LED bathroom mirror intelligent control method and system based on environment perception

Abstract

The invention relates to the technical field of LED light source control, in particular to an intelligent control method and system for an LED bathroom mirror based on environmental perception, and the method comprises the steps: firstly obtaining environmental parameters in a bathroom environment, the environmental parameters including humidity data, temperature data, human body induction data and associated equipment state data, and then according to the environmental parameters, carrying out the intelligent control of the LED bathroom mirror; and obtaining the use probability of the target LED bathroom mirror, controlling the target LED bathroom mirror to enter a low-power-consumption protection mode if the use probability obtained continuously for multiple times is lower than a preset threshold value, and performing light attenuation protection on the target LED bathroom mirror in the low-power-consumption protection mode. According to the invention, a'use probability 'dynamic evaluation mechanism is introduced, the time period in which illumination is really needed is accurately identified, and the idle time period in which the LED bathroom mirror is electrified but not used is used for light attenuation protection control, so that the user experience and durability requirements are perfectly balanced, and the problem that the light attenuation control of the LED bathroom mirror in the prior art affects the user experience is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of LED light source control, and in particular to an intelligent control method and system for an LED bathroom mirror based on environmental perception. Background Art

[0002] LED bathroom mirrors are bathroom mirrors with integrated LED lighting modules. They utilize LED light sources to provide uniform, energy-efficient lighting and are widely used in both home and commercial bathrooms. However, LED light sources inherently suffer from light decay, a process in which their luminous intensity gradually decreases over time. This decay is primarily caused by factors such as thermal effects on LED chips, material aging, and current stress, manifesting as reduced illumination and color temperature shift. For LED bathroom mirrors, light decay directly impacts the user's visual experience. For example, insufficient lighting can cause blurred reflections on the mirror surface, affecting accuracy in everyday activities like applying makeup or shaving. It also shortens the product's useful life and increases maintenance costs.

[0003] Various existing technologies have proposed protection and compensation measures for LED light decay, such as algorithms for detecting light decay when the lights are off or mechanisms for adjusting the brightness of the heating film and light source. However, these methods often come at the expense of user experience. For example, frequent light-off detection can disrupt normal user experience, while forced reduction of light source brightness can lead to unstable lighting effects.

[0004] Therefore, people need a control method that can intelligently sense environmental conditions and dynamically compensate for light attenuation without affecting normal user use, so as to take into account the lighting quality, service life and user experience of LED bathroom mirrors. Summary of the Invention

[0005] Therefore, the present invention provides an intelligent control method and system for LED bathroom mirrors based on environmental perception, so as to solve the problem in the prior art that the light decay control of LED bathroom mirrors affects the user experience.

[0006] The present invention provides an intelligent control method for an LED bathroom mirror based on environmental perception, comprising:

[0007] Obtaining environmental parameters in the bathroom environment, including humidity data, temperature data, human body sensing data, and associated device status data. The human body sensing data is used to represent the relative positional relationship between a person and the target LED bathroom mirror. Associated devices include devices located in the same bathroom environment as the target LED bathroom mirror and affected by a person's washing activities.

[0008] According to the environmental parameters, the usage probability of the target LED bathroom mirror is obtained;

[0009] If the usage probability obtained for multiple consecutive times is lower than a preset threshold, the target LED bathroom mirror is controlled to enter a low-power protection mode. In the low-power protection mode, the working intensity of the LED lamp beads in the target LED bathroom mirror is lower than the working intensity in the normal mode to perform light decay protection.

[0010] In a preferred implementation, obtaining the usage probability of a target LED bathroom mirror according to environmental parameters includes:

[0011] According to the environmental parameters, the input vector is established;

[0012] Inputting the input vector into a preset first neural network model to obtain a usage probability of the preset first neural network model output;

[0013] Among them, the preset first neural network model includes a first input layer, a first fully connected layer and a first output layer. The first input layer is used to accept input vectors, the first fully connected layer is used to perform weighted operations on the input vectors, and the first output layer is used to output usage probability according to the output results of the first fully connected layer. The preset first neural network model is iterated during actual use.

[0014] In a preferred implementation, the method further includes:

[0015] In low-power protection mode, multiple historical usage probabilities within a preset time window are obtained;

[0016] Make a prediction based on the historical usage probability to obtain the predicted usage time of the target LED bathroom mirror;

[0017] Based on the predicted usage time, the target LED bathroom mirror is preheated and controlled.

[0018] In a preferred implementation, the method of predicting the usage time of the target LED bathroom mirror based on the historical usage probability includes:

[0019] Obtain multiple historical environmental parameters within a preset time window, combine them with historical usage probabilities, and establish a historical input vector sequence;

[0020] The historical input vector sequence is input into the preset second neural network model to obtain the predicted usage time output by the preset second neural network model.

