LED display quality stability control method, device, equipment and medium

Abstract

The invention relates to the technical field of LED display, solves the problems that in the prior art, dynamic light attenuation compensation based on the real-time operation state of an LED chip cannot be achieved, and long-term uniformity and display quality of a display screen are difficult to guarantee, and provides an LED display quality stability control method, device and equipment and a medium. The method comprises the following steps: correcting the LED display screen according to an initial calibration coefficient; in the operation process of the corrected LED display screen, operation parameters of each LED chip in the LED display screen are collected in real time; acquiring the light attenuation degree of the LED display screen according to the operation parameters and a pre-constructed chip light attenuation model; when the light attenuation degree of the LED display screen meets a preset condition, adjusting the initial calibration coefficient according to the light attenuation degree to obtain a target calibration coefficient; and correcting the LED display screen according to the target calibration coefficient. The display stability, the service life and the maintenance convenience of the LED display screen are improved.

Description

Technical Field

[0001] The present invention relates to the field of display technology, and in particular to a method, device, equipment and storage medium for stabilizing LED display quality. Background Art

[0002] LED displays, with their advantages of high brightness, low energy consumption, and long life, have been widely used in various applications, including information display, advertising, and stage performances. However, with the continuous increase in display size and diversification of application scenarios, the issue of display quality stability has become increasingly prominent. In practical applications, due to the inherent light decay characteristics of LED chips, which are affected by multiple factors such as operating temperature, current, and lighting duration, mura (uneven brightness, color distortion, and other mura) can easily occur after long-term operation, seriously affecting the display quality.

[0003] Automatic calibration solutions for compensating for light decay in LED displays are already available. For example, patent publication number CN113611242 A discloses an automatic calibration method for LED displays. This method monitors the junction temperature of LED lamp beads and, in combination with a preset light decay curve, adjusts the calibration coefficient based on usage time to achieve a certain degree of light decay compensation and improve uniformity. This method can regularly adjust the calibration parameters based on temperature changes and accumulated usage time, thereby improving the problem of display quality degradation caused by light decay.

[0004] However, the above existing solutions still have obvious shortcomings. First, they only use the average junction temperature and lighting time as the main reference basis, which fails to fully reflect the comprehensive impact of various actual working conditions such as current and environmental changes on light decay, resulting in limited compensation accuracy and difficulty in adapting to complex and dynamic usage environments. Second, most existing methods are based on regular detection and batch parameter updates, and cannot perform refined, dynamic and real-time compensation and adjustment according to the actual operating status. After long-term operation, they still need to rely on manual intervention or regular maintenance. Third, traditional solutions lack sufficient consideration for the chip-level differences of large-scale high-resolution LED displays, making it difficult to achieve single-chip precision correction.

[0005] Therefore, there is an urgent need for a LED display quality stabilization control method that can combine the real-time operating parameters of LED chips, adapt to dynamic changes in multiple working conditions, and dynamically adjust the calibration coefficient based on a refined light decay model, so as to further improve the long-term operation uniformity, color consistency and degree of automation of the display screen. Summary of the Invention

[0006] In view of this, the embodiments of the present invention provide a method, device, equipment and storage medium for stabilizing the quality of LED display, so as to solve the problem in the prior art that dynamic light attenuation compensation based on the real-time operating status of the LED chip cannot be achieved, and it is difficult to ensure the long-term uniformity and display quality of the display screen.

[0007] In a first aspect, an embodiment of the present invention provides a method for controlling LED display quality stability, the method comprising:

[0008] Correcting the LED display screen according to an initial calibration coefficient, wherein the initial calibration coefficient is obtained by performing a mura test on the LED display screen;

[0009] During the operation of the calibrated LED display screen, the operating parameters of each LED chip in the LED display screen are collected in real time;

[0010] Obtaining the light decay degree of the LED display screen according to the operating parameters and a pre-built chip light decay model;

[0011] When the light decay degree of the LED display screen meets a preset condition, the initial calibration coefficient is adjusted according to the light decay degree to obtain a target calibration coefficient;

[0012] The LED display screen is calibrated according to the target calibration coefficient.

[0013] Preferably, during the operation of the calibrated LED display screen, real-time collection of operating parameters of each LED chip in the LED display screen includes:

[0014] According to the lighting record of the LED display, the lighting time of each LED chip is counted to obtain the cumulative working time;

[0015] Obtain the operating temperature of each LED chip based on the pre-built temperature database;

[0016] According to the preset sampling frequency, the working current of each LED chip is collected;

[0017] According to the operating current, obtaining an average current value of each LED chip during the operating time;

[0018] The operating parameters are obtained according to the current average, the operating temperature, and the accumulated operating time.

[0019] Preferably, obtaining the operating temperature of each LED chip according to a pre-built temperature database includes:

[0020] According to the physical structure parameters of the LED display and the LED chip arrangement information, a mapping relationship between the physical row and column coordinates of the LED chip and its number is established;

[0021] After the target LED screen reaches a thermal equilibrium state, obtaining a temperature field distribution image of the target LED screen;

[0022] According to the mapping relationship, pixel position information of each LED chip in the temperature field distribution image is obtained;

[0023] Divide the temperature field distribution image according to the pixel position information and a preset deep learning model to obtain a temperature region image of each LED chip;

[0024] Obtaining a temperature value of each LED chip according to the temperature region image;

[0025] Establishing the temperature database according to the temperature value and the mapping relationship;

[0026] The temperature database is queried according to the chip number of each LED chip to obtain the operating temperature of each LED chip.

[0027] Preferably, the temperature field distribution image is divided according to the pixel position information and the trained deep learning model to obtain a temperature region image of each LED chip;

[0028] Generate a coordinate priori heat map with the same resolution as the temperature field distribution image based on the pixel position information, wherein the center pixel of each LED chip is assigned a value of 1 and the remaining pixels are assigned a value of 0 in the coordinate priori heat map;

[0029] splicing the infrared temperature field distribution image and the coordinate prior heat map to obtain a dual-channel input tensor;

[0030] Inputting the dual-channel input tensor into a trained deep learning model to obtain a multi-scale mixed feature of the temperature coordinate, wherein the deep learning model includes a full convolutional network model, a U-Net model, and a regional convolutional neural network model;

[0031] According to the multi-scale mixed features, the temperature characteristic component corresponding to each pixel point in the infrared temperature field distribution map is obtained to obtain a temperature characteristic map;

[0032] According to the temperature characteristic map, the first-order difference of each pixel in the horizontal and vertical directions is calculated to obtain the temperature gradient map;

[0033] Calculate the gradient amplitude of each pixel according to the temperature gradient map and obtain the temperature difference attention weight;

[0034] Perform weighted fusion based on the temperature difference attention weight and the features of the decoding layer of the deep learning model to obtain a chip area probability map;

[0035] Performing connected domain screening based on the chip region probability map to obtain a set of candidate chip regions;

[0036] According to the candidate chip area set and the coordinate prior heat map, the connected domain closest to the center pixel of each LED chip is obtained to obtain the temperature area image of each LED chip.

[0037] Preferably, obtaining the light decay degree of the LED display screen according to the operating parameters and a pre-built chip light decay model includes:

[0038] According to the historical operating data of the LED display screen in different operating ranges, a chip light attenuation model under different operating ranges is constructed;

[0039] determining an actual operating condition range according to the operating parameters;

[0040] The operating parameters are input into a chip light decay model corresponding to the actual operating condition range to obtain the light decay degree of the LED display.

[0041] Preferably, the chip light attenuation model under different operating conditions is constructed according to the historical operating data of the LED display screen under different operating conditions, including:

[0042] Obtaining an experimental sample set for each operating condition interval based on historical operating data for the operating condition interval;

[0043] Performing feature extraction on the test sample set to obtain an attenuation feature data set under each operating condition interval;

[0044] Based on the attenuation characteristic data set, nonlinear regression analysis is performed to obtain the light attenuation mathematical model under each operating condition range;

[0045] Analyze the attenuation rate under the working condition range according to the light attenuation model to obtain the attenuation rate coefficient;

[0046] According to the attenuation rate coefficient under different working conditions and the corresponding light attenuation mathematical model, the chip light attenuation model under different working conditions is obtained.

