Energy-saving display method of environment-friendly LED display screen

Abstract

The application discloses an energy-saving display method of an environment-friendly LED display screen and relates to the technical field of display screen energy saving, which comprises the following steps: acquiring display content data in a current image frame; collecting ambient light data of the LED display screen; counting people flow data in front of the LED display screen; analyzing the collected ambient light data and the people flow data; predicting an energy consumption trend of the LED display screen according to the collected data; generating an energy-saving display strategy of the LED display screen through the energy consumption trend; and recording and storing log data of the energy-saving display of the LED display screen. Through the collection of head data and the prediction of personnel motion trajectories, the people flow data in front of the LED display screen is identified, meanwhile, the ambient light data around the LED display screen is collected in real time, the future display energy consumption of the LED display screen is predicted through the establishment of a model, and a corresponding energy-saving display regulation scheme is generated in combination with a set constraint condition.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of display screen energy saving, in particular to an energy-saving display method for an environmentally friendly LED display screen. BACKGROUND

[0002] An LED display screen is a flat display device that displays text, images, videos, and other information by controlling the brightness of semiconductor light-emitting diodes (LEDs). Its core advantages include high brightness, wide color gamut, long service life, low energy consumption, and environmental adaptability, making it suitable for a variety of indoor and outdoor scenarios. Outdoor LED display screens are mainly used in scenarios such as shopping malls and landmark buildings, so their lighting conditions must ensure brightness visibility. Traditional fixed power consumption modes cannot match this dynamic scenario, leading to two major problems: continuous high energy consumption in low-light environments (such as at night) or during low-traffic periods, resulting in a large amount of wasted power resources and increased operating costs, as well as excessive lighting that causes light pollution and disrupts the ecological balance of the city.

[0003] Therefore, the essence of energy-saving display for outdoor LED display screens is to perceive environmental light intensity and traffic density in real time, build a dynamic response mechanism, ensure visibility in strong light and high traffic, and actively reduce power consumption in weak light and low traffic, thereby accurately matching energy supply and scenario demand and achieving the coordinated optimization of resource efficiency, public information efficiency, and ecological sustainability.

[0004] The patent CN117873301B discloses an LED display screen energy-saving display method, which includes: S101: taking a set display radiation area as a location reference to obtain unpredictability influence characteristic data and predictability influence characteristic data within a future time T to a future time T+N, T and N are both integers greater than zero; S102: inputting the unpredictability influence characteristic data and the predictability influence characteristic data into a pre-configured traffic density regression model to obtain traffic density; S103: comparing the traffic density with a preset traffic density threshold, if the traffic density is greater than or equal to the preset traffic density threshold, then taking the time range between the future time T and the future time T+N as a playing time interval; if the traffic density is less than the preset traffic density threshold, then setting T=T+M and returning to step S101, M is an integer greater than zero; S104: controlling the LED display screen to turn on or off according to the playing time interval. This scheme can control the on-off operation of the LED display screen according to the optimal playing time period, which is beneficial to avoid energy waste under long-term operation of the LED display screen, but this scheme does not combine the surrounding environmental data of the LED display screen for regulation and control, which has certain applicability problems. SUMMARY

[0005] The application provides an energy-saving display method of an environment-friendly LED display screen.

[0006] To solve the above technical problems, the application provides the following technical scheme.

[0007] The application provides an energy-saving display method of an environment-friendly LED display screen, comprising:

[0008] S1, acquiring display content data in a current image frame;

[0009] S2, collecting ambient light data of the LED display screen;

[0010] S3, collecting people flow data in front of the LED display screen;

[0011] S4, analyzing the collected ambient light data and people flow data;

[0012] S5, predicting an energy consumption trend of the LED display screen according to the collected data;

[0013] S6, generating an energy-saving display strategy of the LED display screen through the energy consumption trend;

[0014] S7, recording and storing log data of the energy-saving display of the LED display screen.

[0015] The application provides the technical scheme, and the beneficial effects thereof at least include:

[0016] The application collects ambient light data of the LED display screen through an ambient light sensor in real time, and compensates and corrects the collected ambient light data, so as to ensure the accuracy of the ambient light data.

[0017] The application collects head data in front of the LED display screen, predicts personnel motion tracks according to the head data, can identify people flow data in front of the LED, and provides a basis for subsequent energy-saving display regulation.

[0018] The application can predict the display energy consumption of the LED display screen according to the ambient light data and people flow data, generate a regulation scheme of the energy-saving display of the LED display screen through setting constraint conditions, ensure the best brightness of the human eye, and reduce energy waste. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments description. Obviously, the drawings in the following description only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0020] Figure 1 The flow chart of the energy-saving display method of the environment-friendly LED display screen provided by the embodiments of the present application. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solutions and advantages of the present application more clear, the following will further describe the embodiments of the present application in detail with the drawings.