[0021] In a preferred implementation: the historical input vector sequence includes a first vector sequence, a second vector sequence and a usage probability sequence, wherein the elements of each vector in the first vector sequence include temperature and humidity, and the elements of each vector in the second vector sequence include human body sensing data and associated device status data; the preset second neural network model includes a first input layer, a first time series neural network branch, a second time series neural network branch, a third time series neural network branch, a fusion layer, a second fully connected layer and a second output layer, wherein the first input layer is used to input the first vector sequence, the second vector sequence and the usage probability sequence into the first time series neural network branch, the second time series neural network branch and the third time series neural network branch respectively, the first time series neural network branch, the second time series neural network branch and the third time series neural network branch respectively output context vectors corresponding to the three sequences, the fusion layer is used to perform weighted summation on the three context vectors, and input the fusion result into the second fully connected layer, and the second output layer is used to output the predicted usage time.

[0022] In a preferred implementation, preheating control of a target LED bathroom mirror based on predicted usage time includes:

[0023] Obtain the heating area of ​​the target LED bathroom mirror. The heating area is divided based on the distribution of LED lamp beads in the target LED bathroom mirror. The heating area includes the middle main light source area, the edge light strip area, and the backup area. Each heating area corresponds to a priority.

[0024] At the predicted usage time, obtain the panel temperature of each heating zone;

[0025] Determine the risk level of each heating zone based on its priority, panel temperature, and humidity data. The risk levels include low risk, medium risk, and high risk.

[0026] If the heating area is at a low risk level, the heating area will not be preheated;

[0027] If the heating area is at a medium risk level, the heating area is preheated at low power;

[0028] If the heating area is at a high risk level, the heating area is preheated with light attenuation protection.

[0029] In a preferred implementation, the method further includes:

[0030] In low-power protection mode, the light intensity data of the target LED bathroom mirror is collected at preset intervals;

[0031] According to the changes in light intensity data, the light decay rate is obtained;

[0032] According to the light decay rate, the light decay compensation strategy of the target LED bathroom mirror is obtained.

[0033] The present invention also provides an intelligent control system for LED bathroom mirrors based on environmental perception, comprising:

[0034] An environmental perception module, used to obtain environmental parameters in the bathroom environment, including humidity data, temperature data, human body sensing data, and associated device status data. The human body sensing data is used to represent the relative positional relationship between a person and the target LED bathroom mirror. Associated devices include devices located in the same bathroom environment as the target LED bathroom mirror and affected by a person's washing activities.

[0035] The usage analysis module is used to obtain the usage probability of the target LED bathroom mirror according to the environmental parameters;

[0036] The light decay protection module is used to control the target LED bathroom mirror to enter a low-power protection mode if the usage probability obtained for multiple consecutive times is lower than a preset threshold. In the low-power protection mode, the working intensity of the LED lamp beads in the target LED bathroom mirror is lower than the working intensity in the normal mode to perform light decay protection.

[0037] The present invention further provides an electronic device, comprising:

[0038] memory and processor;

[0039] The memory is used to store a program, and the processor is used to perform the steps of any of the above-mentioned environmental perception-based intelligent control methods for LED bathroom mirrors when executing the program.

[0040] The present invention also provides a computer-readable storage medium for storing a computer-readable program or instruction. When the program or instruction is executed by a processor, the steps in any of the above-mentioned environmental perception-based intelligent control methods for LED bathroom mirrors can be implemented.

[0041] The beneficial effects of adopting the above scheme are:

[0042] The present invention provides an intelligent control method for LED bathroom mirrors based on environmental perception. The method first obtains environmental parameters in the bathroom environment, including humidity data, temperature data, human body sensing data, and associated device status data. Then, based on the environmental parameters, the usage probability of the target LED bathroom mirror is obtained. If the usage probability obtained multiple times in a row is lower than a preset threshold, the target LED bathroom mirror is controlled to enter a low-power protection mode. In low-power protection mode, the operating intensity of the LED lamp beads in the target LED bathroom mirror is lower than that in normal mode to provide light decay protection. This method does not rely on complex sensor settings, but instead cleverly utilizes the status data of bathroom-related devices (such as showers and faucets) to indirectly judge user behavior, significantly reducing hardware costs and system complexity. Most importantly, the present invention innovatively introduces a dynamic "usage probability" evaluation mechanism to accurately identify time periods when lighting is actually needed, and utilizes idle time periods when the LED bathroom mirror is powered on but not in use for light decay protection control, solving the problem in the prior art that light decay control of LED bathroom mirrors affects user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 A flow chart of the method for intelligent control of LED bathroom mirrors based on environmental perception provided by the present invention;

[0044] Figure 2 This is a system architecture diagram of the environmental perception-based LED bathroom mirror intelligent control system provided by the present invention. DETAILED DESCRIPTION

[0045] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0046] Combine Figure 1 As shown, a specific embodiment of the present invention discloses an intelligent control method for LED bathroom mirrors based on environmental perception, including:

[0047] S101. Acquire environmental parameters in a bathroom environment, including humidity data, temperature data, human body sensing data, and associated device status data. The human body sensing data is used to represent the relative positional relationship between a person and a target LED bathroom mirror. Associated devices include devices located in the same bathroom environment as the target LED bathroom mirror and affected by a person's washing activities.

