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

Abstract

The invention discloses an energy-saving display method of an environment-friendly LED display screen, and relates to the technical field of energy conservation of display screens, and the method comprises the following steps: obtaining 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 human traffic data; predicting the 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 displayed by the LED display screen in an energy-saving manner. According to the method, the head data is collected, the motion trail of people is predicted, the flow data of people in front of the LED display screen is recognized, 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 by establishing a model, and a corresponding energy-saving display regulation and control scheme is generated in combination with set constraint conditions.

Description

Technical Field

[0001] The present invention relates to the technical field of energy-saving display screens, and in particular to an energy-saving display method for an environmentally friendly LED display screen. Background Art

[0002] An LED display is a flat-panel 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, a wide color gamut, a long lifespan, low energy consumption, and environmental adaptability, making it suitable for a variety of indoor and outdoor scenarios. Outdoor LED displays are primarily used in shopping malls, landmark buildings, and other settings, so their lighting conditions must ensure visibility. Traditional fixed power consumption modes are unable to adapt to these dynamic scenarios, leading to two core issues: continued high energy consumption in low-light environments (such as at night) or during periods of low traffic, resulting in significant waste of electricity resources and increased operating costs, while excessive lighting creates light pollution, disrupting the city's ecological balance.

[0003] Therefore, the essence of energy-saving display of outdoor LED display screens is to build a dynamic response mechanism through real-time perception of ambient light intensity and crowd density, ensure visibility in strong light and high crowd flow, and actively reduce power consumption in weak light and low crowd flow, so as to accurately match energy supply and scene requirements, and achieve coordinated optimization of resource efficiency, public information effectiveness and ecological sustainability.

[0004] The invention patent with publication number CN117873301B discloses an energy-saving display method for an LED display screen, including: S101: taking a set display radiation area as a location reference, obtaining unpredictable impact feature data and predictable impact feature data from future time T to future time T+N, where T and N are both integers greater than zero; S102: inputting the unpredictable impact feature data and predictable impact feature data into a preconfigured crowd density regression model to obtain crowd density; S103: comparing the crowd density with a preset crowd density threshold; if the crowd density is greater than or equal to the preset crowd density threshold, then taking the time range between future time T and future time T+N as the playback time interval; if the crowd density is less than the preset crowd density threshold, then setting T=T+M, and returning to step S101, where M is an integer greater than zero; S104: controlling the LED display screen to turn on or off according to the playback time interval. This solution predicts the optimal playback period of the LED display and can turn the LED display on and off according to the optimal playback period, which helps to avoid energy waste caused by long-term operation of the LED display. However, this solution does not combine the surrounding environmental data of the LED display for regulation and control, and there are certain applicability issues. Summary of the Invention

[0005] The present invention provides an energy-saving display method for an environment-friendly LED display screen. By collecting the ambient environment data and the pedestrian flow data of the LED display screen, it can accurately adjust the display brightness of the LED according to the ambient environment of the LED display screen, so as to solve the technical problem of excessive energy consumption of the LED display screen and resulting in energy waste.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: The present invention provides an energy-saving display method for an environment-friendly LED display screen, including: S1, obtaining the display content data in the current image frame; S2, collecting the ambient light data of the LED display screen; S3, counting the pedestrian flow data in front of the LED display screen; S4, analyzing the collected ambient light data and pedestrian flow data; S5, predicting the energy consumption trend of the LED display screen according to the collected data; S6, generating an energy-saving display strategy for the LED display screen through the energy consumption trend; S7, recording and storing the log data of the energy-saving display of the LED display screen.

[0007] The beneficial effects brought by the technical solutions provided by the present invention at least include: The present invention can ensure the accuracy of the ambient light data by collecting the ambient light data of the LED display screen in real time through an ambient light sensor and compensating and correcting the collected ambient light data.

[0008] The present invention can identify the pedestrian flow data in front of the LED by collecting the head data in front of the LED display screen and predicting the personnel movement trajectory according to the head data, providing a basis for subsequent energy-saving display regulation.

[0009] The present invention can predict the display energy consumption of the LED display screen according to the ambient light data and pedestrian flow data, and can generate a regulation scheme for the energy-saving display of the LED display screen by setting constraint conditions, reducing energy waste while ensuring the best brightness for the human eye. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0011] Figure 1 It is a flowchart of the energy-saving display method for the environment-friendly LED display screen provided by the embodiment of the present invention. Detailed implementation mode

[0012] To make the objectives, technical solutions and advantages of the present invention clearer, the embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.