[0022] EMBODIMENT

[0023] An energy-saving display method of an environment-friendly LED display screen.

[0024] Please refer to Figure 1 , Figure 1 The flow chart of the energy-saving display method of the environment-friendly LED display screen provided by the embodiments of the present application.

[0025] S1, obtaining display content data in a current image frame;

[0026] S101, the image frame content data is read in real time through the API interface of the display screen control system, the image frame content data is captured by a protocol parser to obtain original data stream, the communication protocol is automatically parsed through signal characteristics, and the timing of the parsing is kept synchronous with the refresh rate of the display screen;

[0027] S102, the image frame content data is extracted to obtain original RGB data through the built-in function of the OpenCV library, the RGB data is mapped to a brightness matrix according to the pixel coordinates of the image frame content data after the extraction, the brightness matrix converts the RGB image data into a gray value according to a preset weight, maps the gray value into a two-dimensional array according to the physical pixel arrangement of the LED display screen, and performs normalization and non-linear correction on the gray value;

[0028] It should be noted that the resolution of the input data must be strictly consistent with the physical pixel layout of the LED display screen, so as to avoid errors caused by interpolation or cropping.

[0029] S2, collecting ambient light data of the LED display screen;

[0030] S201, the ambient light includes the display screen self-luminous and the outside environment light, the ambient light data is collected in real time through the digital ambient light sensor, the sensor triggers the reading according to the VSync signal of the display screen, the sensor adopts multi-point installation, is installed in the four corners and the center position of the LED display screen respectively, and the average value of multiple sensors is selected for data collection;

[0031] It should be noted that the digital ambient light sensor should be selected to support the visible light band 380~780nm, and the interference of infrared and ultraviolet is excluded.

[0032] S202, the data collected by the sensor is eliminated by the median filter and sliding average combination algorithm, the illumination is converted into PWM duty cycle by adopting a nonlinear brightness mapping curve, and the Gamma correction is carried out by adopting a gradual algorithm to limit the brightness change rate;

[0033] It should be noted that the brightness mapping curve is forced to lock the minimum brightness when it is lower than 50 Lux, is adjusted in a linear proportion in the interval of 50~5000 Lux, is maintained at the maximum brightness when it is higher than 5000 Lux, and the change rate of brightness per second should be less than 5%.

[0034] S203, the sensor collection data is corrected by light residual, the ambient light of the blanking period of the LED display screen is compensated, and the specific formula is as follows:

[0035]

[0036] In the formula, Indicates the compensated data; Indicates the reading of the current sensor collection; Indicates the reading of the sensor measurement full white picture; Indicates the light leakage coefficient.

[0037] S3, the people flow data in front of the LED display screen is counted;

[0038] S301, the people flow data is obtained by shooting the head image data of the person with binocular camera, the head features of pedestrians are extracted by the CNN-SVM detector, and the positive sample image and the negative sample image are trained, the positive sample image refers to the head image of the person, and the negative sample image refers to the interference feature image;

[0039] It should be noted that the positive sample image and the negative sample image are obtained through the network and imported into the CNN-SVM detector, the positive sample image selects each angle of the head of the person, and the negative sample image selects the image sample similar to the head feature of the person, such as trees, street lamp poles and landmark buildings.

[0040] S302, the sample training process of the CNN-SVM detector is as follows: local features are extracted through a plurality of convolution kernels and feature maps are generated, a ReLU is used to introduce a nonlinear parameter, the model expression capability is enhanced, down-sampling is performed through average pooling, the feature map size is reduced and key information is retained, batch normalization is added after the convolution layer to accelerate convergence and prevent gradient disappearance;

[0041] S303, after recognizing the head features of the image, the image associated head is selected, the image associated head uses the Euclidean distance limit, the image associated head with a Euclidean distance of 50 in adjacent two frames is selected, and the image associated head is selected as the center point to select a range with a Euclidean distance of 100, to obtain a candidate image associated head matching area, and the specific formula is as follows:

[0042]

[0043] In the formula, Euclidean distance is represented; The coordinate position of the head in the first frame image is represented; The coordinate position of the head in the second frame image is represented;

[0044] S304, after the image associated head is selected, the corresponding CNN head feature vector is extracted, the feature vector and the feature vector of the specified head in the current frame are measured for similarity, the head correlation coefficient is calculated, and the specific formula is as follows:

[0045]

[0046] In the formula, The head correlation coefficient is represented; The total number of samples is represented; And The feature vector values in the first frame and the second frame images are represented respectively; And The average values of the feature vectors in the first frame and the second frame images are represented respectively.