[0048] S102: Obtaining a usage probability of a target LED bathroom mirror based on environmental parameters;

[0049] S103. If the usage probability obtained for multiple consecutive times is lower than a preset threshold, the target LED bathroom mirror is controlled to enter a low power protection mode. In the low power protection mode, the working intensity of the LED lamp beads in the target LED bathroom mirror is lower than the working intensity in the normal mode to perform light decay protection.

[0050] Among the above environmental parameters, humidity data can be obtained through a humidity sensor, which can be set on the top / back of the LED bathroom mirror, or other locations in the bathroom environment. It is mainly used to indicate the real-time humidity in the bathroom (accuracy ±2% RH) and determine whether it is in a high-humidity state after showering (humidity > 70%) or a dry state (humidity < 50%).

[0051] Temperature data can be obtained through a temperature sensor, which can be set on the mirror surface (with an embedded NTC thermistor) or other locations in the bathroom environment. The mirror surface temperature (accuracy ±0.5°C) is mainly used to determine whether the heating film has heated up (>50°C). The ambient temperature (accuracy ±1°C) can be used to assist in identifying user activities (for example, in winter, the user may not have entered due to the low temperature).

[0052] Human body sensing data can be obtained through human body sensing sensors (infrared / microwave sensors, etc.), which can be set on the edge / top of the mirror, or other locations in the bathroom environment. It mainly detects the distance between the user and the mirror (0.5-2 meters is "close", and <0.5 meters is "in use"). Combined with the residence time (>30 seconds), it can be used to determine the usage status of the bathroom mirror.

[0053] The data of associated devices can be obtained by connecting to the smart home platform through technologies such as Wi-Fi / Bluetooth / Zigbee. The status of associated devices mainly includes the following:

[0054] Shower equipment (water heater / shower head / faucet): water flow sensor (whether there is water flow), water temperature sensor (whether it is at the bathing temperature of 40-50℃);

[0055] Smart toilet: seat temperature (whether heated), lid opening and closing status (whether in use);

[0056] Fresh air system: operating mode (whether dehumidification is turned on), humidity adjustment target value (whether it matches the current humidity in the bathroom).

[0057] The present invention does not rely on complex sensor settings, but cleverly uses status data of bathroom-related equipment (such as showers, faucets, etc.) to indirectly judge user behavior, greatly reducing hardware costs and system complexity.

[0058] Understandably, in most cases, users will turn on the LED bathroom mirror's lighting upon entering the bathroom, but this doesn't necessarily mean they'll use it immediately. This can happen while waiting for the water temperature to adjust, retrieving toiletries, or using the toilet or showering. For another example, in a hotel setting, the LED bathroom mirror turns on by default upon inserting the room card, but users don't necessarily use it immediately. Therefore, the present invention addresses this habitual nature by innovatively introducing a "probability of use" dynamic assessment mechanism to accurately identify the time periods when lighting is truly needed. This mechanism utilizes idle periods when the LED bathroom mirror is powered on but not in use to implement light decay protection, effectively entering a low-power protection mode. During this time, the LED bathroom mirror can implement any of the following light decay protection measures: reducing the drive current, shutting down LEDs in specific areas, adjusting the color temperature and brightness, or even shutting down the entire mirror's lighting.

[0059] This approach not only avoids the user experience interruption problem caused by fixed-duration protection in traditional solutions, but also makes full use of the gaps between user behaviors for low-power light decay protection, extending the life of the LED with almost no impact on normal use, and achieving the effect of "non-sensing protection": users get stable and sufficient light output when they need lighting, and the protection mechanism is automatically activated during non-use intervals, perfectly balancing functionality and durability requirements, and solving the problem in the existing technology that the light decay control of LED bathroom mirrors will affect the user experience.