[0013] Embodiment An energy-saving display method for an environment-friendly LED display screen.

[0014] Please refer to Figure 1 , Figure 1 which is a flowchart of the energy-saving display method for the environment-friendly LED display screen provided by the embodiment of the present invention.

[0015] S1. Obtain the display content data in the current image frame; S101. The image frame content data is read in real time through the API interface for docking with the display control system. The image frame content data captures the original data stream through a protocol parser, automatically analyzes the communication protocol through signal characteristics, and the analyzed timing is synchronized with the refresh rate of the display screen; S102. The image frame content data uses the OpenCV library and extracts the original RGB data through its built-in functions. After the RGB data is extracted, it is mapped into a luminance matrix according to the pixel coordinates of the image frame content data. The luminance matrix converts the RGB image data into gray values according to a preset weight, maps it into a two-dimensional array according to the physical pixel arrangement of the LED display screen, and normalizes and non-linearly corrects the gray values; 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 to avoid errors caused by interpolation or cropping.

[0016] S2. Collect the ambient light data of the LED display screen; S201. The ambient light includes the self-emission of the display screen and the external ambient light. The ambient light data is collected in real time through a digital ambient light sensor. The acquisition period of the sensor triggers the reading according to the VSync signal of the display screen. The sensor is installed at multiple points, respectively installed at the four corners and the center position of the LED display screen, and the average value of the data collected by multiple sensors is selected; It should be noted that the digital ambient light sensor should select a model that supports the visible light band of 380~780nm to exclude the interference of infrared and ultraviolet rays.

[0017] S202. The data collected by the sensor eliminates instantaneous noise through a combined algorithm of median filtering and moving average, converts the illuminance into a PWM duty cycle using a non-linear brightness mapping curve, and performs Gamma correction using a gradient algorithm to limit the brightness change rate; It should be noted that the brightness mapping curve forcibly locks the minimum brightness when it is below 50 Lux, adjusts linearly in the range of 50 - 5000 Lux, maintains the maximum brightness when it is above 5000 Lux, and the change rate of brightness per second should be less than 5%.

[0018] S203. The data collected by the sensor is corrected by light residue to compensate for the ambient light during the blanking period of the LED display screen, as follows:

[0019] In the formula, represents the compensated data; represents the current reading collected by the sensor; represents the reading when the sensor measures a full - white screen; represents the light leakage coefficient.

[0020] S3. Statistically analyze the pedestrian flow data in front of the LED display screen; S301. The pedestrian flow data is obtained by using a binocular camera to capture the head image data of people. The image extracts the pedestrian head features through a CNN - SVM detector, and is trained with positive sample images and negative sample images. The positive sample images refer to the head images of people, and the negative sample images refer to interference feature images; It should be noted that the positive sample images and negative sample images are obtained through the network and imported into the CNN - SVM detector. The positive sample images select various angles of the human head, and the negative sample images select image samples similar to the human head features, such as trees, street lamp poles, and landmark buildings.

[0021] S302. The sample training process of the CNN - SVM detector is as follows: extract local features through multiple convolutional kernels to generate a feature map, introduce non - linear parameters using ReLU to enhance the model's expression ability, perform downsampling through average pooling to reduce the feature map size and retain key information, and add batch normalization after the convolutional layer to accelerate convergence and prevent gradient disappearance; S303. After the image recognizes the human head features, select the image - associated human head. The image - associated human head uses the Euclidean distance limit. Select the associated human head with an Euclidean distance of 50 within two adjacent frames, and select a range with an Euclidean distance of 100 with the associated human head as the center point to obtain the candidate associated human head matching area, as follows:

[0022] In the formula, represents the Euclidean distance; represents the coordinate position of the human head in the first - frame image; represents the coordinate position of the human head in the second - frame image; After the extraction of the CNN head feature vector corresponding to the selected head associated with the image is completed in S304, the similarity measurement is performed between the feature vector and the feature vector of the specified head in the current frame, and the head correlation coefficient is calculated as follows:

[0023] In the formula, represents the head correlation coefficient; represents the total number of samples; and respectively represent the feature vector values in the first frame and the second frame images; and respectively represent the average values of the feature vectors in the first frame and the second frame images.