[0047] It should be noted that if the head correlation coefficient is greater than or equal to 0.5, it is considered that the head in the current frame matches the associated head, the matched head is associated, and finally the associated head motion trajectory is obtained. If the head correlation coefficient is less than 0.5, the head in the current frame is considered as a new appearing head, which is matched with the head in the subsequent frame.

[0048] S4 analyzes the collected environmental light data and passenger flow data;

[0049] S401, the data analysis calculates the information entropy value of each index data in a fixed time window, and the specific formula is as follows:

[0050]

[0051] wherein, represents an information entropy value; represents a constant, and ; represents a size of a time window; represents a proportion of index j at time point i;

[0052] S402, an entropy weight is generated by using the information entropy value, a difference coefficient of the information entropy value is calculated, and a weight distribution condition is selected in combination with a real-time environment state of the LED display screen, and the specific formula is as follows:

[0053]

[0054]

[0055] wherein, represents a difference coefficient; represents a weight value; represents a constant of a proportion;

[0056] It should be noted that if the environmental light data is greater than 5000Lux, then the weight is forcibly assigned as 0.6, if the crowd density is greater than 3 people / ㎡, then the weight is forcibly assigned as 0.7, and under the remaining conditions, the weight is assigned according to the entropy weight method.

[0057] S403, the server performs smoothing filtering, boundary constraint, and normalization processing on the output weight, the smoothing filtering adopts a sliding average filter with a window size of 5, the boundary constraint constrains the weight value in the interval of 0.1-0.8, and the normalization makes the sum of each weight equal to 1.

[0058] S5, the energy consumption trend of the LED display screen is predicted according to the data;

[0059] S501, the energy consumption of the LED display screen is realized by using a deep learning model, the future energy consumption trend is predicted according to historical energy consumption data and real-time energy consumption data, and the specific formula is as follows:

[0060]

[0061] wherein, represents predicted energy consumption data; represents a deep learning model; represents input feature data, including crowd data and environmental light data; represents a model parameter;

[0062] S502, the deep learning model updates the model parameter by using a gradient descent method to minimize the prediction error, and the specific formula is as follows:

[0063]

[0064] wherein, denotes the updated model parameters; denotes the updated model parameters; denotes the learning rate of the model; denotes the cost function the gradient with respect to θ.

[0065] S6 generates the energy-saving display strategy of the LED display screen through the energy consumption trend;

[0066] S601, the energy-saving display strategy model is calculated and generated based on the prediction result and the preset constraint condition, and the specific formula is as follows:

[0067]

[0068]

[0069] wherein, denotes the cost function; denotes the predicted energy consumption parameter; denotes the real-time energy consumption parameter; denotes the parameter affecting the real-time energy consumption, and the passenger flow data and the ambient light data are selected here; denotes the energy-saving display strategy; denotes the comfort function; denotes the constraint parameter; denotes the constraint condition; denotes the minimum requirement of the brightness function.

[0070] S602, the constraint condition includes the core information display constraint, the severe weather adjustment constraint, and the equipment protection constraint, the cost function adopts the form of a quadratic function, is solved through a genetic algorithm, and the comfort function adopts a linear form, and is solved through a linear programming algorithm.

[0071] It should be noted that the optimal solution is obtained after the model is solved, the energy-saving display strategy is generated according to the optimal solution, and the effect of the energy-saving control strategy can be evaluated. If the effect does not meet the expectation, the cost function, the comfort function, and the optimization algorithm can be adjusted, the model is re-solved, and a new energy-saving control strategy is generated.

[0072] When the visibility is less than 1000 meters, the forced minimum brightness is greater than 50%, when the screen temperature is greater than 60℃, the brightness reduction coefficient is 0.7, otherwise the brightness reduction coefficient is 1, and if it is activated, the forced full-screen brightness is 100% and covers the display content.

[0073] S7 records the log data of the energy-saving display of the LED display screen and stores the log data;

[0074] S701, the log data is transmitted by TLS 1.3 encryption, and static data is encrypted by AES-256, and the stored data includes environment perception data, device running data and decision control data, the environment perception data is stored by using an edge time series database, the device running data is stored by using a relational database and is partitioned according to time, and the decision control data adopts a double storage mode, the double storage mode includes an in-memory database and a document database, the in-memory database is used to store real-time instructions, and the document database is used to store data history logs;

[0075] It should be noted that the environment perception data refers to surrounding environment data of the display screen, for example, ambient light, passenger flow, temperature and humidity, the device running data refers to data in the device running process, for example, brightness, screen refresh rate and voltage, and the decision control data refers to control instruction data of the strategy in the energy-saving display process, including constraint conditions, weight vectors and control commands.

