Energy-saving control method system of LED light strip based on ambient light

Abstract

The present invention discloses an energy-saving control method system for an LED light strip based on ambient light, the method comprising obtaining ambient light data and original brightness and chromaticity data of the LED light strip; performing preprocessing operations on the ambient light data to obtain ambient light standardized data; inputting the original brightness and chromaticity data and the ambient light standardized data into a pre-trained ambient light depth compensation model to obtain target parameter coefficients, and calculating a brightness and chromaticity correction coefficient matrix; inputting the brightness and chromaticity correction coefficient matrix and the original brightness and chromaticity data into a pre-trained energy-saving strategy generation model to obtain adjustment coefficients, and calculating an energy-saving adjustment strategy; adjusting the brightness and chromaticity of the LED light strip according to the energy-saving strategy. The method realizes intelligent selection of the most energy-saving brightness and chromaticity adjustment strategy according to real-time changes in ambient light, thereby saving energy and ensuring lighting effects.

Description

Technical Field

[0001] The present invention relates to the technical field of LED light strip intelligent control, and in particular to an energy-saving control method system of an LED light strip based on ambient light. Background Art

[0002] At present, LED lighting technology is widely used in various environments such as residential, commercial, and office. Its high efficiency, long life, and low power consumption make it an ideal choice to replace traditional lighting methods. However, in practical applications, the brightness and color adjustment of LED light strips usually do not take into account the intelligent control of actual ambient light changes, resulting in energy waste. Especially in complex dynamic environments, the adjustment of LED light strips often cannot be optimized for energy saving according to changes in ambient light, thereby reducing the energy efficiency of the system.

[0003] In one prior art, the brightness and color adjustment of LED light strips is performed by monitoring ambient light data through an ambient light sensor. Based on the collected ambient light data, the system automatically adjusts the brightness and color temperature of the LED light strip to maintain a relatively fixed lighting level. For example, when the ambient light is weak, the LED light strip will increase the brightness to supplement the insufficient light; when the ambient light is strong, the brightness will decrease accordingly. For the adjustment of the color, the system will also make corresponding adjustments according to the changes in the ambient light, usually allowing the light strip to adaptively change the color temperature under different lighting conditions to provide a comfortable lighting effect.

[0004] The existing technology has the problem of being unable to select the most appropriate brightness and color temperature adjustment strategy under different ambient light conditions to achieve the best energy saving effect. Summary of the invention

[0005] The present invention provides an energy-saving control method system for an LED light strip based on ambient light, so as to realize intelligent selection of the most energy-saving brightness and chromaticity adjustment strategy according to the real-time changes of ambient light, thereby maximizing energy saving and ensuring lighting effects.

[0006] In a first aspect, in order to solve the above technical problems, the present invention provides an energy-saving control method for an LED light strip based on ambient light, comprising:

[0007] Obtain ambient light data and original brightness and chromaticity data of LED light strips;

[0008] Performing a preprocessing operation on the ambient light data to obtain ambient light standardized data;

[0009] Input the original brightness and chromaticity data and the ambient light normalization data into a pre-trained ambient light depth compensation model to obtain target parameter coefficients for correcting the output brightness and chromaticity of the LED light strip, and calculate a brightness and chromaticity correction coefficient matrix;

[0010] Inputting the brightness and chromaticity correction coefficient matrix and the original brightness and chromaticity data into a pre-trained energy-saving strategy generation model to obtain an adjustment coefficient for optimizing current output and PWM signal distribution, and calculating an energy-saving adjustment strategy;

[0011] According to the energy-saving strategy, the brightness and chromaticity of the LED light strip are adjusted.

[0012] In an optional implementation, the training process of the ambient light depth compensation model includes:

[0013] Building a convolutional neural network model based on the brightness response and chromaticity response of the LED light strip under different ambient lighting conditions and the brightness and chromaticity data of the LED light strip under an ideal environment, and training the convolutional neural network model;

[0014] When the number of training times is greater than or equal to the preset maximum number of training times, or when the loss function value of the convolutional neural network model is less than the preset loss threshold, the training is determined to be completed, and the trained convolutional neural network model is used as the ambient light depth compensation model.

[0015] In an optional implementation, the training process of the energy-saving strategy generation model includes:

[0016] Building a multi-layer perceptron model based on historical brightness and chromaticity correction coefficient matrices, historical original brightness and chromaticity, ideal display effect standard parameters, and historical strategy energy consumption values, and training the multi-layer perceptron model;

[0017] When the number of training times is greater than or equal to a preset maximum number of training times, or when the loss function value of the multilayer perceptron model is less than a preset loss threshold, the training is determined to be completed, and the multilayer perceptron model that has completed the training is used as an energy-saving strategy generation model.

[0018] In an optional implementation, the original brightness and chromaticity data and the ambient light normalization data are input into a pre-trained ambient light depth compensation model to obtain target parameter coefficients for correcting the output brightness and chromaticity of the LED light strip, and a brightness and chromaticity correction coefficient matrix is ​​calculated, including:

[0019] The target parameter coefficients for correcting the output brightness and chromaticity of the LED light strip include , , , ;

[0020] The brightness and chromaticity correction coefficient matrix is ​​obtained by the following formula:

[0021]

[0022]

[0023]

[0024] in, is the brightness correction coefficient, To control the coefficient of the proportion of the original brightness in the overall brightness adjustment, is the equilibrium constant, and Respectively represent the original brightness and chromaticity data of the LED display. and Respectively represent the brightness and chromaticity data after ambient light standardization, is the chroma adjustment coefficient, is the chroma adjustment gain coefficient, is a small constant, Represents the brightness and chromaticity correction coefficient matrix.

[0025] In an optional implementation, the brightness and color correction coefficient matrix and the original brightness and color data are input into a pre-trained energy-saving strategy generation model to obtain an adjustment coefficient for optimizing current output and PWM signal distribution, and the energy-saving adjustment strategy is calculated, including:

[0026] Calculating a brightness adjustment value and a chromaticity adjustment value according to the brightness and chromaticity correction coefficient matrix and the original brightness and chromaticity data;

[0027] An energy-saving adjustment strategy is calculated based on the brightness adjustment value and the chromaticity adjustment value in combination with the adjustment coefficient.

[0028] In an optional implementation manner, the calculating the brightness adjustment value and the chromaticity adjustment value according to the brightness and chromaticity correction coefficient matrix and the original brightness and chromaticity data includes:

[0029] The brightness and chromaticity adjustment values ​​are obtained by the following formula:

[0030]

[0031]

[0032] in, is the brightness adjustment value, is the chroma adjustment value, represents the brightness and chromaticity correction coefficient matrix, and Respectively represent the original brightness and chromaticity data of the LED light strip, and Respectively represent the brightness and chromaticity data after ambient light standardization, To control the coefficient of the proportion of the original brightness in the overall brightness adjustment, is the equilibrium constant.

[0033] In an optional implementation manner, the calculating the energy-saving adjustment strategy according to the brightness adjustment value and the chromaticity adjustment value in combination with the adjustment coefficient includes:

[0034] The adjustment factors include , , , ;

[0035] The energy-saving adjustment strategy includes a current magnitude adjustment value and a PWM magnitude adjustment value;

[0036] The energy-saving adjustment strategy is obtained through the following formula:

[0037]

[0038]

[0039] in, is the current adjustment value, is the PWM size adjustment value, Adjust the gain factor for brightness, is the brightness energy efficiency adjustment factor, is the brightness adjustment value, is the chroma adjustment value, is the energy efficiency value, is the weight function, is the time-integrated variable, Adjust the gain factor for chroma, is the chromaticity energy efficiency adjustment coefficient, is the weight function, for Chroma adjustment value at the moment, for Brightness adjustment value at all times.

