HTTPS or MQTT). The uploaded data should include information such as the warning signal's trigger time, signal type, and warning level. A dedicated data storage structure (such as a database or data warehouse) is created on the cloud platform to store the uploaded warning signal data. Data cleaning and preprocessing are performed to eliminate invalid or duplicate data and ensure the accuracy of the signal trigger data. Leveraging the cloud platform's powerful data processing capabilities, a time series analysis of signal trigger frequencies is performed to calculate the trigger frequencies of different types of warning signals (e.g., daily, weekly, or monthly triggering times). Periodic and trend analysis is performed based on factors such as device usage and environmental conditions. Changes in the trigger frequency of each warning signal are calculated to generate device monitoring warning trigger frequency data. This data reflects the overall health of the device, particularly potential issues with key components and skin stress. Machine learning or statistical analysis methods, such as cluster analysis and anomaly detection, are used to identify normal warning trigger frequency patterns under different device operating conditions. Compare the monitoring and early warning trigger frequencies of different devices to establish normal and abnormal patterns for early warning signals, identifying frequent or abnormal triggering frequencies. Based on monitoring and early warning trigger frequency data, develop equipment operation early warning decision rules. For example, when the performance degradation warning frequency of a key component reaches a certain value, maintenance or shutdown is triggered. Or, when the skin stress warning trigger frequency increases abnormally, it indicates the need to adjust device settings or implement safety measures. Early warning decision rules can also be adjusted based on the device's actual usage environment, maintenance history, and operating load, ensuring dynamic and adaptive decision-making. Based on historical trigger frequency data and continuously collected real-time data, data mining or deep learning models are used to optimize decision models for more accurate decisions. By establishing predictive models, early warnings of equipment failures and risks are provided to ensure safe operation. Based on trigger frequency analysis and early warning decision rules, medical aesthetic equipment operation early warning decision data is generated. This data includes decisions on whether the device requires immediate shutdown, maintenance, or adjustments, such as stopping use, adjusting device parameters, or undergoing professional testing. The frequency and severity of early warning triggers determine the timeliness of the early warning signal (e.g., immediate, short-term, or long-term follow-up). The generated medical beauty equipment operation warning decision data is fed back to the equipment control system or operator, and corresponding operational measures are taken in a timely manner, such as stopping the equipment, adjusting parameters or performing repairs.

[0079] Step S4: Evaluate the accuracy of the warning decision data for the operation of medical cosmetic equipment to generate operation monitoring warning accuracy evaluation data; adjust the warning signals of the first warning signal of operation monitoring and the second warning signal of operation monitoring based on the operation monitoring warning accuracy evaluation data to perform the operation parameter monitoring and warning optimization operation of the medical cosmetic equipment.

[0080] In an embodiment of the present invention, actual failure events and warning data occurring during the operation of medical cosmetic devices are collected, including device operation logs, fault detection data, and historical warning trigger data. Actual failure events are annotated to determine which failures were triggered by warning signals and which were false alarms or missed alarms. Key indicators for evaluating warning accuracy, such as precision, recall, and F1 score, are defined: Precision: The proportion of warning signals correctly identified. Recall: The proportion of all actual failure events successfully identified by warning signals. F1 score: The harmonic mean of precision and recall, a comprehensive measure of warning accuracy. A warning accuracy evaluation model is constructed based on machine learning or statistical analysis methods. Warning signals in historical data are compared with actual failure events to calculate and evaluate the accuracy of warning signals. A confusion matrix can be used to evaluate the effectiveness of warning classification, distinguishing between correct warnings, false alarms, missed alarms, and correct absence of warnings. Based on the evaluation model, warning accuracy data is calculated for each device and each warning signal type, and an evaluation report is generated. This data reflects the reliability and effectiveness of warning signals in actual device operation. Based on the evaluation results, analyze the accuracy of each warning signal and identify the patterns of false alarms and missed alarms. Optimize and adjust warning signals with frequent false alarms and missed alarms. For signals with more false alarms, the severity of the trigger conditions needs to be increased to avoid premature or excessive triggering of warnings. For signals with more missed alarms, the trigger conditions can be adjusted to lower the trigger threshold to ensure that potential problems can be identified earlier. Based on the accuracy evaluation results, a dynamic threshold adjustment method is adopted. For example, based on the frequency of use of the equipment, the operating environment and historical fault data, the threshold of the warning trigger is adaptively adjusted to avoid false alarms or missed alarms caused by setting the threshold too high or too low. Optimize the triggering logic of the first warning signal and the second warning signal of the operation monitoring, and adjust the parameters in the signal detection algorithm based on the accuracy evaluation data.

[0081] Preferably, step S1 includes the following steps:

[0082] Step S11: Acquire medical beauty equipment data;

[0083] Step S12: extracting text features from the medical beauty equipment data to generate medical beauty equipment text feature data; performing text semantic analysis on the medical beauty equipment text feature data to generate medical beauty equipment text semantic analysis data;

[0084] Step S13: performing a medical beauty device scope analysis on the medical beauty device text semantic analysis data to generate medical beauty device scope data; integrating device monitoring parameters using multi-source sensors based on the medical beauty device scope data to generate medical beauty device multimodal monitoring data;

[0085] Step S14: Preprocess the multimodal monitoring data of medical cosmetic equipment to generate standard multimodal monitoring data of medical cosmetic equipment, wherein the data preprocessing includes data cleaning, data denoising, data missing value filling and data standardization.