[0076] S702, the edge time series database uses a ZSTD compression algorithm, and stores adjacent grid value differences by using Delta coding, a partition strategy includes creating a partition table every month according to a time range, sharding according to a display screen ID hash value, creating a BRIN index to accelerate time range query, and the decision control data is stored in a JSONB format and is optimized by establishing a GIN index.

[0077] In addition, it should be noted that the present application can be provided as a method, an apparatus or a computer program product. Therefore, the embodiments of the present application can adopt a completely hardware embodiment, a completely software embodiment or an embodiment in combination of software and hardware aspects. Moreover, the embodiments of the present application can adopt a form of a computer program product implemented on one or more computer usable storage media including computer usable program code.

[0078] The embodiments of the present application are described with reference to flowcharts and / or block diagrams according to the method, terminal device (system) and computer program product of the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be realized by computer program instructions. These computer program instructions can be provided to a general-purpose computer, embedded processor or other programmable data processing terminal device to produce a machine, so that the instructions executed by the computer or other programmable data processing terminal device produce a machine that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one flow or multiple flows and / or blocks Figure 1 The apparatus that realizes the functions specified in one block or multiple blocks.

[0079] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the Figure 1 function specified in the flow or flows and / or blocks Figure 1 These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flow or flows and / or blocks Figure 1 function specified in the flow or flows and / or blocks Figure 1 These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flow or flows and / or blocks

[0080] It is also important to note that while the above describes example embodiments, there are several variations and modifications which can be made to them without departing from the scope of the present application. For example, the order or sequence of any process steps can be varied or re-sequenced without departing from the scope of the present application. Other steps can be performed or it can be decided to omit some steps. It is therefore contemplated to cover any and all modifications, variations or equivalents that fall with the scope of the present application. It is intended that the following claims cover all such

[0081] Finally, it is to be noted that the above-described arrangements are merely meant to be illustrative of only some of the various ways of implementing the present application. Other embodiments of the present application that are not explicitly described herein are contemplated as well. Although the present application has been described in some detail with the aid of the previous examples, it is to be understood that certain changes and modifications will be apparent from the foregoing disclosure, for which reason the present application is not to be construed as being limited to the prior example embodiments. Therefore, the foregoing disclosure is not intended to be limiting; but rather an aid in providing a patentable scope including equivalent variations over the present application. The wording of the appended claims should be interpreted in the light of this preambular detail.

Claims

1. An energy-saving display method for an environmentally friendly LED display screen, characterized in that, include: S1, Obtain the display content data in the current image frame; S2, collect ambient light data around the LED display screen; S3, to collect pedestrian traffic data in front of the LED display screen; S4, analyze the collected ambient light data and pedestrian flow data; S5, predicts the energy consumption trend of the LED display screen based on the collected data; S6 generates energy-saving display strategies for LED displays based on energy consumption trends; S7 records and stores log data of energy-saving display on the LED screen; The S6 generates an energy-saving display strategy model for the LED display screen based on energy consumption trends, wherein: S601, the energy-saving display strategy model is generated based on the prediction results and preset constraints, specifically as follows: In the formula, Represents the cost function; This represents the predicted energy consumption parameters; This represents real-time energy consumption parameters; These represent parameters that affect real-time energy consumption; here, we select pedestrian traffic data and ambient light data. Indicates energy-saving display strategy; Represents the comfort function; Indicates constraint parameters; Indicates constraints; The minimum requirement for representing the brightness function; S602, the constraints include core information display constraints, severe weather adjustment constraints, and equipment protection constraints. The cost function is represented in the form of a quadratic function and solved by a genetic algorithm. The comfort function is represented in the form of a linear function and solved by a linear programming algorithm.

2. The energy-saving display method for the environmentally friendly LED display screen according to claim 1, characterized in that, S1 acquires the display content data in the current image frame, wherein: S101, the image frame content data is read in real time through the API interface of the display screen control system. The image frame content data captures the original data stream through the protocol parser and automatically parses the communication protocol through signal characteristics. The timing of the parsing is synchronized with the refresh rate of the display screen. S102, the image frame content data uses the OpenCV library and its built-in functions to extract the original RGB data. After the RGB data is extracted, it is mapped to a brightness matrix according to the pixel coordinates of the image frame content data. The brightness matrix converts the RGB image data into grayscale values ​​according to preset weights, maps it into a two-dimensional array according to the physical pixel arrangement of the LED display screen, and normalizes and corrects the grayscale values ​​for nonlinearity.

