LED lamp adaptive control method and device of LED backlight bathroom mirror

Abstract

The present application relates to the field of bathroom mirror LED lamp control, especially to a kind of LED backlight bathroom mirror LED lamp adaptive control method and device.The method includes the following steps: obtaining the monitoring log of bathroom mirror LED lamp, performing usage time frequency distribution statistics and usage behavior prediction, and generating usage behavior prediction time point;According to the real-time brightness demand prediction of usage behavior prediction time point, and light intensity output parameter calculation is carried out, to obtain initial light intensity output parameter;According to initial light intensity output parameter, carry out immediate bathroom mirror illumination control, according to environmental humidity monitoring parameter, carry out mirror surface fogging situation analysis, and construct mirror surface fogging situation evolution diagram;According to mirror surface fogging situation evolution diagram, carry out mirror surface thermal effect defogging analysis and dynamic heating temperature adaptive adjustment, to generate adaptive water mist fogging adjustment strategy.The present application improves the clear visualization effect of bathroom mirror under water mist fogging condition by dynamically adjusting illumination parameters, and enhances user visual effect.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of bathroom mirror LED lamp control, and in particular to an LED lamp adaptive control method and device for LED backlit bathroom mirror. BACKGROUND

[0002] With the continuous development of smart home technology, LED backlit bathroom mirror, as a product integrating modern technology and home life, has gradually become a standard in many families and commercial places. Compared with traditional bathroom mirrors, LED backlit bathroom mirrors not only provide more uniform lighting effects and improve mirror clarity, but also have higher energy efficiency and longer service life. Especially in daily activities such as beauty, shaving, and makeup, the lighting effect of the bathroom mirror is crucial to user experience. Therefore, LED backlit bathroom mirrors have been widely used in the market. However, with the continuous penetration of intelligent technology, how to improve the convenience, comfort, and energy efficiency of LED backlit bathroom mirrors has become a problem to be solved.

[0003] The lighting control method of traditional LED backlit bathroom mirrors mostly relies on manual adjustment switches or simple brightness adjustment buttons, and users need to manually adjust the light intensity according to different needs. However, manual control not only increases the user's operation burden, but also often cannot accurately meet the demand for light intensity in different time periods and different environmental conditions. In addition, due to the high humidity of the bathroom environment, water mist is easily produced on the mirror surface, affecting the visibility of the mirror, which makes the traditional LED light control method unable to effectively adapt to this special use environment. Therefore, with the continuous development of smart home technology and adaptive control theory, there is an urgent need for a more intelligent, real-time, and adaptive LED backlit bathroom mirror control method. SUMMARY

[0004] To solve the above technical problems, the present application provides an LED lamp adaptive control method and device for LED backlit bathroom mirror to solve at least one of the above technical problems.

[0005] To achieve the above purpose, the present application provides an LED lamp adaptive control method for LED backlit bathroom mirror, comprising the following steps:

[0006] Step S1: Obtain the monitoring log of the bathroom mirror LED lamp, perform usage time frequency distribution statistics and usage behavior prediction, and generate a usage behavior prediction time point;

[0007] Step S2: Perform real-time brightness demand prediction according to the usage behavior prediction time point, and perform light intensity output parameter calculation to obtain an initial light intensity output parameter;

[0008] Step S3: Perform real-time bathroom mirror light control according to the initial light intensity output parameter, obtain the environmental humidity monitoring parameter; perform mirror surface fogging situation analysis according to the environmental humidity monitoring parameter, and construct a mirror surface fogging situation evolution map;

[0009] Step S4: Perform mirror surface thermal effect defogging analysis and dynamic heating temperature self-adaptive adjustment according to the mirror surface fogging situation evolution map, to generate an adaptive water mist fogging adjustment strategy;

[0010] Step S5: Perform dynamic brightness compensation optimization and adaptive light color temperature adaptation according to the mirror surface fogging situation evolution map, to construct a dynamic light adjustment strategy;

[0011] Step S6: Perform dynamic bathroom mirror LED lamp control and intelligent reinforcement transfer learning based on the adaptive water mist fogging adjustment strategy and the dynamic light adjustment strategy, to construct an intelligent bathroom lamp control engine.

[0012] The application can establish a user's daily behavior model by collecting long-term data on the time when the user enables the LED lamp of the bathroom mirror. The user has a high frequency of use at 6:45 in the morning, and this time point can be identified and predicted as a high-probability use period. Generating a prediction time point based on the use frequency distribution helps to start the relevant modules (lighting, heating, defogging, etc.) in advance to achieve "unconscious pre-start", avoiding poor user experience due to waiting for the function to respond. Through user behavior clustering, the use habits of different members in the family can be distinguished, and multi-time period prediction can be performed to improve the applicability and intelligence. Only in the predicted high-probability use period, the preparation is in advance, reducing the time of invalid operation, especially in the night or daytime period which is not often used, so that the device can remain in a low-power standby state. Combining the prediction time point with the external environment (such as early morning, dusk, night), the brightness of natural light is automatically judged whether it needs to be enhanced, and the appropriate light intensity output parameter is calculated. For example, in the morning, the vision is more sensitive, and the brightness is automatically reduced to avoid glare; at night or in a poorly lit bathroom, the brightness is increased to meet the visual needs. Automatically calculating the light intensity output parameter, the user does not need to manually adjust the brightness, improving the convenience. By predicting the light intensity demand, the LED output power is reasonably controlled to maximize energy saving while ensuring the use experience. Since the initial light intensity parameter has been pre-calculated, the lighting state can be adjusted immediately when the user approaches or is active in front of the mirror, achieving the experience of "ready-to-use bright". Based on the light intensity parameter, the LED is quickly turned on to improve the response speed and automatically match the current required lighting intensity. By integrating a humidity sensor, the bathroom humidity level is collected in real time to identify the risk of fogging and provide basic data for defogging. The humidity change trend is associated with historical mirror fogging data to establish a "fogging trend evolution map" for analyzing the correlation between different humidity and mirror fogging degree. Compared with the traditional "timed heating" method, the trend evolution map can be used to determine whether defogging is needed, providing an accurate response rather than blind heating. Different regions, seasons, and family use habits differ significantly, and the fogging trend evolution map can dynamically adjust the model parameters to ensure the universality and accuracy of the defogging judgment. Through the fogging trend evolution map, the defogging intensity demand is determined to dynamically adjust the heating power, rather than using the "fixed time / fixed power" mode, saving energy. According to the real-time situation, the heating temperature is accurately controlled to make the mirror reach a "just not foggy" state, rather than over-heating, ensuring comfort and safety. Different family users and climates can form personalized heating strategies (such as different heating logic in humid southern and dry northern environments). The clarity of the mirror after defogging is significantly improved, and it does not affect the user's operation of looking in the mirror, making up, etc. When the mirror fogging is still in the residual stage, the brightness or color temperature can be increased to compensate for the vision, improving the overall mirror use experience. Dynamically adjusting the color temperature can improve the skin tone perception, making tasks such as makeup, skincare, and shaving more accurate. Integrating environmental perception, user behavior analysis, and light and heat adjustment strategies, the "smart mirror" in the true sense is realized.Through reinforcement learning and transfer learning, the control model is continuously iterated and upgraded to adapt to the use habits of different users or family members. Compared with traditional bathroom mirrors, it has stronger intelligence, energy saving and humanization, forming a differentiated advantage.

[0013] In the present specification, an LED lamp adaptive control device of an LED backlit bathroom mirror is provided for performing the LED lamp adaptive control method of the LED backlit bathroom mirror as described above, comprising:

[0014] A behavior prediction module is configured to obtain a monitoring log of the bathroom mirror LED lamp, perform usage time frequency distribution statistics and usage behavior prediction, and generate a usage behavior prediction time point.

[0015] A brightness demand prediction module is configured to perform real-time brightness demand prediction according to the usage behavior prediction time point, and perform light intensity output parameter calculation to obtain initial light intensity output parameters.

[0016] A mirror fog analysis module is configured to perform immediate bathroom mirror illumination control according to the initial light intensity output parameters, obtain environmental humidity monitoring parameters, perform mirror fog state analysis according to the environmental humidity monitoring parameters, and construct a mirror fog state evolution map.

[0017] A heating temperature adjustment module is configured to perform mirror thermal effect defogging analysis and dynamic heating temperature adaptive adjustment according to the mirror fog state evolution map, to generate an adaptive water mist fog adjustment strategy.

[0018] A dynamic illumination adjustment module is configured to perform dynamic brightness compensation optimization and adaptive illumination color temperature adaptation according to the mirror fog state evolution map, to construct a dynamic illumination adjustment strategy.

[0019] An intelligent control module is configured to perform dynamic bathroom mirror LED lamp control and intelligent reinforcement transfer learning based on the adaptive water mist fog adjustment strategy and the dynamic illumination adjustment strategy, to construct an intelligent bathroom lamp control engine.