[0047] Preferably, when the light decay degree of the LED display screen meets a preset condition, adjusting the initial calibration coefficient according to the light decay degree to obtain a target calibration coefficient includes:

[0048] Obtaining an actual light decay rate of the LED display screen according to the light decay degree and a preset light decay threshold;

[0049] Determine the LED chip that needs to be compensated for brightness based on the actual light decay rate of each LED chip and the preset light decay threshold, and obtain the chip that needs to be compensated;

[0050] Calculate the brightness compensation value of each chip to be compensated according to the actual light decay rate of the chip to be compensated and the preset brightness value;

[0051] generating a target brightness instruction for each chip requiring compensation according to the brightness compensation value;

[0052] According to the target brightness instruction and the initial calibration coefficient, the calibration coefficient of each chip to be compensated is adjusted to obtain the target calibration coefficient.

[0053] In a second aspect, an embodiment of the present invention provides an LED display quality stabilization control device, the device comprising:

[0054] A first correction module is used to calibrate the LED display screen according to an initial calibration coefficient, wherein the initial calibration coefficient is obtained by performing a mura test on the LED display screen;

[0055] An operating parameter acquisition module is used to collect the operating parameters of each LED chip in the LED display screen in real time during the operation of the calibrated LED display screen;

[0056] A light decay degree acquisition module, configured to acquire the light decay degree of the LED display screen according to the operating parameters and a pre-built chip light decay model;

[0057] a calibration coefficient adjustment module, configured to adjust the initial calibration coefficient according to the light decay degree of the LED display screen to obtain a target calibration coefficient when the light decay degree of the LED display screen meets a preset condition;

[0058] The second correction module is used to correct the LED display screen according to the target calibration coefficient.

[0059] In a third aspect, an embodiment of the present invention provides an electronic device comprising: at least one processor, at least one memory, and computer program instructions stored in the memory, which, when executed by the processor, implement the method of the first aspect in the above-mentioned embodiment.

[0060] In a fourth aspect, an embodiment of the present invention provides a storage medium having computer program instructions stored thereon, which implements the method of the first aspect of the above-mentioned embodiment when the computer program instructions are executed by a processor.

[0061] In summary, the beneficial effects of the present invention are as follows:

[0062] The LED display quality stability control method, device, equipment and storage medium provided by the embodiments of the present invention can achieve precise correction for the initial unevenness of each display screen by obtaining the initial calibration coefficient through mura testing of the LED display screen, thereby improving the initial display uniformity and image quality consistency. During the operation of the display screen, the operating parameters of each LED chip are continuously collected, providing a data basis for subsequent dynamic compensation, and realizing comprehensive perception of the chip-level operating status. By utilizing the pre-built chip light decay model and combining the operating parameters collected in real time, the light decay degree of each chip can be dynamically calculated and accurately reflected, thereby accurately determining the current state of the display screen. When it is detected that the light decay degree meets the preset conditions, the calibration coefficient can be dynamically adjusted based on the actual light decay condition to compensate for the brightness drop of the LED chip in time and ensure the long-term stability of the display effect. By continuously feeding back and adjusting the calibration coefficient, dynamic and adaptive closed-loop compensation of the display screen is achieved without the need for frequent manual intervention, effectively improving the long-term uniformity and display quality stability of the LED display screen.

[0063] In summary, the present invention can achieve high-precision automatic uniformity compensation for the display screen from its initial factory release to long-term operation, effectively solving problems such as uneven brightness and color distortion caused by LED chip light decay and changes in operating conditions, and significantly improving the display quality, lifespan and maintenance convenience of the LED display screen. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work, and these are all within the scope of protection of the present invention.

[0065] Figure 1 The figure is a flow chart of a method for controlling the stabilization of LED display quality according to an embodiment of the present invention.

[0066] Figure 2 This is another flow chart of the LED display quality stabilization control method according to an embodiment of the present invention.

[0067] Figure 3 This is another flow chart of the LED display quality stabilization control method according to an embodiment of the present invention.

[0068] Figure 4 This is a schematic diagram of the structure of the LED display quality stabilization control device according to an embodiment of the present invention.

[0069] Figure 5 2 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0070] The features and exemplary embodiments of various aspects of the present invention will be described in detail below. In order to make the objects, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below in conjunction with the accompanying drawings and Examples. It should be understood that the specific embodiments described herein are only configured to explain the present invention and are not configured to limit the present invention. For those skilled in the art, the present invention can be implemented without the need for some of these specific details. The following description of the embodiments is merely to provide a better understanding of the present invention by illustrating examples of the present invention.

[0071] It should be noted that, in this document, relational terms such as first and second, etc., are used only 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. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, the elements defined by the phrase "comprising..." do not exclude the presence of other identical elements in the process, method, article, or device comprising the elements.

[0072] Example 1

[0073] See Figure 1-3 , an embodiment of the present invention provides a method for controlling LED display quality stability, the method comprising:

[0074] S1. Calibrate the LED display screen according to an initial calibration coefficient, wherein the initial calibration coefficient is obtained by performing a mura test on the LED display screen;

[0075] Specifically, mura testing refers to the use of high-resolution image acquisition equipment to accurately detect the brightness and color distribution of LED display screens, quantify dark spots, bright spots, color unevenness and other problems on the screen, and express these unevenness as quantifiable data. Based on these test results, the corresponding calibration coefficient (i.e., initial calibration coefficient) can be automatically calculated for each pixel or LED chip. These coefficients are used to compensate for the brightness or color differences in different areas. In this way, before the LED display screen is officially put into use, the luminous performance of each area can be unified by adjusting the driver IC or control system parameters to achieve factory-standard brightness and color uniformity. In this way, the initial unevenness caused by chip performance fluctuations, splicing errors, etc. is greatly improved, laying a solid foundation for subsequent long-term automated uniformity maintenance.

[0076] S2. During the operation of the calibrated LED display screen, collecting operating parameters of each LED chip in the LED display screen in real time;

[0077] Specifically, this step is a work that is carried out continuously during the operation phase after the initial calibration is completed. Its core is to collect the operating parameters of each LED chip in the LED display in real time. Operating parameters refer to various data that can reflect the actual working status of the LED chip, which commonly include driving current, cumulative lighting time, operating temperature, etc. The main purpose of implementing this step is to provide data support for subsequent light decay evaluation and dynamic compensation, and to ensure that subsequent compensation measures are based on the actual operating conditions. In the actual process, the relevant operating data of each chip can be obtained and stored regularly according to the preset sampling period through the integrated current detection module, temperature sensor, timing counter and other hardware, combined with the software acquisition logic of the display control system. Continuous data collection not only provides a detailed basis for the dynamic evaluation of LED chip performance changes, but also provides conditions for large-scale automated operation and maintenance.

[0078] S3. Obtaining the light decay degree of the LED display screen according to the operating parameters and a pre-built chip light decay model;

[0079] Specifically, this step combines the real-time operating parameters obtained in the previous step with the pre-built chip light decay model to dynamically calculate the light decay degree of the display screen. The chip light decay model is established based on a large number of historical experiments and actual operating data, and can reflect the quantitative relationship between the brightness of the LED chip and changes in time, temperature, current and other factors. The main purpose of this step is to use the model to accurately evaluate the current brightness decay level of each chip, so as to timely grasp the trend of changes in the uniformity of the display screen. In specific implementation, the operating time, operating current and temperature of each chip and other parameters are input into the light decay model to obtain the current brightness decay value or decay rate of each chip. Through the modeling and data-driven evaluation method, not only the accuracy of light decay compensation is improved, but also a scientific basis is provided for the subsequent compensation threshold determination and automatic adjustment. This technical feature can make the light decay judgment objective and real-time, effectively improving the intelligence level of display uniformity maintenance.