[0060] Specifically, in the process of obtaining the usage probability of the target LED bathroom mirror based on the environmental parameters in step S102, any method can be used to calculate the probability, such as weighted summation of different environmental parameters, or calculation using any function model artificially fitted based on experimental data to obtain the usage probability. The present invention also provides a preferred method. In a preferred embodiment, the process of obtaining the usage probability of the target LED bathroom mirror based on the environmental parameters in step S102 specifically includes:

[0061] According to the environmental parameters, the input vector is established;

[0062] Inputting the input vector into a preset first neural network model to obtain a usage probability of the preset first neural network model output;

[0063] Among them, the preset first neural network model includes a first input layer, a first fully connected layer and a first output layer. The first input layer is used to accept input vectors, the first fully connected layer is used to perform weighted operations on the input vectors, and the first output layer is used to output usage probability according to the output results of the first fully connected layer. The preset first neural network model is iterated during actual use.

[0064] This embodiment specifically provides a preferred solution based on a neural network model. This neural network model adopts a streamlined, lightweight structure, significantly reducing model complexity while ensuring computational accuracy, enabling rapid system response and meeting the real-time requirements of bathroom scenarios. Furthermore, the preset first neural network model can be optimized and iterated during actual use. For example, within a short period of time after determining that a user has not used the bathroom mirror, if the user does not adjust the brightness of the LED bathroom mirror, the judgment can be considered accurate. If the user does adjust the brightness, the judgment is considered inaccurate. Because the output of the preset first neural network model in this embodiment is a probability, and the meaning of accurate and inaccurate judgments can be represented by probabilities such as 1 and 0, actual sample data and true labels can be obtained to optimize the preset neural network, achieving personalization and improving the user experience.

[0065] Overall, the data-driven approach used in this example demonstrates greater generalization capabilities than traditional fixed algorithms, flexibly adapting to varying bathroom layouts, equipment configurations, and usage scenarios. This design strikes an ideal balance between computing resource consumption, response speed, and prediction accuracy. It avoids the system burden of complex models while significantly enhancing the intelligence of probability-based judgments, providing a reliable basis for subsequent light-loss protection decisions.

[0066] Furthermore, in the actual use of LED bathroom mirrors, when the humidity in the bathroom environment is high (such as after a shower), condensation mist is easily generated on the mirror surface. At this time, the system will activate the heating film for demisting. The heating film is usually installed close to or near the mirror body, and its operating temperature can reach 40°C to 60°C or even higher (depending on the demisting requirements and the ambient humidity). The purpose is to quickly evaporate the water mist by raising the mirror surface temperature. It is conceivable that the heating film preheating and demisting process will significantly accelerate the light decay of the LED. This effect is mainly due to the interaction between the high temperature environment when the heating film is working and the thermal sensitivity of the LED chip. When the heating film is continuously working, the temperature of the mirror body and the surrounding environment remains high for a long time, and the LED chip is in a high temperature state for a long time, and its light decay rate will be significantly accelerated. This high-temperature environment caused by the heated film defogging not only directly accelerates the LED's light decay, but can also trigger a vicious cycle due to the accumulation of light decay: light decay leads to insufficient lighting brightness, and users may increase the drive current to compensate. This higher current further increases chip heat generation, forming a closed loop of "light decay, higher current, higher temperature, accelerated light decay," which ultimately significantly shortens the effective life of the LED bathroom mirror and affects the user experience. Therefore, based on the technical features described above, this embodiment further designs a preheating control method to balance the defogging requirements and LED light decay protection during the heated film defogging process.

[0067] For details, please refer to Figure 1In a preferred embodiment, the above-mentioned LED bathroom mirror intelligent control method based on environmental perception further includes:

[0068] S104. In the low power protection mode, obtain multiple historical usage probabilities within a preset time window;

[0069] S105: Predict the usage time of the target LED bathroom mirror based on the historical usage probability;

[0070] S106 : Preheating the target LED bathroom mirror based on the predicted usage time.

[0071] This embodiment utilizes the usage probability obtained above and, through an intelligent prediction mechanism, continuously monitors and analyzes historical usage probability data in low-power protection mode. This allows for a relatively accurate prediction of the specific time point when a user will use the bathroom mirror (i.e., the predicted usage time), thereby achieving precise timing control of the heating film operation—the heating film is activated for demisting and preheating only during the critical period before the user actually uses it, avoiding the problem of LEDs being in a long-term high-temperature stress state due to continuous high-temperature operation in traditional solutions.

[0072] This dynamic preheating strategy, on the one hand, ensures the timeliness and effectiveness of the defogger function (there is no water mist interference on the mirror when the user uses it), and on the other hand, greatly shortens the high-temperature action time of the heating film, so that the LED chip can work in a lower temperature environment most of the time, suppressing the accelerated light decay effect from the source. At the same time, this embodiment can break out of the vicious cycle mode described above, effectively extending the service life of the LED, ensuring the lighting quality, and improving the overall durability of the system.