[0020] The present application constructs a user usage behavior portrait based on the log data of the opening time, frequency, use duration, etc. of the LED lamp, realizes the transition from "passive response" to "active prediction", avoids unnecessary lighting of the LED lamp in the period of no use, effectively reduces energy consumption, and prolongs the service life of the lamp. It can be fused with sensor (such as human body induction) data for multi-user behavior separation and personalized analysis, and improve the intelligent degree. It can automatically adjust the light intensity according to the historical preference and environmental brightness before the user uses the bathroom mirror, improve the response speed and use experience. According to the lighting demand preference of different users (such as high brightness for men shaving and soft light for women making up), the personalized initial light setting is realized. Through real-time environmental humidity data (combined with temperature and use period), the mirror fog model is established, which can predict the change of fog degree. The fog state is quantified and presented, and the evolution map of "clear-mild fog-severe fog" is constructed, which provides visual basis for defogging decision. It can identify the actual fog or fog scene, effectively avoid false triggering of heating, and save energy. The mirror fog state will affect the light reflection effect, which can be combined with light change to judge the fog level and improve the analysis accuracy. According to the fog degree, the reasonable heating power and duration are matched to avoid the increase of energy consumption caused by excessive heating or the incomplete defogging caused by insufficient heating. The temperature control algorithm can be adjusted according to different environments (winter / summer, humid / dry) and mirror fog levels to improve adaptability. It avoids repeated fog or clear of the mirror surface during the defogging process, and always maintains visual clarity to improve the use comfort in high humidity environment. In the case of no fog or only mild fog on the mirror surface, low power mode is adopted to realize "on-demand defogging". In the case of mild fog on the mirror surface, the reflection clarity is improved through brightness compensation, and the defogging device does not need to be started immediately. The color temperature can be automatically adjusted to match the scene, such as warm light to help wake up in the morning, cold light to help sleep at night, and high color rendering index light source for makeup. Through intelligent adjustment of light angle and brightness gradient, the visual problems such as glare and light spot caused by mirror fog are relieved. Dynamic lighting enhances visual safety, especially in high humidity scenes after hot water bathing, providing clearer vision and reducing the risk of use. Through user feedback (such as manual intervention frequency and use satisfaction), the control strategy is adjusted to improve long-term performance. BRIEF DESCRIPTION OF DRAWINGS

[0021] Figure 1 It is a step flow chart of the LED lamp adaptive control method of the LED backlit bathroom mirror of the present application;

[0022] Figure 2 It is a detailed implementation step flow chart of step S1;

[0023] Figure 3 It is a detailed implementation step flow chart of step S2;

[0024] Figure 4 It is a detailed implementation step flow chart of step S3. DETAILED DESCRIPTION

[0025] It is to be understood that the specific examples described herein are merely illustrative of the present application and are not intended to limit the scope of the present application.

[0026] The present application provides an LED lamp adaptive control method and device for an LED backlit bathroom mirror. The execution subject of the LED lamp adaptive control method and device for the LED backlit bathroom mirror includes but is not limited to mechanical equipment, a data processing platform, a cloud server node, a network upload device, etc., which can be regarded as a general computing node of the present application, and the data processing platform includes but is not limited to at least one of an audio image management system, an information management system, and a cloud data management system.

[0027] Please refer to Figures 1 to 4 The present application provides an LED lamp adaptive control method for an LED backlit bathroom mirror, which includes the following steps:

[0028] Step S1: Obtain the monitoring log of the bathroom mirror LED lamp, perform usage time frequency distribution statistics and usage behavior prediction, and generate a usage behavior prediction time point.

[0029] Step S2: Perform real-time brightness demand prediction according to the usage behavior prediction time point, and perform light intensity output parameter calculation to obtain initial light intensity output parameters.

[0030] Step S3: Perform immediate bathroom mirror illumination control according to the initial light intensity output parameters, obtain environmental humidity monitoring parameters, perform mirror surface fogging situation analysis according to the environmental humidity monitoring parameters, and construct a mirror surface fogging situation evolution map.

[0031] Step S4: Perform mirror surface thermal effect defogging analysis and dynamic heating temperature adaptive adjustment according to the mirror surface fogging situation evolution map to generate an adaptive water mist fogging adjustment strategy.

[0032] Step S5: Perform dynamic brightness compensation optimization and adaptive illumination color temperature adaptation according to the mirror surface fogging situation evolution map to construct a dynamic illumination adjustment strategy.

[0033] Step S6: Perform dynamic bathroom mirror LED lamp control and intelligent reinforcement transfer learning based on the adaptive water mist fogging adjustment strategy and the dynamic illumination adjustment strategy to construct an intelligent bathroom lamp control engine.

[0034] The application can establish a user's daily behavior model by collecting long-term data on the time when the user enables the LED lamp of the bathroom mirror. The user has a high frequency of use at 6:45 in the morning, and this time point can be identified and predicted as a high-probability use period. Generating a prediction time point based on the frequency distribution of use helps to start the relevant modules (lighting, heating, defogging, etc.) in advance to achieve "unconscious pre-start", avoiding poor user experience due to waiting for the function to respond. By clustering user behavior, the use habits of different members in the family can be distinguished, and multi-time period prediction can be performed to improve applicability and intelligence. Only in the predicted high-probability use period, the preparation is in advance, reducing the time of invalid operation, especially in the night or daytime period which is not often used, so that the device can remain in a low-power standby state. Combining the prediction time point with the external environment (such as early morning, dusk, night), the brightness of natural light is automatically judged whether it needs to be enhanced, and the appropriate light intensity output parameter is calculated. For example, in the morning, the vision is more sensitive, and the brightness is automatically reduced to avoid glare; at night or in a poorly lit bathroom, the brightness is increased to meet the visual needs. Automatically calculating the light intensity output parameter, the user does not need to manually adjust the brightness, improving convenience. By predicting the light intensity demand, the LED output power is reasonably controlled to maximize energy saving while ensuring user experience. Since the initial light intensity parameter has been pre-calculated, the lighting state can be adjusted immediately when the user approaches or is active in front of the mirror, achieving the experience of "ready-to-use lighting". Based on the light intensity parameter, the LED is quickly turned on to improve the response speed and automatically match the current required lighting intensity. By integrating a humidity sensor, the bathroom humidity level is collected in real time to identify the risk of fogging and provide basic data for defogging. The humidity change trend is associated with historical mirror fogging data to establish a "fogging trend evolution map" for analyzing the correlation between different humidity and mirror fogging degree. Compared with the traditional "timed heating" method, the trend evolution map can be used to determine whether defogging is needed, providing an accurate response rather than blind heating. Different regions, seasons, and family use habits differ significantly, and the fogging trend evolution map can dynamically adjust the model parameters to ensure the universality and accuracy of the defogging judgment. By judging the defogging intensity demand through the fogging trend evolution map, the heating power is dynamically adjusted, rather than using the "fixed time / fixed power" mode, saving energy. According to the real-time situation, the heating temperature is accurately controlled to make the mirror reach a "just not foggy" state, rather than over-heating, ensuring comfort and safety. Different family users and climates can form personalized heating strategies (such as different heating logic in humid southern and dry northern environments). The clarity of the mirror after defogging is significantly improved, and it does not affect the user's operation of looking in the mirror, making up, etc. When the mirror fogging is still in the residual stage, the brightness or color temperature can be increased to compensate for the vision, improving the overall mirror experience. Dynamically adjusting the color temperature can improve the skin tone perception, making tasks such as makeup, skincare, and shaving more accurate. Integrating environmental perception, user behavior analysis, and light and heat adjustment strategies, the application realizes a truly "intelligent mirror".The control model is continuously iterated and upgraded through reinforcement learning and transfer learning to adapt to the use habits of different users or family members. Compared with traditional bathroom mirrors, the bathroom mirror has stronger intelligence, energy saving and humanization, and forms a differentiated advantage.

[0035] In the embodiment of the present application, referring to Figure 1 The LED lamp adaptive control method of the LED backlight bathroom mirror is used for the LED lamp adaptive control method of the LED backlight bathroom mirror, and the steps of the LED lamp adaptive control method of the LED backlight bathroom mirror include:

[0036] Step S1: Obtain the monitoring log of the bathroom mirror LED lamp, perform use time frequency distribution statistics and use behavior prediction, and generate a use behavior prediction time point;

[0037] In this embodiment, the usage logs of the bathroom mirror LED lamp are recorded regularly. These logs should include the timestamp of each use, the duration of use, the brightness setting, user feedback, and other information. These data can be automatically collected through built-in sensors and control systems and stored in a database. Set to automatically record data at each use, format: timestamp: 2023-04-0108:00:00, duration: 15 minutes, brightness: 400 lux, user feedback: satisfied. In this way, the accuracy and integrity of the data can be ensured, providing a basis for subsequent analysis. The collected monitoring log data is sorted and cleaned to remove duplicate records and outliers, ensuring the reliability of the data. A time window can be set to combine records within the same time period to form a structured data set. If a user turns on the LED lamp multiple times within the same time period, these records will be combined into one, recording the total usage time and average brightness. This step is crucial to ensure the effectiveness of subsequent statistical analysis. Using the sorted data, the frequency distribution of usage time is calculated. The frequency distribution of user usage frequency in different time periods can be calculated in the form of a histogram or frequency table. Set the time interval to be one hour, and calculate the number of uses and total duration per hour. The analysis results show that: between 08:00-09:00, the number of uses is 20 times, and the total usage time is 300 minutes; between 09:00-10:00, the number of uses is 15 times, and the total usage time is 200 minutes. These statistical data will help identify the user's peak usage period. Based on the frequency distribution of usage time, a usage behavior prediction model is constructed. Time series analysis or machine learning algorithms such as ARIMA model or LSTM model can be used to predict future usage time points. The goal of this step is to identify the user's usage habits and predict when they may use the bathroom mirror in the future. Using historical data to train the model, it is found that users have a higher usage frequency between 6:00 and 8:00 in the morning, and the model predicts that the probability of users using the bathroom mirror at 7:00 in the morning in the next few days is 80%. According to the output of the prediction model, specific usage behavior prediction time points are generated. These time points will be used to dynamically adjust the lighting parameters of the LED lamp to meet the user's usage needs. The predicted time points can be recorded in the system for future use. If the model predicts that the user will use the bathroom mirror at 2023-04-0207:00:00, 2023-04-0208:00:00, etc., the system will adjust the lighting settings in advance to ensure optimal usage effect.