[0086] In this embodiment of the present invention, basic device information, including device name, model, and function description, is obtained through a database interface provided by the device manufacturer. Real-time device operating parameters, such as temperature, power, and light wave frequency, are obtained by combining actual usage data from medical institutions. Multi-source data acquisition techniques are used to supplement other necessary data from device sensors, user operation logs, and relevant literature. Natural language processing techniques (such as TF-IDF or Word2Vec) are used to extract key feature words from medical cosmetic device data, such as device function, operating environment, and scope of application, to generate a structured data table containing device feature information (medical cosmetic device text feature data). Pre-trained language models (such as BERT or GPT) are used to semantically parse the device text feature data to understand its contextual associations and potential meaning. This outputs semantically parsed text data for medical cosmetic devices, including device function semantic categories, descriptions of applicable populations, and other semantic information. Based on this semantically parsed text data, a classification algorithm (such as SVM or logistic regression) is used to analyze the device's scope of application and generate data on the device's scope of application. This scope of application is mapped to specific application scenarios, such as cosmetic procedure type and skin treatment area. Collect device operating status (e.g., energy output, operating environment parameters) through multi-source sensors. Utilize data fusion techniques (e.g., weighted averaging or Kalman filtering) to integrate monitoring parameters and generate multimodal monitoring data for medical aesthetic devices. Remove redundant or abnormal data, such as duplicate records or data points that clearly fall outside the normal range. Apply signal processing algorithms (e.g., wavelet denoising or low-pass filtering) to remove noise signals from multimodal data. Use interpolation, regression prediction, or deep learning methods to fill in missing values and ensure data integrity. Normalize multimodal monitoring data (e.g., using Z-Score or Min-Max normalization) to make it suitable for subsequent analysis and modeling needs.

[0087] Preferably, integrating equipment monitoring parameters through multi-source sensors based on the range data of medical cosmetic equipment includes:

[0088] Using the skin condition sensor to collect the user's real-time physiological signals within the range of the medical beauty device, the user's real-time physiological signals are obtained; the user's real-time physiological signals are conditioned to generate a real-time physiological conditioning signal;

[0089] Perform analog-to-digital conversion on the user's real-time physiological conditioning signal to generate the user's real-time physiological data; perform data change correlation analysis on the user's real-time physiological data and medical beauty equipment data to generate monitoring correlation change data; use environmental sensors to collect environmental parameters based on the monitoring correlation change data to obtain the environmental data of the medical beauty equipment;

[0090] The medical beauty equipment data, the user's real-time physiological data and the medical beauty equipment's working environment data are integrated and displayed to generate multimodal monitoring data of medical beauty equipment.

[0091] In an embodiment of the present invention, a skin condition sensor is placed within the range of a medical cosmetic device to monitor a user's skin temperature, humidity, conductivity, and other physiological signals in real time. The sensor is synchronized with the control system of the medical cosmetic device to ensure real-time and accurate signal acquisition. The skin condition sensor acquires the user's real-time physiological signals (such as skin impedance, surface temperature rise, and microcirculatory changes). The acquired signals are recorded in a real-time monitoring system. Analog signal processing techniques are used to amplify, filter, and offset-adjust the acquired real-time physiological signals to remove interference. A band-pass filter is applied to eliminate low-frequency drift and high-frequency noise, ensuring signal stability and validity. Conditioned signal data with enhanced physiological relevance is output as input for subsequent signal processing. The user's real-time physiological conditioning signal is converted from analog to digital. A high-precision analog-to-digital converter (e.g., a 16-bit ADC) is used to ensure fine resolution of the sampled signal. The digitized real-time user physiological data is output for subsequent analysis. A correlation analysis model is established based on the user's real-time physiological data and medical cosmetic device data (such as energy output and contact pressure) to calculate the changing relationship between the two. Use correlation analysis (such as the Pearson correlation coefficient) or dynamic time warping (DTW) algorithms to quantify the correlation between changes in data. Output monitoring correlation change data that reflects the changing patterns between device effects and user physiological responses. Place environmental sensors within the range of the medical aesthetic device to monitor environmental parameters such as temperature, humidity, light intensity, and air quality. Collect real-time environmental parameters and synchronize them with the monitoring correlation change data. Output precise data related to the device's operating environment. Utilize multimodal data fusion techniques (such as principal component analysis or multi-kernel learning) to integrate and process medical aesthetic device data, real-time user physiological data, and data on the environment in which the device is used. Output integrated, standardized multimodal monitoring data, including device operating status, user physiological responses, and environmental status data. This data is used for device performance optimization, user experience evaluation, and safety monitoring.

[0092] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0093] Step S21: extracting operating parameters of key components of a standard medical cosmetic device from multimodal monitoring data to obtain operating parameters of key components of the device, wherein the key components of the device include a laser, a radio frequency electrode, and a cooling system;

[0094] Step S22: monitoring the long-term performance degradation trend of the operating parameters of the key components of the equipment to generate long-term performance degradation trend data of the key components of the equipment; generating a first early warning signal based on the long-term performance degradation trend data of the key components of the equipment to obtain a first early warning signal for operation monitoring;

[0095] Step S23: extracting skin contact optical perception data from the multimodal monitoring data of the standard medical cosmetic equipment to obtain skin contact optical perception data;

[0096] Step S24: Perform biomechanical modeling on the skin contact optical perception data to generate skin stress distribution data; identify potential risks based on the skin stress distribution data to generate skin micro-injury prediction data; generate a second warning signal based on the skin micro-injury prediction data to obtain a second warning signal for operation monitoring.

