LED display screen brightness intelligent adjusting system and method combined with environment perception

Abstract

The invention discloses an LED display screen brightness intelligent adjusting system and method combined with environment perception, and belongs to the technical field of LED adjustment, and the system comprises a brightness analysis unit which is used for generating a dynamic brightness adjustment parameter set; the brightness adjusting unit is used for generating an initial brightness adjusting result; and the brightness compensation unit is used for intelligently adjusting the brightness of the LED display screen. The technical problems that a traditional LED display screen is single in brightness adjusting mode and cannot dynamically adapt to the display characteristics of small-spacing light-emitting diodes according to ambient light, so that the display effect is poor, and energy consumption is too high are solved, and the purposes that self-adaptive brightness optimization of the small-spacing light-emitting diode display screen is achieved through environmental perception and a dynamic compensation strategy, and the display quality is improved are achieved. The display consistency is obviously improved; the energy consumption is reduced; and the service life of the device is prolonged.

Description

Technical Field

[0001] The present invention relates to the technical field of LED adjustment, and in particular to a system and method for intelligently adjusting the brightness of an LED display screen in combination with environmental perception. Background Art

[0002] Amid the rapid development of LED display technology, fine-pitch LEDs, thanks to their high pixel density and self-luminous properties, have been widely used in scenarios such as indoor command and dispatch, virtual studios, stage performances, and commercial displays. However, brightness control in complex environments still faces significant challenges. Firstly, the high-density pixel arrangement leads to significant localized brightness unevenness, making traditional static brightness control strategies difficult to accurately adapt to dynamic lighting conditions (such as direct sunlight and nighttime light interference) or crowded areas. Secondly, the light decay and color temperature drift of LED devices over long periods of operation further degrade display quality, affecting visual consistency and increasing energy consumption. Existing technologies often rely on fixed thresholds or manual adjustment methods, lacking real-time sensing and dynamic feedback capabilities for environmental data. This makes them unable to effectively address the impact of sudden weather changes (such as heavy rain and smog) or the dynamic distribution of human traffic on display performance. Furthermore, the high integration density of fine-pitch LEDs places higher demands on the precise control of the driver circuits. Traditional methods struggle to balance the multiple objectives of brightness uniformity, energy efficiency optimization, and device lifespan extension. Therefore, there is an urgent need for an intelligent brightness adjustment system that can achieve adaptive optimization of small-pitch LED displays by integrating environmental perception, dynamic compensation, and equipment aging analysis, thereby improving display stability and user experience in complex application scenarios. Summary of the Invention

[0003] This application provides an intelligent brightness adjustment system and method for LED display screens combined with environmental perception, aiming to solve the technical problems that traditional LED display screens have a single brightness adjustment method and cannot dynamically adapt to the display characteristics of small-pitch light-emitting diodes according to ambient light, resulting in poor display effects and excessive energy consumption. The application achieves the technical effect of realizing adaptive brightness optimization of small-pitch light-emitting diode displays through environmental perception and dynamic compensation strategies, significantly improving display consistency, reducing energy consumption and extending device life.

[0004] In view of the above problems, the present application provides a system and method for intelligently adjusting the brightness of an LED display screen combined with environmental perception.

[0005] The first aspect disclosed in the present application provides an intelligent brightness adjustment system for an LED display screen combined with environmental perception, the system comprising: a brightness analysis unit, configured to perform real-time perception of a target area of ​​the LED display screen through an environmental perception module, obtain an environmental perception data set, perform multi-dimensional brightness analysis on the environmental perception data set, and generate a dynamic brightness adjustment parameter set; a brightness adjustment unit, configured to retrieve a device parameter set of the LED display screen, correct the dynamic brightness adjustment parameter set, generate a brightness control instruction set, execute the brightness control instruction set to adjust the brightness of the LED display screen, and generate an initial brightness adjustment result; a brightness compensation unit, configured to perform continuous verification based on the initial brightness adjustment result in combination with the environmental perception data set, compensate the initial brightness adjustment result according to verification feedback data, determine a brightness adjustment strategy, and intelligently adjust the brightness of the LED display screen through the brightness adjustment strategy.

[0006] Another aspect disclosed in the present application provides a method for intelligently adjusting the brightness of an LED display screen in combination with environmental perception, the method comprising: performing real-time perception of a target area of ​​the LED display screen through an environmental perception module to obtain an environmental perception data set, performing multi-dimensional brightness analysis on the environmental perception data set, and generating a dynamic brightness adjustment parameter set; retrieving a device parameter set of the LED display screen, correcting the dynamic brightness adjustment parameter set, generating a brightness control instruction set, executing the brightness control instruction set to adjust the brightness of the LED display screen, and generating an initial brightness adjustment result; performing continuous verification based on the initial brightness adjustment result in combination with the environmental perception data set, compensating the initial brightness adjustment result according to verification feedback data, determining a brightness adjustment strategy, and intelligently adjusting the brightness of the LED display screen through the brightness adjustment strategy.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: In the brightness analysis unit, the target area of ​​the LED display screen is perceived in real time through the environmental perception module to obtain an environmental perception data set, and the environmental perception data set is subjected to multi-dimensional brightness analysis to generate a dynamic brightness adjustment parameter set; in the brightness adjustment unit, the device parameter set of the LED display screen is retrieved, the dynamic brightness adjustment parameter set is corrected, a brightness control instruction set is generated, and the brightness control instruction set is executed to adjust the brightness of the LED display screen to generate an initial brightness adjustment result; in the brightness compensation unit, the initial brightness adjustment result is continuously verified in combination with the environmental perception data set, the initial brightness adjustment result is compensated according to the verification feedback data, a brightness adjustment strategy is determined, and the brightness of the LED display screen is intelligently adjusted by the brightness adjustment strategy. This solves the technical problem that the traditional LED display screen has a single brightness adjustment method and cannot dynamically adapt to the display characteristics of small-pitch light-emitting diodes according to ambient light, resulting in poor display effects and excessive energy consumption. It achieves the technical effect of adaptive brightness optimization of small-pitch light-emitting diode displays through environmental perception and dynamic compensation strategies, significantly improving display consistency, reducing energy consumption, and extending device life.

[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 A structural schematic diagram of an intelligent brightness adjustment system for an LED display screen combined with environmental perception is provided for an embodiment of the present application.

[0010] Figure 2 A flow chart of a method for intelligently adjusting the brightness of an LED display screen in combination with environmental perception is provided for an embodiment of the present application.

[0011] Description of reference numerals: brightness analyzing unit 11 , brightness adjusting unit 12 , brightness compensating unit 13 . DETAILED DESCRIPTION

[0012] This application provides an intelligent brightness adjustment system and method for LED display screens combined with environmental perception, thereby solving the technical problems that traditional LED display screens have a single brightness adjustment method and cannot dynamically adapt to the display characteristics of small-pitch light-emitting diodes according to ambient light, resulting in poor display effects and excessive energy consumption. The application achieves the technical effect of realizing adaptive brightness optimization of small-pitch light-emitting diode display screens through environmental perception and dynamic compensation strategies, significantly improving display consistency, reducing energy consumption and extending device life.