[0080] S4. When the light decay degree of the LED display screen meets a preset condition, the initial calibration coefficient is adjusted according to the light decay degree to obtain a target calibration coefficient;

[0081] When it is detected that the light decay level meets the preset conditions, the initial calibration coefficient is automatically adjusted based on the specific light decay situation, thereby generating a new target calibration coefficient. The core purpose of this step is to achieve dynamic adaptive compensation for performance changes of each LED chip during operation. During implementation, the actual light decay level is compared with the preset threshold. When it is found that the brightness attenuation of a certain area or a certain chip exceeds the allowable range, the required compensation amount is automatically calculated and the calibration coefficient corresponding to the chip or area is corrected to ensure that its output brightness is restored to the designed level or close to the initial state. This process does not require human intervention and can efficiently respond to and correct changes in display uniformity during the operation of the display, significantly improving the stability and self-maintenance capabilities of the display system.

[0082] S5. Calibrate the LED display screen according to the target calibration coefficient.

[0083] This step implements the results of the aforementioned dynamic adjustment and performs global or local correction on the display screen again according to the target calibration coefficient. The purpose of this step is to apply the newly calculated calibration parameters to the control logic of each chip of the display screen to ensure that the compensation effect takes effect in a timely manner, thereby maintaining the long-term brightness and color uniformity of the display screen. In specific implementation, the brightness compensation of the relevant LED chips is completed by updating the chip drive parameters or PWM duty cycle. Through the continuous closed-loop dynamic correction mechanism, the display screen can adaptively respond to performance fluctuations and unevenness that occur during long-term operation, effectively extending the product life, reducing maintenance costs, and improving the display experience of end users.

[0084] Preferably, during the operation of the calibrated LED display screen, real-time collection of operating parameters of each LED chip in the LED display screen includes:

[0085] S21. Count the lighting time of each LED chip based on the lighting record of the LED display screen to obtain the cumulative working time;

[0086] Specifically, calculating the on-time of each LED chip is done by tracking the power-on, power-on, and power-off operation logs for each chip in the display control system. The accumulated on-time periods are then added up to determine the cumulative operating hours of each chip since it was put into operation. This accumulated operating time not only provides basic data for subsequent aging analysis but also directly reflects the operating load experienced by the chip, playing a key role in chip lifespan management and light decay assessment.

[0087] S22. Obtain the operating temperature of each LED chip according to a pre-built temperature database;

[0088] Specifically, the operating temperature of each LED chip is determined based on a pre-built temperature database. This database, previously established through infrared thermal imaging, spatial coordinate mapping, and chip numbering, is combined with the chip's physical location and layout information to accurately retrieve the corresponding temperature value for each LED chip under actual operating conditions. Operating temperature, a key environmental parameter that affects a chip's luminous efficiency and light decay rate, is crucial for evaluating its long-term stability.

[0089] S23, collecting the operating current of each LED chip according to a preset sampling frequency;

[0090] Specifically, the operating current of each LED chip is collected in real time at a set sampling frequency. This process uses a built-in current detection module to regularly measure and record the driving current of each chip, dynamically reflecting the chip's actual power consumption under different loads and display content. Periodic data collection not only ensures sample integrity but also provides a reliable basis for analyzing long-term chip energy consumption and load changes.

[0091] S24. Obtaining an average current value of each LED chip during the operating time according to the operating current;

[0092] Specifically, this step statistically analyzes all collected current data based on the cumulative operating time of each chip, calculating the average current for the chip throughout its entire operating cycle. This average current, as an indicator of the chip's typical drive strength, can reveal its long-term power consumption characteristics and changes in load conditions.

[0093] S25. Obtain the operating parameters according to the current average, the operating temperature, and the accumulated operating time.

[0094] Specifically, the average current, operating temperature, and cumulative operating hours of each LED chip are aggregated to form an operating parameter set that comprehensively reflects the chip's actual operating status. This process provides comprehensive and detailed data support for subsequent light decay modeling and dynamic correction strategies based on operating parameters, helping to improve the overall display quality and operational controllability of LED displays.

[0095] Preferably, obtaining the operating temperature of each LED chip according to a pre-built temperature database includes:

[0096] S221. Establish a mapping relationship between the physical row and column coordinates of the LED chips and their numbers based on the physical structural parameters of the LED display and the LED chip arrangement information;

[0097] Specifically, based on the physical structural parameters of the LED display and the chip layout information, a mapping relationship is established between the physical row and column coordinates of each LED chip and its unique number. Specifically, based on the display module's size, resolution, and the chip arrangement on the circuit board, each chip's actual physical location is mapped one-to-one with the logical number assigned in the display system, ensuring that the spatial information and data identifiers of any subsequent chip are precisely matched. This mapping relationship provides a standardized foundation for spatial positioning for subsequent thermal distribution analysis and temperature data archiving.

[0098] S222. After the target LED screen reaches a thermal equilibrium state, obtaining a temperature field distribution image of the target LED screen;

[0099] The screen reaching a thermal equilibrium state means that after the display screen has been running continuously for a certain period of time, the overall heat distribution tends to be stable and no longer has violent fluctuations. At this time, the temperature field distribution image collected can reflect the stable thermal environment of the LED chip under actual working conditions. The purpose of collecting the temperature field distribution image is to obtain the temperature distribution of each area of ​​the entire screen at present, and provide basic data for the subsequent accurate extraction of the working temperature of a single chip. During implementation, after the display screen is powered on and continuously displays a high-brightness or standard picture for a set period of time, a high-precision infrared thermal imager can be used to shoot the entire screen to obtain the original temperature image containing the heat distribution of all chips. This temperature image serves as a base map for subsequent analysis, which can fully reflect the thermal load status of the screen and significantly improve the representativeness and accuracy of temperature acquisition.

[0100] S223. Obtain pixel position information of each LED chip in the temperature field distribution image according to the mapping relationship;

[0101] The key purpose of this step is to accurately match the spatial information of the LED chip with the pixel coordinates of the temperature field image. Through the aforementioned established chip row and column and number mapping relationship, the physical space position of each chip is mapped to the specific pixel point in the thermal imaging image through coordinate transformation. For example, the pixel coordinates corresponding to the chip in the 10th row and 20th column on the temperature field image are (x, y). This step can be implemented by using image calibration algorithms (such as perspective transformation, automatic identification of calibration points, etc.), combined with the actual module layout for coordinate conversion, to ensure the accurate positioning of each chip in the temperature image. This technical feature helps to seamlessly connect the actual physical structure and digital image data, laying a precise spatial foundation for subsequent area division and temperature value extraction.

[0102] S224. Divide the temperature field distribution image according to the pixel position information and a preset deep learning model to obtain a temperature region image of each LED chip;

[0103] Specifically, a deep learning model is used to automatically segment the temperature field distribution image to obtain the temperature region image of each LED chip. Deep learning models such as U-Net can perform pixel-level segmentation on thermal imaging images based on input chip pixel coordinates, thermal distribution patterns and other information, and accurately separate the temperature region where each chip is located from the overall image. The purpose of this step is to improve the automation and accuracy of chip temperature region extraction and avoid errors caused by manual division or simple threshold segmentation. In actual operation, the temperature image and chip coordinates are first input into the trained neural network model, and the model automatically outputs the temperature region mask corresponding to each chip, and finally forms a temperature sub-map corresponding to each chip. The introduction of deep learning segmentation has greatly improved the degree of automation of data processing and the robustness of segmentation under complex working conditions.

[0104] S225, obtaining the temperature value of each LED chip according to the temperature region image;

[0105] Specifically, representative temperature values ​​are extracted from the temperature region image of each chip. The temperature value is usually based on the average, median, or weighted value of all pixels in the region, and can objectively reflect the operating temperature of the chip at the moment of thermal equilibrium. The purpose is to convert the original high-dimensional data of the thermal imaging image into structured temperature data that can be directly used for chip-level data analysis. Specific methods can include regional mean method, cluster statistics method, or filtering of abnormal pixels to ensure that the extracted temperature values ​​are true and stable. This step greatly simplifies the original temperature data structure and provides a basic guarantee for the subsequent establishment and query of the temperature database.