3. The energy-saving display method for the environmentally friendly LED display screen according to claim 1, characterized in that, The S2 collects ambient light data around the LED display screen, wherein: S201, the ambient light includes the self-illumination of the display screen and the external ambient light. The ambient light data is collected in real time by a digital ambient light sensor. The sensor is triggered to read the data according to the VSync signal of the display screen. The sensor is installed at multiple points, respectively at the four corners and the center of the LED display screen. The collected data is the average value of multiple sensors. S202, the data collected by the sensor is processed by a combination of median filtering and moving average algorithm to eliminate instantaneous noise, and a nonlinear brightness mapping curve is used to convert illuminance into PWM duty cycle. A gradual algorithm is used to limit the rate of brightness change for Gamma correction. S203, the sensor collects data and compensates for the ambient light during the blanking period of the LED display screen through light retention correction, as shown in the following formula: In the formula, This represents the data after compensation; This indicates the current reading collected by the sensor; This indicates the sensor reading when measuring a completely white screen. This represents the light leakage coefficient.

4. The energy-saving display method for the environmentally friendly LED display screen according to claim 1, characterized in that, The S3 method collects pedestrian traffic data in front of the LED display screen, including: S301, the pedestrian flow data is obtained by capturing human head images with a binocular camera. The images are used to extract pedestrian head features through a CNN-SVM detector, and are trained using positive sample images and negative sample images. The positive sample images refer to human head images, and the negative sample images refer to interference feature images. S302, the sample training process of the CNN-SVM detector is as follows: local features are extracted and feature maps are generated through multiple convolutional kernels, nonlinear parameters are introduced using ReLU to enhance the model's expressive power, downsampling is performed through average pooling to reduce the size of the feature map and retain key information, and batch normalization is added after the convolutional layer to accelerate convergence and prevent gradient vanishing. S303, after recognizing the features of the human head, select image-related human heads. The image-related human heads are restricted by Euclidean distance. Select the related human heads with an Euclidean distance of 50 between two adjacent frames, and select a range with an Euclidean distance of 100 with the related human head as the center point to obtain the candidate related human head matching region, as shown in the following formula: In the formula, Indicates Euclidean distance; This indicates the coordinates of the head in the first frame of the image; This indicates the coordinates of the person's head in the second frame image; S304, after the image-associated head selection is completed, the corresponding CNN head feature vector is extracted. The similarity between the feature vector and the feature vector of the specified head in the current frame is measured, and the head correlation coefficient is calculated, as follows: In the formula, Represents the correlation coefficient among individuals; Indicates the total number of samples; and These represent the feature vector values ​​in the first and second frames of the image, respectively. and These represent the average values ​​of the feature vectors in the first and second frames of the image, respectively.

5. The energy-saving display method for an environmentally friendly LED display screen according to claim 1, characterized in that, S5 predicts the energy consumption trend of the LED display screen based on data, wherein: S501, the energy consumption of the LED display screen is realized through a deep learning model, which predicts future energy consumption trends based on historical and real-time energy consumption data, as shown in the following formula: In the formula, This represents the predicted energy consumption data; Represents a deep learning model; This represents the input feature data, including pedestrian flow data and ambient light data; Indicates model parameters; S502, the deep learning model uses gradient descent to update model parameters to minimize prediction error, as shown in the following formula: In the formula, This represents the updated model parameters; This represents the model parameters before the update; This represents the model's learning rate; Representing the cost function The gradient with respect to θ.

6. The energy-saving display method for an environmentally friendly LED display screen according to claim 1, characterized in that, The S7 records and stores the log data of energy-saving display on the LED screen, wherein: S701, the log data is transmitted using TLS 1.3 encryption, and static data is encrypted using AES-256. The log data includes environmental perception data, device operation data, and decision control data. The environmental perception data is stored using an edge time-series database. The device operation data is stored using a relational database and partitioned according to a partitioning strategy. The decision control data adopts a dual storage mode, which includes a memory database and a document database. The memory database is used to store real-time instructions, and the document database is used to store historical logs. S702, the edge time series database uses the ZSTD compression algorithm and stores the differences in adjacent grid values ​​through Delta encoding. The partitioning strategy includes creating a partition table monthly based on the time range, sharding based on the display ID hash value, and creating a BRIN index to accelerate time range queries. The decision control data is stored in JSONB format and the retrieval steps are optimized by establishing a GIN index.

Images