[0013] Below, the technical solutions in this application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of this application, rather than all the embodiments of this application. It should be understood that this application is not limited to the example embodiments described herein. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application. It should also be noted that, for the convenience of description, only the parts related to this application, rather than all of them, are shown in the accompanying drawings.

[0014] Example 1, as Figure 1 As shown, the embodiment of the present application provides an intelligent brightness adjustment system for an LED display screen combined with environmental perception, the system comprising: The brightness analysis unit is used to perceive the target area of ​​the LED display screen in real time through the environmental perception module, obtain an environmental perception data set, perform multi-dimensional brightness analysis on the environmental perception data set, and generate a dynamic brightness adjustment parameter set.

[0015] Specifically, in the brightness analysis unit, the environmental perception module performs real-time perception of the target area of ​​the LED display, collecting data such as light intensity, crowd density, and meteorological conditions. This data together constitutes the environmental perception dataset. LED displays can be composed of fine-pitch light-emitting diodes (Mini LEDs), whose high-precision pixels and delicate brightness adjustment capabilities enable them to precisely respond to environmental changes. This environmental perception dataset is then subjected to multi-dimensional brightness analysis. Specifically, the light intensity data is combined with crowd density data and meteorological data. Through environmental mutation response analysis, the required brightness adjustment parameters for the LED display in the current environment are analyzed. These brightness adjustment parameters reflect the impact of changes in ambient light, crowd flow, and meteorological factors on display brightness, resulting in a set of dynamic brightness adjustment parameters. These dynamic brightness adjustment parameters are then used in the subsequent brightness control process to ensure that the LED display's brightness adapts to the current environmental conditions and provides the best display quality. This approach enables the LED display to respond to environmental changes in real time, optimize its display quality, and avoid the viewing experience affected by insufficient or excessive light, while leveraging the advantages of fine-pitch LEDs in precise control and brightness adjustment.

[0016] Furthermore, the brightness analysis unit includes: The invention relates to a method for realizing a light sensing system for a target area of ​​an LED display screen through an environmental perception module, and obtaining spectral distribution data of the target area; performing multi-channel filtering processing based on the spectral distribution data to generate effective light intensity data; capturing pedestrian movement trajectories in the target area of ​​the LED display screen through the environmental perception module, and calculating pedestrian trajectory density data; connecting to a meteorological monitoring terminal through the environmental perception module to construct meteorological environment data; aligning the effective light intensity data, the pedestrian trajectory density data, and the meteorological environment data according to spatiotemporal characteristics to obtain an environmental perception feature vector group; and adding the environmental perception feature vector group to the environmental perception dataset.

[0017] In a preferred embodiment, the environmental sensing module uses an integrated light sensor to sense the illumination of a target area on the LED display screen, measuring the illumination intensity in that area in real time. This spectral distribution data is then obtained. This spectral distribution data contains information about light intensity within different wavelength ranges, reflecting the distribution characteristics of the illumination within the area. Subsequently, multi-channel filtering is performed based on the acquired spectral distribution data. The filter channels are typically set based on predetermined wavelength bands (e.g., short wavelength, medium wavelength, and long wavelength), which correspond to different illumination information. Each filter channel focuses on a specific spectral range, thereby extracting different components of the illumination. For each channel, a filtering algorithm is used to process the spectral distribution data. Common filtering methods include low-pass filtering (which removes high-frequency noise while retaining low-frequency components, suitable for removing unnecessary high-frequency signals), band-pass filtering (which only allows light in a specific wavelength band to pass), and high-pass filtering (which removes low-frequency components while retaining high-frequency information, suitable for emphasizing rapidly changing illumination signals). Each channel uses an appropriate filtering method to extract and enhance the illumination data for the target wavelength band. After completing multi-channel filtering, the filtered results from each channel are merged. The light intensity data extracted from each channel reflects the lighting conditions within that wavelength band. The merged data is the effective light intensity data, representing the actual light intensity of the area under specific lighting conditions, eliminating noise or irrelevant light signals. The environmental perception module then uses a high-definition camera integrated into the LED display to capture pedestrian flow within the target area. Pedestrians are detected in images or video streams using computer vision algorithms such as YOLO and OpenCV, obtaining their location and movement information. The target area is then divided into multiple smaller blocks using a preset grid. The pedestrian density for each block is calculated by dividing the number of pedestrians in each block by its area. These pedestrian density data is then used to generate pedestrian trajectory data, helping the system understand the distribution of people within the area and further influencing brightness adjustment strategies. Furthermore, the environmental perception module connects to a weather monitoring terminal to receive external weather data (such as temperature, humidity, and wind speed) to construct meteorological environmental data. This data helps identify potential impacts of weather changes (such as strong winds or humidity fluctuations) on the display brightness. The collected effective light intensity data, pedestrian trajectory density data, and meteorological environment data are then aligned based on temporal and spatial characteristics. This process synchronizes the timestamps and geographic location information of each data type, ensuring that all data can be compared and analyzed at the same time and within the same region, forming consistent spatiotemporal data. After data alignment, the processed effective light intensity data, pedestrian trajectory density data, and meteorological environment data are combined into an environmental perception feature vector group. This vector group includes all relevant data obtained by the environmental perception module and provides detailed input information for subsequent brightness adjustment calculations.Finally, the resulting environmental perception feature vectors are added to the environmental perception dataset to support the subsequent dynamic brightness adjustment process. In summary, this process, through real-time perception and processing of multi-dimensional data, can more comprehensively reflect current environmental changes and provide a more accurate and intelligent basis for brightness adjustment on the LED display, thereby achieving automated brightness optimization and improving the visibility and comfort of the display.

[0018] Furthermore, the brightness analysis unit includes: Brightness constraints are set based on the effective light intensity data, and environmental brightness correlation analysis is performed on the crowd trajectory density data and the meteorological environment data according to the brightness constraints to construct an environment-brightness mapping network; brightness prediction is performed based on the environmental perception data set to obtain an initial brightness value matrix; environmental mutation response is performed on the initial brightness value matrix according to the environment-brightness mapping network to generate brightness switching data; distributed brightness control is performed on the LED display screen through the brightness switching data to generate the dynamic brightness adjustment parameter set.