[0040] In a second aspect, the present invention provides an energy-saving control system for an LED light strip based on ambient light, comprising:

[0041] A data acquisition module is used to acquire ambient light data and original brightness and chromaticity data of the LED light strip;

[0042] A data processing module, used for performing a preprocessing operation on the ambient light data to obtain ambient light standardized data;

[0043] A matrix generation module, used to input the original brightness and chromaticity data and the ambient light standardized data into a pre-trained ambient light depth compensation model, obtain target parameter coefficients for correcting the output brightness and chromaticity of the LED light strip, and calculate a brightness and chromaticity correction coefficient matrix;

[0044] A strategy generation module, used to input the brightness and color correction coefficient matrix and the original brightness and color data into a pre-trained energy-saving strategy generation model, obtain an adjustment coefficient for optimizing current output and PWM signal distribution, and calculate an energy-saving adjustment strategy;

[0045] The display correction module is used to adjust the brightness and chromaticity of the LED light strip according to the energy-saving strategy.

[0046] In a third aspect, the present invention further provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the energy-saving control method of the LED light strip based on ambient light as described above is implemented.

[0047] In a fourth aspect, the present invention further provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned energy-saving control methods for LED light strips based on ambient light.

[0048] Compared with the prior art, the present invention has the following beneficial effects: the present invention proposes an energy-saving control method for LED light strips based on ambient light, by obtaining ambient light data and original brightness and chromaticity data of the LED light strip, preprocessing the ambient light data to obtain standardized data, and then inputting these data into a pre-trained ambient light depth compensation model, calculating the target parameter coefficients for correcting the output brightness and chromaticity of the LED light strip, and forming a brightness and chromaticity correction coefficient matrix. Furthermore, the brightness and chromaticity correction coefficient matrix and the original brightness and chromaticity data are input into the energy-saving strategy generation model to obtain the adjustment coefficients for optimizing the current output and PWM signal distribution, and finally adjusting the brightness and chromaticity of the LED light strip according to the energy-saving strategy. This technical solution not only takes into account the changes in ambient light, but also realizes the precise adjustment of the output characteristics of the LED light strip through a machine learning model, thereby achieving the effect of maximizing energy conservation while maintaining good lighting effects under different lighting conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 It is a schematic flow chart of an energy-saving control method for an LED light strip based on ambient light provided by a first embodiment of the present invention;

[0050] Figure 2 It is a schematic structural diagram of an energy-saving control system for an LED light strip based on ambient light provided in a second embodiment of the present invention. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0052] Reference Figure 1 The first embodiment of the present invention provides an energy-saving control method for an LED light strip based on ambient light, comprising the following steps:

[0053] S11, obtaining ambient light data and original brightness and chromaticity data of the LED light strip;

[0054] S12, performing a preprocessing operation on the ambient light data to obtain ambient light standardized data;

[0055] S13, inputting the original brightness and chromaticity data and the ambient light standardized data into a pre-trained ambient light depth compensation model, obtaining target parameter coefficients for correcting the output brightness and chromaticity of the LED light strip, and calculating a brightness and chromaticity correction coefficient matrix;

[0056] S14, inputting the brightness and chromaticity correction coefficient matrix and the original brightness and chromaticity data into a pre-trained energy-saving strategy generation model to obtain an adjustment coefficient for optimizing current output and PWM signal distribution, and calculating an energy-saving adjustment strategy;

[0057] S15, adjusting the brightness and chromaticity of the LED light strip according to the energy-saving strategy.

[0058] In step S11, obtaining ambient light data and the original brightness and chromaticity data of the LED light strip is the key premise and basic operation for realizing energy-saving control of the LED light strip based on ambient light adjustment. It should be noted that the execution of this step depends on the real-time data acquisition capability of the sensor hardware and the system's ability to accurately decode and process the acquired data. Its core purpose is to provide reliable input data for subsequent brightness and chromaticity adjustment.

[0059] Specifically, the acquisition of ambient light data requires the arrangement of multiple high-precision ambient light sensors on the LED light strip or in the environment where the light strip is used. These sensors can detect ambient light information at different angles, positions and intensities in real time. According to actual needs, these sensors can be arranged evenly to ensure the comprehensiveness of the coverage, or they can be arranged in a direction according to the lighting conditions and environmental layout to improve the pertinence of the collected data. For example, in indoor application scenarios, sensors can be installed at the center and edge of the light strip to collect the main lighting data in the center area and the auxiliary lighting data in the edge area respectively. In outdoor application scenarios, it is necessary to consider the characteristics of large changes in ambient light intensity, and to arrange a sensor network to collect multi-directional lighting information in real time. In order to avoid interference from occlusion or light reflection on a single sensor, the system can also interpolate the collected data or optimize the accuracy of the lighting information through weighted average calculation.

[0060] At the same time, the original brightness and color data of the LED light strip needs to be collected in real time through the built-in photoelectric detection device. During the operation of the LED light strip, the brightness and color temperature of its output will be affected by many factors, such as power supply voltage, current fluctuations and driving circuit characteristics. Therefore, real-time collection of these raw data can help the system accurately evaluate the actual lighting status of the current LED light strip. In order to improve the collection efficiency and data accuracy, a common method is to directly obtain electrical parameters (such as current value, voltage value, etc.) from the LED light strip control drive module, and calculate the brightness and color temperature data through a preset conversion model. Another method is to monitor the light intensity and spectral distribution emitted by the LED light strip through an independent optical sensor to obtain more intuitive brightness and color data.

[0061] In the process of data collection, in order to ensure the validity and consistency of the data, the collection equipment needs to be calibrated and calibrated. For example, before installing the sensor, the ambient light sensor can be calibrated with a standard light source to eliminate the deviation between devices; for the brightness and chromaticity data collection of LED light strips, the system can be adjusted in combination with the standard color temperature and brightness table. In addition, noise interference or signal loss may occur during the data collection process. The system needs to pre-process the raw data through a filtering algorithm to reduce errors and improve the credibility of the data.

[0062] The acquired ambient light data and the original brightness and color data of the LED strip can be transmitted to the central processing unit through the data bus or wireless communication module. After receiving these data, the central processing unit will format them and store them in the system database to provide support for subsequent brightness and color adjustment and energy-saving strategy generation. The storage format of these data needs to meet the requirements of efficient query and concurrent processing. The storage methods include matrix form and hierarchical structure storage to facilitate matching with subsequent model inputs.

[0063] By implementing step S11, the system can obtain real-time and accurate ambient light and LED light strip luminous state data, providing a reliable input source for subsequent steps. This real-time acquisition mechanism is the basis of the dynamic adjustment strategy, enabling the system to respond quickly according to changes in the external environment, thereby achieving the purpose of both ensuring display effects and optimizing energy consumption.

[0064] In step S12, preprocessing the ambient light data to obtain standardized ambient light data is an important intermediate link in implementing the energy-saving control method. The main purpose of this step is to convert the original collected ambient light data into a unified and standardized expression form to meet the needs of subsequent model input and provide high-quality input features for strategy generation. It should be noted that the original ambient light data has problems such as noise, uneven distribution and dimensional differences. If used directly, it may interfere with subsequent calculations and decisions, so standardization is essential.