[0097] In this embodiment of the present invention, by identifying key components of the device, including the laser, RF electrode, and cooling system, and combining the device's structural design with multimodal monitoring data, the operating parameter collection range is determined. Parameters such as laser power, wavelength, pulse frequency, and spot energy density are extracted, and real-time data is recorded using optical sensors. Parameters such as the RF electrode's output current, voltage, energy density, and electrode temperature are acquired using electromagnetic and temperature sensors. The cooling system's circulating fluid flow rate, temperature gradient, and cooling efficiency are recorded using flow sensors and thermocouples. This data is integrated to form the operating parameters of key components of the device, which serve as the basis for device performance analysis. Based on these key component operating parameters, time series analysis models (such as ARIMA and LSTM) are used to predict long-term performance trends and monitor performance degradation. Trend modeling is performed for indicators such as laser attenuation rate, RF electrode aging, and cooling system efficiency decline. Performance degradation trend data for each key component is output, quantifying its operating lifespan and rate of performance degradation. Warning thresholds are set (e.g., a 20% drop in laser power or a cooling efficiency below 85%), triggering a first warning signal when the degradation trend approaches or exceeds the threshold. Outputs a first operational monitoring warning signal, indicating that the device requires maintenance or component replacement. Optical sensors are placed at the point of contact between the medical cosmetic device and the user's skin to capture the reflectance spectrum, absorptivity, and scattering characteristics of the contact point. Optical data from the skin contact area (such as skin color changes and reflected light intensity) is collected and combined with an optical property analysis algorithm to extract key indicators. Outputs optical perception data related to skin contact as input for biomechanical modeling. Based on this optical perception data and combined with the biomechanical properties of the skin structure (such as elastic modulus and shear force), a skin stress distribution model is established. Finite element analysis (FEA) is used to simulate the stress distribution of the skin under the action of the device. Stress distribution data for different skin regions is calculated and output to identify high-stress areas. Based on this skin stress distribution data, a risk assessment algorithm is used to detect areas at risk of micro-injury, generate micro-injury prediction data, and quantify the potential risk level. A threshold for micro-injury prediction is set (e.g., if the stress exceeds a set safety value). When the predicted data exceeds the threshold, a second operational monitoring warning signal is triggered. Outputs a second operational monitoring warning signal, indicating the need to adjust device parameters or suspend operation.

[0098] Preferably, step S22 includes the following steps:

[0099] Step S221: extracting equipment bearing operating parameters from equipment key component operating parameters to obtain equipment bearing operating data, wherein the equipment bearing operating data includes equipment bearing vibration data and equipment bearing temperature data;

[0100] Step S222: performing envelope demodulation on the equipment bearing vibration data to generate equipment bearing vibration characteristic data; performing fluctuation extraction processing on the bearing temperature data to generate equipment bearing temperature characteristic data; performing time series correlation processing on the equipment bearing vibration characteristic data and the equipment bearing temperature characteristic data to generate coupling characteristic data;

[0101] Step S223: Calculate the vibration-temperature coupling coefficient on the coupling characteristic data to generate coupling index data; perform state mapping on the coupling index data to generate equipment health assessment data; perform trend fitting on the equipment health assessment data to generate long-term performance degradation trend data of key equipment components;

[0102] Step S224: generating a first warning signal for the long-term performance degradation trend data of key components of the equipment based on a preset first signal frequency, and obtaining a first warning signal for operation monitoring.

[0103] In an embodiment of the present invention, the vibration signal of the bearing is collected by using an acceleration sensor and a vibration sensor, and data such as the vibration amplitude, frequency, and acceleration are recorded to generate equipment bearing vibration data. A temperature sensor is used to monitor the operating temperature of the bearing in real time, and temperature change data is recorded to generate equipment bearing temperature data. This includes equipment bearing vibration data and equipment bearing temperature data, providing basic data for subsequent analysis. The equipment bearing vibration data is envelope demodulated, and the frequency characteristics are extracted using Hilbert transform or FFT (Fast Fourier Transform) to generate equipment bearing vibration characteristic data. The vibration characteristic data includes indicators such as envelope amplitude, frequency peak, and spectrum energy distribution. Fluctuation extraction is performed on the equipment bearing temperature data, and characteristics such as temperature fluctuation amplitude and temperature rise rate are analyzed to generate equipment bearing temperature characteristic data. Based on a time series model (such as the DTW dynamic time warping algorithm), the equipment bearing vibration characteristic data and the equipment bearing temperature characteristic data are correlated and analyzed to quantify the relationship between vibration and temperature and generate coupling characteristic data. Combined with the coupling characteristic data, the coupling coefficient between vibration and temperature is calculated. The formula is as follows: ;in is the coupling coefficient, and They are vibration characteristic data and temperature characteristic data respectively, is the covariance, and The standard deviations of vibration and temperature are used, respectively. Coupling index data is output to reflect the degree of interaction between vibration and temperature. The coupling index data is mapped to a device health status model (e.g., healthy, sub-healthy, or failure precursor) to generate device health assessment data. Health assessment data can be used to visually reflect device status through a health index (e.g., a scale of 0-1). Trend fitting analysis is performed on the device health assessment data, using regression models (e.g., linear regression or LSTM) to predict the long-term performance degradation trends of key device components and generate long-term performance degradation trend data. A first signal frequency threshold for early warning is set. The critical value of vibration frequency or temperature change is defined based on device operating standards and actual requirements. The long-term performance degradation trend data of key device components is compared with the first signal frequency threshold. When the trend data exceeds the threshold, a first early warning signal is generated, indicating an abnormality or potential failure. This signal can be displayed in real time on the device's monitoring system or transmitted to maintenance personnel via the communication module so that appropriate maintenance measures can be taken.