[0106] S226. Establishing the temperature database according to the temperature value and the mapping relationship;

[0107] The temperature values ​​of all chips are further integrated with their corresponding spatial numbers to systematically establish a structured temperature database. This database, with the chip number as the primary key, stores the operating temperature of each chip under current thermal equilibrium and, as needed, associates metadata such as its coordinates, acquisition time, and environmental conditions. This provides a unified data platform for efficient retrieval, dynamic maintenance, and historical tracing of subsequent chip-level temperature data in the display system. The establishment of a temperature database facilitates continuous monitoring of temperature evolution trends in chips across various regions, providing early warning of potential risks such as abnormal temperature rise or uneven heat distribution, and enhancing the system's overall intelligent perception and self-maintenance capabilities.

[0108] S227 , querying the temperature database according to the chip number of each LED chip to obtain the operating temperature of each LED chip.

[0109] Specifically, the chip number can be used to efficiently query and obtain the target chip's real-time operating temperature in the temperature database, providing accurate environmental input for subsequent temperature-based light attenuation modeling, dynamic compensation, fault detection, and other processes. This query mechanism ensures the timeliness and consistency of temperature data, enabling the system to respond in real time to changes in the display's thermal environment during operation, further enhancing the intelligent and automated level of display uniformity maintenance and anomaly management.

[0110] Preferably, the temperature field distribution image is divided according to the pixel position information and the trained deep learning model to obtain a temperature region image of each LED chip;

[0111] S2241. Generate a coordinate priori heat map with the same resolution as the temperature field distribution image based on the pixel position information, wherein in the coordinate priori heat map, the center pixel of each LED chip is assigned a value of 1, and the remaining pixels are assigned a value of 0;

[0112] Specifically, the coordinate prior heat map refers to an auxiliary image with the same resolution as the infrared temperature field distribution image, which assigns a value of 1 to the center pixel of each LED chip and a value of 0 to the remaining pixels. The purpose of generating this heat map is to explicitly embed the spatial position information of each chip into the subsequent image analysis process, and provide clear spatial positioning guidance for the deep learning model. In the specific implementation process, the chip arrangement information is used to highlight the pixels corresponding to the center of all chips on a completely black background image, and the other pixels remain zero. Using this structured prior information as an auxiliary feature not only improves the convergence speed of the model for chip positioning, but also significantly enhances the model's perception of spatial structure, reducing the risk of misjudgment in segmentation when the chips are densely arranged or partially occluded.

[0113] S2242, splicing the infrared temperature field distribution image and the coordinate prior heat map to obtain a dual-channel input tensor;

[0114] The spatial prior is fused with the actual thermal distribution data to obtain a multi-channel input tensor for deep learning segmentation. During implementation, the infrared temperature field distribution image and the aforementioned coordinate prior heat map are spliced ​​in the channel dimension to form a three-dimensional array with two feature layers (temperature distribution and spatial prior), that is, a dual-channel input tensor. This approach is beneficial for the deep model to automatically focus on the location area related to the chip while learning the temperature characteristics, thereby improving the context perception ability and model robustness of the segmentation process.

[0115] S2243. Inputting the dual-channel input tensor into a trained deep learning model to obtain a multi-scale mixed feature of the temperature coordinate, wherein the deep learning model includes a full convolutional network model, a U-Net model, and a regional convolutional neural network model;

[0116] The dual-channel input tensor is fed into a trained deep learning model. This model can include segmentation structures such as a fully convolutional network (FCN), a U-Net network, or a regional convolutional neural network (such as Mask R-CNN). Leveraging the model's multi-layer convolution and feature fusion capabilities, it automatically extracts and encodes the temperature variation and spatial position information in the input tensor, outputting a multi-scale hybrid temperature-coordinate feature. This feature fusion mechanism simultaneously captures global thermal distribution patterns and local spatial details, providing a highly discriminative information foundation for subsequent chip-level segmentation.

[0117] S2244. Obtaining a temperature characteristic component corresponding to each pixel point in the infrared temperature field distribution map based on the multi-scale mixed feature to obtain a temperature characteristic map;

[0118] The goal of this step is to transform complex multi-scale mixed features into an easily analyzable temperature signature map. This step extracts the feature channels or combinations of channels most relevant to temperature changes from the feature map output by the deep network, constructing a two-dimensional map reflecting the temperature properties of each pixel. This temperature signature map makes subsequent gradient and regional analysis operational and intuitive, facilitating the identification of subtle temperature differences between chips.

[0119] S2245. Calculate the first-order difference of each pixel in the horizontal and vertical directions according to the temperature characteristic map to obtain a temperature gradient map;

[0120] Specifically, based on the temperature feature map, the first-order differences in the horizontal and vertical directions of each pixel are calculated to generate a temperature gradient map. The temperature gradient reflects the severity of temperature changes in space and helps subsequent models accurately identify chip boundaries. Convolving the feature map with a gradient operator quickly generates two-dimensional data reflecting temperature trends, providing key support for the attention mechanism.

[0121] S2246. Calculate the gradient amplitude of each pixel according to the temperature gradient map to obtain the temperature difference attention weight;

[0122] Specifically, the temperature gradient map is amplitude-calculated to obtain the attention weight for each pixel's temperature difference. This operation typically normalizes the gradient vector magnitude at each point, generating a weight map between 0 and 1 that reflects the sensitivity of each region to temperature changes. Regions with higher weights often correspond to chip edges or areas of thermal abrupt change, and subsequent models will pay more attention to these critical areas. This mechanism significantly improves the model's ability to identify chip boundaries under complex thermal distributions.

[0123] S2247. Perform weighted fusion based on the temperature difference attention weight and the features of the decoding layer of the deep learning model to obtain a chip area probability map;

[0124] Temperature-difference attention weights guide the weighted fusion of features in the decoding layer of a deep learning model. During implementation, the attention weights serve as masks to weight the multi-channel features output by the decoding layer pixel by pixel, improving segmentation sensitivity at chip region boundaries. The fused output is a chip region probability map, where each pixel's value represents the probability of belonging to the chip region. This method, through a soft segmentation strategy, avoids boundary jumps caused by hard thresholding, significantly improving segmentation smoothness and boundary accuracy.

[0125] S2248. Screen connected domains based on the chip region probability map to obtain a set of candidate chip regions.

[0126] Connected domain screening is performed based on the chip region probability map, with the goal of extracting high-confidence candidate chip regions from the probability map. By setting a probability threshold, regions above the threshold are identified as chip regions. Connectivity analysis and labeling are performed on these regions to identify a set of independent candidate regions. This screening process eliminates isolated pixel noise that may be output by the model, ensuring the stability and accuracy of subsequent temperature extraction.

[0127] S2249. According to the candidate chip region set and the coordinate prior heat map, obtain the connected domain closest to the center pixel of each LED chip to obtain the temperature region image of each LED chip.

[0128] Based on the resulting candidate chip region set and the coordinate prior heat map, the center pixel of each LED chip is matched to its nearest connected domain, accurately assigning each chip's temperature region. Ultimately, a temperature region image corresponding to the physical chip is output, providing a reliable foundation for subsequent temperature statistics within the region and the acquisition of chip operating temperatures. This refined process significantly improves the accuracy of chip-level temperature analysis for high-density LED displays, providing solid technical support for display thermal management and light attenuation compensation.

[0129] Preferably, obtaining the light decay degree of the LED display screen according to the operating parameters and a pre-built chip light decay model includes:

[0130] S31, constructing a chip light attenuation model under different operating conditions according to the historical operating data of the LED display screen under different operating conditions;

[0131] The chip light decay model refers to a mathematical model that can reflect the brightness decay law of LED chips over time under different operating conditions (such as temperature, current, lighting duration, etc.). The historical operating data of the display screen is classified and statistically analyzed according to different operating conditions such as temperature, current, and operating time. The chip brightness change characteristics are extracted for each operating condition interval, and algorithms such as nonlinear regression are used for fitting. Finally, an independent light decay curve is established for each typical operating condition. In this way, the light decay model can not only reflect the overall trend, but also carefully distinguish the influence of various typical operating conditions, providing a high-precision prediction basis for subsequent dynamic compensation. Through multi-operating condition interval modeling, the model's adaptability and predictive ability for actual complex application environments can be significantly improved.