[0065] Specifically, the preprocessing operation of ambient light data includes the following stages: data cleaning, noise filtering, feature extraction and normalization. First of all, data cleaning is the first step of preprocessing, which aims to eliminate invalid or abnormal data. For example, during the data collection process, the collected values ​​may suddenly change or data may be missing due to hardware failure, occlusion, light reflection and other reasons of the sensor. If these abnormal data are not cleaned, they will significantly affect the accuracy of subsequent processing. The implementation methods of data cleaning include technologies such as outlier detection and interpolation repair. Outlier detection can identify abnormal points by setting a reasonable threshold range or using statistical methods (such as Z-score or box plot analysis); while interpolation repair can use linear interpolation, spline interpolation or prediction methods based on historical data to fill in missing data.

[0066] Secondly, in order to eliminate the influence of environmental noise, the data needs to be filtered for noise removal. The data collected by the ambient light sensor is usually interfered by background light sources, such as sunlight, fluorescent lights, and other environmental factors. These interferences may cause random fluctuations in the collected data in the time dimension or space dimension. Filtering methods include low-pass filters, sliding average filters, and Kalman filters. These methods can effectively smooth the data curve, retain the main light intensity change trend, and remove high-frequency noise components.

[0067] Then comes the feature extraction stage, which is to extract the core information that has a direct impact on the brightness and chromaticity adjustment from the raw data. Taking ambient light data as an example, the raw data may include multiple dimensions, such as light intensity, color temperature, directionality, etc. During the preprocessing process, the main eigenvalues, such as the mean, maximum, and directional distribution parameters of illumination, can be extracted according to specific application requirements to simplify the data dimension and improve the efficiency of subsequent calculations. In addition, feature extraction can also use dimensionality reduction algorithms such as principal component analysis (PCA) to convert multidimensional data into principal component features that are easier to process, so as to avoid the complexity of calculations caused by too high dimensions.

[0068] The last step is normalization, which converts the extracted ambient light feature data into dimensionless standardized data. The purpose of normalization is to eliminate the dimensional differences between different data, so that each feature is comparable in value, thereby preventing a feature from having an excessive impact on subsequent model calculations due to its large magnitude. Common methods of normalization include minimum-maximum normalization and Z-score normalization. Minimum-maximum normalization is to scale the data to the [0,1] interval. Z-score normalization, on the other hand, is to standardize the data by the mean and standard deviation of the data. These two methods can be flexibly selected according to the application scenario.

[0069] After the preprocessing operation is completed, the obtained ambient light standardized data has consistent dimensions and high quality, which can better reflect the actual situation of the current ambient light and provide a stable and reliable basis for the subsequent strategy generation model input. Through the preprocessing step, the system can reduce the noise and interference in the original data, while improving the standardization and adaptability of the data, thereby improving the overall performance of energy-saving control.

[0070] In step S13, the original brightness and chromaticity data and the ambient light normalization data are input into the pre-trained ambient light depth compensation model, which is the core link to achieve the output brightness and chromaticity correction of the LED light strip. Through this operation, the system can generate the target parameter coefficients for optimizing the brightness and chromaticity of the LED light strip, and further calculate the brightness and chromaticity correction coefficient matrix, providing key support for the formulation and implementation of subsequent energy-saving control strategies.

[0071] First, the original brightness and chromaticity data reflect the actual output state of the LED light strip under the current working conditions. These data are collected through sensors, including parameters such as the light intensity and color temperature emitted by the LED light strip, which can fully characterize the brightness and chromaticity performance of the current LED light strip. The ambient light standardized data is obtained after preprocessing the ambient light data. The data is normalized or denoised to eliminate errors caused by sensor deviation or environmental interference, and can accurately characterize the current external lighting conditions. The combined input of these two types of data provides comprehensive basic information for the operation of the ambient light depth compensation model.

[0072] Next, the ambient light depth compensation model processes the input data. This model is built based on a convolutional neural network and trained on a large amount of historical data. Its design purpose is to learn the complex influence of ambient light on the brightness and chromaticity output of LED light strips, and generate a set of target parameter coefficients for correcting the actual output of LED light strips. The input of the model is the ambient light standardization data and the original brightness and chromaticity data, and the output is the parameters required for the target brightness and chromaticity adjustment, such as the coefficients and balance constants mentioned in the brightness and chromaticity correction coefficient matrix formula. Through these parameters, the model can provide a refined adjustment basis for the output state of the LED light strip.

[0073] Then, using the target parameter coefficients generated by the model, the system further calculates the brightness and chromaticity correction coefficient matrix. This matrix is ​​an intermediate result used to quantify the adjustment requirements of the LED light strip, and its row and column elements correspond to the brightness and chromaticity adjustment ranges of different optical channels. Through the calculation of the correction coefficient matrix, the system converts the abstract target parameters into specific adjustment instructions, providing direct input for the hardware controller that drives the LED light strip. The generation process of this matrix is ​​fully automated, ensuring the real-time and accuracy of the output results.

[0074] After completing the calculation of the correction coefficient matrix, the system dynamically matches the current brightness and chromaticity of the LED strip with the ideal output effect, ensuring that the output of the LED strip meets expectations even under complex and changing ambient light conditions. This correction mechanism not only improves the consistency of the display effect, but also lays a data foundation for the next step of generating energy-saving control strategies.

[0075] In general, step S13 realizes the conversion from ambient light and current LED light strip output state to correction parameters. Through the pre-trained depth compensation model, the system effectively solves the problem of interference of complex ambient light on LED light strip output, enabling it to dynamically and adaptively adjust brightness and chromaticity output, providing technical support for energy saving and display quality optimization.

[0076] In a preferred implementation, the training process of the ambient light depth compensation model includes:

[0077] Building a convolutional neural network model based on the brightness response and chromaticity response of the LED light strip under different ambient lighting conditions and the brightness and chromaticity data of the LED light strip under an ideal environment, and training the convolutional neural network model;

[0078] When the number of training times is greater than or equal to the preset maximum number of training times, or when the loss function value of the convolutional neural network model is less than the preset loss threshold, the training is determined to be completed, and the trained convolutional neural network model is used as the ambient light depth compensation model.

[0079] It should be noted that in order to ensure that the model can adapt to various changes in ambient light and provide reliable corrections to the output state of the LED light strip, the construction and training of the model need to fully consider the complex influence of ambient light on the brightness and chromaticity of the LED light strip, and achieve accurate modeling of these relationships through scientific data processing and algorithm training.

[0080] In actual implementation, the training data of the model mainly comes from the systematic testing and collection of the performance of LED light strips under different ambient light conditions. Specifically, these data include three parts: the first part is the data of ambient light conditions, covering multiple characteristics such as light intensity, light direction, color temperature and spectral distribution, to fully reflect the characteristics of different lighting environments; the second part is the brightness response data of the LED light strip, that is, the actual brightness value output by the LED light strip under specific ambient light conditions, such as luminous flux or illuminance; the third part is the chromaticity response data of the LED light strip, including its color temperature value or color coordinate information under different lighting conditions. In addition, it is also necessary to record the brightness and chromaticity data of the LED light strip under ideal environmental conditions. These ideal data are used as target output values ​​to guide model training.