[0019] In one feasible implementation, first, a set of brightness constraints are set based on the effective light intensity data. These constraints are set based on, among other things, the ambient light intensity, which is usually determined based on real-time collected light intensity data. For example, during the day when sunlight is strong, the brightness constraint sets a higher upper limit for brightness. At night or in environments with low light levels, the upper limit for brightness is lowered to avoid energy waste and visual fatigue. Subsequently, the pedestrian trajectory density data, meteorological environment data, and effective light intensity data are combined, and a bidirectional neural network is trained by screening historical pedestrian trajectory density data, historical meteorological environment data, historical light intensity, and historical brightness that meet the constraints. The bidirectional neural network can be a Bi-LSTM (bidirectional long short-term memory network), and training is performed iteratively through steps such as forward propagation, loss calculation (such as mean square error), backpropagation, and parameter optimization (such as Adam). After training, an environment-brightness mapping network is generated, representing the relationship between environmental data and brightness. For example, high crowd density indicates an increase in the number of people viewing the display, necessitating increased brightness to ensure clarity. In hot and sunny conditions, LED displays may face greater ambient light impact, requiring increased brightness to ensure clear display. The network then uses the environmental perception dataset to predict the appropriate brightness setting for the current environment, generating an initial brightness matrix containing preliminary brightness adjustment results for different regions. Furthermore, the network also responds to sudden environmental changes for the regions included in the initial brightness matrix. When the rate of illumination change between two adjacent regions exceeds 50 lux / s (instantaneous strong light), a brightness gradient transition algorithm, such as an S-curve smoothing algorithm, is activated to smooth the brightness change and avoid disruptive viewing experiences due to excessive brightness fluctuations. Furthermore, if rainfall occurs, an anti-glare strategy is activated, increasing the blue channel's contribution to 35% while minimizing overall brightness fluctuations (ensuring a standard deviation of ≤15 cd / m2) to minimize reflections and glare in rainy conditions, ensuring a clear and stable display. After processing the environmental mutation response, a set of brightness switching data will be obtained based on the generated environmental mutation response data. These data indicate how the LED display screen should adjust its brightness under various environmental mutations (such as strong light, rainfall, etc.). Through these switching data, the brightness of the display screen can be adjusted in time under rapidly changing environmental conditions.Finally, based on the brightness switching data, the LED display screen is distributedly controlled. That is, by controlling the brightness of different areas, the display effect of each area is optimized. Each area is individually adjusted for brightness according to actual environmental changes and needs, thereby obtaining a brightness adjustment strategy that meets the needs of the entire screen. This strategy contains a set of dynamic brightness adjustment parameters, which specifically include maximum brightness setting, minimum brightness setting, color temperature difference, LED drive current, LED drive voltage, brightness adjustment coefficient, etc. This set provides complete parameter support for the subsequent brightness adjustment of the LED display screen under different environmental changes, ensuring the best display effect at all times under various dynamic environmental conditions and improving user experience.

[0020] The brightness adjustment unit is used to retrieve the device parameter set of the LED display screen, modify the dynamic brightness adjustment parameter set, generate a brightness control instruction set, execute the brightness control instruction set to adjust the brightness of the LED display screen, and generate an initial brightness adjustment result.

[0021] Specifically, in the brightness adjustment unit, the device parameter set is first retrieved from the LED display screen, including the hardware characteristics of the LED display screen, the current operating status, historical brightness data and other information. By retrieving these device parameters, the current performance of the LED display screen can be fully understood, thereby providing basic data for subsequent brightness adjustment. After obtaining the device parameter set, the previously generated dynamic brightness adjustment parameter set will be corrected. These correction processes take into account the current display device performance and historical brightness data to ensure that the brightness adjustment can accurately adapt to the actual situation. Subsequently, based on the corrected adjustment parameters, a set of brightness control instruction sets are generated. These instructions include how to accurately adjust the brightness values ​​of each area of ​​the display screen to achieve overall screen brightness optimization. Finally, these control instructions are executed to adjust the brightness of the LED display screen, thereby generating an initial brightness adjustment result. This result is the optimal brightness configuration required by the display screen under the current environmental conditions, providing a basis for subsequent continuous adjustment and compensation.

[0022] Furthermore, the brightness adjustment unit includes: Performing device aging analysis based on the device parameter set of the LED display screen to obtain device aging parameters, wherein the device aging parameters include a device historical brightness data set; traversing the device historical brightness data set to perform light decay analysis to generate light decay compensation data; correcting the dynamic brightness adjustment parameter set based on the light decay compensation data to determine a brightness and light decay correction result; performing color temperature correction based on the brightness and light decay correction result to obtain a full-screen color temperature difference of the LED display screen; constructing a color temperature-brightness lookup table based on the brightness and light decay correction result and the full-screen color temperature difference; performing regional slicing on the LED display screen according to the color temperature-brightness lookup table to generate multiple pixel blocks, wherein the multiple pixel blocks include multiple control instruction packets, wherein the multiple control instruction packets correspond to the multiple pixel blocks; encapsulating the multiple control instruction packets to generate the brightness control instruction set.

[0023] In one feasible implementation, a device aging analysis is first performed based on a set of device parameters for the LED display. This step aims to assess the aging of the LED display during use. The device aging analysis monitors the display's historical operating conditions, usage duration, ambient temperature, and other factors to obtain a set of device aging parameters. These parameters include a historical device brightness dataset, which records the display's brightness performance at different points in time, helping the system determine the display's performance degradation. The system then iterates through the historical device brightness dataset and uses linear regression to fit the temporal trends of the device brightness. This fitting process uses the least squares method to calculate a specific regression equation. The LED display's factory brightness minus the brightness after a certain period of use is then divided by the factory brightness to obtain a light decay ratio. The brightness after a certain period of use is calculated by inputting the current time into the regression equation. The system then calculates light decay compensation data by dividing the difference between 1 and the light decay ratio. This light decay compensation data is used to correct for brightness drops caused by aging, ensuring that subsequent brightness adjustments still achieve the desired effect. Based on the generated light decay compensation data, the previously obtained dynamic brightness adjustment parameter set is corrected. During this correction process, the light decay compensation data is directly multiplied by each parameter in the dynamic brightness adjustment parameter set to obtain a brightness light decay correction result. This brightness light decay correction result reflects the corrected brightness adjustment parameters, enabling the LED display to maintain efficient display performance even in a decayed state. Then, based on the brightness light decay correction result, color temperature correction is performed through steps such as pixel scanning, gain compensation, and color temperature gradient correction to ensure that the color temperature of the display remains consistent during the adjustment process and avoid color temperature changes caused by aging. After color temperature correction, the full-screen color temperature difference—the color temperature difference across the entire screen—is calculated to ensure color temperature balance across different areas. After obtaining the full-screen color temperature difference, a color temperature-brightness lookup table is constructed based on the brightness light decay correction result and the full-screen color temperature difference. This lookup table records the optimal brightness parameters at different color temperatures and is used to dynamically adjust the brightness of each area to ensure a balance between color temperature and brightness. Furthermore, the LED display is segmented into regions based on the color temperature-brightness lookup table. Specifically, pixels with the same color temperature are merged to create multiple pixel blocks. The color temperature of each pixel block is then compared with a color temperature-brightness lookup table to obtain the brightness and light decay correction result corresponding to that color temperature. The matched brightness and light decay correction result is used as the control instruction packet for this pixel block. Each control instruction packet contains specific brightness and color temperature adjustment parameters. Finally, all control instruction packets are encapsulated to generate a complete brightness control instruction set. This instruction set contains the adjustment parameters for each pixel block, ensuring that the entire LED display can achieve precise brightness adjustment and color temperature control in different environments and device aging conditions.In summary, through this process, the brightness attenuation caused by equipment aging can be accurately compensated, and the brightness can be intelligently adjusted according to the real-time environment and equipment status, ensuring that the display effect of the LED display screen always remains optimal under different usage conditions.