[0132] S32. Determine an actual operating range based on the operating parameters;

[0133] Specifically, the core of step S32 is to determine the actual operating range of the LED chip based on the collected operating parameters. The operating parameters include but are not limited to the cumulative working time, average operating temperature, typical operating current and other data. The purpose of determining the operating range is to be able to select the light decay model that is closest to the current actual environment under the multi-model system, so as to obtain the most accurate attenuation estimate. During implementation, the current chip state is classified into the corresponding operating condition category by comparing the operating parameters with the pre-defined operating condition partition thresholds (such as the temperature above a certain value is classified as a high temperature range, the current within a certain range is classified as a standard range, etc.). In this way, each chip can be matched with its most suitable light decay model, thereby improving the pertinence of the light decay assessment.

[0134] S33: Input the operating parameters into a chip light decay model corresponding to the actual operating range to obtain the light decay degree of the LED display.

[0135] Combining the first two steps, the real-time collected operating parameters are input into the corresponding chip light decay model to obtain the light decay degree of the LED display under the current working conditions. The light decay degree here is usually quantified in terms of brightness decay rate, residual brightness percentage, etc. The specific process is to find the operating condition interval corresponding to the operating parameters, call the light decay model of the interval, and use the real-time parameters (such as running time, current current and temperature) as model input to calculate the current brightness decay level of the chip or area. In this way, not only can accurate light decay assessment be achieved for different usage environments, but it also provides a reliable foundation for subsequent dynamic brightness compensation and calibration coefficient adjustment, improving the intelligence level of long-term stability and consistency maintenance of the display.

[0136] Preferably, the chip light attenuation model under different operating conditions is constructed according to the historical operating data of the LED display screen under different operating conditions, including:

[0137] S311, obtaining an experimental sample set for each operating condition interval based on the historical operating data of the operating condition interval;

[0138] The experimental sample set refers to the historical operating data of the LED display screen, which classifies all data according to pre-divided operating conditions and archives them into multiple experimental sample sets. The operating condition range is usually set according to environmental and load conditions such as temperature range, current size, and operating time. For example, it can be divided into high temperature and high current range, low temperature and low current range, etc. The purpose of this step is to provide targeted data support for the establishment of subsequent models, and to ensure that the light decay modeling in each operating condition range can be based on sufficient and effective historical samples. In practice, historical operation records belonging to the same range can be automatically aggregated into independent data sets through database retrieval and screening, laying the foundation for feature analysis and modeling. This approach is conducive to finely characterizing the impact of multiple operating conditions on chip light decay, and improving the adaptability and generalization ability of subsequent models.

[0139] S312, extracting features from the test sample set to obtain an attenuation feature data set under each operating condition interval;

[0140] For each experimental sample set, feature extraction is performed to transform the raw time-series operating data into a characteristic dataset reflecting the light decay patterns of the LED chip. Common features include the brightness decay curve corresponding to the duration of the light, the relationship between ambient temperature and decay rate, and the impact of current changes on brightness. Feature extraction can be performed not only using statistical methods such as calculating the rate of change of brightness, maximum and minimum values, and average trends, but also through signal processing or machine learning methods to discover hidden patterns. The resulting decay feature dataset provides rich and representative input variables for subsequent regression modeling, effectively improving the model's ability to characterize actual operating patterns.

[0141] S313, performing nonlinear regression analysis on the attenuation characteristic data set to obtain a mathematical model of light attenuation in each operating range;

[0142] Based on the attenuation characteristic dataset for each operating range, nonlinear regression analysis is used to model light attenuation. Nonlinear regression methods, such as exponential, logarithmic, and polynomial regression, can be used to fit the nonlinear trends of chip brightness over time and other variables, thereby deriving a mathematical model of light attenuation for each operating range. This mathematical model can be used to quantitatively describe the brightness attenuation process of the chip under specific operating conditions. Through regression fitting, the model parameters can be highly consistent with actual historical data, ensuring the reliability of subsequent predictions. The technical feature of this step is the use of mathematical fitting tools to automatically find the optimal model form and parameters, improving the scientific nature and engineering practicality of light attenuation modeling.

[0143] S314, analyzing the attenuation rate under the working condition in the working range according to the light attenuation model to obtain the attenuation rate coefficient;

[0144] Analyze the established mathematical model for light decay to quantify the decay rate under different operating conditions. The so-called "decay rate coefficient" refers to the factor within the model parameters that directly reflects the speed of light decay. Analysis methods typically include parsing model derivatives and analyzing parameter sensitivity. The purpose of this step is to quantify the specific impact of various environmental and load factors on the decay rate of LED chips, clarifying the operating conditions under which light decay is most significant, and providing theoretical support for developing differentiated compensation strategies in practical applications. By scientifically decomposing and extracting the decay rate coefficient, more accurate parameter input can be provided for subsequent applications such as dynamic brightness correction and life management.

[0145] S315 , obtaining a chip light attenuation model under different operating conditions according to the attenuation rate coefficient under different operating conditions and the corresponding light attenuation mathematical model.

[0146] By combining the attenuation coefficients obtained under each operating range with the corresponding light decay mathematical model, a chip light decay model library under different operating ranges is systematically formed. Each model not only contains mathematical expressions, but also clearly associates the corresponding environment and load ranges, achieving seamless integration of the model with the actual operating scenario. After obtaining a complete light decay model, the most matching light decay model can be dynamically selected and called based on the real-time monitoring of the chip operating conditions to achieve targeted compensation and accurate prediction. This technical feature significantly improves the display stability and intelligent adaptability of LED displays under variable operating conditions, providing a solid data and theoretical foundation for achieving high reliability and long-life displays.

[0147] Preferably, when the light decay degree of the LED display screen meets a preset condition, adjusting the initial calibration coefficient according to the light decay degree to obtain a target calibration coefficient includes:

[0148] S41. Obtaining an actual light decay rate of the LED display screen according to the light decay degree and a preset light decay threshold;

[0149] By comparing actual test results with threshold standards, the system quantifies the degree of light decay for each chip and determines whether it has reached the threshold for compensation. During implementation, the system automatically calculates the actual brightness decay ratio of each LED chip and compares it with the corresponding threshold, providing a quantitative basis for compensation decisions. This design helps accurately identify chips with degraded performance, avoids overcompensation or misses anomalies, and provides a scientific basis for maintaining display uniformity.

[0150] S42, determining the LED chips that need to be compensated based on the actual light decay rate of each LED chip and the preset light decay threshold, and obtaining the chips that need to be compensated;

[0151] Based on the aforementioned light decay analysis results, a clear determination is made as to which LED chips require brightness compensation. Chips requiring compensation are those whose actual light decay rates exceed the system's preset threshold. The primary purpose of this step is to screen all LED chips across the entire screen to identify the key factors that truly impact display uniformity and brightness consistency, effectively focusing compensation resources. This is achieved by traversing all chips and automatically assigning those with actual light decay rates exceeding the threshold to the compensation list, while the remaining chips remain in their original state. This dynamic screening significantly improves the accuracy and efficiency of the compensation algorithm, avoids ineffective operations, and ensures stable and consistent display performance.

[0152] S43, calculating the brightness compensation value of each chip to be compensated according to the actual light decay rate of the chip to be compensated and the preset brightness value;

[0153] The brightness compensation value refers to the amount of compensation that needs to be added or adjusted for each chip that needs to be compensated, based on the difference between its actual light decay rate and the target brightness. For example, if the actual brightness of a chip is 85%, and the preset target is 95%, the compensation value is 10%. The purpose of this step is to develop a personalized compensation plan for each chip that needs compensation to achieve accurate and differentiated brightness improvement. During the implementation process, the system calculates the numerical difference between the current brightness attenuation of each chip and the preset target brightness, and outputs the corresponding compensation value. This technical feature can restore and maintain the consistency of chip brightness to the greatest extent, providing a precise basis for the next step of automatic instruction generation.