[0081] After the data preprocessing is completed, a convolutional neural network model is constructed based on these data. The convolutional neural network is selected as the basic structure of the ambient light depth compensation model because it has strong feature extraction capabilities for multidimensional data, especially in nonlinear mapping modeling of brightness and chromaticity. The input of the model is ambient light data and the brightness and chromaticity response data of the LED light strip, and the output is the correction parameters for adjusting the brightness and chromaticity of the LED light strip. The architecture of the convolutional neural network can include multiple layers of convolutional layers, pooling layers, and fully connected layers, where the convolutional layer is used to extract local features of the relationship between ambient light and the output of the LED light strip, the pooling layer reduces the amount of calculation by reducing the dimension, and the fully connected layer integrates all features and generates the final adjustment parameters.

[0082] During model training, the objective function used is the mean square error (MSE) of the luminance and chrominance outputs, which is the average of the squared errors between the model predictions and the ideal target values. This objective function can quantify the accuracy of the model predictions and provide guidance for the optimization algorithm. The optimization process of training is achieved through backpropagation and gradient descent. Each iteration of the model parameters will be adjusted according to the gradient information of the objective function to gradually reduce the error.

[0083] During the training process, it is also necessary to set the stopping conditions for model training. One condition is that the number of training times reaches the preset maximum value, at which point the model parameters have fully learned the data features; the other condition is that the objective function value (i.e., the loss value) is less than the preset threshold, indicating that the model has achieved sufficient prediction accuracy. These two conditions can be used alone or in combination to ensure the efficiency and accuracy of model training.

[0084] After training, the model needs to have strong generalization ability after validation set evaluation, that is, it can still accurately generate adjustment parameters under unseen ambient light conditions. If the model performance meets the standard, it will be deployed as an ambient light depth compensation model to handle the brightness and color adjustment needs of LED light strips in real time. In actual applications, the model will generate adjustment parameters based on the real-time changes in ambient light and the current brightness and color status of the LED light strip, and further use them to correct the output of the LED light strip.

[0085] Through the above process, the ambient light depth compensation model can effectively capture the complex mapping relationship between ambient light and LED light strip output, providing strong technical support for the intelligent adjustment and energy-saving optimization of LED light strips. The model training process not only ensures the accuracy of the compensation parameters, but also enhances the overall stability and robustness of the system through its adaptability to complex light environments.

[0086] In a preferred implementation, the original brightness and chromaticity data and the ambient light standardized data are input into a pre-trained ambient light depth compensation model to obtain target parameter coefficients for correcting the output brightness and chromaticity of the LED light strip, and a brightness and chromaticity correction coefficient matrix is ​​calculated, including:

[0087] The target parameter coefficients for correcting the output brightness and chromaticity of the LED light strip include , , , ;

[0088] The brightness and chromaticity correction coefficient matrix is ​​obtained by the following formula:

[0089]

[0090]

[0091]

[0092] in, is the brightness correction coefficient, To control the coefficient of the proportion of the original brightness in the overall brightness adjustment, is the equilibrium constant, and Respectively represent the original brightness and chromaticity data of the LED display. and Respectively represent the brightness and chromaticity data after ambient light standardization, is the chromaticity adjustment coefficient, is the chroma adjustment gain coefficient, is a small constant, Represents the brightness and chromaticity correction coefficient matrix.

[0093] It should be noted that the formula achieves a dynamic balance between the influence of ambient light and the output of LED strips by combining mathematical logic with physical relationships when constructing the brightness and chromaticity correction coefficient matrix. The core idea is to use the ambient light standardization data and the original brightness and chromaticity data of the LED strips as inputs, and derive the target parameter coefficients ( , , , ), and then based on these coefficients, the correction matrix is ​​calculated through formulas to guide the brightness and color adjustment of the LED light strip. This process essentially converts complex nonlinear adjustment problems into a set of formula-driven linear weight adjustments, thereby achieving efficient and accurate correction.

[0094] First, the brightness correction factor The calculation formula introduces the brightness data after the ambient light is standardized And the original brightness data of LED light strip And through the coefficient and A nonlinear adjustment is made. This calculation reflects the interaction between ambient light and original brightness. Specifically, Characterizes the brightness characteristics of the current ambient light, which directly affects the brightness requirements of the LED light strip; Represents the brightness output capability of the LED light strip in the current driving state. and With the introduction of , the system can flexibly adjust the weight relationship between ambient light and LED strip brightness, making brightness correction more adaptive. For example, under low ambient light conditions, the formula can tend to amplify to increase the overall brightness; in high ambient light conditions, the formula Giving higher weights reduces energy consumption while maintaining visual comfort.

[0095] Likewise, the chromaticity correction factor The calculation formula is to normalize the chromaticity data by ambient light And the original chromaticity data of LED light strip The ratio relationship and gain coefficient and offset This mechanism can effectively deal with the interference of ambient light color temperature changes on the output chromaticity of LED light strips. For example, when the color temperature of the ambient light is high (cold light), the system can increase The system uses the weight of the LED light strip to enhance the warm color output to neutralize the cold light tendency of the overall light environment, thereby improving the consistency of the visual effect; conversely, when the color temperature of the ambient light is low (warm light), the system tends to compensate for the chromaticity of the cold color.

[0096] Finally, these correction coefficients are integrated into the brightness and color correction coefficient matrix The matrix is ​​constructed in the form of a diagonal matrix in linear algebra, so that the adjustment of brightness and chromaticity can be performed independently, avoiding mutual interference between different adjustment dimensions. Elements and Acting on the brightness and chromaticity adjustment channels respectively, the correction results are directly applied to the output control of the LED light strip through matrix multiplication. This method not only simplifies the complex adjustment logic, but also improves the calculation efficiency, which is particularly suitable for scenes with high real-time requirements.

[0097] It is worth mentioning that the use of these formulas can effectively balance the contradiction between the interference of ambient light on the output of LED strips and the need for energy saving. , , and With flexible adjustment, the system can dynamically adapt to various ambient light conditions and generate accurate brightness and color correction results. In addition, the design of these formulas also fully considers the scalability of the system. For example, by adjusting the gain coefficient and offset in the formula, the system can adapt to more types of ambient light change scenes or LED light strip specifications, providing space for subsequent optimization.

[0098] Therefore, the brightness and chromaticity correction coefficient matrix mentioned in the steps is not only a key tool for adjusting the output of LED light strips, but also a bridge that combines theoretical models with practical control. The relationship between ambient light and LED light strips is concretized and calculable through mathematical formulas. The entire correction process achieves efficient and accurate closed-loop control, laying a solid foundation for the generation of subsequent energy-saving strategies.

[0099] In step S14, the system generates optimization coefficients for brightness and chromaticity adjustment, including brightness adjustment gain coefficient, brightness energy efficiency adjustment coefficient, chromaticity adjustment gain coefficient and chromaticity energy efficiency adjustment coefficient, through calculation of the energy-saving strategy generation model, and calculates a specific energy-saving adjustment strategy based on it, which is used to optimize the current output and PWM signal distribution of the LED light strip. This process generates a dynamic adjustment plan through a comprehensive analysis of the current ambient light conditions and the actual working state of the LED light strip, ensuring that the optimal energy consumption is achieved while meeting the brightness and chromaticity adjustment requirements.