[0024] 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, and the matched head is associated. Finally, the movement trajectory of the associated head is obtained. If the head correlation coefficient is less than 0.5, the head in the current frame is regarded as a newly emerged head and matched with the heads in subsequent frames.

[0025] S4 Analyze the collected ambient light data and pedestrian flow data; S401 In data analysis, within a fixed time window, calculate the information entropy value of each index data as follows:

[0026] In the formula, represents the information entropy value; represents a constant, and ; represents the size of the time window; represents the proportion of index j at time point i; S402 Generate the weight of the entropy weight method by using the information entropy value. By calculating the information entropy value difference coefficient and combining the real-time environmental state of the LED display screen, select the weight distribution as follows:

[0027]

[0028] In the formula, represents the difference coefficient; represents the weight value; represents the ratio of the constant ; It should be noted that if the ambient light data is greater than 5000 Lux, the forced weight is 0.6. If the pedestrian flow density is greater than 3 people / ㎡, the forced weight is 0.7. Under other conditions, the weight is distributed according to the entropy weight method.

[0029] S403. The server performs smoothing filtering, boundary constraint, and normalization on the output weights. The smoothing filtering uses a moving average filter with a window size of 5. The boundary constraint confines the weight values within the range of 0.1 to 0.8, and the normalization makes the sum of each weight equal to 1.

[0030] S5. Predict the energy consumption trend of the LED display screen based on the data; S501. The energy consumption of the LED display screen is realized through a deep learning model. The future energy consumption trend is predicted based on historical energy consumption data and real-time energy consumption data, as shown in the following formula:

[0031] In the formula, represents the predicted energy consumption data; represents the deep learning model; represents the input feature data, including pedestrian flow data and ambient light data; represents the model parameters; S502. The deep learning model updates the model parameters using the gradient descent method to minimize the prediction error, as shown in the following formula:

[0032] In the formula, represents the updated model parameters; represents the model parameters before update; represents the learning rate of the model; represents the gradient of the cost function J with respect to θ.

[0033] S6. Generate an energy-saving display strategy for the LED display screen based on the energy consumption trend; S601. The energy-saving display strategy model is generated according to the prediction result and the set constraint conditions, combined with the optimal brightness value, as shown in the following formula:

[0034]

[0035] In the formula, represents the cost function; represents the predicted energy consumption parameter; represents the real-time energy consumption parameter; represents the parameters affecting the real-time energy consumption. Here, pedestrian flow data and ambient light data are selected; represents the energy-saving display strategy; represents the comfort function; represents the constraint parameter; represents the constraint condition; Indicates the minimum requirement of the brightness function.

[0036] S602, the constraint conditions include core information display constraint, bad weather adjustment constraint, and device protection constraint. The cost function is represented in the form of a quadratic function and solved by a genetic algorithm. The comfort function is represented in a linear form and solved by a linear programming algorithm.

[0037] It should be noted that after the model is solved to obtain the optimal solution, an energy-saving display strategy is generated according to the optimal solution. Moreover, the effect of the energy-saving control strategy can be evaluated. If the effect does not meet the expectation, the cost function, comfort function, and optimization algorithm can be adjusted, and the model can be re-solved to generate a new energy-saving control strategy.

[0038] When the visibility is less than 1000 meters, the forced minimum brightness is greater than 50%. When the screen temperature is greater than 60 °C, the brightness reduction factor of 0.7 is applied. Otherwise, the brightness reduction factor of 1 is applied. If activated, the forced full-screen brightness is 100% and the display content is overwritten.

[0039] S7 records and stores the log data of the energy-saving display of the LED display screen; S701, the log data is encrypted and transmitted through TLS 1.3, and the static data is encrypted using AES-256. The stored data includes environmental perception data, device operation data, and decision control data. The environmental perception data is stored in an edge time-series database. The device operation data is stored in a relational database and partitioned according to time. 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 data historical logs; It should be noted that the environmental perception data refers to the surrounding environment data of the display screen, such as ambient light, pedestrian flow, temperature, and humidity. The device operation data refers to the data during the operation of the device, such as brightness, screen refresh rate, and voltage. The decision control data refers to the control instruction data of the strategy during the energy-saving display process, including constraint conditions, weight vectors, and control commands.