[0154] S44, generating a target brightness instruction for each chip requiring compensation according to the brightness compensation value;

[0155] Converting numerical brightness compensation requirements into specific hardware execution instructions. Target brightness instructions are system-generated adjustment commands that can directly act on the LED driver IC or control unit, such as current gain adjustment and PWM duty cycle correction. The goal is to automate the distribution and hardware-level execution of compensation strategies. In actual operation, the system generates matching target brightness instructions for each chip requiring compensation based on the compensation value and sends them to the corresponding chip control circuit via the data bus, ensuring that compensation measures are immediately and accurately applied to the display terminal. This step significantly improves the automation and responsiveness of the display compensation process, effectively reducing manual intervention and adjustment errors.

[0156] S45 , adjusting the calibration coefficient of each chip to be compensated according to the target brightness instruction and the initial calibration coefficient to obtain a target calibration coefficient.

[0157] Based on the target brightness instruction and the original initial calibration coefficient, the calibration coefficient of each chip requiring compensation is updated, ultimately resulting in the target calibration coefficient. The calibration coefficient here is the core parameter that drives the control system to adjust the actual brightness of each chip. By dynamically adjusting the calibration coefficient based on the latest brightness requirements, the system can continuously correct the chip output to keep its brightness within the set range. The specific process involves reading the current calibration coefficient, mathematically superimposing or replacing it with the target brightness adjustment amount, and applying the result as the new target calibration coefficient to the chip control process. This closed-loop compensation mechanism significantly improves the brightness stability and uniformity of LED displays during long-term operation, ensuring high-quality image display and a longer, intervention-free operating life.

[0158] In one embodiment, step S45 further includes:

[0159] S451. Divide the screen area according to the LED display and chip arrangement information to obtain the partition numbers of the partitions and the chip sets corresponding to the partitions;

[0160] Specifically, the screen area is first divided according to the physical structure parameters of the LED display and the specific arrangement information of the chips, resulting in the partition numbers of the partitions and the corresponding chip sets for each area. The physical structure parameters here usually include the number of rows and columns of pixels on the screen, the distribution of unit modules, etc., and the chip arrangement information is the physical coordinates or unique number of each LED chip in the entire screen. By scientifically dividing the areas, it is not only convenient for subsequent zoning management of the display status, but also provides a physical basis for regional error and aging trend analysis. For example, a large display screen can be divided into several rectangular areas, and the number and distribution of chips in each area are as uniform as possible to achieve refined compensation and control.

[0161] S452: Statistically analyze the drift error data of all chips in each partition during the most recent preset number of calibrations to obtain a drift error time series for each partition.

[0162] Based on the drift error data of all chips within each partition during the most recent calibrations, a statistical analysis is performed to generate a time series of drift errors for each partition. Drift error refers to the deviation of chip parameters such as brightness and chromaticity from their ideal baseline values. By collecting and chronologically sorting the calibration results for each partition, a data series can be generated that reflects the performance evolution trend of the partition. The goal of this step is to fully understand the historical changes in each region and provide a sufficient data foundation for the subsequent correlation analysis. For example, the average brightness drift of a particular region over the last ten calibrations can be plotted as a time series curve, visually reflecting its aging process or environmental impact.

[0163] S453, performing correlation analysis based on the drift error time series of each partition to obtain a correlation coefficient matrix between the partitions;

[0164] Specifically, after obtaining the drift error time series for each partition, a correlation analysis is performed between each partition and the others to obtain a correlation coefficient matrix between the partitions. Correlation analysis often uses methods such as the Pearson correlation coefficient to assess the degree of synchronization of errors between different partitions over time. By constructing a correlation matrix, it is possible to clearly identify which partitions have strong error linkage and which are more independent. The purpose of this step is to provide a data basis for subsequent linkage adjustments during regional compensation, ensuring that compensation decisions are more consistent with the actual situation of the entire screen.

[0165] S454: Determine the associated partitions of each partition based on the correlation coefficient matrix and a preset correlation threshold;

[0166] Specifically, based on step S453, the associated partitions of each partition are determined according to the correlation coefficient matrix and the preset correlation threshold. Associated partitions refer to other partitions that exhibit strong synchronization with the current partition in terms of error change trends. Typically, partitions with correlation coefficients greater than a certain threshold (such as 0.5 or 0.7) are selected as associated partitions. This screening process can eliminate weakly correlated or irrelevant partitions, focusing on areas that have a practical impact on the compensation strategy, greatly improving the effectiveness and computational efficiency of the compensation algorithm.

[0167] S455: Assign linkage weights according to the correlation coefficient matrix to obtain linkage weights between each partition and the corresponding associated partitions;

[0168] Subsequently, linkage weights are assigned based on the correlation coefficient matrix to obtain linkage weights between each partition and the corresponding associated partition (S455). The linkage weight reflects the degree of influence of the compensation adjustment of one partition on other related partitions. The correlation coefficient is usually normalized into a weight value so that the weight assignment not only reflects the linkage strength between partitions, but also facilitates the subsequent quantitative assignment of compensation parameters. For example, for a certain area A, assuming that its correlation coefficients with areas B and C are 0.8 and 0.6 respectively, the linkage weights of AB and AC can be set to 0.57 and 0.43 respectively (after normalization).

[0169] S456, performing preliminary adjustment on the chip calibration coefficients according to the target brightness instruction and the initial calibration coefficients of each chip to be compensated, to obtain intermediate calibration coefficients;

[0170] Next, based on the target brightness command and initial calibration coefficients for each chip requiring compensation, a preliminary adjustment of the chip calibration coefficients is performed to obtain intermediate calibration coefficients. The target brightness command is based on the actual brightness attenuation detected. Each chip requiring compensation, combined with its own initial calibration parameters, produces a preliminary compensation result that does not yet account for the effects of regional linkage. This step lays the foundation for regional compensation, but does not yet incorporate inter-regional linkage effects.

[0171] S457: adjusting the intermediate calibration coefficient of each partition's associated partitions according to the linkage weight to obtain a target calibration coefficient;

[0172] First, for each partition, the system searches for its associated partitions, identified in the previous steps ( S454 and S455 ). These associated partitions are those that exhibit strong synchronization with the current partition in terms of error trends, and they have been assigned corresponding linkage weights. Each linkage weight represents the degree to which the associated partition influences the current partition's compensation results during compensation adjustments.

[0173] During actual adjustments, the system doesn't simply use the partition's own intermediate calibration coefficient as the final compensation value. Instead, it combines the intermediate calibration coefficients of the partition with those of all its associated partitions. Specifically, the system assigns different weights to the intermediate calibration coefficients of the partition and its associated partitions, depending on the linkage weights between each pair of partitions. A partition's own intermediate calibration coefficient typically receives a higher weight, while the intermediate calibration coefficients of highly correlated associated partitions also receive a certain weight.

[0174] This approach ensures that the final compensation result for each zone fully reflects its own brightness attenuation while also adaptively correcting for changes in surrounding areas. If a zone exhibits significant synchronization of brightness changes with one or more associated zones, the compensation for that zone will automatically incorporate the compensation values ​​of those associated zones when performing compensation for the zone, ensuring a smooth transition between zones. This effectively prevents drastic calibration changes in a single zone from causing on-screen boundaries or color blocks.

[0175] Finally, the system uses the calibration coefficients, adjusted using the linkage weights, as the target calibration coefficients for each zone and distributes them to each zone or chip requiring compensation. This entire process is automated, requiring no human intervention. This enables highly adaptive, dynamic, and smooth compensation control between zones, significantly improving the overall display uniformity and visual quality of the LED display.