[0104] Preferably, step S24 includes the following steps:

[0105] Step S241: performing perception area calculation on the skin contact optical perception data to obtain the skin contact perception area; performing three-dimensional geometric reconstruction of the skin contact surface on the skin contact optical perception data based on the skin contact perception area to generate three-dimensional geometric data of the skin contact surface;

[0106] Step S242: performing skin-layer stress analysis on the three-dimensional geometric data of the skin contact surface to generate skin stress distribution data, wherein the skin-layer stress analysis includes skin surface stress analysis and skin deep layer stress analysis; performing stress extreme value screening on the skin stress distribution data to obtain skin stress distribution extreme value data;

[0107] Step S243: Potential damage identification is performed using the preset skin damage stress threshold and the skin stress distribution extreme value data. When the skin stress distribution extreme value data is greater than the preset skin damage stress threshold, stress concentration points are marked on the skin stress distribution data based on the skin stress distribution extreme value data to generate stress concentration points.

[0108] Step S244: Using the stress concentration points, the skin stress distribution extreme value data is screened for remaining extreme value points to obtain remaining skin stress distribution extreme value data; the remaining skin stress distribution extreme value data is marked as skin stress distribution extreme value data, and step S243 is repeatedly performed until the skin stress distribution extreme value data is less than or equal to a preset skin damage stress threshold, thereby generating a stress concentration area;

[0109] Step S245: Identify potential skin risks based on the three-dimensional geometric data of the skin contact surface according to the stress concentration area, and generate skin micro-injury prediction data; generate a second warning signal for the skin micro-injury prediction data based on the preset first signal frequency to obtain a second warning signal for operation monitoring.

[0110] In an embodiment of the present invention, the contact area is identified and the skin contact perception area is calculated using optical skin contact perception data. The contact perception area is calculated and quantified as area data using an integration method or image pixel statistics. Based on the skin contact perception area and combined with optical depth information, a reconstruction algorithm (such as a ray casting method or a point cloud fitting algorithm) is used to perform three-dimensional geometric reconstruction of the contact area, generating three-dimensional geometric data of the skin contact surface. This data describes the geometric characteristics of the skin contact surface, including shape, curvature, and contact depth. The three-dimensional geometric data of the skin contact surface is layered to distinguish between the surface and deep layers of the skin. Finite element analysis (FEA) is used to simulate the mechanical responses of the surface and deep layers of the skin and calculate the stress distribution. Skin surface stress data and deep skin stress data are output and integrated to generate skin stress distribution data. The skin stress distribution data is analyzed to identify stress extremes within the region and generate skin stress distribution extreme value data. Stress extremes include local maxima and minima, representing stress concentrations on the skin. The skin stress distribution extreme value data is compared with a preset skin damage stress threshold. If the stress extreme value data is greater than the threshold, it is marked as a potential damage area and a stress concentration point is generated. Based on the stress concentration point, the stress distribution data is located and the spatial coordinates of the stress concentration point are generated. Using the stress concentration point, the remaining extreme value points are screened out from the skin stress distribution extreme value data to generate the remaining skin stress distribution extreme value data. Repeat step S243 on the remaining extreme value data until the skin stress distribution extreme value data is less than or equal to the preset skin damage stress threshold. Mark and aggregate the stress concentration points to form a stress concentration area, which reflects the potential high-risk damage area of the skin. Based on the stress concentration area, the three-dimensional geometric data of the skin contact surface is analyzed to identify the damage area and generate skin micro-damage prediction data to describe the potential skin damage type, location and severity. Using the preset first signal frequency threshold, the skin micro-damage prediction data is converted into a second early warning signal. This signal reminds the equipment operator to take protective measures or adjust the equipment parameters to avoid further development of skin damage.

[0111] Preferably, identifying potential skin risks based on the three-dimensional geometric data of the skin contact surface according to the stress concentration area includes:

[0112] Contact stress characteristics are extracted from stress concentration areas to obtain contact stress characteristic data. The contact stress characteristic data are divided into data sets to generate model training sets and model test sets. The model training sets are trained using a convolutional neural network algorithm to generate a skin micro-injury prediction model.

[0113] The skin micro-injury prediction pre-model is optimized and iterated using the model test set to generate a skin micro-injury prediction model; the three-dimensional geometric data of the skin contact surface is imported into the skin micro-injury prediction model to identify potential skin risks and generate skin micro-injury prediction data.