[0024] Furthermore, when the brightness adjustment unit performs color temperature correction, it includes: The LED display screen is pixel-scanned to obtain the initial brightness of the RGB three-color LEDs; a compensation gain is performed on the initial brightness of the RGB three-color LEDs based on the brightness light decay correction result to generate an RGB gain coefficient; target color temperature data is set, and the target color temperature data is mapped into a chromaticity space according to the RGB gain coefficient to construct a dynamic mixing matrix; a color temperature correction instruction is initiated based on the dynamic mixing matrix to perform color temperature gradient correction to obtain the full-screen color temperature difference of the LED display screen.

[0025] In one feasible implementation, the LED display screen is first pixel-scanned. This process scans each pixel of the display screen one by one to obtain the initial brightness data of the RGB three-color LED at each pixel. The initial brightness of the RGB three-color LED refers to the brightness values ​​of the red, green, and blue light sources in each pixel. These brightness values ​​are the initial output values ​​of the LED display screen under normal working conditions. Through this process, the initial brightness information of the entire screen can be obtained, providing basic data for subsequent light decay compensation and color temperature correction. After obtaining the initial brightness of the RGB three-color LED, based on the previous brightness and light decay correction results, the initial brightness of the RGB three-color LED is compensated for by gain. Light decay compensation is intended to compensate for brightness attenuation caused by equipment aging. By dividing the brightness value corresponding to the brightness and light decay correction results by the initial brightness of the RGB three-color LED, an RGB gain coefficient is generated. This RGB gain coefficient can adjust the initial brightness of the RGB three-color LED to ensure color accuracy and brightness consistency. Next, the target color temperature data is set and chromaticity space mapping is performed on the target color temperature data using RGB gain coefficients. The goal of chromaticity space mapping is to convert the target color temperature data into the color gamut achievable by the LED display and ensure that the mapped color temperature matches the display's color gamut. The mapping process is performed by multiplying the RGB gain coefficients with the target color temperature data. Based on this mapping, a dynamic mixing matrix is ​​constructed. This matrix contains the actual color temperature corresponding to each pixel and can offset color temperature display anomalies caused by aging. Next, based on the constructed dynamic mixing matrix, a color temperature correction command is activated. Based on this color temperature correction command, a color temperature gradient correction is performed. This smoothly adjusts the current color temperature of the LED display to the actual color temperature corresponding to the dynamic mixing matrix, ensuring consistent color temperature changes across different areas of the screen and avoiding color temperature unevenness. This process optimizes the color temperature of the LED display, ensuring a more natural and uniform color presentation across different display scenarios. Finally, the standard deviation is used to calculate the full-screen color temperature difference. This difference reflects the color temperature differences between different areas of the entire LED display after color temperature correction. Based on this color temperature difference, the system will further fine-tune the display's color temperature to ensure uniformity across the entire screen, providing a more consistent and high-quality display. Through this series of steps, the brightness and color temperature of the LED display can be precisely adjusted based on light attenuation correction, color temperature correction, and chromaticity mapping, ensuring that the display is always optimal.

[0026] Furthermore, the brightness adjustment unit includes: Based on the environmental perception data set, distribution analysis is performed according to the multiple pixel blocks to generate spatial distribution characteristics; a block priority weight matrix of the multiple pixel blocks is constructed according to the spatial distribution characteristics; the multiple control instruction packets are sorted according to the block priority weight matrix to generate an instruction execution sequence; the multiple pixel blocks are independently controlled according to the instruction execution sequence to obtain multiple regional brightness feedback data; and the multiple regional brightness feedback data are added to the initial brightness adjustment result.

[0027] In one feasible implementation, based on the acquired environmental perception dataset, a distribution analysis is first performed on multiple pixel blocks on the LED display. Effective light intensity data, pedestrian trajectory density data, and meteorological environment data for the location corresponding to each pixel block are obtained from the environmental perception dataset. These environmental perception data are then stored separately to obtain the spatial distribution characteristics of each block. Subsequently, the spatial distribution characteristics of each pixel block are processed using the maximum-minimum normalization method to ensure that each characteristic is in the same dimension. The normalized characteristics of each pixel block are then weighted to obtain the corresponding priority weight. By summarizing these priority weights, a block priority weight matrix is ​​constructed. This priority weight matrix contains the brightness adjustment priority of each pixel block across the entire display. Typically, pixel blocks with low light levels or in areas with concentrated user vision may have higher priorities and therefore require priority during the adjustment process. All control command packets are then sorted according to the block priority weight matrix to generate a command execution sequence. This command execution sequence ensures that high-priority areas receive brightness adjustment first and effectively avoids insufficient brightness or adjustment delays in high-demand areas. Then, based on the generated instruction execution sequence, multiple pixel blocks are independently controlled, with each pixel block adjusting its brightness according to its specific control instruction package to meet its environmental perception needs. During this process, each block of the display adjusts its brightness according to the instructions. At the same time, the system collects regional brightness feedback data from each block. This data reflects the brightness changes of each block after the actual brightness adjustment, ensuring that the brightness of each block meets the expected target. Finally, the multiple regional brightness feedback data collected from each block is integrated into the initial brightness adjustment result. Through this process, the system updates the brightness adjustment status of the display and optimizes the preliminary brightness adjustment results based on the feedback data. This update ensures more precise brightness adjustment in different areas of the display, thereby improving the quality of the overall display effect.

[0028] A brightness compensation unit is used to perform continuous verification based on the initial brightness adjustment result in combination with the environmental perception data set, compensate the initial brightness adjustment result according to the verification feedback data, determine the brightness adjustment strategy, and intelligently adjust the brightness of the LED display screen through the brightness adjustment strategy.

[0029] A brightness compensation unit is used to perform continuous verification based on the initial brightness adjustment result in combination with the environmental perception data set, compensate the initial brightness adjustment result according to the verification feedback data, determine the brightness adjustment strategy, and intelligently adjust the brightness of the LED display screen through the brightness adjustment strategy.