[0176] In one embodiment, after step S457, the step further includes:

[0177] S458. Screen adjacent partition pairs based on the target calibration coefficients of all partitions and the spatial adjacency relationship of the partitions to obtain a set of all directly spatially adjacent partition pairs.

[0178] In this embodiment, after completing the linkage adjustment of the partition target calibration coefficients, a regional boundary smoothing step is further introduced to optimize the display continuity between adjacent partitions. First, in step S458, the system determines the spatial adjacency of all partitions on the display screen based on the target calibration coefficients of all partitions and the known spatial adjacency of the partitions. Through this judgment method, the system can filter out all directly adjacent partition pairs in space and obtain a set of partition pairs for subsequent boundary smoothing. The adjacent relationship here usually refers to the partitions that have a physical common boundary or are closest to each other, ensuring that the compensation parameter smoothing process focuses on the position where the actual visual connection effect will be produced.

[0179] S459: Calculate the calibration coefficient difference based on the target calibration coefficients of each pair of adjacent partitions to obtain calibration coefficient difference data between each pair of adjacent partitions;

[0180] Then, in step S459, the system obtains the target calibration coefficients for each pair of adjacent partitions, compares their values, and calculates the calibration coefficient difference between each pair of adjacent partitions. This difference data reflects the magnitude of the calibration coefficient jump between directly adjacent spatial regions after compensation adjustment, providing a quantitative basis for determining whether subsequent smoothing correction is necessary.

[0181] S4510: Compare the calibration coefficient difference data between each pair of adjacent partitions with a preset boundary smoothing threshold to obtain a set of partition pairs whose calibration coefficient differences exceed the threshold, and record them as a set of partition boundaries to be smoothed.

[0182] In step S4510, the system compares the calibration coefficient difference data for all partition pairs obtained in the previous step against a pre-set boundary smoothing threshold. All partition pairs with calibration coefficient differences exceeding this threshold are screened out, forming a set of partition boundaries to be smoothed. This threshold is typically set based on the human eye's sensitivity to sudden changes in brightness or chromaticity, ensuring that only areas that may cause visual discontinuities or color blocks are included in the smoothing process.

[0183] S4511, determining smoothing correction parameters based on the target calibration coefficients of each pair of partitions in the set of partition boundaries to be smoothed, and obtaining a correction amplitude and correction method for each partition to be smoothed;

[0184] For each partition to be smoothed, appropriate smoothing correction parameters are determined based on the actual differences in the target calibration coefficients and the physical layout of the screen. Specifically, the correction amplitude (the amount of compensation required) is determined for each pair of partitions, along with the correction method to be used, such as linear interpolation, weighted averaging, or boundary transition layering. This ensures that the smoothing process eliminates sudden changes without affecting the overall compensation trend of the entire screen.

[0185] Specifically, the system first iterates over the set of partition boundaries to be smoothed. For each pair of partitions, it extracts the target calibration coefficients for the two partitions and calculates the actual difference between them. The correction magnitude and specific correction method for each partition are then determined based on the magnitude of the difference, the physical location of the boundary on the screen, and the overall calibration strategy.

[0186] The correction amount is primarily determined based on the difference between the calibration coefficients of the two zones. For example, based on the actual difference, a tiered approach can be used to select an appropriate correction amount that eliminates sudden changes without excessively disrupting the overall compensation trend of each zone. The correction amount can be half the difference, or a weighted adjustment can be made based on factors such as zone importance, displayed content, and the visual sensitivity of the boundary within the overall screen.

[0187] A variety of algorithmic strategies can be used to select correction methods. For example, for large-area partitions, linear interpolation can be used to gradually adjust the calibration coefficients of two partitions at the boundary, creating a smooth transition in the transition area. For smaller or locally sensitive areas, weighted averaging can be used to adjust the calibration coefficients of the two partitions toward the intermediate value according to a set ratio. In addition, if the boundaries of certain partition pairs involve complex image details or special display content, the system can also use more advanced correction methods such as multi-level decrement / increment or adaptive transition to achieve optimal visual smoothness.

[0188] After the correction parameters are determined, the system will use the correction amplitude and selected correction method for each smoothed partition as the basis for subsequent synchronous adjustments, ensuring that the next adjustment operation can proceed in an orderly manner according to the established strategy. This step lays the foundation for parameter continuity between partitions and is a key part of the entire boundary smoothing process, effectively improving the image uniformity and engineering applicability of the LED display.

[0189] S4512: Synchronously adjust the partition target calibration coefficients according to the correction amplitude and correction method of each partition to be smoothed, to obtain a smoothed and corrected partition target calibration coefficient set;

[0190] Based on the correction magnitude and method obtained in the previous step, the target calibration coefficients for each partition to be smoothed are adjusted synchronously. This synchronous adjustment process can be used to move the calibration coefficients of two adjacent partitions closer to their median values, or to distribute the adjustment according to a weighted distribution, to achieve a smooth transition across the transition zone. The final output is a set of partition target calibration coefficients that have been smoothed to achieve a more continuous spatial distribution across all processed partitions.

[0191] S4513. Based on the synchronous adjustment results of all partition calibration coefficients, perform full-screen calibration coefficient consistency and transition detection to obtain the final target calibration coefficient that meets the boundary continuity and smooth transition requirements.

[0192] Finally, the results of the synchronous adjustment of the calibration coefficients of all partitions are tested for full-screen consistency and boundary transition. The test content includes but is not limited to re-verifying whether the differences in the calibration coefficients of all adjacent partitions are all lower than the smoothing threshold, and judging whether the overall parameter distribution is continuous and smooth. Only when the full-screen calibration coefficients meet the requirements of accurate compensation within the area and achieve smooth transitions on all spatial boundaries, the final target calibration coefficients are output to ensure that the LED display can always present a highly uniform visual effect without obvious faults and color blocks under long-term operation and dynamic compensation. This series of boundary smoothing processing steps effectively solves the problem of compensation mutations that may occur at partition boundaries in traditional compensation algorithms, significantly improving the picture quality and user experience of LED display products.

[0193] Example 2

[0194] See also Figure 4 The embodiment of the present invention provides a device for controlling the quality stability of LED display, the device comprising:

[0195] A first correction module is used to calibrate the LED display screen according to an initial calibration coefficient, wherein the initial calibration coefficient is obtained by performing a mura test on the LED display screen;

[0196] An operating parameter acquisition module is used to collect the operating parameters of each LED chip in the LED display screen in real time during the operation of the calibrated LED display screen;

[0197] A light decay degree acquisition module, configured to acquire the light decay degree of the LED display screen according to the operating parameters and a pre-built chip light decay model;

[0198] a calibration coefficient adjustment module, configured to adjust the initial calibration coefficient according to the light decay degree of the LED display screen to obtain a target calibration coefficient when the light decay degree of the LED display screen meets a preset condition;

[0199] The second correction module is used to correct the LED display screen according to the target calibration coefficient.

[0200] It should be noted that the modules and units in the LED display quality stabilization control device in this embodiment correspond one-to-one to the steps in the LED display quality stabilization control method in the aforementioned embodiment. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned LED display quality stabilization control method, and will not be repeated here.

[0201] Example 3

[0202] In addition, combined Figure 1 The LED display quality stabilization control method according to the embodiment of the present invention can be implemented by an electronic device. Figure 5 A schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present invention is shown.

[0203] An electronic device may include a processor and a memory storing computer program instructions.

[0204] Specifically, the processor may include a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits for implementing the embodiments of the present invention.

[0205] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0206] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology for information storage. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media such as modulated communication signals and carrier waves.

[0207] The processor implements any one of the LED display quality stabilization control methods in the above embodiments by reading and executing computer program instructions stored in the memory.

[0208] In one example, the electronic device may further include a communication interface and a bus. Figure 5 As shown, the processor 401 , the memory 402 , and the communication interface 403 are connected via a bus 410 and communicate with each other.

[0209] The communication interface is mainly used to implement communication between the modules, devices, units and / or equipment in the embodiments of the present invention.