[0040] S702, the edge time-series database uses the ZSTD compression algorithm and stores the differences between adjacent grid values through Delta encoding. The partitioning strategy includes creating a partition table monthly by time range, sharding by the hash value of the display screen ID, 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.

[0041] In addition, it should be noted that the present invention can be provided as a method, apparatus, or computer program product. Therefore, embodiments of the present invention can take the form of an all-hardware embodiment, an all-software embodiment, or an embodiment combining software and hardware aspects. Moreover, embodiments of the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code.

[0042] Embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing terminal device generate a device for implementing the functions specified in Figure 1 one or more of the flows Figure 1 or a plurality of flows and / or blocks

[0043] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device that implements the functions specified in Figure 1 one or more of the flows Figure 1 or a plurality of flows and / or blocks Figure 1 These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device, such that a series of operation steps are executed on the computer or other programmable terminal device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable terminal device provide steps for implementing the functions specified in Figure 1 one or more of the flows

[0044] It should also be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. The term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or terminal device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or terminal device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or terminal device comprising the element.

[0045] Finally, it should be noted that the above description is the preferred embodiment of the present invention. It should be pointed out that although the preferred embodiments of the present invention have been described, for those skilled in the art of this technology, once the basic creative concept of the present invention is known, without departing from the principle described in the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the embodiments of the present invention.

Claims

1. An energy-saving display method for an environment-friendly LED display screen, characterized in that, Including: S1, obtaining the display content data in the current image frame; S2, collecting the ambient light data around the LED display screen; S3, counting the pedestrian flow data in front of the LED display screen; S4, analyzing the collected ambient light data and pedestrian flow data; S5, predicting the energy consumption trend of the LED display screen according to the collected data; S6, generating an energy-saving display strategy for the LED display screen through the energy consumption trend; S7, recording and storing the log data of the energy-saving display of the LED display screen.

2. The energy-saving display method of the environment-friendly LED display screen according to claim 1, characterized in that, The S1 obtains the display content data in the current image frame, where: S101, the image frame content data is read in real time by docking the API interface of the display control system. The image frame content data captures the original data stream through a protocol parser, automatically analyzes the communication protocol through signal characteristics, and the timing of the analysis is synchronized with the refresh rate of the display screen; S102, the image frame content data uses the OpenCV library and extracts the original RGB data through its built-in functions. After the RGB data is extracted, it is mapped to a luminance matrix according to the pixel coordinates of the image frame content data. The luminance matrix converts the RGB image data into grayscale values according to a preset weight, maps it to a two-dimensional array according to the physical pixel arrangement of the LED display screen, and normalizes and non-linearly corrects the grayscale values.

3. The energy-saving display method of the environment-friendly LED display screen according to claim 1, characterized in that The S2 collects the ambient light data around the LED display screen, where: S201, the ambient light includes the self-emission 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 acquisition period of the sensor is triggered by the VSync signal of the display screen to read data. The sensor is installed at multiple points, respectively installed at the four corners and the center position of the LED display screen, and the average value of multiple sensors is selected for the collected data; S202, the data collected by the sensor eliminates instantaneous noise through a median filter and moving average combined algorithm, converts the illuminance to the PWM duty cycle using a non-linear luminance mapping curve, and performs Gamma correction using a gradient algorithm to limit the brightness change rate; S203, the data collected by the sensor is corrected by light residue compensation to compensate for the ambient light during the blanking period of the LED display screen, as shown in the following formula: In the formula, represents the compensated data; represents the reading collected by the current sensor; represents the reading when the sensor measures a full white screen; represents the light leakage coefficient.