[0114] In an embodiment of the present invention, stress distribution characteristics of the contact area are extracted based on the stress concentration areas, including stress peaks, stress gradients, stress concentration ranges, and directionality. Key features are extracted using algorithms such as principal component analysis (PCA) or statistical methods to generate contact stress characteristic data. The characteristic data is stored as vectors or tensors and serves as the basis for subsequent model training. The contact stress characteristic data is divided into a model training set and a model test set in a certain ratio (e.g., an 8:2 ratio). The training and test sets are ensured to contain representative samples of each type of stress characteristic data to improve the generalization capability of the model. The training and test sets are normalized to eliminate dimensionality effects. Data augmentation: The training set is randomly rotated, scaled, or noisy to generate more samples to improve the robustness of the model. A convolutional neural network (CNN) is used as the basic model architecture, characterized by its ability to extract local features and capture spatial information. Input layer: The input is contact stress characteristic data. Convolution layer: Multiple layers of convolution kernels extract the spatial pattern of the contact stress characteristics. Pooling layer: Downsampling reduces the data dimensionality while preserving key features. Fully connected layer: Maps the extracted features to potential damage predictions. Output layer: Outputs the predicted probability of skin microinjury risk. Using the model training set, an optimization algorithm (such as the Adam optimizer) is used to adjust the weight parameters. The loss function used is either cross-entropy loss or mean squared error (MSE), depending on the damage prediction task objective. The number of training epochs and batch size are set, and the model is trained until convergence. The model test set is input into the skin microinjury prediction pre-model to evaluate the model's prediction accuracy, recall, and F1 score. The error distribution in the prediction results is analyzed to identify deficiencies. The model is iteratively optimized using error samples, including adjusting the network structure (such as adding convolutional layers or neurons), changing the learning rate, or applying regularization (such as L2 regularization) to reduce overfitting. Optimization is continued until the model performance reaches the expected level. The optimized skin microinjury prediction model is output, demonstrating high prediction accuracy and generalization capability. The optimized skin microinjury prediction model is fed with 3D geometric data of the skin contact surface. The model automatically analyzes input data and identifies potential injury risks in the contact area, including injury type, extent, and severity. Risk identification results are output graphically or numerically. The model also outputs skin micro-injury prediction data, including predicted micro-injury location, probability, and risk level. This data can be used as a basis for further device parameter adjustments or early warning generation.

[0115] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0116] Step S31: integrating the first operation monitoring warning signal and the second operation monitoring warning signal to generate a medical cosmetic equipment operation monitoring warning signal;

[0117] Step S32: Upload the medical beauty equipment operation monitoring and warning signals to the cloud platform for monitoring and warning triggering, and generate equipment monitoring and warning triggering data;

[0118] Step S33: Perform trigger timing frequency analysis on the equipment monitoring and early warning trigger data to generate equipment monitoring and early warning trigger frequency data;

[0119] Step S34: construct a trigger decision for the equipment monitoring warning trigger data based on the equipment monitoring warning trigger frequency data to generate medical beauty equipment operation warning decision data.

[0120] In this embodiment of the present invention, a first operation monitoring warning signal (generated based on long-term performance degradation trend data of key device components) is received. A second operation monitoring warning signal (generated based on skin micro-injury prediction data) is received. Timestamps of the two warning signals are synchronized to ensure signal timing consistency. A signal integration algorithm (such as weighted fusion or signal priority determination) is used to integrate the two signals to generate a comprehensive medical cosmetic device operation monitoring warning signal. The integrated signal output includes the trigger probability, severity level, and trigger time of each signal. The medical cosmetic device operation monitoring warning signal is uploaded to a cloud platform via an encrypted transmission protocol (such as HTTPS or MQTT) to ensure the security and reliability of data transmission. A distributed database is used on the cloud platform to store the signal and record metadata such as trigger time, signal level, and device identification. The cloud platform monitors the warning signal in real time using built-in monitoring rules. Once a warning condition is triggered (e.g., the signal level exceeds a set threshold), the corresponding warning processing program is initiated, generating device monitoring warning trigger data. The device monitoring warning trigger data, including the trigger time series and trigger count of each warning signal, is obtained from the cloud platform. Based on the trigger data, a time series analysis algorithm (such as a fast Fourier transform (FFT)) is used to calculate the frequency distribution of the trigger signal, identifying the dominant frequency and periodic characteristics of the signal trigger. The signal frequency data is statistically analyzed to generate trigger frequency data, such as the average frequency, maximum frequency, and frequency fluctuation range. During the frequency analysis process, frequency anomalies are detected using a set abnormal frequency threshold and marked as trigger events. The device monitors and receives the trigger frequency data for early warning, including frequency characteristics and abnormal signal markers. The frequency data is analyzed based on preset trigger decision rules (such as threshold judgment rules or expert system rules). An example of a trigger decision rule is: if a signal frequency exceeds a set threshold and persists for a specific period, it is marked as a high-risk event. Based on the signal frequency trend, the future device operating status is predicted and the warning level is adjusted. Based on the trigger decision rules, medical aesthetic device operation warning decision data is generated, containing the following information: warning level (e.g., low, medium, high), warning type (e.g., device failure, skin risk), and response recommendations (e.g., adjusting device parameters, suspending operation). This medical aesthetic device operation warning decision data is uploaded to the cloud platform and pushed to relevant management systems or operation terminals for device adjustments and user notifications.

[0121] Preferably, step S4 includes the following steps:

[0122] Step S41: collecting decision feedback data on the medical cosmetic equipment operation warning decision data to obtain warning decision feedback data; performing a warning accuracy assessment on the medical cosmetic equipment operation warning decision data based on the warning decision feedback data to generate operation monitoring warning accuracy assessment data;

[0123] Step S42: Based on the operation monitoring and early warning accuracy evaluation data, the early warning signal of the operation monitoring and the second early warning signal of the operation monitoring are adjusted to perform the operation parameter monitoring and early warning optimization operation of the medical cosmetic equipment.