[0100] Specifically, the input brightness and chromaticity correction coefficient matrix contains the brightness and chromaticity correction amplitudes that the LED light strip needs to adjust under the current ambient light conditions. It is a mathematical quantitative expression that comprehensively considers the external ambient light and internal target effects. The original brightness and chromaticity data reflects the actual current luminous state of the LED light strip, indicating the brightness output value and chromaticity characteristics under the current working conditions. The combination of these two types of data can fully describe the difference between the current state of the system and the target requirements, and provide complete input information for the energy-saving strategy generation model. Through model calculation, the system can output optimization coefficients for hardware driver adjustment, including brightness adjustment gain coefficients to determine the amplitude of LED light strip brightness adjustment; brightness energy efficiency adjustment coefficients to optimize power consumption performance during brightness adjustment; chromaticity adjustment gain coefficients to control the amplitude of chromaticity adjustment so that the color temperature or color coordinates meet the target requirements; and chromaticity energy efficiency adjustment coefficients to further reduce power consumption during chromaticity adjustment.

[0101] The energy-saving strategy generation model is built through deep learning technology and trained on a large amount of historical data. Its training data covers the historical brightness and chromaticity correction coefficient matrix, historical original brightness and chromaticity data, ideal display effect standard parameters and historical strategy energy consumption values. By learning the relationship between these data, the model can identify and predict how to optimize the adjustment strategy of LED light strips under different ambient light conditions, so as to find a balance between the correction requirements of brightness and chromaticity and energy efficiency goals. In actual operation, the optimization coefficients generated by the model through nonlinear mapping calculation are directly used to guide the energy-saving adjustment strategy. For example, the model can dynamically adjust the current output and PWM signal distribution according to the input brightness and chromaticity correction requirements and the actual working status to meet the target output while minimizing power consumption.

[0102] The formation of energy-saving adjustment strategies not only depends on model calculations, but also needs to fully consider the actual working limitations of the hardware. For example, actual constraints such as the current load capacity of the LED light strip drive circuit and the frequency range of PWM modulation will have a direct impact on the execution of the strategy. To this end, when generating strategies, the system will constrain the adjustment coefficients through specific algorithms to ensure that the generated strategies can not only optimize energy efficiency but also be executed safely and reliably. These strategies are ultimately sent to the LED driver in the form of specific hardware signals to dynamically adjust the current output and PWM signal duty cycle, thereby achieving real-time correction and optimization of brightness and chromaticity.

[0103] Through the implementation of step S14, the system can generate accurate energy-saving adjustment strategies according to the brightness and chromaticity correction requirements, and dynamically optimize the output state of the LED light strip according to the changes in the actual ambient light. This process ensures the stability of the target brightness and chromaticity effects, while significantly reducing energy consumption, providing technical support and implementation paths for intelligent energy-saving control of LED light strips.

[0104] In a preferred implementation, the training process of the energy-saving strategy generation model includes:

[0105] Building a multi-layer perceptron model based on historical brightness and chromaticity correction coefficient matrices, historical original brightness and chromaticity, ideal display effect standard parameters, and historical strategy energy consumption values, and training the multi-layer perceptron model;

[0106] When the number of training times is greater than or equal to a preset maximum number of training times, or when the loss function value of the multilayer perceptron model is less than a preset loss threshold, the training is determined to be completed, and the multilayer perceptron model that has completed the training is used as an energy-saving strategy generation model.

[0107] It should be noted that the training process of the energy-saving strategy generation model is based on the multi-layer perceptron model. Its core goal is to generate a strategy that can optimize current output and PWM signal distribution under different environmental conditions by learning the complex relationship between brightness and chromaticity correction requirements, ideal display effects, and energy consumption in historical data. The training of the multi-layer perceptron model relies on a high-quality training data set, which includes historical brightness and chromaticity correction coefficient matrices, historical original brightness and chromaticity, standard parameters for ideal display effects, and energy consumption values ​​of historical strategies. These data comprehensively reflect the system's correction requirements, display goals, and energy consumption performance under various ambient light conditions, providing a multi-dimensional information basis for model training.

[0108] During the training process, the multi-layer perceptron model gradually optimizes the model parameters by constructing a nonlinear mapping relationship between the input features and the output adjustment coefficients. The input features include the brightness and chromaticity correction coefficient matrix and the original brightness and chromaticity data, which describe the correction requirements and actual lighting status of the current LED light strip. The standard parameters of the ideal display effect provide specific reference values ​​for the target brightness and chromaticity, while the energy consumption values ​​of the historical strategies record the energy efficiency performance corresponding to different adjustment strategies. Through multiple layers of nonlinear transformation, the model extracts the deep relationship between brightness and chromaticity adjustment and energy consumption from these features, thereby generating an adjustment strategy that can optimize energy efficiency.

[0109] The optimization process of the model uses back propagation and gradient descent algorithms. In each iteration, the loss function is used to measure the deviation between the model prediction result and the ideal target, and the model weight is adjusted according to the deviation. The loss function uses the mean square error (MSE) to calculate the difference between the adjustment coefficient predicted by the model and the actual adjustment requirement. During the training process, when the loss function value is lower than the preset loss threshold, or the number of training times reaches the preset maximum number, the model is judged to have completed the training. At this point, the model is able to generate an adjustment strategy that meets the brightness and color correction requirements and has the lowest energy consumption under a variety of ambient light conditions.

[0110] Through this training process, the energy-saving strategy generation model has a wide range of generalization capabilities and can adapt to a variety of ambient light conditions and different display requirements. In practical applications, the model can not only quickly generate the optimal adjustment strategy based on the current input, but also dynamically respond to changes in ambient light and continuously optimize the energy efficiency performance of the LED light strip. This training process provides a reliable technical foundation for subsequent energy-saving control, while ensuring the stability and efficient operation of the system in complex light environments.

[0111] In a preferred implementation, the brightness and color correction coefficient matrix and the original brightness and color data are input into a pre-trained energy-saving strategy generation model to obtain an adjustment coefficient for optimizing current output and PWM signal distribution, and calculate an energy-saving adjustment strategy, including:

[0112] Calculating a brightness adjustment value and a chromaticity adjustment value according to the brightness and chromaticity correction coefficient matrix and the original brightness and chromaticity data;

[0113] An energy-saving adjustment strategy is calculated based on the brightness adjustment value and the chromaticity adjustment value in combination with the adjustment coefficient.

[0114] It should be noted that this step converts the brightness and chromaticity correction requirements into specific control instructions at the hardware level by jointly analyzing the brightness and chromaticity correction coefficient matrix and the original brightness and chromaticity data, and combining the calculation of the adjustment coefficient, providing a clear technical path for achieving energy-saving optimization of LED light strips. First, the brightness and chromaticity correction coefficient matrix characterizes the brightness and chromaticity correction amplitudes that need to be adjusted for the LED light strip under the current ambient light conditions, while the original brightness and chromaticity data reflects the actual luminous characteristics of the LED light strip under the current working state, including the current light intensity distribution and chromaticity coordinates. Through the input of these two types of data, the energy-saving strategy generation model can comprehensively analyze the deviation between the current state of the LED light strip and the correction requirements, and generate key parameters for driving adjustment based on the built-in optimization logic.

[0115] The energy-saving strategy generation model is pre-trained based on a large amount of historical data and target optimization requirements. Its core goal is to minimize the power consumption of current output and PWM signals while meeting the brightness and chromaticity adjustment requirements. The model first calculates the brightness adjustment value and chromaticity adjustment value based on the input brightness and chromaticity correction coefficient matrix and the original brightness and chromaticity data. These adjustment values ​​are extracted and quantified through the deep learning layer of the model, which can accurately reflect the correction requirements of the LED light strip in the current environment, such as the proportion of brightness increase or the direction of chromaticity shift.