[0030] Specifically, after initially completing brightness adjustment, the brightness compensation unit continuously verifies the initial brightness adjustment results using the environmental perception dataset. This verification process compares the actual display performance with the expected brightness, detecting in real time the impact of environmental changes on the brightness adjustment. For example, when light intensity or traffic density changes, the initial brightness adjustment is checked to ensure that the display still meets the required display requirements. After verification, verification feedback data is collected and analyzed, reflecting any brightness deviations or mismatches that may have occurred during the actual adjustment process. Based on this feedback data, the initial brightness adjustment results are compensated accordingly. This compensation process may include adjusting brightness, color temperature, or other display parameters to correct display inaccuracies caused by environmental changes or fluctuations in device performance. Through this series of compensations, a brightness adjustment strategy is determined. This strategy includes how to dynamically adjust the display brightness under different environmental conditions to ensure optimal display performance at all times. Finally, the LED display's brightness is intelligently adjusted based on this brightness adjustment strategy. By continuously optimizing the adjustment process, real-time brightness optimization based on environmental changes is achieved, ensuring that the display maintains appropriate brightness and color temperature in all environments.

[0031] Furthermore, the brightness compensation unit includes: Based on the environmental perception data set, the brightness feedback data of the multiple areas are continuously verified to generate verification feedback data; based on the verification feedback data, the expected brightness data of the LED display is extracted, the deviation of the expected brightness data and the initial brightness adjustment result is analyzed, and a brightness deviation distribution map is constructed; in combination with the equipment aging parameter, the brightness deviation distribution map is traversed for weighted calculation to determine the deviation source weight coefficient; based on the deviation source weight coefficient, the initial brightness adjustment result is brightness compensated to determine the brightness adjustment strategy.

[0032] In one feasible implementation, previously adjusted brightness feedback data for multiple zones is continuously verified based on an environmental perception dataset. This process aims to ensure that the LED display's brightness remains within the optimal range despite environmental changes. By continuously collecting the difference between actual and expected brightness, verification feedback data is generated. This data reflects the performance and error of the initial brightness adjustment results in the actual environment. After obtaining the verification feedback data, the expected brightness data for the LED display is extracted from it, representing the ideal brightness value under the current environmental conditions. By performing a deviation analysis on this expected brightness data and the previously obtained initial brightness adjustment results, the difference between the expected and actual brightness is compared to generate a brightness deviation distribution map. This map depicts the distribution of brightness adjustment errors for different zones and environmental conditions. To account for the aging effects of the LED display, a weighted calculation is performed using device aging parameters. These parameters record the device's aging level and historical performance data, reflecting the potential brightness decay or color temperature changes that may occur over time. By traversing the brightness deviation distribution map and weighting the deviations of different zones according to the device aging parameters, the source of each zone's deviation and its impact on brightness adjustment are determined. After weighted calculation, the deviation source weight coefficient is obtained. The larger the deviation source weight coefficient, the greater the impact of device aging on brightness deviation. Finally, the calculated deviation source weight coefficient is multiplied by the difference between the actual brightness and the desired brightness to obtain a weighted brightness compensation value. The weighted brightness compensation value is then subtracted from the actual brightness to obtain the compensated brightness value. By adding these compensated brightness values ​​to the brightness adjustment strategy, the display brightness is adjusted to ensure that the LED display provides a clear and balanced display under various conditions.

[0033] Furthermore, when the brightness compensation unit performs continuous verification, it includes: Data mapping is performed based on the effective light intensity data, the crowd trajectory density data, and the meteorological environment data to construct a three-dimensional environmental perception tensor; a multi-dimensional feedback feature vector is extracted through the three-dimensional environmental perception tensor, and the multi-dimensional feedback feature vector includes the illumination gradient change rate, the coordinates of the crowd gathering area, and the meteorological mutation label; the brightness feedback data of the multiple regions are continuously verified according to the illumination gradient change rate to generate illumination verification feedback data; the brightness feedback data of the multiple regions are continuously verified according to the coordinates of the crowd gathering area to generate crowd verification feedback data; the brightness feedback data of the multiple regions are continuously verified according to the meteorological mutation label to generate meteorological verification feedback data; the illumination verification feedback data, the crowd verification feedback data, and the meteorological verification feedback data are correlated and integrated to obtain verification feedback data.

[0034] In one feasible implementation, data mapping is first performed based on the collected effective light intensity data, crowd density data, and meteorological environment data. The three data types (light, crowd, and weather) are aligned in spatial and temporal dimensions to form a complete environmental perception data set. This data is then fused to construct a three-dimensional environmental perception tensor. This tensor contains information on the three dimensions of light intensity, crowd density, and weather conditions, providing a basic data structure for subsequent analysis and feedback verification. Subsequently, based on the constructed three-dimensional environmental perception tensor, multi-dimensional feedback feature vectors are obtained through multi-scale extraction. These feature vectors summarize the key change factors in the environmental data, specifically including the light gradient change rate, the coordinates of the crowd gathering area, and the weather mutation label. The light gradient change rate describes the speed of change of light intensity in time and space, reflecting the magnitude of the change in lighting conditions; the crowd gathering area coordinates identify the dense areas of crowd gathering within the target display area, reflecting the hot spots of crowd activity; and the weather mutation label marks sudden changes in weather conditions (such as a sudden drop in temperature or a sharp change in wind speed), helping to identify changes in display demand caused by sudden weather changes. Subsequently, based on the rate of change of the illumination gradient, the brightness feedback data from multiple regions is continuously verified. This verification aims to test whether the display's brightness adjustment responds promptly to environmental changes under sudden illumination changes. By comparing actual feedback with expected results, illumination verification feedback data is generated. This data indicates whether the display's brightness adjustment meets requirements under specific lighting conditions. Based on the coordinates of crowded areas, the brightness feedback data from multiple regions is continuously verified. This verification aims to ensure that the display's brightness is appropriately increased in areas with high pedestrian flow to improve visibility. By continuously monitoring the pedestrian density data at these coordinates, it is determined whether the actual feedback meets the requirements of changing pedestrian flow, that is, whether it meets the brightness range corresponding to the pedestrian density, and pedestrian verification feedback data is generated. Based on the sudden meteorological change labels, the brightness feedback data from multiple regions is continuously verified to ensure that the display can intelligently adjust its brightness under sudden meteorological changes (such as strong winds and heavy rain). For example, during rain or strong sunlight, the display reduces to the required brightness or color temperature. This verification process generates meteorological verification feedback data, reflecting the display's response to changing meteorological conditions. Finally, the lighting verification feedback data, the crowd verification feedback data, and the weather verification feedback data are correlated and integrated. The purpose of this integration process is to combine the feedback results of different environmental factors (lighting, crowd flow, and weather) to form a unified verification feedback data. This data comprehensively reflects the performance of the display brightness adjustment under various environmental changes. This method can more accurately adjust the brightness, ensuring that the display effect is always maintained at the optimal state in different environments, making it more intelligent and adaptable to changing environmental conditions.