[0124] In an embodiment of the present invention, decision-execution feedback data is collected from medical cosmetic device users, operation and maintenance teams, or automated monitoring systems. This data includes, but is not limited to, changes in device operating status (e.g., changes in vibration and temperature), skin contact status records (e.g., micro-damage detection results), and user responses to device operations. Embedded sensors and data recording modules are used to automatically collect device operation-related data. Operational feedback, such as problem feedback or satisfaction scores, is collected through the user interface. The collected data is uploaded to a cloud platform for unified management and storage. Based on this decision feedback data, the accuracy of the operation monitoring early warning signals is evaluated. Key metrics include: the ratio of correct warnings to total warnings, the percentage of cases where warnings were not triggered but risks actually occurred, and the percentage of cases where warnings were triggered but risks did not actually occur. The operation monitoring early warning signals (first and second warning signals) are compared with the actual feedback data to generate a classification evaluation matrix (e.g., TP, FP, FN, TN) for the warning signals. Statistical methods are used to calculate comprehensive metrics, such as the F1 score and AUC value, to generate operation monitoring early warning accuracy evaluation data. This operation monitoring early warning accuracy evaluation data is used to optimize the generation logic of the first and second operation monitoring early warning signals. For situations with high false alarm rates, increase the threshold for triggering warning signals and reduce unnecessary warning signals. For situations with high missed alarm rates, lower the threshold for triggering warning signals and increase sensitivity. Based on historical accuracy evaluation data of warning signals, adjust the weight coefficients during signal fusion and optimize the signal integration results. Introduce machine learning algorithms (such as adaptive threshold algorithms or decision tree models) to dynamically adjust signal generation parameters based on newly collected feedback data. Reintegrate the adjusted first and second warning signals to generate a warning signal for monitoring the operation of medical cosmetic equipment. Based on the optimized warning signal, re-trigger the monitoring and adjustment of equipment operating parameters. Automatically adjust the operating parameters of key equipment components (such as laser power and cooling system temperature). Optimize skin contact conditions (such as applied pressure and duration) based on the adjusted second warning signal. Incorporate the optimized signal and its corresponding warning decision execution feedback data into the next round of accuracy evaluation to form a closed-loop optimization mechanism.

[0125] In this specification, a medical cosmetic device operating parameter monitoring and early warning system is provided, which is used to execute the above-mentioned medical cosmetic device operating parameter monitoring and early warning method. The medical cosmetic device operating parameter monitoring and early warning system includes:

[0126] The data fusion module is used to obtain medical beauty equipment data; perform equipment range analysis on the medical beauty equipment data to generate medical beauty equipment range data; integrate equipment monitoring parameters through multi-source sensors based on the medical beauty equipment range data to generate standard medical beauty equipment multimodal monitoring data;

[0127] The monitoring and early warning module is used to monitor the long-term performance degradation trend of the multimodal monitoring data of standard medical cosmetic equipment and generate long-term performance degradation trend data of key equipment components; generate a first early warning signal based on the long-term performance degradation trend data of key equipment components to obtain a first early warning signal for operation monitoring; perform biomechanical modeling on the multimodal monitoring data of standard medical cosmetic equipment to generate skin stress distribution data; and generate a second early warning signal based on the skin stress distribution data to obtain a second early warning signal for operation monitoring;

[0128] The early warning prediction module is used to upload the first early warning signal of operation monitoring and the second early warning signal of operation monitoring to the cloud platform for monitoring and early warning trigger frequency analysis, and generate equipment monitoring and early warning trigger frequency data; based on the equipment monitoring and early warning trigger frequency data, trigger decision construction is carried out to generate medical beauty equipment operation early warning decision data;

[0129] The early warning optimization module is used to evaluate the early warning accuracy of the medical beauty equipment operation early warning decision data and generate operation monitoring early warning accuracy evaluation data; based on the operation monitoring early warning accuracy evaluation data, the early warning signal of the operation monitoring first early warning signal and the operation monitoring second early warning signal are adjusted to perform the operation parameter monitoring and early warning optimization operation of the medical beauty equipment.

[0130] The beneficial effects of the present invention lie in that, through multi-source sensor integration and device range analysis, the data fusion module can comprehensively and accurately collect device operating data, ensuring that all important device parameters are monitored. This multimodal data fusion provides a reliable foundation for subsequent analysis, improves data accuracy and comprehensiveness, and avoids bias caused by single sensor data. By monitoring long-term performance degradation trends and biomechanical modeling, potential device failure risks can be predicted in advance. A second warning signal is generated based on skin stress distribution to ensure that device operation matches patient skin reactions, minimizing operational risks. The generated warning signal provides important early warning information for device maintenance, effectively extending the device's service life and ensuring the stability of treatment effects. By uploading warning signals to a cloud platform and performing trigger frequency analysis, the module can provide real-time monitoring of device operating status and optimize the warning system based on trigger frequency, avoiding over-warning and under-reporting, thereby enhancing the intelligence level of warning. In addition, the trigger decision-making structure can dynamically adjust the device's monitoring strategy, ensuring the flexibility and adaptability of the warning system and improving device management efficiency. By evaluating and adjusting the accuracy of warnings, the accuracy and reliability of the warning system are further improved. Optimizing early warning signals based on evaluation results dynamically adapts to the device's actual operating status, reducing the likelihood of false alarms and missed alerts, and ensuring operational safety and the stability of treatment outcomes. This early warning optimization process empowers the entire system with continuous optimization and self-adjustment capabilities, enhancing the intelligence and efficiency of medical cosmetic equipment. Therefore, through multimodal data integration, long-term performance trend analysis, biomechanical modeling, and intelligent early warning decision optimization, this invention improves the reliability and intelligence of medical cosmetic equipment operating parameter monitoring and early warning systems.