[0116] Next, the model combines the calculated brightness adjustment value and chromaticity adjustment value with the adjustment coefficient obtained by the model to construct an energy-saving adjustment strategy. The adjustment coefficient is the output parameter of the model, including the brightness adjustment gain coefficient, the brightness energy efficiency adjustment coefficient, the chromaticity adjustment gain coefficient, and the chromaticity energy efficiency adjustment coefficient. These coefficients directly determine the specific schemes of current distribution and PWM signal adjustment. For example, during the brightness adjustment process, the brightness adjustment gain coefficient is used to determine the amplitude by which the LED light strip needs to increase or decrease the brightness, while the brightness energy efficiency adjustment coefficient further reduces energy consumption by optimizing the efficiency of current output. During the chromaticity adjustment process, the chromaticity adjustment gain coefficient ensures that the color temperature offset meets the visual target, while the chromaticity energy efficiency adjustment coefficient reduces unnecessary energy loss by reasonably allocating signal power.

[0117] Finally, the energy-saving adjustment strategy is output in the form of hardware drive signals, including specific current values ​​and PWM duty cycle settings. These control instructions can act on each drive channel of the LED light strip in real time, so that it can achieve the lowest power consumption while meeting the target brightness and chromaticity. Through this step, the system completes the transformation from data analysis to hardware control, providing efficient and reliable technical support for the intelligent energy-saving regulation of LED light strips.

[0118] In a preferred implementation, the step of calculating the brightness adjustment value and the chromaticity adjustment value according to the brightness and chromaticity correction coefficient matrix and the original brightness and chromaticity data includes:

[0119] The brightness and chromaticity adjustment values ​​are obtained by the following formula:

[0120]

[0121]

[0122] in, is the brightness adjustment value, is the chroma adjustment value, represents the brightness and chromaticity correction coefficient matrix, and Respectively represent the original brightness and chromaticity data of the LED light strip, and Respectively represent the brightness and chromaticity data after ambient light standardization, To control the coefficient of the proportion of the original brightness in the overall brightness adjustment, is the equilibrium constant.

[0123] It should be noted that the brightness adjustment value in the formula and chroma adjustment values They are used to describe the specific correction values ​​required to achieve the target brightness and chromaticity under the current ambient light conditions. The calculation of these two adjustment values ​​depends on the brightness and chromaticity correction coefficient matrix , the original brightness and chromaticity data of LED light strips and , and the brightness and chromaticity data after ambient light standardization and These input variables cover the current working state of the system and the external environmental conditions, providing sufficient basis for the accurate calculation of the adjustment amount. The adjustment formula is divided into two main parts. The first part is through matrix operation Calculate the weighted values ​​of brightness and chromaticity in the correction dimension. The significance of this step is to uniformly quantify the degree of deviation of brightness and chromaticity in the correction direction of the current output state according to the correction coefficient generated by the ambient light depth compensation model. The correction matrix plays a key role in this process. By mapping the influence of ambient light to different adjustment dimensions of brightness and chromaticity, the accuracy and coordination of the correction are guaranteed. The second part combines the standardized data of ambient light and the deviation of the original brightness and chromaticity data, and adjusts the linear coefficients to obtain the correction matrix. and The original data is weighted and adjusted, where The proportion of the original brightness data in the overall brightness adjustment is controlled so that the adjustment value can retain some of the original brightness characteristics while referring to the ambient light brightness, thereby avoiding brightness distortion caused by over-reliance on ambient light data. As a balance constant, it is used to adjust the contribution of the original chromaticity data to the chromaticity correction, ensuring that the adjustment effect under different ambient color temperatures is both accurate and natural. The advantage of this weighted calculation method is that by appropriately introducing the original data characteristics, it can improve the adaptability and stability of the adjustment result. Through the above formula, the brightness adjustment value and chroma adjustment values The values ​​are calculated accurately, providing key data support for the subsequent energy-saving strategy generation. These adjustment values ​​directly reflect the correction amplitude of the LED light strip in brightness and chromaticity under the current ambient light conditions. They not only take into account the impact of ambient light on the target output, but also combine the characteristics of the original data to ensure the accuracy, naturalness and energy-saving effect of the adjustment results. This calculation method provides a basic guarantee for the efficient operation of the entire energy-saving control system.

[0124] In a preferred implementation, the energy-saving adjustment strategy is calculated based on the brightness adjustment value and the chromaticity adjustment value in combination with the adjustment coefficient, including:

[0125] The adjustment factors include , , , ;

[0126] The energy-saving adjustment strategy includes a current magnitude adjustment value and a PWM magnitude adjustment value;

[0127] The energy-saving adjustment strategy is obtained through the following formula:

[0128]

[0129]

[0130] in, is the current adjustment value, is the PWM size adjustment value, Adjust the gain factor for brightness, is the brightness energy efficiency adjustment factor, is the brightness adjustment value, is the chroma adjustment value, is the energy efficiency value, is the weight function, is the time-integrated variable, Adjust the gain factor for chroma, is the chromaticity energy efficiency adjustment coefficient, is the weight function, for Chroma adjustment value at the moment, for Brightness adjustment value at all times.

[0131] It should be noted that the adjustment factor , , and These coefficients are the core parameters for calculating energy-saving adjustment strategies. These coefficients are pre-trained through the energy-saving strategy generation model and provide optimization guidance for brightness and color correction requirements under different ambient light conditions. and They are used to control the amplitude of brightness and chromaticity adjustment respectively, which determine the brightness and chromaticity gain values ​​that the system needs to allocate to each channel under the current ambient light conditions. and are adjustment factors related to energy efficiency, which are adjusted by adjusting the energy efficiency value Dynamic feedback limits unnecessary power consumption, thereby effectively reducing energy consumption while achieving the target effect. Based on these adjustment coefficients, the energy-saving adjustment strategy further adjusts the brightness value and chroma adjustment values Perform precise calculations. The calculation formula includes the brightness adjustment gain coefficient and brightness efficiency adjustment factor Specifically, Used to increase or decrease the current output value to achieve the target brightness, and By introducing energy efficiency feedback, the adjustment behavior of excessive power consumption is suppressed. In addition, the integral term The time weight function is further introduced , which can provide dynamic correction for the current adjustment based on the trend of historical brightness adjustment. This time dimension consideration enables the system to avoid instability caused by brightness changes that are too fast or too slow. Similarly, the PWM adjustment value The PWM calculation also incorporates the chroma adjustment gain factor and chromaticity energy efficiency adjustment factor ,in, Used to adjust the PWM duty cycle, thereby adjusting the color temperature to make it close to the target value. By dynamically limiting the energy efficiency, the power consumption performance in the chromaticity adjustment is optimized. Combined weight function ,The time continuity constraint is introduced for chromaticity adjustment to ensure the smoothness and consistency of the adjustment process. Through the above formula calculation, the energy-saving adjustment strategy finally includes two core outputs: current size adjustment value and PWM duty cycle adjustment value PWM. The current adjustment value directly affects the driving current distribution of the LED light strip, while the PWM adjustment value controls the power output of each channel through precise adjustment of the duty cycle. The two work together to enable the LED light strip to dynamically achieve the target requirements of brightness and color under complex ambient light conditions while optimizing energy consumption.