[0035] Furthermore, when the brightness compensation unit extracts the multi-dimensional feedback feature vector, it includes: Multi-scale extraction is performed based on the three-dimensional environmental perception tensor to obtain multi-scale features; light intensity feedback is performed according to the multi-scale features to construct a light intensity matrix, and gradient change calculation is performed based on the light intensity matrix to obtain the light gradient change rate; crowd density feedback is performed according to the multi-scale features to construct a crowd density heat map, and the crowd density heat map is traversed to perform clustering and division to construct the coordinates of the crowd clustering area; meteorological change feedback is performed according to the multi-scale features to construct a meteorological time series sequence, and meteorological mutation identification is performed according to the meteorological time series sequence to construct the meteorological mutation label.

[0036] In one feasible implementation, based on the constructed three-dimensional environmental perception tensor, one can first generally select local scales (smaller areas or short time periods) and global scales (larger areas or long time periods) for analysis. The local scale is used to capture detailed information, while the global scale is used to capture macro trends. Then, a sliding window is used to operate on the three-dimensional environmental perception tensor, and features are extracted in each window. The size of each window can be determined based on the selected scale. For example, at smaller scales, the window size is smaller to capture local details; at larger scales, the window size is larger to capture global trends. At different scales, light intensity data, meteorological data, and crowd density data are processed using methods such as Gaussian filtering and median filtering to balance local details and global information, thereby extracting effective information at each scale, such as the changing trend and light fluctuation of light intensity, the density fluctuation and rate of change of crowd density, the temperature change rate, and the humidity change trend. After obtaining features at multiple scales, they are scale-aggregated through weighted fusion and concatenation, merging features from all scales into a single multi-scale feature. This multi-scale feature integrates information from different scales within the environmental perception tensor, reflecting both microscopic environmental changes and macroscopic environmental trends. Regarding light intensity, light intensity feedback is generated based on the obtained multi-scale features. This process analyzes light intensity data at different scales to determine the illumination variations in each region. A light intensity matrix is ​​then constructed based on this light intensity data, detailing the illumination intensity information for each region. This matrix enables analysis of the brightness requirements and adjustment levels for each region. Subsequently, gradient change calculation is performed based on the light intensity matrix. This involves evaluating the rate of change of light intensity in each region. By calculating the gradient of light intensity over time or space, the light gradient change rate is calculated. This metric measures the abruptness of illumination changes and reflects sudden changes in illumination, such as a rapid increase or decrease in ambient light. The system can then adjust the smoothness of brightness changes accordingly to avoid visual discomfort caused by sudden changes. For crowd density, crowd density feedback is provided based on multi-scale features to understand the distribution of people within the target area of ​​the display screen. The feedback crowd density data is then converted into a heat map to visualize the crowd distribution. The crowd density heat map shows the density changes in each area. Different colors in the heat map represent different density levels. The warmer the color, the higher the crowd density in the area, and the colder the color, the lower the crowd density. Afterwards, the constructed crowd density heat map is traversed, and dense crowd areas are identified through threshold comparison. Adjacent high-density areas in the heat map are merged into a group of areas, defined as crowd gathering areas, thereby helping the system convert crowd distribution data into multiple areas with clear boundaries. After the cluster division is completed, the center position of each crowd gathering area is used as the coordinate of the crowd gathering area, which is used as the basis for brightness adjustment.For meteorological changes, the system uses multi-scale features to generate feedback, acquire real-time meteorological data, and construct a meteorological time series. This series records changes in meteorological data at different time points, reflecting the changing trends of meteorological conditions (such as temperature, humidity, and wind speed). Based on the meteorological time series, it detects sudden changes in meteorological conditions (when the rate of change exceeds a limit), such as a sudden drop in temperature or a sharp change in wind speed. These sudden changes are identified and labeled, generating meteorological sudden change labels. These labels help identify changes in meteorological conditions in real time and adjust the display brightness accordingly, avoiding discomfort in extreme weather conditions. In summary, through this series of processes, the system can fully understand and respond to environmental changes, including dynamic changes in lighting, traffic flow, and weather. This ensures precise brightness adjustment and color temperature control of the LED display under various conditions, providing a consistently optimized display quality.

[0037] In summary, the LED display screen brightness intelligent adjustment system combined with environmental perception provided by the embodiments of the present application has the following technical effects: The brightness analysis unit is used to perceive the target area of ​​the LED display screen in real time through the environmental perception module, obtain the environmental perception data set, perform multi-dimensional brightness analysis on the environmental perception data set, and generate a dynamic brightness adjustment parameter set; the brightness adjustment unit is used to retrieve the device parameter set of the LED display screen, correct the dynamic brightness adjustment parameter set, generate a brightness control instruction set, execute the brightness control instruction set to adjust the brightness of the LED display screen, and generate an initial brightness adjustment result; the brightness compensation unit is used to perform continuous verification based on the initial brightness adjustment result in combination with the environmental perception data set, compensate the initial brightness adjustment result according to the verification feedback data, determine the brightness adjustment strategy, and intelligently adjust the brightness of the LED display screen through the brightness adjustment strategy. Through the above steps, the technical problems of the traditional LED display screen having a single brightness adjustment method and being unable to dynamically adapt to the display characteristics of small-pitch light-emitting diodes according to ambient light, resulting in poor display effects and excessive energy consumption, are solved. The technical effect of realizing adaptive brightness optimization of small-pitch light-emitting diode displays through environmental perception and dynamic compensation strategies, significantly improving display consistency, reducing energy consumption and extending device life is achieved.

[0038] The second embodiment is based on the same inventive concept as the LED display screen brightness intelligent adjustment system combined with environmental perception in the previous embodiment. Figure 2 As shown, the embodiment of the present application provides a method for intelligently adjusting the brightness of an LED display screen in combination with environmental perception, the method comprising: The target area of ​​the LED display is perceived in real time through the environmental perception module to obtain an environmental perception data set, and the environmental perception data set is subjected to multi-dimensional brightness analysis to generate a dynamic brightness adjustment parameter set; the device parameter set of the LED display is retrieved, the dynamic brightness adjustment parameter set is corrected, a brightness control instruction set is generated, and the brightness control instruction set is executed to adjust the brightness of the LED display to generate an initial brightness adjustment result; based on the initial brightness adjustment result and in combination with the environmental perception data set, continuous verification is performed, the initial brightness adjustment result is compensated according to the verification feedback data, a brightness adjustment strategy is determined, and the brightness of the LED display is intelligently adjusted using the brightness adjustment strategy.