[0131] The present invention is therefore intended to be illustrative and non-restrictive in all respects, with the scope of the invention being defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the application documents are intended to be embraced therein.

[0132] The foregoing description is intended only to provide specific embodiments of the present invention, which will enable those skilled in the art to understand and implement the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown herein, but is to be construed in the widest possible manner consistent with the principles and novel features disclosed herein.

Claims

1. A method for monitoring and early warning the operating parameters of medical cosmetic equipment, characterized in that: The following steps are involved: Step S1: Acquire medical cosmetic equipment data; perform equipment range analysis on the medical cosmetic equipment data to generate medical cosmetic equipment range data; integrate equipment monitoring parameters using multi-source sensors based on the medical cosmetic equipment range data to generate standard medical cosmetic equipment multimodal monitoring data; Step S2: Performing long-term performance degradation trend monitoring on the multimodal monitoring data of the standard medical cosmetic equipment to generate long-term performance degradation trend data of the key components of the equipment; generating a first early warning signal based on the long-term performance degradation trend data of the key components of the equipment to obtain a first early warning signal for operation monitoring; Perform biomechanical modeling on multimodal monitoring data of standard medical cosmetic equipment to generate skin stress distribution data; Generating a second warning signal based on the skin stress distribution data to obtain a second operation monitoring warning signal; Step S2 includes the following steps: Step S21: extracting operating parameters of key components of a standard medical cosmetic device from multimodal monitoring data to obtain operating parameters of key components of the device, wherein the key components of the device include a laser, a radio frequency electrode, and a cooling system; Step S22: monitoring the long-term performance degradation trend of the operating parameters of the key components of the equipment to generate long-term performance degradation trend data of the key components of the equipment; generating a first early warning signal based on the long-term performance degradation trend data of the key components of the equipment to obtain a first early warning signal for operation monitoring; Step S22 includes the following steps: Step S221: extracting equipment bearing operating parameters from equipment key component operating parameters to obtain equipment bearing operating data, wherein the equipment bearing operating data includes equipment bearing vibration data and equipment bearing temperature data; Step S222: performing envelope demodulation on the equipment bearing vibration data to generate equipment bearing vibration characteristic data; performing fluctuation extraction processing on the bearing temperature data to generate equipment bearing temperature characteristic data; performing time series correlation processing on the equipment bearing vibration characteristic data and the equipment bearing temperature characteristic data to generate coupling characteristic data; Step S223: Calculate the vibration-temperature coupling coefficient on the coupling characteristic data to generate coupling index data; perform state mapping on the coupling index data to generate equipment health assessment data; perform trend fitting on the equipment health assessment data to generate long-term performance degradation trend data of key equipment components; Step S224: generating a first warning signal based on the long-term performance degradation trend data of the key components of the equipment based on the preset first signal frequency to obtain a first warning signal for operation monitoring; Step S23: extracting skin contact optical perception data from the multimodal monitoring data of the standard medical cosmetic equipment to obtain skin contact optical perception data; Step S24: performing biomechanical modeling on the skin contact optical perception data to generate skin stress distribution data; performing potential risk identification based on the skin stress distribution data to generate skin micro-injury prediction data; generating a second warning signal based on the skin micro-injury prediction data to obtain a second operation monitoring warning signal; Step S24 includes the following steps: Step S241: performing perception area calculation on the skin contact optical perception data to obtain the skin contact perception area; performing three-dimensional geometric reconstruction of the skin contact surface on the skin contact optical perception data based on the skin contact perception area to generate three-dimensional geometric data of the skin contact surface; Step S242: performing skin-layer stress analysis on the three-dimensional geometric data of the skin contact surface to generate skin stress distribution data, wherein the skin-layer stress analysis includes skin surface stress analysis and skin deep layer stress analysis; performing stress extreme value screening on the skin stress distribution data to obtain skin stress distribution extreme value data; Step S243: Potential damage identification is performed using the preset skin damage stress threshold and the skin stress distribution extreme value data. When the skin stress distribution extreme value data is greater than the preset skin damage stress threshold, stress concentration points are marked on the skin stress distribution data based on the skin stress distribution extreme value data to generate stress concentration points. Step S244: Using the stress concentration points, the skin stress distribution extreme value data is screened for remaining extreme value points to obtain remaining skin stress distribution extreme value data; the remaining skin stress distribution extreme value data is marked as skin stress distribution extreme value data, and step S243 is repeatedly performed until the skin stress distribution extreme value data is less than or equal to a preset skin damage stress threshold, thereby generating a stress concentration area; Step S245: Identifying potential skin risks based on the three-dimensional geometric data of the skin contact surface according to the stress concentration area to generate skin micro-injury prediction data; generating a second warning signal based on the skin micro-injury prediction data based on the preset first signal frequency to obtain a second operation monitoring warning signal; Step S3: Uploading the first operation monitoring warning signal and the second operation monitoring warning signal to the cloud platform for monitoring warning trigger frequency analysis to generate equipment monitoring warning trigger frequency data; constructing a trigger decision based on the equipment monitoring warning trigger frequency data to generate medical beauty equipment operation warning decision data; Step S4: Evaluate the accuracy of the warning decision data for the operation of medical cosmetic equipment to generate operation monitoring warning accuracy evaluation data; adjust the warning signals of the first warning signal of operation monitoring and the second warning signal of operation monitoring based on the operation monitoring warning accuracy evaluation data to perform the operation parameter monitoring and warning optimization operation of the medical cosmetic equipment.