[0132] In general, this step organically combines the correction requirements of brightness and chromaticity with energy efficiency optimization through precise formula calculations. While controlling the output of LED light strips in real time, it significantly reduces power consumption and provides a reliable technical foundation for realizing intelligent energy-saving control.

[0133] In step S15, according to the energy-saving adjustment strategy generated above, the system will adjust the brightness and chromaticity of the LED light strip. This process sends the calculated current adjustment value and PWM signal adjustment value to the driving circuit of the LED light strip, thereby achieving precise control of the brightness and chromaticity. It should be noted that the sending and execution of these instructions need to ensure the fast response of the hardware to ensure that the working state of the LED light strip can be adjusted in real time when the ambient light changes, ensuring that the system runs efficiently and stably.

[0134] Specifically, the current adjustment value is used to control the brightness of the LED light strip. The brightness of the LED is proportional to the size of the driving current. Therefore, by adjusting the current value, the system can accurately adjust the brightness of the LED light strip. When the system generates a brightness adjustment value based on the energy-saving strategy, the value will be passed to the LED driver module, and the driver module will control the output current size according to the current adjustment value. This process controls the power amplifier in the driver module through digital or analog signals to achieve brightness adjustment of the LED light strip. In order to ensure that the system can achieve fine brightness control, the current adjustment value will take into account the maximum current limit and operating voltage range of the LED light strip to prevent the current from being too large or too small, and ensure that the system operates within a safe operating range.

[0135] At the same time, chromaticity adjustment is achieved by adjusting the duty cycle of the PWM signal. The duty cycle of the PWM (pulse width modulation) signal directly affects the color temperature or chromaticity of the LED light strip. In this process, the chromaticity adjustment value is transmitted to the LED driver circuit as a control parameter of the PWM signal. By adjusting the duty cycle of the PWM signal, the system can accurately control the color temperature and chromaticity of the LED light strip to achieve the target chromaticity effect. Specifically, increasing the PWM duty cycle will increase the average current of the LED, thereby improving its color temperature; while reducing the PWM duty cycle will reduce the average current of the LED, resulting in a decrease in color temperature. This adjustment method can efficiently change the chromaticity without changing the current supply of the LED.

[0136] It should be noted that the sending and execution of these instructions need to be fast and accurate. To this end, the LED driver module uses an efficient digital control system to ensure that the current and PWM signals can be fed back to the LED light strip in a timely and accurate manner, thereby achieving dynamic adjustment. In addition, the entire process also requires real-time monitoring of the working status of the LED light strip and changes in ambient light so that rapid adjustments can be made when necessary. For example, when the ambient light intensity changes, the system will dynamically adjust the current and PWM signals based on the previously generated energy-saving adjustment strategy to achieve the best brightness and color effects while minimizing energy consumption.

[0137] In summary, in step S15, the system accurately controls the brightness and chromaticity output of the LED light strip through current adjustment and PWM signal adjustment, and sends these instructions to the driver module to ensure that the LED light strip can be efficiently energy-saving controlled according to real-time needs. This process not only ensures the consistency of visual effects, but also effectively reduces the energy consumption of the system, achieving the purpose of optimizing energy saving.

[0138] In order to facilitate the understanding of the present invention, some preferred embodiments of the present invention are further described below.

[0139] In one implementation, the present invention directly obtains key electrical parameters (such as current value and PWM value) from the LED light strip control driver module, and converts these parameters into brightness and color temperature data with the help of a preset conversion model. This method relies on the stable output of the driver module and the high-precision mapping relationship of the model, and can quickly and cost-effectively measure brightness and chromaticity, which is suitable for scenarios with limited hardware resources.

[0140] In another implementation, the present invention monitors the light intensity and spectral distribution emitted by the LED light strip through independently arranged optical sensors to directly obtain brightness and chromaticity data. This method has higher intuitiveness and flexibility, can better capture the optical characteristics of the actual luminous state of the LED light strip, and is suitable for application scenarios with high requirements for measurement accuracy and environmental adaptability. In addition, the layout of optical sensors can be optimized according to specific needs, such as selecting a multi-point distribution scheme to cover complex environments, or adopting a centralized sensor layout to reduce costs.

[0141] The following describes the working process of the present invention using a common scenario as an example. Figure 2 , which is Figure 1 Schematic diagram of the working scenario of the method.

[0142] In an office, an energy-saving control system for LED light strips based on ambient light is installed. The system includes multiple ambient light sensors, LED light strips, a data processing unit, and a central control unit. Ambient light sensors are distributed in different locations in the room to capture changes in the intensity and color temperature of ambient light. LED light strips are arranged along the walls and ceiling to provide the main lighting source. The ambient light sensor monitors changes in ambient light in real time and sends the data to the data processing unit. At the same time, the photoelectric detection device inside the LED light strip also collects the current brightness and color data of the light strip in real time. These data are transmitted to the central processing unit through the wireless communication module.

[0143] The central processing unit preprocesses the received ambient light data, including data cleaning, noise filtering, feature extraction and normalization. The preprocessed ambient light data is standardized to meet the needs of subsequent model input. The preprocessed ambient light data and the original brightness and chromaticity data of the LED light strip are input into the pre-trained ambient light depth compensation model. The model is based on a convolutional neural network. By learning the influence of ambient light on the brightness and chromaticity of the LED light strip, it generates target parameter coefficients for correcting the output of the LED light strip and calculates the brightness and chromaticity correction coefficient matrix. The brightness and chromaticity correction coefficient matrix and the original brightness and chromaticity data are input into the pre-trained energy-saving strategy generation model. The model is based on a multi-layer perceptron. By learning historical data, it generates adjustment coefficients for optimizing current output and PWM signal distribution and calculates an energy-saving adjustment strategy. The central control unit adjusts the brightness and chromaticity of the LED light strip according to the generated energy-saving strategy.

[0144] Specifically, by adjusting the current size and the duty cycle of the PWM signal, the LED light strip can maintain the best lighting effect under different ambient light conditions while maximizing energy conservation. For example, when the ambient light is dim, the system will increase the brightness of the LED light strip to supplement the insufficient light; when the ambient light is bright, the system will appropriately reduce the brightness to avoid energy waste caused by excessive light. At the same time, the system will dynamically adjust the color temperature of the LED light strip according to the color temperature changes of the ambient light to provide a more comfortable lighting effect.

[0145] In summary, the present invention provides an energy-saving control method system for LED light strips based on ambient light, which realizes intelligent adjustment of LED light strips under different lighting conditions by real-time monitoring of changes in ambient light and combining correction coefficients and energy-saving strategies generated by deep learning models. This method not only dynamically adjusts lighting parameters according to different ambient light conditions to improve the user experience, but also improves the energy efficiency of LED light strips and reduces energy waste.

[0146] Reference Figure 2The second embodiment of the present invention provides an energy-saving control system for an LED light strip based on ambient light, comprising:

[0147] A data acquisition module is used to acquire ambient light data and original brightness and chromaticity data of the LED light strip;

[0148] A data processing module, used for performing a preprocessing operation on the ambient light data to obtain ambient light standardized data;

[0149] A matrix generation module, used to input the original brightness and chromaticity data and the ambient light standardized data into a pre-trained ambient light depth compensation model, obtain target parameter coefficients for correcting the output brightness and chromaticity of the LED light strip, and calculate a brightness and chromaticity correction coefficient matrix;

[0150] A strategy generation module, used to input the brightness and color correction coefficient matrix and the original brightness and color data into a pre-trained energy-saving strategy generation model, obtain an adjustment coefficient for optimizing current output and PWM signal distribution, and calculate an energy-saving adjustment strategy;

[0151] The display correction module adjusts the brightness and chromaticity of the LED light strip according to the energy-saving strategy.