[0038] Step S2: Real-time brightness demand prediction according to usage behavior prediction time points, and light intensity output parameter calculation to obtain initial light intensity output parameters;

[0039] In this embodiment, after completing the usage behavior prediction, the system generates a series of potential usage time points. These time points will serve as the basis for subsequent brightness demand prediction. First, the system should organize and mark these time points for subsequent real-time monitoring and analysis. Assuming the predicted time points are 2023-04-02 07:00:00 and 2023-04-02 08:00:00, the system will consider these time points as key moments when users may use the bathroom mirror in the future. Before the predicted time points arrive, the system needs to monitor environmental conditions in real time to accurately predict brightness demand. This includes parameters such as ambient light intensity, humidity, and temperature. This data can be collected in real time through built-in sensors. Assuming that at 2023-04-02 06:59:00, the system detects an ambient light intensity of 200 lux and a humidity of 70%, this environmental data will provide an important basis for subsequent brightness demand calculation. Based on historical usage data and real-time environmental data, a brightness demand prediction model is constructed. Linear regression, decision tree, or machine learning models can be used to predict the user's brightness demand under specific environmental conditions. Analysis of historical data revealed that users typically prefer a brightness of 400 lux when the ambient light intensity is 200 lux. The model can predict that the user's brightness requirement is 400 lux under these environmental conditions. Based on the real-time brightness demand prediction and ambient light intensity, the required light intensity output parameter is calculated: I(output) = I(demand) - I(ambient), where I(output) is the required output light intensity, I(demand) is the predicted brightness demand, and I(ambient) is the current ambient light intensity. If the predicted brightness demand is 400 lux and the ambient light intensity is 200 lux, then the required light intensity output parameter is: II(output) = 400 lux - 200 lux = 200 lux. The calculated initial light intensity output parameter is recorded in the system for adjustment during actual user use. These parameters should be correlated with the time point and relevant environmental data to ensure data traceability.

[0040] Step S3: Perform real-time bathroom mirror illumination control based on initial light intensity output parameters and obtain ambient humidity monitoring parameters; perform mirror blurring status analysis based on ambient humidity monitoring parameters and construct a mirror blurring status evolution diagram.

[0041] In this embodiment, based on the calculated initial light intensity output parameter, the system will automatically control the brightness output of the LED lights. This step involves real-time adjustment of the power of the LED lights to ensure that the mirror reaches the required brightness level. If the initial light intensity output parameter is 200 lux, the system will ensure that the mirror brightness stabilizes at 400 lux (when the ambient light intensity is 200 lux) by adjusting the output power of the LED lights. PWM (Pulse Width Modulation) technology can be used to accurately control the brightness and ensure smooth transition of the light. At the same time of light control, the system will monitor the environmental humidity in the bathroom in real time through the installed humidity sensors. These sensors should have high precision and fast response capability to obtain humidity data in time. Assuming that the system detects that the environmental humidity is 75% at 2023-04-0207:01:00. This data is the basis for analyzing the mirror fogging situation and will be used for subsequent analysis of the impact of humidity on fogging. The obtained environmental humidity data is recorded in the database of the system and is associated with the current time stamp and light conditions. Ensure that the data is complete and traceable to support subsequent analysis. The record format is: Time stamp: 2023-04-0207:01:00, Environmental humidity: 75%, LED brightness: 400 lux. These records will be used to construct the mirror fogging situation evolution graph. According to the environmental humidity monitoring parameters, analyze the mirror fogging situation. The impact of fogging on the clarity of the mirror can be evaluated by calculating the concentration of water vapor on the mirror and its relationship with environmental humidity. If the humidity is 75%, the current water vapor concentration can be calculated using the previous water vapor concentration formula and the degree of influence of fogging on the mirror clarity is determined. Assuming that after analysis, it is found that when the humidity reaches 75%, the fogging of the mirror increases by 30%. The relationship between humidity and fogging can be visualized to construct the mirror fogging situation evolution graph. This graph should show the trends of water vapor concentration, humidity and fogging over time, helping users understand the changes in mirror clarity.

[0042] Step S4: Mirror thermal effect defogging analysis and dynamic heating temperature adaptive adjustment are performed according to the mirror fogging situation evolution graph to generate an adaptive water mist fogging adjustment strategy;

[0043] In this embodiment, the generated mirror fog evolution graph is used to analyze the trend of mirror fog under different humidity conditions. By observing the relationship between water vapor concentration and fog in the graph, the key humidity threshold and the rule of fog change are identified. Assuming that the fog evolution graph shows that when the humidity exceeds 70%, the mirror fog increases sharply and reaches 90% fog. This finding will provide an important basis for subsequent thermal effect analysis, helping to determine when to start the heating demisting function. According to the mirror fog evolution graph, a thermal effect model is constructed to analyze the influence of mirror heating on demisting. The model should consider factors such as the thermal conductivity of the mirror material, environmental temperature, humidity, and water vapor concentration to evaluate the required heating temperature. After analyzing the thermal effect, the system will dynamically adjust the heating temperature of the mirror according to the real-time humidity and fog value. When the humidity is detected to reach the set threshold (such as 70%), the system will automatically start the heating function and adjust the heating intensity and time according to the current fog. If the current fog is 85%, the system may heat the mirror to 60°C and set the heating time to 5 minutes to achieve the best demisting effect. The system should monitor the temperature change of the mirror in real time and adjust the heating strategy according to the feedback of the fog. During the dynamic heating process, the system will generate an adaptive water fog adjustment strategy that can automatically adjust the heating temperature and time according to real-time environmental changes to ensure that the mirror remains clear in high humidity environments. If the fog is found to decrease to 70% during heating, the system will automatically record this effect and adjust the strategy to adapt to similar future environmental conditions. Strategy rules can be set, such as automatically heating to 65°C when the humidity exceeds 75% for 6 minutes. The generated adaptive adjustment strategy and its implementation results are recorded in the system for subsequent analysis and optimization. The records should include information such as the temperature, duration, fog change, and user feedback of each heating. The record format is: timestamp: 2023-04-0207:10:00, heating temperature: 60°C, heating time: 5 minutes, fog change before: 85%, after: 70%, user feedback: satisfied. These data will provide a basis for subsequent system optimization and user experience improvement.

[0044] Step S5: Dynamic brightness compensation optimization is performed according to the mirror fog evolution graph, and adaptive light color temperature adaptation is performed to construct a dynamic light adjustment strategy;

[0045] In this embodiment, the light requirements under different humidity and fog conditions are analyzed based on the mirror fog evolution map. By comparing historical usage data and current environmental conditions, the user's preferred brightness level and the impact of fog on brightness are determined. Assuming the analysis data shows that when the fog reaches 80%, the user usually expects a brightness of 450 lux to maintain clarity. The system will use this data to establish a dynamic brightness compensation model to ensure that the LED light brightness adjusts in time under high fog conditions. Using real-time monitored fog and ambient light intensity, the required dynamic compensation parameters are calculated. Based on dynamic brightness compensation, the system will adaptively adjust the color temperature of the light according to the humidity of the environment and the user's preferences. Color temperature adjustment not only affects the visual effect of the mirror but also improves the overall user experience. When the humidity reaches 75% and the fog is 80%, the system may adjust the color temperature to warm tones (about 3000K) to reduce visual fatigue and improve comfort. Through user feedback data, the optimal color temperature settings under different humidity conditions are determined. Combining brightness compensation and color temperature adaptation, a comprehensive dynamic light adjustment strategy is constructed. The system should have real-time response capabilities to automatically adjust the light parameters during user use to achieve the best effect. Set the rules: if the humidity exceeds 70% and the fog reaches 80%, automatically set the LED light brightness to 450 lux and the color temperature to 3000K; if the fog decreases to below 70%, it will return to the standard color temperature (about 4000K). This strategy ensures that users always have a comfortable user experience under different environmental conditions. The implementation results of the dynamic light adjustment strategy are recorded in the system and performance verification is conducted. The records should include the specific parameters of each adjustment and their impact on user experience for subsequent analysis and optimization.

[0046] Step S6: Perform dynamic bathroom mirror LED light control based on the adaptive water mist fog adjustment strategy and the dynamic light adjustment strategy, and perform intelligent reinforcement transfer learning to construct an intelligent bathroom light control engine.

[0047] In this embodiment, based on the aforementioned adaptive water mist blur adjustment strategy and dynamic lighting adjustment strategy, the system will start the dynamic control of the LED lamp. This control will automatically adjust the brightness and color temperature of the LED lamp according to real-time environmental data (such as humidity, blur, brightness demand, etc.) to ensure the clarity of the mirror and the comfort of the user. When the system detects that the humidity is 75% and the blur is 80%, the LED lamp will automatically adjust to a brightness of 450 lux and a color temperature of 3000K. This process relies on real-time monitoring and feedback, enabling the system to quickly respond to user needs. During the dynamic control process, the system will continuously monitor environmental conditions, including humidity, temperature, light intensity, etc. These data will provide a basis for subsequent intelligent learning, ensuring the effectiveness of the control strategy. Assuming that during the control process, the system records real-time humidity changes and finds that the humidity decreases from 75% to 65%. This change will trigger the corresponding adjustment strategy, possibly resulting in adjustments to brightness and color temperature to adapt to the new environmental conditions. To enhance the intelligence level of the system, a reinforcement learning framework is constructed. This framework should include the state space (such as environmental humidity, blur, user feedback, etc.), the action space (such as brightness and color temperature adjustments of the LED lamp), and the reward function (based on user satisfaction and clarity changes). The model can be trained through historical data and user feedback, enabling it to quickly adapt and optimize the control strategy under similar environmental conditions. The system will use existing usage data to accelerate the learning process, thereby improving the accuracy and efficiency of control. In the intelligent reinforcement learning framework, transfer learning technology is used to utilize existing user feedback and environmental data to accelerate the learning process in new situations. By transferring the knowledge learned in the early stages to new situations, the system can immediately provide optimized lighting settings when the user first uses it. If the system records that the user has a high level of satisfaction under a certain humidity and blur, the system will preferentially select the corresponding brightness and color temperature settings under similar conditions, reducing the user's adaptation time. After the intelligent control engine is put into actual use, performance verification is carried out, and user feedback and system operation data are collected. According to user satisfaction and actual usage, the control strategy and model parameters are continuously optimized to ensure that the system always provides the best user experience. If most users are satisfied with the clarity at a humidity of 75% with a satisfaction score of 4 out of 5, the system may further adjust the brightness and color temperature settings at that humidity to improve overall user satisfaction.