2. The method for monitoring and early warning of operating parameters of medical cosmetic equipment according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: Acquire medical beauty equipment data; Step S12: extracting text features from the medical beauty equipment data to generate medical beauty equipment text feature data; performing text semantic analysis on the medical beauty equipment text feature data to generate medical beauty equipment text semantic analysis data; Step S13: performing a medical beauty device scope analysis on the medical beauty device text semantic analysis data to generate medical beauty device scope data; integrating device monitoring parameters using multi-source sensors based on the medical beauty device scope data to generate medical beauty device multimodal monitoring data; Step S14: Preprocess the multimodal monitoring data of medical cosmetic equipment to generate standard multimodal monitoring data of medical cosmetic equipment, wherein the data preprocessing includes data cleaning, data denoising, data missing value filling and data standardization.

3. The method for monitoring and early warning of operating parameters of medical cosmetic equipment according to claim 2, characterized in that: Based on the range data of medical cosmetic equipment, equipment monitoring parameter integration through multi-source sensors includes: Using the skin condition sensor to collect the user's real-time physiological signals within the range of the medical beauty device, the user's real-time physiological signals are obtained; the user's real-time physiological signals are conditioned to generate a real-time physiological conditioning signal; Perform analog-to-digital conversion on the user's real-time physiological conditioning signal to generate the user's real-time physiological data; perform data change correlation analysis on the user's real-time physiological data and medical beauty equipment data to generate monitoring correlation change data; use environmental sensors to collect environmental parameters based on the monitoring correlation change data to obtain the environmental data of the medical beauty equipment; The medical beauty equipment data, the user's real-time physiological data and the medical beauty equipment's working environment data are integrated and displayed to generate multimodal monitoring data of medical beauty equipment.

4. The method for monitoring and early warning of operating parameters of medical cosmetic equipment according to claim 1, characterized in that: Identification of potential skin risks based on the three-dimensional geometric data of the skin contact surface based on stress concentration areas includes: Contact stress characteristics are extracted from stress concentration areas to obtain contact stress characteristic data. The contact stress characteristic data are divided into data sets to generate model training sets and model test sets. The model training sets are trained using a convolutional neural network algorithm to generate a skin micro-injury prediction model. The skin micro-injury prediction pre-model is optimized and iterated using the model test set to generate a skin micro-injury prediction model; the three-dimensional geometric data of the skin contact surface is imported into the skin micro-injury prediction model to identify potential skin risks and generate skin micro-injury prediction data.

5. The method for monitoring and early warning of operating parameters of medical cosmetic equipment according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: integrating the first operation monitoring warning signal and the second operation monitoring warning signal to generate a medical cosmetic equipment operation monitoring warning signal; Step S32: Upload the medical beauty equipment operation monitoring and warning signals to the cloud platform for monitoring and warning triggering, and generate equipment monitoring and warning triggering data; Step S33: Perform trigger timing frequency analysis on the equipment monitoring and early warning trigger data to generate equipment monitoring and early warning trigger frequency data; Step S34: construct a trigger decision for the equipment monitoring warning trigger data based on the equipment monitoring warning trigger frequency data to generate medical beauty equipment operation warning decision data.

6. The method for monitoring and early warning of operating parameters of medical cosmetic equipment according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: collecting decision feedback data on the medical cosmetic equipment operation warning decision data to obtain warning decision feedback data; performing a warning accuracy assessment on the medical cosmetic equipment operation warning decision data based on the warning decision feedback data to generate operation monitoring warning accuracy assessment data; Step S42: Based on the operation monitoring and early warning accuracy evaluation data, the early warning signal of the operation monitoring and the second early warning signal of the operation monitoring are adjusted to perform the operation parameter monitoring and early warning optimization operation of the medical cosmetic equipment.

7. A medical cosmetic equipment operating parameter monitoring and early warning system, characterized in that: Used to execute the operating parameter monitoring and early warning method of medical cosmetic equipment according to claim 1, the operating parameter monitoring and early warning system of the medical cosmetic equipment comprises: The data fusion module is used to obtain medical beauty equipment data; perform equipment range analysis on the medical beauty equipment data to generate medical beauty equipment range data; integrate equipment monitoring parameters through multi-source sensors based on the medical beauty equipment range data to generate standard medical beauty equipment multimodal monitoring data; The monitoring and early warning module is used to monitor the long-term performance degradation trend of the multimodal monitoring data of standard medical cosmetic equipment and generate long-term performance degradation trend data of key equipment components; generate a first early warning signal based on the long-term performance degradation trend data of key equipment components to obtain a first early warning signal for operation monitoring; perform biomechanical modeling on the multimodal monitoring data of standard medical cosmetic equipment to generate skin stress distribution data; and generate a second early warning signal based on the skin stress distribution data to obtain a second early warning signal for operation monitoring; The early warning prediction module is used to upload the first early warning signal of operation monitoring and the second early warning signal of operation monitoring to the cloud platform for monitoring and early warning trigger frequency analysis, and generate equipment monitoring and early warning trigger frequency data; based on the equipment monitoring and early warning trigger frequency data, trigger decision construction is carried out to generate medical beauty equipment operation early warning decision data; The early warning optimization module is used to evaluate the early warning accuracy of the medical beauty equipment operation early warning decision data and generate operation monitoring early warning accuracy evaluation data; based on the operation monitoring early warning accuracy evaluation data, the early warning signal of the operation monitoring first early warning signal and the operation monitoring second early warning signal are adjusted to perform the operation parameter monitoring and early warning optimization operation of the medical beauty equipment.

Images