[0073] It is understandable that in the above step S105, in the process of predicting the usage time of the target LED bathroom mirror based on the historical usage probability, the calculation of the predicted usage time can be performed using any existing method. For example, the historical usage probability can be fitted to obtain a function that describes the probability change trend, thereby obtaining the time when the probability reaches a certain threshold as the predicted usage time.

[0074] The present invention also provides a more accurate method. In a preferred embodiment, the above step S105, predicting the usage time of the target LED bathroom mirror based on the historical usage probability, specifically includes:

[0075] Obtain multiple historical environmental parameters within a preset time window, combine them with historical usage probabilities, and establish a historical input vector sequence;

[0076] The historical input vector sequence is input into the preset second neural network model to obtain the predicted usage time output by the preset second neural network model.

[0077] This embodiment combines multi-dimensional historical environmental parameters (such as humidity, temperature, etc.) within a preset time window with the corresponding historical usage probabilities to jointly construct an input vector sequence. By presetting a second neural network model for deep feature learning and time series modeling, it can accurately capture the complex nonlinear laws of user usage behavior and the dynamic correlation between environmental changes. Compared with traditional fitting function methods, it has stronger generalization ability and higher prediction accuracy.

[0078] It is particularly noteworthy that this embodiment fully utilizes the technical characteristics of the low-power protection mode. In this mode, the user has not yet enabled the bathroom mirror and the system does not need to respond in real time, thus providing an ideal operating environment for neural network models with high computational complexity. This not only ensures the reliability of the prediction results, but also avoids the impact of complex calculations on the real-time performance of the system, achieving a perfect balance between "high-precision prediction" and "low computational overhead", enabling the system to accurately predict user usage needs in advance, providing a reliable basis for subsequent precise preheating control, and further optimizing the synergistic effect of LED light decay protection and user experience.

[0079] Specifically, in a preferred embodiment, the historical input vector sequence includes a first vector sequence, a second vector sequence and a usage probability sequence, wherein the elements of each vector in the first vector sequence include temperature and humidity, and the elements of each vector in the second vector sequence include human body sensing data and associated device status data; the preset second neural network model includes a first input layer, a first time series neural network branch, a second time series neural network branch, a third time series neural network branch, a fusion layer, a second fully connected layer and a second output layer, wherein the first input layer is used to input the first vector sequence, the second vector sequence and the usage probability sequence into the first time series neural network branch, the second time series neural network branch and the third time series neural network branch respectively, the first time series neural network branch, the second time series neural network branch and the third time series neural network branch respectively output context vectors corresponding to the three sequences, the fusion layer is used to perform weighted summation on the three context vectors, and input the fusion result into the second fully connected layer, and the second output layer is used to output the predicted usage time.

[0080] There is a strong intrinsic correlation between temperature and humidity, and there is a strong intrinsic correlation between human body sensing data and associated device status data. Therefore, this embodiment adopts a three-branch parallel structure. The first time-series neural network branch accurately models the temperature and humidity environmental characteristics, the second branch deeply analyzes the behavioral patterns of human body sensing and associated device status, and the third branch dynamically tracks the changing trends of historical usage probabilities, thereby realizing multi-dimensional feature fusion and high-dimensional time series modeling of user usage behavior. Compared with traditional single-variable prediction methods, this multi-dimensional feature fusion mechanism can more comprehensively capture the complex nonlinear relationship between environmental parameters, user activity patterns and historical usage habits in bathroom scenes, significantly improving the accuracy and robustness of the prediction results. The specially designed fusion layer dynamically balances the contribution of different feature branches through an adaptive weighting mechanism, further optimizing the model's adaptability to complex scenarios. At the same time, the branch parallel mode can also improve processing efficiency, achieving a perfect balance between high-precision prediction and low-latency response. It can be understood that the above-mentioned first time series neural network branch, second time series neural network branch, and third time series neural network branch can be implemented using any existing neural network structure that can process time series data, such as RNN, LSTM, transformer, etc. The specific details are existing technologies that can be understood by technicians in this field.

[0081] Furthermore, in a preferred embodiment, the above step S106, preheating control of the target LED bathroom mirror based on the predicted usage time, specifically includes:

[0082] Obtain the heating area of ​​the target LED bathroom mirror. The heating area is divided based on the distribution of LED lamp beads in the target LED bathroom mirror. The heating area includes the middle main light source area, the edge light strip area, and the backup area. Each heating area corresponds to a priority.

[0083] At the predicted usage time, obtain the panel temperature of each heating zone;

[0084] Determine the risk level of each heating zone based on its priority, panel temperature, and humidity data. The risk levels include low risk, medium risk, and high risk.

[0085] If the heating area is at a low risk level, the heating area will not be preheated;

[0086] If the heating area is at a medium risk level, the heating area is preheated at low power;

[0087] If the heating area is at a high risk level, the heating area is preheated with light attenuation protection.