[0039] Furthermore, the method includes: The invention relates to a method for realizing a light sensing system for a target area of ​​an LED display screen through an environmental perception module, and obtaining spectral distribution data of the target area; performing multi-channel filtering processing based on the spectral distribution data to generate effective light intensity data; capturing pedestrian movement trajectories in the target area of ​​the LED display screen through the environmental perception module, and calculating pedestrian trajectory density data; connecting to a meteorological monitoring terminal through the environmental perception module to construct meteorological environment data; aligning the effective light intensity data, the pedestrian trajectory density data, and the meteorological environment data according to spatiotemporal characteristics to obtain an environmental perception feature vector group; and adding the environmental perception feature vector group to the environmental perception dataset.

[0040] Furthermore, the method includes: Brightness constraints are set based on the effective light intensity data, and environmental brightness correlation analysis is performed on the crowd trajectory density data and the meteorological environment data according to the brightness constraints to construct an environment-brightness mapping network; brightness prediction is performed based on the environmental perception data set to obtain an initial brightness value matrix; environmental mutation response is performed on the initial brightness value matrix according to the environment-brightness mapping network to generate brightness switching data; distributed brightness control is performed on the LED display screen through the brightness switching data to generate the dynamic brightness adjustment parameter set.

[0041] Furthermore, the method includes: Performing device aging analysis based on the device parameter set of the LED display screen to obtain device aging parameters, wherein the device aging parameters include a device historical brightness data set; traversing the device historical brightness data set to perform light decay analysis to generate light decay compensation data; correcting the dynamic brightness adjustment parameter set based on the light decay compensation data to determine a brightness and light decay correction result; performing color temperature correction based on the brightness and light decay correction result to obtain a full-screen color temperature difference of the LED display screen; constructing a color temperature-brightness lookup table based on the brightness and light decay correction result and the full-screen color temperature difference; performing regional slicing on the LED display screen according to the color temperature-brightness lookup table to generate multiple pixel blocks, wherein the multiple pixel blocks include multiple control instruction packets, wherein the multiple control instruction packets correspond to the multiple pixel blocks; encapsulating the multiple control instruction packets to generate the brightness control instruction set.

[0042] Furthermore, the method includes: The LED display screen is pixel-scanned to obtain the initial brightness of the RGB three-color LEDs; a compensation gain is performed on the initial brightness of the RGB three-color LEDs based on the brightness light decay correction result to generate an RGB gain coefficient; target color temperature data is set, and the target color temperature data is mapped into a chromaticity space according to the RGB gain coefficient to construct a dynamic mixing matrix; a color temperature correction instruction is initiated based on the dynamic mixing matrix to perform color temperature gradient correction to obtain the full-screen color temperature difference of the LED display screen.

[0043] Furthermore, the method includes: Based on the environmental perception data set, distribution analysis is performed according to the multiple pixel blocks to generate spatial distribution characteristics; a block priority weight matrix of the multiple pixel blocks is constructed according to the spatial distribution characteristics; the multiple control instruction packets are sorted according to the block priority weight matrix to generate an instruction execution sequence; the multiple pixel blocks are independently controlled according to the instruction execution sequence to obtain multiple regional brightness feedback data; and the multiple regional brightness feedback data are added to the initial brightness adjustment result.

[0044] Furthermore, the method includes: Based on the environmental perception data set, the brightness feedback data of the multiple areas are continuously verified to generate verification feedback data; based on the verification feedback data, the expected brightness data of the LED display is extracted, the deviation of the expected brightness data and the initial brightness adjustment result is analyzed, and a brightness deviation distribution map is constructed; in combination with the equipment aging parameter, the brightness deviation distribution map is traversed for weighted calculation to determine the deviation source weight coefficient; based on the deviation source weight coefficient, the initial brightness adjustment result is brightness compensated to determine the brightness adjustment strategy.

[0045] Furthermore, the method includes: Data mapping is performed based on the effective light intensity data, the crowd trajectory density data, and the meteorological environment data to construct a three-dimensional environmental perception tensor; a multi-dimensional feedback feature vector is extracted through the three-dimensional environmental perception tensor, and the multi-dimensional feedback feature vector includes the illumination gradient change rate, the coordinates of the crowd gathering area, and the meteorological mutation label; the brightness feedback data of the multiple regions are continuously verified according to the illumination gradient change rate to generate illumination verification feedback data; the brightness feedback data of the multiple regions are continuously verified according to the coordinates of the crowd gathering area to generate crowd verification feedback data; the brightness feedback data of the multiple regions are continuously verified according to the meteorological mutation label to generate meteorological verification feedback data; the illumination verification feedback data, the crowd verification feedback data, and the meteorological verification feedback data are correlated and integrated to obtain verification feedback data.

[0046] Furthermore, the method includes: Multi-scale extraction is performed based on the three-dimensional environmental perception tensor to obtain multi-scale features; light intensity feedback is performed according to the multi-scale features to construct a light intensity matrix, and gradient change calculation is performed based on the light intensity matrix to obtain the light gradient change rate; crowd density feedback is performed according to the multi-scale features to construct a crowd density heat map, and the crowd density heat map is traversed to perform clustering and division to construct the coordinates of the crowd clustering area; meteorological change feedback is performed according to the multi-scale features to construct a meteorological time series sequence, and meteorological mutation identification is performed according to the meteorological time series sequence to construct the meteorological mutation label.

[0047] Any step of the method described above can be stored as a computer instruction or program in an unlimited computer memory, and can be called and recognized by an unlimited computer processor to implement any method in the embodiments of the present application, without any unnecessary restrictions.

[0048] Furthermore, the terms "first" or "second" as described above may not only represent an order relationship but may also represent a specific concept and / or refer to the selectability of multiple elements individually or collectively. Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of this application. Thus, if such modifications and variations fall within the scope of this application and its equivalents, this application is intended to include such modifications and variations.

Claims

1. The LED display screen brightness intelligent adjustment system combined with environmental perception is characterized by: The system comprises: A brightness analysis unit is used to perceive the target area of ​​the LED display screen in real time through the environment perception module, obtain an environment perception data set, perform multi-dimensional brightness analysis on the environment perception data set, and generate a dynamic brightness adjustment parameter set; A brightness adjustment unit is used to retrieve a device parameter set of the LED display, modify the dynamic brightness adjustment parameter set, generate a brightness control instruction set, execute the brightness control instruction set to adjust the brightness of the LED display, and generate an initial brightness adjustment result; A brightness compensation unit is used to perform continuous verification based on the initial brightness adjustment result in combination with the environmental perception data set, compensate the initial brightness adjustment result according to the verification feedback data, determine the brightness adjustment strategy, and intelligently adjust the brightness of the LED display screen through the brightness adjustment strategy.