[0048] In this embodiment, referring to Figure 2 For the detailed implementation step flowchart of step S1, in this embodiment, the detailed implementation steps of step S1 include:

[0049] Obtain the monitoring log of the bathroom mirror LED lamp; analyze the user usage behavior of the monitoring log to extract all user usage behavior information;

[0050] performing use time period calculation on the user use behavior information, marking a plurality of use time periods;

[0051] performing user use time frequency distribution statistics according to the plurality of use time periods to obtain a use time frequency distribution graph;

[0052] performing use time demand analysis on the use time frequency distribution graph to obtain historical use time demand characteristics;

[0053] performing use behavior prediction based on the historical use time demand characteristics to generate a use behavior prediction time point.

[0054] In this example, we ensure that the monitoring system for LED lights has been correctly installed and can record usage data in real-time. The monitoring system should include sensors and a data recording module that captures the on-off status, brightness changes, and user usage time of the lights in real-time. Set the sensor to record state changes every second, and record data including timestamp, on-off status (on / off), brightness value, etc. for subsequent analysis. Store the monitored log data in a database to ensure data integrity and traceability. Data should be stored in a structured format, including timestamp, user ID (if applicable), status information, etc. fields. The record format is: Timestamp: 2023-04-0108:00:00, Status: On, Brightness: 300 lumens. These data will provide a basis for subsequent analysis. Export the monitoring log to an analyzable file format (such as CSV or Excel) at regular intervals to facilitate subsequent data analysis and processing. Ensure the timeliness of the exported data to reflect the user's usage behavior in a timely manner. Export data once a day, and the file contains all monitoring records for the past 24 hours to facilitate subsequent usage behavior analysis. Perform data cleaning and preprocessing on the exported monitoring log, including removing invalid data, filling missing values, etc. Ensure that the data analyzed is accurate and effective. Check the format of the timestamp to ensure its uniformity, and if you find abnormal records (such as multiple records with the same timestamp), you need to filter them out. Based on the monitoring log, identify the user's usage behavior, including the time period of turning on and off the light. You can set the usage behavior standard, and continuous lighting for more than 5 minutes is considered "usage behavior". Analyze the records, and if the status is "on" between 2023-04-0108:00:00 and 2023-04-0108:05:00, mark it as user usage behavior. Extract all user usage behavior information to form a usage behavior list, recording the specific time and duration of each user's usage. According to the extracted user usage behavior information, classify the usage behavior by time period. Set the size of the time period, divide it by hour or 30 minutes to facilitate more detailed analysis. Divide a day into 24 hours and count the number of uses and duration in each hour. Label each user's usage behavior and record the corresponding time period. Form the association between time period and usage behavior to facilitate subsequent statistical analysis. If a user uses 3 times between 8:00 and 9:00, mark it as: Time period: 08:00-09:00, Usage times: 3 times. Organize the usage of all time periods and summarize the user usage frequency and duration of each time period to form a time period usage statistics table. The statistical result is: 08:00-09:00, Usage times: 5 times, Average usage duration: 4 minutes. Based on the usage of the time period, calculate the user's usage frequency in each time period. You can form a frequency distribution data by counting the number of uses in each time period.Assuming usage occurs 5 times between 08:00 and 09:00 and 3 times between 09:00 and 10:00, the frequency distribution is: 08:00-09:00: 5 times, 09:00-10:00: 3 times. Use statistical software or tools to generate a usage time frequency distribution chart to visually display user behavior patterns. This helps identify high-frequency and low-frequency usage periods. Generate a bar chart, with the X-axis representing the time period and the Y-axis representing the number of uses, to visually display usage in each time period. Record the frequency distribution statistics and conduct preliminary analysis to identify users' high-frequency usage periods and their characteristics. This will provide a basis for subsequent demand analysis. If 08:00-09:00 is found to be a peak usage period, record the usage characteristics of this period for subsequent analysis. Conduct in-depth analysis of the frequency distribution chart data to extract users' historical usage time demand characteristics. Characteristics can be summarized by calculating the average usage duration and number of uses for each time period. The average usage time from 08:00 to 09:00 was calculated to be 4 minutes, and from 09:00 to 10:00, the average usage time was 3 minutes. The usage demand trends across different time periods were analyzed to identify user preferences and their changes. In-depth analysis can be conducted using time series analysis methods. If it is found that morning usage frequency increases year by year while evening usage frequency decreases, this trend change is recorded for subsequent strategy adjustments. The extracted historical time demand characteristics are recorded in the system to form a detailed user behavior profile for future usage behavior prediction. The recording format is: Time period: 08:00-09:00, Average usage time: 4 minutes, Usage frequency: 5 times, Trend: Upward. Measurement, regression analysis, or machine learning methods are used to predict future usage behavior. A linear regression model is used to predict the usage frequency for each future time period based on past usage data. The constructed prediction model is used to predict future usage behavior, generating future usage time points and corresponding usage frequencies. The model predicts 6 uses between 08:00 and 09:00 next Monday, and 4 uses between 09:00 and 10:00. The predicted usage behavior will be recorded in the system and analyzed to identify future usage trends. Ensure detailed records for each prediction to allow for subsequent strategy adjustments. The record format is: Prediction Time: 2023-04-10, Time Period: 08:00-09:00, Predicted Uses: 6, Status: Expected Increase.

[0055] In this embodiment, see Figure 3 The diagram below illustrates the detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include:

[0056] Real-time bathroom ambient lighting parameters are obtained based on usage behavior prediction time points;

[0057] Calculate the light intensity parameter of the real-time bathroom ambient lighting parameters;

[0058] Evolve the light intensity timing fluctuation of the light intensity parameter to obtain the bathroom light intensity timing fluctuation characteristics;

[0059] Based on the real-time bathroom environment light parameter, light distribution recognition is performed to obtain bathroom light space distribution data;

[0060] According to the bathroom light space distribution data, the spatiotemporal light distribution fitting of the bathroom light intensity timing fluctuation characteristics is performed to construct a real-time bathroom light distribution network;

[0061] According to all user usage behavior information, real-time brightness demand prediction is performed to generate a brightness demand prediction value;

[0062] According to the brightness demand prediction value and the real-time bathroom light distribution network, light intensity output parameter calculation is performed to obtain an initial light intensity output parameter.

[0063] In this example, the sensor is set to record the light intensity every second, and the monitoring data includes a timestamp and the corresponding light intensity value for subsequent analysis. The collected light data is stored in a database to ensure data integrity and traceability. The data should be stored in a structured format for subsequent analysis and processing. The record format is: Timestamp: 2023-04-01 08:00:00, Light Intensity: 300 lux. These data will provide a basis for subsequent analysis. At the user behavior prediction time point, obtain the latest real-time ambient light parameters. These parameters will be used to calculate the light intensity and analyze the lighting conditions in the bathroom environment. Obtain the light data 5 minutes before the user's expected use time to prepare for subsequent light intensity calculation. Based on real-time light data, calculate the light intensity parameter. The lux value collected by the sensor can be directly used as the main parameter of light intensity. If the light sensor records a light intensity of 350 lux at a certain time, this value is directly used as the current environmental light intensity parameter. Record the calculated light intensity parameter to form a light intensity dataset for subsequent analysis and comparison. The record format is: Timestamp: 2023-04-01 08:00:05, Light Intensity: 350 lux. These records will be used to analyze the timing fluctuation characteristics of light intensity. Visualize the light intensity parameter to intuitively understand the light change situation. A line chart can be used to show the change trend of light intensity at different time points. Generate a chart with X-axis representing time and Y-axis representing light intensity to show the light intensity change in the past hour. Organize the real-time light intensity parameter into timing data to form a time series for fluctuation analysis. Ensure the timing of the data for subsequent analysis. Record the light intensity data in the past hour to form a time series list: [(t0, 300 lux), (t1, 350 lux), (t2, 320 lux)]. Perform fluctuation analysis on the timing data of light intensity to calculate the standard deviation and mean of light intensity to obtain the fluctuation characteristics. Short-term fluctuations can be analyzed using the sliding window method. If the light intensity fluctuation range in the past 10 minutes is 300-350 lux, the mean is 325 lux and the standard deviation is 15 lux. Based on real-time light parameters, identify the light distribution. By placing sensors at different locations in the bathroom, obtain light intensity data for each region to form light space distribution data. Install multiple sensors in different areas of the bathroom (such as above the mirror, next to the sink, etc.) to record the light intensity at each location to form a light distribution map. Organize the light intensity data at different locations into spatial distribution data for subsequent light analysis. Ensure that the data includes location coordinates and corresponding light intensity. The record format is: Location: (x1, y1), Light Intensity: 300 lux; Location: (x2, y2), Light Intensity: 350 lux. Visualize the light space distribution data to generate a light distribution map.A heat map is generated to display the light intensity in different areas, helping users understand the distribution of light. The heat map is generated with colors ranging from blue (low light) to red (high light), clearly showing the light distribution in each area of the bathroom. Based on the spatial distribution of light and the temporal fluctuation characteristics of light intensity, a spatio-temporal light distribution model is constructed. This model should be able to reflect the changes in light intensity in time and space. Using a multiple linear regression model, input the light intensity and spatial position data to construct the light distribution model, and predict the light distribution at different time points. Fit the model using historical data to optimize the model parameters to ensure the accuracy and effectiveness of the model. The model performance can be evaluated by cross-validation method. Use historical light data to train the model and adjust the model parameters to minimize the difference between predicted light intensity and actual value. Verify the constructed spatio-temporal light distribution model to ensure its effectiveness in real environment. Record the prediction results of the model and its accuracy for future adjustment. Integrate all user behavior information to analyze the user's brightness demand in different time periods. Through historical usage behavior data, identify the user's brightness preference. If the user's usage frequency is higher in the morning and they prefer higher brightness, record this brightness demand feature. Build a brightness demand prediction model based on user usage frequency and light intensity data to predict future brightness demand. Time series analysis or machine learning methods can be used. Use the ARIMA model to predict the user's brightness demand in the future, and analyze the brightness change trend in the historical data. Through the prediction model, generate the predicted value of the brightness demand at the current time point. This value will serve as the basis for subsequent calculation of light intensity output parameters. The model predicts that the user's brightness demand in the next time period is 400 lux, which will be used as the target brightness value for subsequent adjustments. Calculate the light intensity output parameter based on the brightness demand prediction value and the real-time bathroom light distribution network. This parameter should ensure that the user's brightness demand is met. If the brightness demand is 400 lux and the current light intensity is 300 lux, an output of 100 lux is needed. Adjust the brightness output of the LED lights based on the calculated light intensity output parameter to meet the user's demand. Ensure that the adjustment process is smooth and avoids sudden changes. Smoothly increase the brightness output of the LED lights using PWM (Pulse Width Modulation) technology to achieve the required light intensity. Record the light intensity output parameter and its adjustment results for future optimization and adjustment. Establish a feedback mechanism to ensure real-time monitoring and adjustment of light intensity output during user use.