[0152] It should be noted that an energy-saving control device for an LED light strip based on ambient light provided in an embodiment of the present invention is used to execute all process steps of an energy-saving control method for an LED light strip based on ambient light in the above embodiment. The working principles and beneficial effects of the two correspond one to one, and therefore will not be repeated here.

[0153] An embodiment of the present invention further provides an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as an energy-saving control program for LED light strips based on ambient light. When the processor executes the computer program, the steps in the above-mentioned embodiments of the energy-saving control method for LED light strips based on ambient light are implemented, such as Figure 1 Alternatively, when the processor executes the computer program, the functions of the modules / units in the above-mentioned device embodiments are implemented, such as the strategy generation module.

[0154] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the electronic device.

[0155] The electronic device may be a computing device such as a desktop computer, a notebook, a PDA, and a smart tablet. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the above components are merely examples of electronic devices and do not constitute a limitation on the electronic device. The electronic device may include more or fewer components than the above components, or may combine certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0156] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the electronic device, and uses various interfaces and lines to connect various parts of the entire electronic device.

[0157] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the electronic device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0158] Wherein, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0159] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0160] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. An energy-saving control method for LED light strips based on ambient light, characterized in that: include: Obtain ambient light data and original brightness and chromaticity data of LED light strips; Performing a preprocessing operation on the ambient light data to obtain ambient light standardized data; Input the original brightness and chromaticity data and the ambient light normalization data into a pre-trained ambient light depth compensation model to obtain target parameter coefficients for correcting the output brightness and chromaticity of the LED light strip, and calculate a brightness and chromaticity correction coefficient matrix; Inputting the brightness and chromaticity correction coefficient matrix and the original brightness and chromaticity data into a pre-trained energy-saving strategy generation model to obtain an adjustment coefficient for optimizing current output and PWM signal distribution, and calculating an energy-saving adjustment strategy; According to the energy-saving adjustment strategy, adjust the brightness and chromaticity of the LED light strip; The step of inputting the brightness and chromaticity correction coefficient matrix and the original brightness and chromaticity data into a pre-trained energy-saving strategy generation model to obtain an adjustment coefficient for optimizing current output and PWM signal distribution, and calculating an energy-saving adjustment strategy includes: Calculating a brightness adjustment value and a chromaticity adjustment value according to the brightness and chromaticity correction coefficient matrix and the original brightness and chromaticity data; Calculating an energy-saving adjustment strategy according to the brightness adjustment value and the chromaticity adjustment value in combination with the adjustment coefficient; The step of calculating the brightness adjustment value and the chromaticity adjustment value according to the brightness and chromaticity correction coefficient matrix and the original brightness and chromaticity data includes: The brightness and chromaticity adjustment values ​​are obtained by the following formula: in, is the brightness adjustment value, is the chroma adjustment value, represents the brightness and chromaticity correction coefficient matrix, and Respectively represent the original brightness and chromaticity data of the LED light strip, and Respectively represent the brightness and chromaticity data after ambient light standardization, To control the coefficient of the proportion of the original brightness in the overall brightness adjustment, is the equilibrium constant.

2. The energy-saving control method of LED light strip based on ambient light according to claim 1, characterized in that: The training process of the ambient light depth compensation model includes: Building a convolutional neural network model based on the brightness response and chromaticity response of the LED light strip under different ambient lighting conditions and the brightness and chromaticity data of the LED light strip under an ideal environment, and training the convolutional neural network model; When the number of training times is greater than or equal to the preset maximum number of training times, or when the loss function value of the convolutional neural network model is less than the preset loss threshold, the training is determined to be completed, and the trained convolutional neural network model is used as the ambient light depth compensation model.

3. The energy-saving control method of LED light strip based on ambient light according to claim 1, characterized in that: The training process of the energy-saving strategy generation model includes: Building a multi-layer perceptron model based on historical brightness and chromaticity correction coefficient matrices, historical original brightness and chromaticity, ideal display effect standard parameters, and historical strategy energy consumption values, and training the multi-layer perceptron model; When the number of training times is greater than or equal to a preset maximum number of training times, or when the loss function value of the multilayer perceptron model is less than a preset loss threshold, the training is determined to be completed, and the multilayer perceptron model that has completed the training is used as an energy-saving strategy generation model.

4. The energy-saving control method of LED light strip based on ambient light according to claim 1, characterized in that: The original brightness and chromaticity data and the ambient light standardized data are input into a pre-trained ambient light depth compensation model to obtain target parameter coefficients for correcting the output brightness and chromaticity of the LED light strip, and a brightness and chromaticity correction coefficient matrix is ​​calculated, including: The target parameter coefficients for correcting the output brightness and chromaticity of the LED light strip include , , , ; The brightness and chromaticity correction coefficient matrix is ​​obtained by the following formula: in, is the brightness correction factor, To control the coefficient of the proportion of the original brightness in the overall brightness adjustment, is the equilibrium constant, and Respectively represent the original brightness and chromaticity data of the LED display. and Respectively represent the brightness and chromaticity data after ambient light standardization, is the chroma adjustment coefficient, is the chroma adjustment gain coefficient, is a small constant, Represents the brightness and chromaticity correction coefficient matrix.

5. The energy-saving control method of LED light strip based on ambient light according to claim 1, characterized in that: The energy-saving adjustment strategy is calculated based on the brightness adjustment value and the chromaticity adjustment value in combination with the adjustment coefficient, including: The adjustment factors include , , , ; The energy-saving adjustment strategy includes a current magnitude adjustment value and a PWM magnitude adjustment value; The energy-saving adjustment strategy is obtained through the following formula: in, is the current adjustment value, is the PWM size adjustment value, Adjust the gain factor for brightness, is the brightness energy efficiency adjustment factor, is the brightness adjustment value, is the chroma adjustment value, is the energy efficiency value, is the weight function, is the time-integrated variable, Adjust the gain factor for chroma, is the chromaticity energy efficiency adjustment coefficient, is the weight function, for Chroma adjustment value at the moment, for Brightness adjustment value at all times.

6. An energy-saving control system for LED light strips based on ambient light, characterized in that: The energy-saving control method for an LED light strip based on ambient light according to any one of claims 1 to 5 comprises: A data acquisition module is used to acquire ambient light data and original brightness and chromaticity data of the LED light strip; A data processing module, used for performing a preprocessing operation on the ambient light data to obtain ambient light standardized data; A matrix generation module, used to input the original brightness and chromaticity data and the ambient light standardized data into a pre-trained ambient light depth compensation model, obtain target parameter coefficients for correcting the output brightness and chromaticity of the LED light strip, and calculate a brightness and chromaticity correction coefficient matrix; A strategy generation module, used to input the brightness and color correction coefficient matrix and the original brightness and color data into a pre-trained energy-saving strategy generation model, obtain an adjustment coefficient for optimizing current output and PWM signal distribution, and calculate an energy-saving adjustment strategy; The display correction module is used to adjust the brightness and chromaticity of the LED light strip according to the energy-saving strategy.

7. An electronic device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the energy-saving control method for an LED light strip based on ambient light as described in any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the energy-saving control method for the LED light strip based on ambient light as described in any one of claims 1 to 5.

Images