[0210] Bus comprises hardware, software or both, couples the parts of electronic equipment to each other.For example, and not limitation, bus can comprise accelerated graphics port (AGP) or other graphics bus, enhanced industry standard architecture (EISA) bus, front side bus (FSB), hypertransport (HT) interconnection, industry standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations.In suitable cases, bus can comprise one or more buses.Although the embodiment of the present invention describes and shows specific bus, the present invention considers any suitable bus or interconnection.

[0211] Example 4

[0212] In addition, in conjunction with the LED display quality stabilization control method in the above-mentioned embodiments, embodiments of the present invention may provide a computer-readable storage medium for implementation. The computer-readable storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any of the LED display quality stabilization control methods in the above-mentioned embodiments is implemented.

[0213] It should be understood that the present invention is not limited to the specific configurations and processes described above and illustrated in the figures. For the sake of brevity, a detailed description of known methods is omitted. In the above embodiments, several specific steps are described and illustrated as examples. However, the method of the present invention is not limited to the specific steps described and illustrated. Those skilled in the art may make various changes, modifications, and additions, or change the order of the steps after understanding the spirit of the present invention.

[0214] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0215] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0216] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0217] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0218] It should also be noted that the exemplary embodiments described herein describe methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the steps described above. In other words, the steps may be performed in the order described in the embodiments, or in a different order, or several steps may be performed simultaneously.

[0219] The above description is only a specific embodiment of the present invention. Those skilled in the art will clearly understand that for the convenience and brevity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present invention is not limited to this. Any person skilled in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention.

Claims

1. A method for controlling LED display quality stability, characterized in that: The method comprises: Correcting the LED display screen according to an initial calibration coefficient, wherein the initial calibration coefficient is obtained by performing a mura test on the LED display screen; During the operation of the calibrated LED display screen, the operating parameters of each LED chip in the LED display screen are collected in real time; Obtaining the light decay degree of the LED display screen according to the operating parameters and a pre-built chip light decay model; When the light decay degree of the LED display screen meets a preset condition, the initial calibration coefficient is adjusted according to the light decay degree to obtain a target calibration coefficient; The LED display screen is calibrated according to the target calibration coefficient.

2. The LED display quality stabilization control method according to claim 1, characterized in that: During the operation of the calibrated LED display screen, real-time collection of operating parameters of each LED chip in the LED display screen includes: According to the lighting record of the LED display, the lighting time of each LED chip is counted to obtain the cumulative working time; Obtain the operating temperature of each LED chip based on the pre-built temperature database; According to the preset sampling frequency, the working current of each LED chip is collected; According to the operating current, obtaining an average current value of each LED chip during the operating time; The operating parameters are obtained according to the current average, the operating temperature, and the accumulated operating time.

3. The LED display quality stabilization control method according to claim 2, characterized in that: Based on the pre-built temperature database, the operating temperature of each LED chip is obtained, including: According to the physical structure parameters of the LED display and the LED chip arrangement information, a mapping relationship between the physical row and column coordinates of the LED chip and its number is established; After the target LED screen reaches a thermal equilibrium state, obtaining a temperature field distribution image of the target LED screen; According to the mapping relationship, pixel position information of each LED chip in the temperature field distribution image is obtained; Divide the temperature field distribution image according to the pixel position information and a preset deep learning model to obtain a temperature region image of each LED chip; Obtaining a temperature value of each LED chip according to the temperature region image; Establishing the temperature database according to the temperature value and the mapping relationship; The temperature database is queried according to the chip number of each LED chip to obtain the operating temperature of each LED chip.

4. The LED display quality stabilization control method according to claim 3, characterized in that: The temperature field distribution image is divided according to the pixel position information and the trained deep learning model to obtain a temperature region image of each LED chip; Generate a coordinate priori heat map with the same resolution as the temperature field distribution image based on the pixel position information, wherein the center pixel of each LED chip is assigned a value of 1 and the remaining pixels are assigned a value of 0 in the coordinate priori heat map; splicing the temperature field distribution image and the coordinate prior heat map to obtain a dual-channel input tensor; Inputting the dual-channel input tensor into a trained deep learning model to obtain a multi-scale mixed feature of the temperature coordinate, wherein the deep learning model includes a full convolutional network model, a U-Net model, and a regional convolutional neural network model; According to the multi-scale mixed features, the temperature characteristic component corresponding to each pixel point in the infrared temperature field distribution map is obtained to obtain a temperature characteristic map; According to the temperature characteristic map, the first-order difference of each pixel in the horizontal and vertical directions is calculated to obtain the temperature gradient map; Calculate the gradient amplitude of each pixel according to the temperature gradient map and obtain the temperature difference attention weight; Perform weighted fusion based on the temperature difference attention weight and the features of the decoding layer of the deep learning model to obtain a chip area probability map; Performing connected domain screening based on the chip region probability map to obtain a set of candidate chip regions; According to the candidate chip area set and the coordinate prior heat map, the connected domain closest to the center pixel of each LED chip is obtained to obtain the temperature area image of each LED chip.

5. The LED display quality stabilization control method according to claim 2, characterized in that: Obtaining the light decay degree of the LED display screen according to the operating parameters and a pre-built chip light decay model, including: According to the historical operating data of the LED display screen in different operating ranges, a chip light attenuation model under different operating ranges is constructed; determining an actual operating condition range according to the operating parameters; The operating parameters are input into a chip light decay model corresponding to the actual operating condition range to obtain the light decay degree of the LED display.

6. The LED display quality stabilization control method according to claim 5, characterized in that: The method of constructing a chip light attenuation model under different operating conditions based on historical operating data of the LED display under different operating conditions includes: Obtaining an experimental sample set for each operating condition interval based on historical operating data for the operating condition interval; Performing feature extraction on the test sample set to obtain an attenuation feature data set under each operating condition interval; Based on the attenuation characteristic data set, nonlinear regression analysis is performed to obtain the light attenuation mathematical model under each operating condition range; Analyze the attenuation rate under the working condition range according to the light attenuation model to obtain the attenuation rate coefficient; According to the attenuation rate coefficient under different working conditions and the corresponding light attenuation mathematical model, the chip light attenuation model under different working conditions is obtained.

7. The LED display quality stabilization control method according to any one of claims 1 to 6, characterized in that: When the light decay degree of the LED display screen meets a preset condition, the initial calibration coefficient is adjusted according to the light decay degree to obtain a target calibration coefficient, including: Obtaining an actual light decay rate of the LED display screen according to the light decay degree and a preset light decay threshold; Determine the LED chip that needs to be compensated for brightness based on the actual light decay rate of each LED chip and the preset light decay threshold, and obtain the chip that needs to be compensated; Calculate the brightness compensation value of each chip to be compensated according to the actual light decay rate of the chip to be compensated and the preset brightness value; generating a target brightness instruction for each chip requiring compensation according to the brightness compensation value; According to the target brightness instruction and the initial calibration coefficient, the calibration coefficient of each chip to be compensated is adjusted to obtain the target calibration coefficient.

8. An LED display quality stabilization control device, characterized in that: The device comprises: A first calibration module is configured to calibrate the LED display screen according to an initial calibration coefficient, wherein the initial calibration coefficient is obtained by performing a mura test on the LED display screen; An operating parameter acquisition module is used to collect the operating parameters of each LED chip in the LED display screen in real time during the operation of the calibrated LED display screen; A light decay degree acquisition module, configured to acquire the light decay degree of the LED display screen according to the operating parameters and a pre-built chip light decay model; a calibration coefficient adjustment module, configured to adjust the initial calibration coefficient according to the light decay degree of the LED display screen to obtain a target calibration coefficient when the light decay degree of the LED display screen meets a preset condition; The second correction module is used to correct the LED display screen according to the target calibration coefficient.

9. An electronic device, characterized in that: include: At least one processor, at least one memory, and computer program instructions stored in the memory, when the computer program instructions are executed by the processor, implement the method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: Computer program instructions are stored thereon, and when the computer program instructions are executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images