[0088] This embodiment divides the LED bathroom mirror into three heating zones with different priorities: the central main light source zone, the edge light strip zone, and the backup zone. In combination with real-time panel temperature and ambient humidity data, an innovative three-level risk level dynamic assessment mechanism is established. An energy-saving, no-preheating strategy is adopted for low-risk areas. Low-power preheating is implemented in medium-risk areas to balance energy consumption and defogging requirements. A precise preheating solution with light decay protection is used in high-risk areas.

[0089] This refined control method based on spatial differentiation and risk levels, on the one hand, significantly reduces the ineffective energy consumption of the entire system and avoids the energy waste of unified preheating of the entire area in traditional solutions; on the other hand, by prioritizing the defogging effect of the main light source area (the core area of ​​the user's vision) and intelligently delaying the heating start-up in non-critical areas, it not only ensures the immediate defogging needs of users when using it, but also minimizes the duration of the high temperature generated by the heating film on the LED chip, thereby suppressing the accelerated light decay effect from the source.

[0090] A more specific embodiment of the above step S106 is:

[0091] Divide the heating film into 3 areas according to the distribution of LED lamp beads (consistent with the division of LED light strips):

[0092] Middle main light source area: covers the main lighting area of ​​the face and has the highest heating priority;

[0093] Edge light strip area: close to the edge of the mirror, prone to fogging due to condensation on the mirror, and has medium heating priority;

[0094] Backup area: out of the user's sight, with the lowest heating priority (activated only in extreme high humidity).

[0095] The above heating priority can be expressed in a numerical form. By combining the numerical value with the panel temperature and humidity data (by weighted summation or conditional judgment, etc.), the specific level of each area can be obtained.

[0096] Specific responses for each risk level include:

[0097] Low risk (for example, the area is a backup area or an edge light strip area, and the panel temperature in the area is ≤50°C, and the ambient humidity is ≤70°C): no heating is required;

[0098] Medium risk (such as the area is a backup area, edge light strip area, or middle main light area, and the panel temperature in this area is between 50°C and 60°C, and the ambient humidity is between 70°C and 80°C): low-power heating;

[0099] High risk (for example, the area is an edge light strip area or a central main light source area, and the panel temperature in this area is >60°C, and the ambient humidity is >80°C): medium-to-high power heating (with light decay protection).

[0100] It is understandable that the specific power value ranges such as "low power" and "high power" in the above process can be manually defined according to actual conditions, and only "high", "medium" and "low" need to be distinguished. The specific strategy of optical attenuation protection can also be flexibly set according to actual conditions, for example:

[0101] 1. Real-time monitoring and protection of junction temperature

[0102] Monitoring method: The infrared temperature sensor is used to collect the surface temperature of the LED lamp bead in real time, and then the real-time junction temperature is estimated by the formula;

[0103] Protection threshold: Set the upper limit of junction temperature safety. If the real-time junction temperature approaches the threshold, the heating film power will be automatically reduced or heating will be suspended.

[0104] 2. Collaborative derating of heating and LED driver

[0105] Dynamic current regulation: When the heating film is started, the LED driving current is reduced synchronously to reduce the heat generated by the LED itself;

[0106] Heating-cooling cycle: If heating causes the junction temperature to rise rapidly, a cycle mode such as "heating for 5 minutes and cooling for 2 minutes" can be used to avoid continuous high temperature.

[0107] Furthermore, under normal conditions, real-time monitoring and compensation can be achieved through "current-light intensity curve fitting", for example:

[0108] The main control chip starts the "light decay self-test mode" regularly (for example, at 3 a.m. every day when the user is not using it):

[0109] Step 1: Turn off all zone light strips and record the baseline driving current value of each zone;

[0110] Step 2: Turn on each zone light strip with a fixed duty cycle (e.g. 50%) and collect the corresponding light intensity sensor values;

[0111] Step 3: Calculate the actual light intensity using the pre-calibrated "current-light intensity standard curve" (calibrated before leaving the factory);

[0112] Step 4: Compare the actual light intensity with the initial light intensity and calculate the light attenuation rate of each partition.

[0113] It can be seen that the above method requires closing the partition and waiting, so that the LED bathroom mirror is turned off. When the user is in the bathroom, this mode will attract the user's attention and affect the user experience. The present invention also provides a non-sensitive light attenuation detection method:

[0114] In low-power protection mode, the light intensity data of the target LED bathroom mirror is collected at preset intervals;

[0115] According to the changes in light intensity data, the light decay rate is obtained;

[0116] According to the light decay rate, the light decay compensation strategy of the target LED bathroom mirror is obtained.