[0064] In this embodiment, the specific steps for real-time brightness demand prediction based on all user behavior information are as follows:

[0065] Extract user historical usage brightness based on all user behavior information;

[0066] Calculate the usage frequency of the user's historical usage brightness;

[0067] perform brightness value distribution analysis on the use frequency to generate a brightness value distribution graph;

[0068] calculate the highest frequency use brightness according to the brightness value distribution graph;

[0069] identify the use environment brightness according to the highest frequency use brightness, and extract the corresponding use environment brightness;

[0070] mine user brightness preference based on the corresponding use environment brightness and the highest frequency use brightness, thereby generating user brightness preference features;

[0071] perform real-time brightness demand prediction based on the user brightness preference features, thereby generating a brightness demand prediction value.

[0072] In this embodiment, all use behavior information of the user is collected, which should include the brightness value at each use. The brightness parameters when the user turns on the LED lamp each time are recorded by the monitoring system, and these data are sorted to form a historical use brightness data set. It is assumed that the use records of the user at different time periods are: use time 1: 2023-04-01 08:00:00, brightness: 300 lux; use time 2: 2023-04-01 08:05:00, brightness: 400 lux; use time 3: 2023-04-01 08:10:00, brightness: 350 lux. The collected brightness data is cleaned to remove abnormal values and repeated records, to ensure the accuracy and integrity of the data. A brightness range (such as 100-800 lux) can be set to filter out records that do not meet the range. If the brightness of a record is 900 lux, it is considered as an abnormal value and is deleted.

[0073] Organize the cleaned brightness data into a list or data frame for subsequent analysis. Each record should contain user ID, usage time, brightness value, etc. Record format: User ID:001, brightness records: [(time1, 300lux), (time2, 400lux), (time3, 350lux)]. Based on historical usage brightness data, count the frequency of each brightness value. You can use the histogram method to divide the brightness value into several intervals (such as every 50 lux as an interval), and count the number of times used in each interval. The statistical results may show that the brightness interval 300-350lux has a frequency of 10 times, and the brightness interval 350-400lux has a frequency of 15 times. Organize the statistical frequency data obtained into a frequency table, recording each brightness value and its corresponding frequency. This will provide basic data for subsequent brightness value distribution analysis. Record the frequency statistics and visualize the brightness value distribution chart to visually display the distribution of user historical brightness usage. Analyze the generated brightness value frequency table and calculate the mean, standard deviation and other statistical indicators of brightness value to better understand the user's brightness usage habits. If the calculated mean brightness value is 365lux and the standard deviation is 25lux, it can be inferred that the user's brightness preference is relatively concentrated. Extract the highest frequency brightness value from the frequency table to identify the brightness most frequently used by the user. You can determine the representative value of the interval with the highest frequency by looking up the interval with the highest frequency. If the brightness interval 350-400lux has the highest frequency (15 times), it can be considered that the highest frequency brightness is 375lux (the median value of the interval). Record the analysis results, including the highest frequency brightness value and its corresponding frequency, and generate the corresponding chart for visual display. Record format: Highest frequency brightness value: 375lux, frequency: 15 times, and generate a pie chart to show the proportion of each brightness frequency.

[0074] During user usage, the lighting data of the bathroom environment is monitored in real-time. The current ambient lighting intensity is obtained using a light sensor for ambient brightness recognition. The sensor records an ambient lighting intensity of 200 lux during user usage. The collected ambient lighting data is compared with the user's highest frequency brightness value to identify the brightness characteristics of the current usage environment. The record format is: Current ambient lighting intensity: 200 lux, Highest frequency brightness value: 375 lux. The current ambient brightness and its relationship with the user's preferred brightness value are recorded for subsequent analysis of the user's brightness preference characteristics. The difference between the ambient brightness and the preferred brightness is 175 lux, and the impact of this difference on the user's usage experience is analyzed. Based on the current ambient brightness and the user's highest frequency brightness value, the user's brightness preference characteristics are calculated. The preference characteristics can be set as the user's brightness requirements under different ambient lighting conditions. If the user prefers 375 lux when the ambient lighting is 200 lux, this preference characteristic can be recorded. The user's brightness preference characteristics are classified to form a data archive of the user's brightness preferences. This will provide a basis for subsequent brightness demand prediction. The record format is: User ID: 001, Ambient lighting: 200 lux, Brightness preference: 375 lux, Preference characteristics: [Ambient lighting and preferred brightness difference 175 lux]. The mined brightness preference characteristics are analyzed to identify the brightness demand characteristics of different users in specific environments for personalized brightness adjustment. Analysis finds that users tend to prefer high brightness settings in low light environments, while preferring lower brightness in high light environments. Based on the user's brightness preference characteristics, a real-time brightness demand prediction model is constructed. Machine learning algorithms such as linear regression or decision trees can be used to predict future brightness demands. Collect brightness demand data of users under different ambient lighting conditions, train the model to identify potential brightness demand patterns. Use the constructed prediction model to make real-time predictions of brightness demand under current ambient lighting conditions. Input the current ambient lighting intensity and user preference characteristics to generate a brightness demand prediction value. If the current ambient lighting is 200 lux, the model predicts a brightness demand of 350 lux. Record the brightness demand prediction value and analyze its impact on the user's usage experience. This will provide a basis for subsequent LED light adjustment. The record format is: Prediction time: 2023-04-01 08:30:00, Predicted brightness demand: 350 lux, Status: qualified.

[0075] In this embodiment, referring to Figure 4 For the detailed implementation step flowchart of step S3, in this embodiment, the detailed implementation steps of step S3 include:

[0076] When the user uses the bathroom mirror, instant bathroom mirror lighting control is performed according to the initial light intensity output parameter, and ambient humidity monitoring parameters are obtained based on sensors;

[0077] The concentration of water vapor in the air is calculated based on the environmental humidity monitoring parameters to obtain the water vapor concentration value in the bathroom.

[0078] The concentration trend of water vapor in the bathroom was analyzed to obtain the characteristics of the water vapor concentration trend.

[0079] Based on the water vapor concentration value in the bathroom, a fuzzy quantitative correlation analysis of water mist on the mirror surface was conducted to construct a fuzzy quantitative relationship of water mist on the mirror surface.

[0080] Based on the quantitative relationship of water vapor fuzziness in the mirror surface, the trend change characteristics of water vapor concentration are analyzed to construct a mirror fuzziness situation evolution diagram.