2. The LED display screen brightness intelligent adjustment system combined with environmental perception according to claim 1 is characterized in that: The brightness analysis unit includes: The environmental perception module senses the light in the target area of ​​the LED display screen and obtains the spectral distribution data of the target area; Performing multi-channel filtering based on the spectral distribution data to generate effective light intensity data; The environment perception module captures pedestrian movement trajectories in the target area of ​​the LED display screen and calculates pedestrian trajectory density data; Connect to the meteorological monitoring terminal through the environmental perception module to build meteorological environment data; Aligning the effective light intensity data, the crowd trajectory density data, and the meteorological environment data according to spatiotemporal characteristics to obtain an environmental perception feature vector group; The environment-aware feature vector group is added to the environment-aware dataset.

3. The LED display screen brightness intelligent adjustment system combined with environmental perception as claimed in claim 2 is characterized in that: The brightness analysis unit includes: Setting a brightness constraint condition based on the effective light intensity data, performing an environmental brightness correlation analysis on the crowd trajectory density data and the meteorological environment data according to the brightness constraint condition, and constructing an environment-brightness mapping network; Perform brightness prediction based on the environmental perception data set to obtain an initial brightness value matrix; Performing an environmental mutation response on the initial brightness value matrix according to the environment-brightness mapping network to generate brightness switching data; The LED display screen is subjected to distributed brightness control through the brightness switching data to generate the dynamic brightness adjustment parameter set.

4. The LED display screen brightness intelligent adjustment system combined with environmental perception as claimed in claim 2, characterized in that: The brightness adjustment unit includes: Performing device aging analysis based on the device parameter set of the LED display screen to obtain device aging parameters, wherein the device aging parameters include a device historical brightness data set; Traversing the historical brightness data set of the device to perform light decay analysis and generate light decay compensation data; Correcting the dynamic brightness adjustment parameter set based on the light decay compensation data to determine a brightness and light decay correction result; Perform color temperature correction based on the brightness and light decay correction result to obtain the full-screen color temperature difference of the LED display; Constructing a color temperature-brightness lookup table based on the brightness light decay correction result and the full-screen color temperature difference; Slice the LED display screen according to the color temperature-brightness lookup table to generate a plurality of pixel blocks, wherein the plurality of pixel blocks include a plurality of control instruction packets, wherein the plurality of control instruction packets correspond to the plurality of pixel blocks; The multiple control instruction packets are encapsulated to generate the brightness control instruction set.

5. The LED display screen brightness intelligent adjustment system combined with environmental perception as claimed in claim 4 is characterized in that: When the brightness adjustment unit performs color temperature correction, it includes: Scan the pixels of the LED display to obtain the initial brightness of the RGB three-color LED; Performing compensation gain on the initial brightness of the RGB three-color LED based on the brightness attenuation correction result to generate an RGB gain coefficient; Setting target color temperature data, performing color space mapping on the target color temperature data according to the RGB gain coefficients, and constructing a dynamic mixing matrix; Based on the dynamic mixing matrix, a color temperature correction instruction is started to perform color temperature gradient correction to obtain the full-screen color temperature difference of the LED display screen.

6. The LED display screen brightness intelligent adjustment system combined with environmental perception as claimed in claim 4, characterized in that: The brightness adjustment unit includes: Performing distribution analysis on the plurality of pixel blocks based on the environmental perception data set to generate spatial distribution features; constructing a block priority weight matrix of the plurality of pixel blocks according to the spatial distribution characteristics; sorting the plurality of control instruction packets according to the block priority weight matrix to generate an instruction execution sequence; Independently controlling the plurality of pixel blocks according to the instruction execution sequence to obtain brightness feedback data of a plurality of regions; The plurality of regional brightness feedback data are added to the initial brightness adjustment result.

7. The LED display screen brightness intelligent adjustment system combined with environmental perception according to claim 6, characterized in that: The brightness compensation unit includes: Continuously verifying the plurality of regional brightness feedback data based on the environmental perception data set to generate verification feedback data; Extracting expected brightness data of the LED display based on the verification feedback data, performing deviation analysis between the expected brightness data and the initial brightness adjustment result, and constructing a brightness deviation distribution map; Combining the device aging parameters with the brightness deviation distribution map, performing weighted calculations to determine a deviation source weight coefficient; Brightness compensation is performed on the initial brightness adjustment result based on the deviation source weight coefficient to determine the brightness adjustment strategy.

8. The LED display screen brightness intelligent adjustment system combined with environmental perception according to claim 7, characterized in that: When the brightness compensation unit performs continuous verification, it includes: Perform data mapping based on the effective light intensity data, the crowd trajectory density data, and the meteorological environment data to construct a three-dimensional environment perception tensor; Extracting a multidimensional feedback feature vector through the three-dimensional environment perception tensor, wherein the multidimensional feedback feature vector includes the illumination gradient change rate, the coordinates of the crowd gathering area, and the weather mutation label; Continuously verifying the brightness feedback data of the multiple regions according to the illumination gradient change rate to generate illumination verification feedback data; Continuously verifying the brightness feedback data of the multiple areas according to the coordinates of the crowd gathering area to generate crowd verification feedback data; Continuously verifying the brightness feedback data of the multiple regions according to the meteorological mutation labels to generate meteorological verification feedback data; The lighting verification feedback data, the crowd verification feedback data, and the meteorological verification feedback data are correlated and integrated to obtain verification feedback data.

9. The LED display screen brightness intelligent adjustment system combined with environmental perception according to claim 8, characterized in that: When the brightness compensation unit extracts the multi-dimensional feedback feature vector, it includes: Performing multi-scale extraction based on the three-dimensional environment perception tensor to obtain multi-scale features; Performing illumination intensity feedback according to the multi-scale features, constructing an illumination intensity matrix, and performing gradient change calculation based on the illumination intensity matrix to obtain the illumination gradient change rate; Perform crowd density feedback according to the multi-scale features, construct a crowd density heat map, traverse the crowd density heat map to perform clustering and division, and construct the coordinates of the crowd clustering area; Meteorological change feedback is performed according to the multi-scale features to construct a meteorological time series sequence, meteorological mutation identification is performed according to the meteorological time series sequence, and the meteorological mutation label is constructed.

10. The intelligent adjustment method of LED display brightness combined with environmental perception is characterized by: The method is performed by the LED display screen brightness intelligent adjustment system combined with environmental perception according to any one of claims 1 to 9, and the method includes: The target area of ​​the LED display is perceived in real time by the environment perception module to obtain an environment perception data set, and the environment perception data set is analyzed in multiple dimensions to generate a dynamic brightness adjustment parameter set; Retrieving a device parameter set of the LED display, modifying the dynamic brightness adjustment parameter set, generating a brightness control instruction set, executing the brightness control instruction set to adjust the brightness of the LED display, and generating an initial brightness adjustment result; Based on the initial brightness adjustment result and the environmental perception data set, continuous verification is performed, the initial brightness adjustment result is compensated according to the verification feedback data, a brightness adjustment strategy is determined, and the brightness of the LED display is intelligently adjusted using the brightness adjustment strategy.

Images