4. The energy-saving display method of the environment-friendly LED display screen according to claim 1, characterized in that, The S3 counts the pedestrian flow data in front of the LED display screen, where: S301, the pedestrian flow data is obtained by using a binocular camera to capture the head image data of people. The image extracts the pedestrian head features through a CNN-SVM detector, and is trained using positive sample images and negative sample images. The positive sample images refer to the head images of people, and the negative sample images refer to interference feature images; S302, the sample training process of the CNN-SVM detector is: extracting local features through multiple convolutional kernels and generating feature maps, introducing non-linear parameters using ReLU to enhance the model's expression ability, performing downsampling through average pooling to reduce the size of the feature map and retain key information, and adding batch normalization after the convolutional layer to accelerate convergence and prevent gradient disappearance; S303. After the image recognizes the human head features, select the image-associated human head. The image-associated human head is restricted by the Euclidean distance. Select the associated human heads with an Euclidean distance of 50 within two adjacent frames, and select a range with an Euclidean distance of 100 with the associated human head as the center point to obtain the candidate associated human head matching area, as shown in the following formula: In the formula, represents the Euclidean distance; represents the coordinate position of the human head in the first frame of the image; represents the coordinate position of the human head in the second frame of the image; S304. After the selection of the image-associated human head is completed, extract the corresponding CNN human head feature vector. The feature vector is used for similarity measurement with the feature vector of the specified human head in the current frame, and the human head correlation coefficient is calculated, as shown in the following formula: In the formula, represents the head correlation coefficient; represents the total number of samples; and respectively represent the feature vector values in the first frame and the second frame of the image; and respectively represent the average values of the feature vectors in the first frame and the second frame of the image.

5. The energy-saving display method of the environment-friendly LED display screen according to claim 1, characterized in that In S4, analyze the collected ambient light data and pedestrian flow data, where: S401. The data analysis calculates the information entropy value of each index data within a fixed time window, as shown in the following formula: In the formula, represents the information entropy value; represents a constant, and ; represents the size of the time window; represents the proportion of index j at time point i; S402. Use the information entropy value to generate the weight of the entropy weight method. By calculating the information entropy value difference coefficient and combining the real-time environmental state of the LED display screen, select the weight distribution situation, as shown in the following formula: In the formula, represents the coefficient of variation; represents the weight value; represents a constant ratio; S403. Smooth filter, boundary constraint, and normalization processing are performed on the output weight. The smooth filter uses a moving average filter with a window size of 5. The boundary constraint restricts the weight value within the range of 0.1 to 0.

8. The normalization makes the sum of each weight equal to 1.

6. The energy-saving display method of the environment-friendly LED display screen according to claim 1, characterized in that, In S5, predict the energy consumption trend of the LED display screen based on the data, where: S501. The energy consumption of the LED display screen is realized through a deep learning model. Predict the future energy consumption trend based on historical energy consumption data and real-time energy consumption data, as shown in the following formula: In the formula, represents the predicted energy consumption data; represents the deep learning model; represents the input feature data, including the pedestrian flow data and the ambient light data; represents the model parameters; S502. The deep learning model updates the model parameters using the gradient descent method to minimize the prediction error, as shown in the following formula: In the formula, represents the updated model parameters; represents the model parameters before update; represents the learning rate of the model; represents the gradient of the cost function J with respect to θ.

7. The energy-saving display method of the environment-friendly LED display screen according to claim 1, characterized in that In S6, generate an energy-saving display strategy model for the LED display screen based on the energy consumption trend, where: S601. The energy-saving display strategy model is generated based on the prediction result and the set constraint conditions, combined with the optimal brightness value, as shown in the following formula: In the formula, represents the cost function; represents the predicted energy consumption parameter; represents the real-time energy consumption parameter; represents the parameter affecting the real-time energy consumption. Here, the pedestrian flow data and the ambient light data are selected; represents the energy-saving display strategy; represents the comfort function; represents the constraint parameter; represents the constraint condition; represents the minimum requirement of the brightness function; S602. The constraint conditions include core information display constraints, bad weather adjustment constraints, and device 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 a linear form and solved by a linear programming algorithm.

8. The energy-saving display method of the environment-friendly LED display screen according to claim 1, characterized in that In S7, record and store the log data of the energy-saving display of the LED display screen, where: S701. The log data is encrypted and transmitted through TLS 1.3, and the static data is encrypted using AES-256. The log data includes ambient perception data, device operation data, and decision control data. The ambient perception data is stored in an edge time series database. The device operation data uses a relational database and is partitioned and stored according to the partition strategy. The decision control data uses a dual storage mode. The dual storage mode 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 data historical logs; S702. The edge time series database uses the ZSTD compression algorithm and stores the differences between adjacent grid values through Delta encoding. The partitioning strategy includes creating partition tables monthly by time range, sharding by the hash value of the display screen ID, and creating a BRIN index to accelerate time range queries. The decision control data is stored in the JSONB format and the retrieval steps are optimized by establishing a GIN index.

Images