[0081] In this embodiment, when the system detects a user using the bathroom mirror (via a motion sensor or infrared sensor), it immediately activates the LED light and controls the illumination based on the previously calculated initial light intensity output parameters. This process ensures the user receives the required brightness when using the bathroom mirror. Assuming the initial light intensity output parameter is 400 lux, the system will immediately adjust the LED light's brightness to ensure this level is achieved during user use. The light intensity output is precisely controlled by adjusting the LED light's power or using pulse width modulation (PWM) technology. This technology allows for smooth transitions between different brightness levels, avoiding sudden brightness changes. If the current illumination is 200 lux and the target is 400 lux, the system will gradually increase the brightness, for example, by 50 lux per second, until the target value is reached. The system should monitor the illumination effect in real time to ensure the actual output matches the target. A light sensor can be used to provide feedback on the current light intensity; if a deviation is detected, the system should automatically adjust. If the sensor detects an actual illumination of 380 lux, the system will further increase the brightness until it reaches 400 lux. A humidity sensor is installed in the bathroom to ensure it can monitor changes in ambient humidity in real time. The sensor should possess high accuracy and rapid response capabilities to acquire humidity data promptly. The sensor is configured to record humidity values ​​every minute, with the monitoring data including a timestamp and the current humidity percentage. Humidity monitoring data will be stored in the system database for subsequent analysis. The data format should be structured for easy extraction and processing. The recording format is: Timestamp: 2023-04-01 08:00:00, Humidity: 70%. This data will provide the basis for subsequent water vapor concentration calculations. Ambient humidity monitoring parameters will be continuously acquired during user use of the bathroom mirror to ensure data real-time performance and accuracy. This will help assess the water vapor concentration in the bathroom. Humidity values ​​will be recorded in real-time each time the user uses the mirror, ensuring the data is continuously updated throughout the user's usage. The water vapor concentration in the air will be calculated based on the ambient humidity monitoring parameters. The following formula can be used for calculation: Among them, C v Water vapor concentration (g / m 3 H represents relative humidity (%), P represents relative humidity (%). sPa), R is the gas constant, and T is the absolute temperature in Kelvin (K). Assuming a relative humidity of 70% and a temperature of 25°C (298 K), the saturated water vapor pressure is 3168 Pa according to the table. Substitute the formula to calculate the water vapor concentration. Record the calculated water vapor concentration value in the system for subsequent analysis. Ensure that each calculation result is associated with a timestamp for easy tracking. The record format is: Timestamp: 2023-04-0108:00:05, Water Vapor Concentration: 14.7 g / m 3 . Organize the water vapor concentration data to form a clear dataset. Visualize the concentration changes through charts to help analyze the trends. Generate a line chart with the X-axis representing time and the Y-axis representing water vapor concentration to show the trend of concentration changes over time. Perform trend analysis on the collected water vapor concentration data to calculate the average, standard deviation, and rate of change of the concentration to identify trend characteristics. If the water vapor concentration rises from 10 g / m 3 to 15 g / m 3 in the past hour, calculate the average rate of change as 0.083 g / m 3 / min. Extract the characteristics of water vapor concentration changes, such as the rising rate, stable period, and falling period. You can set thresholds to determine the stages of concentration changes. If the concentration continues to rise by more than 3 g / m 3 in 15 minutes, mark it as a "rapid rise phase". Record the characteristics of concentration trend changes and visualize them through charts for intuitive understanding of concentration changes. Define the haze index of the mirror water mist, usually using physical properties such as light transmittance, reflectivity, etc. to quantify the impact of water mist. Set the haze index as the percentage decrease in light transmittance, if the light transmittance decreases from 90% to 70%, the haze index is 22.2%. Analyze the relationship between water vapor concentration and mirror haze, and establish a quantitative model. You can determine the correlation between the two through regression analysis. If data analysis shows that water vapor concentration increases by 1 g / m 3 , the haze increases by 2%, record this relationship. Record the analysis results of the quantitative relationship between haze in the system and visualize them through charts to help understand the quantitative relationship between water vapor concentration and mirror haze. Generate a scatter plot with the X-axis representing water vapor concentration and the Y-axis representing haze to show the linear relationship between the two. Based on the trend of water vapor concentration and the quantitative relationship of mirror haze, analyze the evolution of mirror haze. You can use a dynamic model to simulate the impact of water vapor concentration changes on mirror haze. If the concentration rises rapidly in a short period of time, it can be inferred that the mirror haze will increase rapidly in a short period of time. According to the analysis results, construct a mirror haze evolution graph to show how water vapor concentration changes affect the trend of mirror haze. The graph should include a time axis and a haze change curve. Generate a dynamic change chart with the X-axis representing time and the Y-axis representing haze to show the impact of water vapor concentration on mirror haze at different time points.

[0082] In this embodiment, step S4 includes the following steps:

[0083] According to the mirror fog accumulation and flow direction evolution map, the water mist accumulation and flow direction of the mirror are identified;

[0084] Based on the water mist accumulation and flow direction, the mirror thermal effect demisting analysis is performed to obtain the mirror thermal effect demisting rule;

[0085] Based on the mirror thermal effect demisting rule, the mirror heating treatment is performed, and the real-time fogging situation of the mirror is analyzed;

[0086] The real-time clarity of the mirror is inferred based on the real-time fogging situation, to obtain the real-time clarity evaluation value under the thermal effect demisting;

[0087] The real-time clarity evaluation value is dynamically adjusted based on the adaptive heating temperature, to generate an adaptive water mist fogging adjustment strategy.

[0088] In this embodiment, based on the mirror fogging situation evolution map, the image processing technology is used to analyze the water mist distribution on the mirror. The edge detection and threshold segmentation methods can be used to identify the boundary of the water mist from the image. By analyzing the fogging situation map, the edge area of the water mist is identified, and the area and distribution density of the water mist are calculated. These data will help determine the accumulation area and flow direction of the water mist. By comparing consecutive frame images, the moving track and flow direction of the water mist are calculated. The optical flow method or motion vector analysis can be used to track the changes of the water mist on the mirror. If the center position of the water mist changes at two consecutive time points, its displacement is calculated to determine the flow direction. The angle and speed of the flow direction are recorded for subsequent analysis. The results of the accumulation area and flow direction of the water mist are recorded in the system and visualized through charts to help users intuitively understand the dynamic characteristics of the water mist. A graph is generated to show the hot spot area of water mist accumulation and flow direction arrows, clearly identifying the distribution of the water mist. Based on the accumulation and flow direction of the water mist, a thermal effect model is constructed. The model should consider factors such as the thermal conductivity of the mirror material, the environmental temperature, and the water vapor concentration to analyze the influence of thermal effect on mirror demisting. The thermal effect model formula is set as: Q=k·A·(T m -T e ), where Q is the heat, k is the thermal conductivity, A is the mirror area, T m is the mirror temperature, and T eThe temperature is ambient. Through experimental data collection, analyze the dissipation speed and clarity changes of the mirror water mist under different temperature conditions. Record the relationship between the time of water mist disappearance and the clarity of the mirror under different heating temperatures. If the water mist disappears in 30 seconds at 60°C and in 50 seconds at 50°C, it can be inferred that the relationship between temperature and demisting efficiency. According to the law of thermal effect demisting, configure the mirror heating system. The system should have adjustable temperature heating elements and be able to monitor the mirror temperature in real time. Set the power of the heating element to 100W to quickly raise the mirror temperature in a short time. While performing mirror heating treatment, monitor the mirror fogging situation in real time. Through light sensors or image sensors, obtain the mirror clarity change data. Record the mirror clarity value every 1 second during heating and compare it with the previous fogging situation. Record the mirror fogging situation change after heating, analyze the impact of heating on mirror clarity. The record format is: heating time: 30 seconds, mirror temperature: 60°C, clarity evaluation value: 80% (20% higher than the previous value). Set the evaluation standard of mirror clarity, which can be quantified by light transmittance or fog index. Set the clarity as the percentage of light transmittance. If the light transmittance is 90%, the clarity is evaluated as 90%, and if it decreases to 70%, it is evaluated as fog. During the mirror heating process, infer the change of the mirror clarity based on the real-time monitoring data. According to the current temperature and water mist concentration, infer the improvement of the mirror clarity. If the clarity improves from 70% to 85% when heated to 55°C, record this change. Record the real-time clarity evaluation value in the system and establish a feedback mechanism to adjust the heating strategy when the clarity does not meet the expectations. The record format is: time: 2023-04-0108:15:00, real-time clarity: 85%, status: qualified; if the clarity does not meet the target, the system will automatically increase the heating temperature. Based on the real-time clarity evaluation value, design a dynamic heating temperature self-adaptive adjustment strategy. The strategy should be able to automatically adjust the heating temperature according to the clarity change to achieve the best demisting effect. Set the rules: if the real-time clarity is less than 75%, increase the heating temperature by 5°C; if it is higher than 85%, reduce the temperature to avoid overheating. Implement the dynamic adjustment strategy to adjust the heating temperature in real time. The system should have a feedback function to automatically adjust the temperature according to the current clarity and environmental changes. When the clarity evaluation value is 70%, the system will automatically adjust the heating temperature from 55°C to 60°C.

[0089] In this embodiment, step S5 includes the following steps:

[0090] Perform mirror water vapor distribution analysis on the mirror fogging evolution graph to obtain mirror water vapor distribution characteristics;

[0091] Perform mirror brightness attenuation trend calculation based on the mirror water vapor distribution characteristics to generate a mirror brightness attenuation trend.

[0092] Optimizing LED lamp dynamic brightness compensation based on mirror brightness decay trend, generating dynamic brightness compensation parameters;

[0093] According to the mirror blur trend evolution map, the light color temperature parameters of the mirror are calculated;

[0094] Adaptive light color temperature adaptation is performed on the water vapor concentration trend change characteristics and the light color temperature parameters, and color temperature adaptation parameters are generated;

[0095] According to the dynamic brightness compensation parameters and the color temperature adaptation parameters, dynamic light parameter adjustment is performed on the initial light intensity output parameters, and a dynamic light adjustment strategy is constructed.