[0117] Compared to traditional methods that require periodic shutdown of light strips to collect baseline values, resulting in periodic light-off phenomena that are noticeable to users, this solution cleverly utilizes the technical characteristics of low-power protection mode to continuously collect light intensity data without the user's awareness. By analyzing the dynamic changes in light intensity data, the light decay rate is calculated, completely eliminating the interference of the detection process on normal user use. By decoupling the detection process from user activities, the system can continuously monitor light decay at any time (including when the user is bathing), achieving truly "unnoticed" intelligent management.

[0118] After light attenuation detection, any existing strategy can be used to compensate for light attenuation, including:

[0119] If the attenuation rate of a certain partition is greater than 20% (critical value), the driving current of the partition is increased, and the compensation effect is verified in real time through the light intensity sensor;

[0120] If the global average attenuation rate is greater than 30%, a "global brightness degradation reminder" (APP push) will be triggered, and the user is advised to clean the mirror or contact after-sales service (to avoid excessive current increase that accelerates light attenuation).

[0121] Combine Figure 2 As shown, the present invention also provides an intelligent control system for LED bathroom mirrors based on environmental perception, comprising:

[0122] Environmental sensing module 210, for acquiring environmental parameters in the bathroom environment, including humidity data, temperature data, human body sensing data, and associated device status data. The human body sensing data is used to represent the relative positional relationship between a person and a target LED bathroom mirror. Associated devices include devices located in the same bathroom environment as the target LED bathroom mirror and affected by a person's washing activities.

[0123] The usage analysis module 220 is used to obtain the usage probability of the target LED bathroom mirror according to the environmental parameters;

[0124] The light decay protection module 230 is used to control the target LED bathroom mirror to enter a low power protection mode if the usage probability obtained multiple times in a row is lower than a preset threshold. In the low power protection mode, the working intensity of the LED lamp beads in the target LED bathroom mirror is lower than the working intensity in the normal mode to perform light decay protection.

[0125] It should be noted here that the corresponding system provided in the above embodiments is a computer program product, which can implement the technical solutions described in the above method embodiments. The specific implementation principles of the above modules or units can be found in the corresponding contents in the above method embodiments, which will not be repeated here.

[0126] The present invention further provides an electronic device, comprising:

[0127] memory and processor;

[0128] The memory is used to store a program, and the processor is used to perform the steps of any of the above-mentioned environmental perception-based intelligent control methods for LED bathroom mirrors when executing the program.

[0129] The present invention also provides a computer-readable storage medium for storing a computer-readable program or instruction. When the program or instruction is executed by a processor, the steps in any of the above-mentioned environmental perception-based intelligent control methods for LED bathroom mirrors can be implemented.

[0130] The present invention provides an intelligent control method for LED bathroom mirrors based on environmental perception. The method first obtains environmental parameters in the bathroom environment, including humidity data, temperature data, human body sensing data, and associated device status data. Then, based on the environmental parameters, the usage probability of the target LED bathroom mirror is obtained. If the usage probability obtained multiple times in a row is lower than a preset threshold, the target LED bathroom mirror is controlled to enter a low-power protection mode. In low-power protection mode, the operating intensity of the LED lamp beads in the target LED bathroom mirror is lower than that in normal mode to provide light decay protection. This method does not rely on complex sensor settings, but instead cleverly utilizes the status data of bathroom-related devices (such as showers and faucets) to indirectly judge user behavior, significantly reducing hardware costs and system complexity. Most importantly, the present invention innovatively introduces a dynamic "usage probability" evaluation mechanism to accurately identify time periods when lighting is actually needed, and utilizes idle time periods when the LED bathroom mirror is powered on but not in use for light decay protection control, solving the problem in the prior art that light decay control of LED bathroom mirrors affects user experience.

[0131] It should be noted that the various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the various embodiments can be referenced to each other.

[0132] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An intelligent control method for LED bathroom mirrors based on environmental perception, characterized in that: include: Obtaining environmental parameters in the bathroom environment, including humidity data, temperature data, human body sensing data, and associated device status data. The human body sensing data is used to represent the relative positional relationship between a person and the target LED bathroom mirror. Associated devices include devices located in the same bathroom environment as the target LED bathroom mirror and affected by a person's washing activities. According to the environmental parameters, the usage probability of the target LED bathroom mirror is obtained; If the usage probability obtained for multiple consecutive times is lower than a preset threshold, the target LED bathroom mirror is controlled to enter a low-power protection mode. In the low-power protection mode, the working intensity of the LED lamp beads in the target LED bathroom mirror is lower than the working intensity in the normal mode to perform light decay protection.