[0096] In this embodiment, water vapor distribution data is extracted from the mirror blur trend evolution map. This can be done by analyzing the density and distribution of the blurred area using image processing techniques. Threshold segmentation and region analysis methods are used to identify the distribution characteristics of water vapor. Set the blur threshold to 50%, extract the pixels of the blurred area, calculate the proportion of the total mirror area, and obtain the distribution characteristics of water vapor. By analyzing the distribution characteristics of water vapor, relevant parameters such as the concentration of distribution, coverage area and maximum concentration are extracted. These features will help to understand the influence of water vapor on the clarity of the mirror. If the extraction result shows that the water vapor is concentrated in the center of the mirror, the coverage area is 60% and the concentration is 15g / m 3If the water vapor concentration exceeds the threshold, record these features. Record the water vapor distribution characteristics in the system and generate visual charts to help users intuitively understand the dynamic distribution of water vapor. Generate a heat map showing the distribution of water vapor on the mirror surface, with different colors representing different concentration levels, to help analyze its impact on mirror clarity. Collect the brightness values of the mirror at different time points and record the brightness changes after each user use. The brightness of the mirror can be monitored in real time by a light sensor. Set the monitoring time interval to once every minute and record the brightness values: Timestamp 1: 2023-04-0108:00:00, Brightness: 400 lux; Timestamp 2: 2023-04-0108:01:00, Brightness: 380 lux. Use linear regression or time series analysis methods to calculate the decay trend of the mirror brightness. Analyze the change of brightness over time and identify the brightness decay rate. If the brightness decreases from 400 lux to 360 lux within 10 minutes, the decay rate is 4 lux / min, and the rate is recorded. Based on the mirror brightness decay trend, set up a dynamic compensation parameter calculation model. This model should consider the brightness decay rate and user usage habits to dynamically adjust the brightness output of the LED light. If the decay rate is set to 4 lux / min, the LED light should compensate 5 lux in advance, then the compensation parameter is calculated as 5 lux. Design a dynamic brightness compensation strategy to automatically adjust the brightness of the LED light during user use to offset the decay of the mirror brightness. This strategy should have real-time response capability. If the user uses for 10 minutes, the system will monitor the brightness every minute and increase the brightness of the LED light accordingly to maintain a stable 400 lux. Record the dynamic brightness compensation parameters in the system and perform real-time verification to ensure the effectiveness of the compensation strategy. Record the parameters of each adjustment and their impact on the brightness of the mirror. The record format is: Compensation time: 2023-04-0108:10:00, Compensation parameter: 5 lux, Adjusted brightness: 400 lux, Status: Qualified. Monitor the color temperature of the LED light in real time through a color temperature sensor to obtain the current color temperature value of the light source. Color temperature is usually expressed in Kelvin (K) and reflects the color tone of the light source. Suppose the current color temperature of the LED light is monitored to be 5000K, which will be used as the basis for subsequent analysis. Record the obtained color temperature data in the system for subsequent analysis. You can set a timed monitoring to record the color temperature changes at different time intervals. The record format is: Timestamp: 2023-04-0108:00:00, Color temperature: 5000K. These data will provide the basis for subsequent color temperature adjustment. Based on the water vapor concentration trend change characteristics and light color temperature parameters, build an adaptive light color temperature model. This model should consider environmental humidity and mirror clarity to optimize color temperature output. If the water vapor concentration rises and causes clarity to decrease, automatically adjust the color temperature to a warm tone (such as 3000K) to improve user visual comfort.A color temperature adaptation strategy is designed to automatically adjust the color temperature of the LED lamp under different environmental conditions to achieve the best use effect. The rules are set: when the environmental humidity exceeds 70%, the color temperature is automatically adjusted to warm 3000K; when the humidity is less than 50%, the color temperature returns to the standard color temperature of 5000K. According to the dynamic brightness compensation parameters and color temperature adaptation parameters, a comprehensive dynamic lighting adjustment strategy is constructed. This strategy should be able to respond to user needs and environmental changes in real time to optimize the lighting effect. When the user is using it, if the clarity is detected to decrease, the system will automatically increase the brightness and adjust the color temperature to maintain the best visual effect. Implement the dynamic lighting adjustment strategy, real-time monitoring of the environment and user state, automatic adjustment of lighting parameters to adapt to the use demand. After the user enters the bathroom, the system will detect the environmental humidity and mirror clarity, dynamically adjust the brightness of the LED lamp to 400lux, and adjust the color temperature according to the humidity change. Record the implementation results of the dynamic lighting adjustment strategy in the system, and establish a feedback mechanism to ensure that the lighting effect can be optimized in real time during user use. The record format is: adjustment time: 2023-04-0108:30:00, brightness: 400lux, color temperature: 3000K, user satisfaction: high.

[0097] In this embodiment, step S6 includes the following steps:

[0098] Based on the adaptive water mist blur adjustment strategy and the dynamic lighting adjustment strategy, the dynamic bathroom mirror LED lamp control is performed, and the feedback information of the user is obtained;

[0099] Based on the feedback information of the user, multi-scenario demand deep mining is performed to obtain the multi-scenario demand characteristics of the user;

[0100] According to the multi-scenario demand characteristics of the user, intelligent reinforcement transfer learning is performed to construct an intelligent bathroom lamp control engine.

[0101] In this embodiment, based on the previously constructed adaptive water mist blur adjustment strategy and dynamic lighting adjustment strategy, the LED lamp control system is started. The system should automatically adjust the brightness and color temperature of the LED lamp according to real-time environmental parameters (such as humidity, temperature, and user behavior) to provide the best user experience. When the user enters the bathroom, the system automatically detects that the humidity is 70% and adjusts the light brightness to 400 lux while adjusting the color temperature to warm tone (about 3000K) to reduce the impact of water mist blur on vision. At an appropriate time after the user uses the bathroom mirror, actively collect user feedback information. Users can provide feedback on lighting effects, clarity, and overall user experience through touch screens, mobile applications, or voice assistants. Set up a feedback questionnaire, including questions such as "Your satisfaction with the current lighting brightness (1-5)" and "Mirror clarity meets expectations (yes / no)". Record user feedback data for subsequent analysis. Organize and store user feedback information in the database, ensuring that each piece of feedback data is associated with a timestamp and user ID for subsequent analysis and tracking. The record format is: Timestamp: 2023-04-0108:30:00, User ID: 001, Lighting Satisfaction: 4, Clarity Satisfaction: Yes. Ensure data integrity and accuracy to provide a foundation for subsequent demand mining. Perform deep analysis on the collected user feedback information to identify user demand characteristics in different use scenarios. This can be achieved through data mining techniques such as clustering analysis and association rule mining. Use the K-means clustering method to divide user feedback data into several main groups, identifying the commonalities and differences between high and low satisfaction users. Based on the results of the demand analysis, extract user demand characteristics in different scenarios, such as lighting requirements and mirror clarity requirements in the morning, evening, or bathing. Record these characteristics for subsequent modeling. The analysis results may show that morning users prefer 400 lux brightness and 3000K color temperature, while evening users prefer 350 lux brightness and 4500K color temperature. Record the extracted user multi-scenario demand characteristics in the system and display the demand differences in different scenarios through visual charts to help understand user preference changes. Generate a radar chart to show the lighting and color temperature preferences in different time periods, making user demand characteristics more intuitive. Based on user multi-scenario demand characteristics, design a reinforcement learning model to optimize the control strategy of the LED lamp. The model should be able to learn user usage habits and feedback and dynamically adjust the control strategy to adapt to changes in user demand. Use the Q-learning algorithm, set the state space as environmental humidity, lighting brightness, and user feedback, the action space as LED lamp brightness and color temperature adjustment, and the reward function according to user feedback satisfaction. Use existing user feedback data and scenario demand characteristics to implement transfer learning to optimize the learning process. Pre-trained models accelerate learning in new scenarios, enabling faster adaptation.If the existing user has successful experience in the use condition, it will be applied to the new user's situation, which improves the learning efficiency of the system in the initial stage. The control strategy optimized by reinforcement learning is integrated into the intelligent bathroom lamp control engine. System testing is conducted to verify the effectiveness of the control engine under different use conditions. The test results show that in a high humidity environment, the control engine can automatically adjust the brightness and color temperature when the user feedback satisfaction is improved by 20%, ensuring the best user experience.

[0102] In the embodiment, an LED lamp adaptive control device of an LED backlit bathroom mirror is provided, comprising:

[0103] A behavior prediction module is configured to acquire a monitoring log of the bathroom mirror LED lamp, perform use time frequency distribution statistics and use behavior prediction, and generate a use behavior prediction time point.

[0104] A brightness demand prediction module is configured to perform real-time brightness demand prediction according to the use behavior prediction time point, and perform light intensity output parameter calculation to obtain initial light intensity output parameters.

[0105] A mirror fog analysis module is configured to perform immediate bathroom mirror lighting control according to the initial light intensity output parameters, and acquire environmental humidity monitoring parameters; perform mirror fog state analysis according to the environmental humidity monitoring parameters, and construct a mirror fog state evolution map.

[0106] A heating temperature adjustment module is configured to perform mirror thermal effect defogging analysis and dynamic heating temperature adaptive adjustment according to the mirror fog state evolution map, to generate an adaptive water mist fog adjustment strategy.

[0107] A dynamic lighting adjustment module is configured to perform dynamic brightness compensation optimization and adaptive lighting color temperature adaptation according to the mirror fog state evolution map, and construct a dynamic lighting adjustment strategy.

[0108] An intelligent control module is configured to perform dynamic bathroom mirror LED lamp control and intelligent reinforcement transfer learning based on the adaptive water mist fog adjustment strategy and the dynamic lighting adjustment strategy, and construct an intelligent bathroom lamp control engine.

[0109] The application constructs a user usage behavior portrait based on log data such as the on time, frequency, use duration, etc. of the LED lamp, realizes the transition from "passive response" to "active prediction", avoids unnecessary lighting of the LED lamp in the period of no use, effectively reduces energy consumption, and prolongs the service life of the lamp. It can be fused with sensor (such as human body induction) data for multi-user behavior separation and personalized analysis, and improve the intelligent degree. It can automatically adjust the light intensity according to the historical preference and environmental brightness before the user uses the bathroom mirror, improve the response speed and use experience. According to the lighting demand preference of different users (such as high brightness for men shaving and soft light for women making up), the personalized initial light setting is realized. Through real-time environmental humidity data (linkage with temperature and use period), the mirror fog model is established, and the fog degree change can be predicted. The fog state is quantified and presented, and the evolution atlas of "clear-mild fog-severe fog" is constructed, which provides visual basis for defogging decision. The actual fog or impending fog scene is identified, and the energy is saved by effectively avoiding false triggering of heating. The mirror fog state will affect the light reflection effect, which can be linked with the light change to judge the fog level and improve the analysis accuracy. According to the fog degree, the reasonable heating power and duration are matched, which avoids the increase of energy consumption due to excessive heating or the incomplete defogging due to insufficient heating. The temperature control algorithm can be adjusted according to different environments (winter / summer, humid / dry) and mirror fog levels to improve adaptability. The mirror surface is always kept clear in vision to improve the use comfort in high humidity environment. In the low power mode, the mirror surface is not foggy or only slightly foggy. The "on-demand defogging" is realized. In the case of slight fog, the reflection clarity is improved by brightness compensation, and the defogging device does not need to be started immediately. The color temperature can be automatically adjusted to match the scene, such as warm light in the morning to help wake up, cold light at night to help sleep, and high color rendering index light source for makeup. Through intelligent adjustment of light angle and brightness gradient, the visual problems such as glare and light spot caused by mirror fog are relieved. Dynamic lighting enhances visual safety, especially in the high humidity scene after hot water bathing, providing a clearer field of view and reducing the risk of use. Through user feedback (such as manual intervention frequency and use satisfaction), the control strategy is adjusted to improve long-term performance.

[0110] Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting, the scope of the application being defined by the appended claims rather than the above description, and it is intended to encompass all variations falling within the meaning and scope of the equivalent elements of the application file.

[0111] The foregoing merely illustrates the principles of the application and application of its principles. Various modifications and alterations to this implementation will occur to those skilled in the art. The scope of the application should be determined, however, by the following claims rather than by the embodiments shown.

Claims

1. A method of adaptive control of LED light of an LED backlit bathroom mirror, characterized in that, The method comprises the following steps: Step S1: Obtain the monitoring log of the bathroom mirror LED lamp, perform usage time frequency distribution statistics and usage behavior prediction, and generate a usage behavior prediction time point; Step S2: Perform real-time brightness demand prediction according to the usage behavior prediction time point, and perform light intensity output parameter calculation to obtain initial light intensity output parameters; Step S3: Perform instant bathroom mirror illumination control according to the initial light intensity output parameters, and obtain environmental humidity monitoring parameters; perform mirror surface fogging trend analysis according to the environmental humidity monitoring parameters, and construct a mirror surface fogging trend evolution map; Step S4: Perform mirror surface thermal effect defogging analysis and dynamic heating temperature adaptive adjustment according to the mirror surface fogging trend evolution map, to generate an adaptive water mist fogging adjustment strategy; Step S5: Perform dynamic brightness compensation optimization and adaptive illumination color temperature adaptation according to the mirror surface fogging trend evolution map, and construct a dynamic illumination adjustment strategy; Step S6: Perform dynamic bathroom mirror LED lamp control and intelligent reinforcement transfer learning based on the adaptive water mist fogging adjustment strategy and the dynamic illumination adjustment strategy, and construct an intelligent bathroom lamp control engine; In step S3, the specific steps are as follows: When it is detected that a user uses the bathroom mirror, instant bathroom mirror illumination control is performed according to the initial light intensity output parameters, and environmental humidity monitoring parameters are obtained based on sensors; Air water vapor concentration is calculated according to the environmental humidity monitoring parameters, to obtain a bathroom water vapor concentration value; Concentration trend change analysis is performed on the bathroom water vapor concentration value, to obtain a water vapor concentration trend change feature; Mirror surface water mist fogging quantitative correlation analysis is performed according to the bathroom water vapor concentration value, to construct a mirror surface water mist fogging quantitative relationship; Based on the mirror surface water mist fogging quantitative relationship, mirror surface fogging trend evolution is performed on the water vapor concentration trend change feature, to construct a mirror surface fogging trend evolution map; In step S4, the specific steps are as follows: Water mist accumulation and flow direction of the mirror are identified according to the mirror surface fogging trend evolution map; Mirror surface thermal effect defogging analysis is performed based on the water mist accumulation and flow direction, to obtain a mirror surface thermal effect defogging rule; Mirror heating treatment is performed based on the mirror surface thermal effect defogging rule, and real-time fogging trend of the mirror is analyzed; Real-time clarity evaluation value under thermal effect defogging is obtained by speculating the real-time fogging trend of the mirror; Dynamic heating temperature adaptive adjustment is performed on the real-time clarity evaluation value, to generate an adaptive water mist fogging adjustment strategy; In step S5, the specific steps are as follows: Mirror surface water vapor distribution analysis is performed on the mirror surface fogging trend evolution map, to obtain a mirror surface water vapor distribution feature; Mirror surface brightness attenuation trend calculation is performed based on the mirror surface water vapor distribution feature, to generate a mirror surface brightness attenuation trend; LED lamp dynamic brightness compensation optimization is performed based on the mirror surface brightness attenuation trend, to generate dynamic brightness compensation parameters; Illumination color temperature parameters of the mirror are calculated according to the mirror surface fogging trend evolution map; Adaptive illumination color temperature adaptation is performed on the water vapor concentration trend change feature and the illumination color temperature parameters, to generate color temperature adaptation parameters; Dynamic illumination parameter adjustment is performed on the initial light intensity output parameters according to the dynamic brightness compensation parameters and the color temperature adaptation parameters, to construct a dynamic illumination adjustment strategy.

2. The LED lamp adaptive control method for LED backlit bathroom mirror according to claim 1, wherein, The specific steps of step S1 are: Obtain the monitoring log of the bathroom mirror LED lamp; analyze the user usage behavior of the monitoring log to extract all user usage behavior information; Calculate the usage time period of the user usage behavior information and mark multiple usage time periods; According to the multiple usage time periods, the user usage time frequency distribution is calculated to obtain a usage time frequency distribution graph; According to the usage time frequency distribution graph, the usage time demand analysis is performed to obtain the historical usage time demand characteristics; Based on the historical usage time demand characteristics, the usage behavior prediction is performed to generate a usage behavior prediction time point.

3. The LED lamp adaptive control method for LED backlit bathroom mirror of claim 1, wherein, The specific steps of step S2 are: According to the usage behavior prediction time point, the real-time bathroom environment light parameter is obtained; Calculate the light intensity parameter of the real-time bathroom environment light parameter; According to the light intensity parameter, the light intensity time sequence fluctuation evolution is performed to obtain the bathroom light intensity time sequence fluctuation characteristics; Based on the real-time bathroom environment light parameter, the light distribution recognition is performed to obtain the bathroom light space distribution data; According to the bathroom light space distribution data, the spatio-temporal light distribution fitting of the bathroom light intensity time sequence fluctuation characteristics is performed to construct a real-time bathroom light distribution network; According to all the user usage behavior information, the real-time brightness demand prediction is performed to generate a brightness demand prediction value; According to the brightness demand prediction value and the real-time bathroom light distribution network, the light intensity output parameter calculation is performed to obtain the initial light intensity output parameter.

4. The LED lamp adaptive control method for LED backlit bathroom mirror of claim 1, wherein, The specific steps of the real-time brightness demand prediction based on all the user usage behavior information to generate a brightness demand prediction value are: According to all the user usage behavior information, the user historical usage brightness is extracted; Calculate the usage frequency of the user historical usage brightness; According to the usage frequency, the brightness value distribution analysis is performed to generate a brightness value distribution graph; According to the brightness value distribution graph, the highest frequency usage brightness is calculated; According to the highest frequency usage brightness, the usage environment brightness is identified to extract the corresponding usage environment brightness; According to the corresponding usage environment brightness and the highest frequency usage brightness, the user brightness preference is mined to generate a user brightness preference feature; Based on the user brightness preference feature, the real-time brightness demand prediction is performed to generate a brightness demand prediction value.

5. The LED lamp adaptive control method for LED backlit bathroom mirror of claim 1, wherein, The specific steps of step S6 are: Based on the adaptive water mist blur adjustment strategy and the dynamic light adjustment strategy, the dynamic bathroom mirror LED lamp control is performed, and the user feedback information is obtained; Based on the user feedback information, the multi-scenario demand deep mining is performed to obtain the user multi-scenario demand characteristics; According to the user multi-scenario demand characteristics, the intelligent reinforcement transfer learning is performed to construct an intelligent bathroom lamp control engine.

6. An LED lamp adaptive control device for an LED backlit bathroom mirror, characterized by, The LED lamp adaptive control method for the LED backlit bathroom mirror as claimed in claim 1 comprises: A behavior prediction module for obtaining the monitoring log of the bathroom mirror LED lamp, performing usage time frequency distribution statistics and usage behavior prediction, and generating a usage behavior prediction time point; A brightness demand prediction module for performing real-time brightness demand prediction according to the usage behavior prediction time point, and performing light intensity output parameter calculation to obtain an initial light intensity output parameter; The mirror surface blur analysis module is configured to perform instant bathroom mirror light control according to the initial light intensity output parameter, and obtain an environmental humidity monitoring parameter; perform mirror surface blur state analysis according to the environmental humidity monitoring parameter, and construct a mirror surface blur state evolution diagram; The heating temperature adjustment module is configured to perform mirror surface thermal effect defogging analysis according to the mirror surface blur state evolution diagram, and perform dynamic heating temperature self-adaptive adjustment, so as to generate an adaptive water mist blur adjustment strategy; The dynamic light adjustment module is configured to perform dynamic brightness compensation optimization according to the mirror surface blur state evolution diagram, and perform adaptive light color temperature adaptation, so as to construct a dynamic light adjustment strategy; The intelligent control module is configured to perform dynamic bathroom mirror LED lamp control and intelligent reinforcement transfer learning based on the adaptive water mist blur adjustment strategy and the dynamic light adjustment strategy, and construct an intelligent bathroom lamp control engine.

Images