2. The method for intelligent control of LED bathroom mirrors based on environmental perception according to claim 1, characterized in that: According to the environmental parameters, the usage probability of the target LED bathroom mirror is obtained, including: According to the environmental parameters, the input vector is established; Inputting the input vector into a preset first neural network model to obtain a usage probability of the preset first neural network model output; Among them, the preset first neural network model includes a first input layer, a first fully connected layer and a first output layer. The first input layer is used to accept input vectors, the first fully connected layer is used to perform weighted operations on the input vectors, and the first output layer is used to output usage probability according to the output results of the first fully connected layer. The preset first neural network model is iterated during actual use.

3. The method for intelligent control of LED bathroom mirrors based on environmental perception according to claim 1, characterized in that: Also includes: In low-power protection mode, multiple historical usage probabilities within a preset time window are obtained; Make a prediction based on the historical usage probability to obtain the predicted usage time of the target LED bathroom mirror; Based on the predicted usage time, the target LED bathroom mirror is preheated and controlled.

4. The method for intelligently controlling an LED bathroom mirror based on environmental perception according to claim 3, characterized in that: Based on the historical usage probability, the predicted usage time of the target LED bathroom mirror is obtained, including: Obtain multiple historical environmental parameters within a preset time window, combine them with historical usage probabilities, and establish a historical input vector sequence; The historical input vector sequence is input into the preset second neural network model to obtain the predicted usage time output by the preset second neural network model.

5. The method for intelligently controlling an LED bathroom mirror based on environmental perception according to claim 4, characterized in that: The historical input vector sequence includes a first vector sequence, a second vector sequence and a usage probability sequence, wherein the elements of each vector in the first vector sequence include temperature and humidity, and the elements of each vector in the second vector sequence include human body sensing data and associated device status data; the preset second neural network model includes a first input layer, a first time series neural network branch, a second time series neural network branch, a third time series neural network branch, a fusion layer, a second fully connected layer and a second output layer, wherein the first input layer is used to input the first vector sequence, the second vector sequence and the usage probability sequence into the first time series neural network branch, the second time series neural network branch and the third time series neural network branch respectively, the first time series neural network branch, the second time series neural network branch and the third time series neural network branch respectively output context vectors corresponding to the three sequences, the fusion layer is used to perform weighted summation on the three context vectors, and input the fusion result into the second fully connected layer, and the second output layer is used to output the predicted usage time.

6. The method for intelligently controlling an LED bathroom mirror based on environmental perception according to claim 3, characterized in that: Based on the predicted usage time, the target LED bathroom mirror is preheated and controlled, including: Obtain the heating area of ​​the target LED bathroom mirror. The heating area is divided based on the distribution of LED lamp beads in the target LED bathroom mirror. The heating area includes the middle main light source area, the edge light strip area, and the backup area. Each heating area corresponds to a priority. At the predicted usage time, obtain the panel temperature of each heating zone; Determine the risk level of each heating zone based on its priority, panel temperature, and humidity data. The risk levels include low, medium, and high risk levels. If the heating area is at a low risk level, the heating area will not be preheated; If the heating area is at a medium risk level, the heating area is preheated at low power; If the heating area is at a high risk level, the heating area is preheated with light attenuation protection.

7. The method for intelligently controlling an LED bathroom mirror based on environmental perception according to claim 3, characterized in that: Also includes: In low-power protection mode, the light intensity data of the target LED bathroom mirror is collected at preset intervals; According to the changes in light intensity data, the light decay rate is obtained; According to the light decay rate, the light decay compensation strategy of the target LED bathroom mirror is obtained.

8. An intelligent control system for LED bathroom mirrors based on environmental perception, characterized in that: include: An environmental perception module, used to obtain environmental parameters in the bathroom environment, including humidity data, temperature data, human body sensing data, and associated device status data. The human body sensing data is used to represent the relative positional relationship between a person and the target LED bathroom mirror. Associated devices include devices located in the same bathroom environment as the target LED bathroom mirror and affected by a person's washing activities. The usage analysis module is used to obtain the usage probability of the target LED bathroom mirror according to the environmental parameters; The light decay protection module is used to control the target LED bathroom mirror to enter a low-power protection mode if the usage probability obtained for multiple consecutive times is lower than a preset threshold. In the low-power protection mode, the working intensity of the LED lamp beads in the target LED bathroom mirror is lower than the working intensity in the normal mode to perform light decay protection.

9. An electronic device, characterized in that: include: memory and processor; The memory is used to store a program, and the processor is used to perform the steps of any one of the environmental perception-based LED bathroom mirror intelligent control methods of claims 1-7 when executing the program.

10. A computer-readable storage medium, characterized in that Used to store computer-readable programs or instructions, which, when executed by a processor, can implement the steps of any one of the environmental perception-based LED bathroom mirror intelligent control methods of claims 1-7.

Images