Aging compensation method and device of display panel, display equipment and storage medium

Abstract

The application relates to a burn-in compensation method and device of a display panel, a display equipment and a storage medium, which comprises the following steps: importing a burn-in debugging model, controlling a display panel to be tested to display a target picture with different display patterns and / or different gray scales, collecting luminance data and chrominance data of the display panel to be tested under different test parameter conditions through the burn-in debugging model; establishing a target burn-in model according to the burn-in debugging model, the luminance data and the chrominance data; importing the target burn-in model, opening a compensation switch of the target burn-in model, and verifying a burn-in compensation effect of the target burn-in model on an abnormal display area in the display panel to be tested; after a preset time, opening a data re-burning switch of the target burn-in model, and optimizing compensation parameters of the target burn-in model. The application can effectively improve the 'burn-in' problem of the display panel by standardizing the import process of the burn-in model.

Description

Technical Field

[0001] This application relates to the field of display technology, and in particular to a method, apparatus, display device, and storage medium for de-aging compensation of display panels. Background Technology

[0002] Prolonged exposure to bright screens on a mobile phone can easily lead to "burn-in" damage, leaving a mark on the screen. This adverse effect cannot be remedied by software or algorithms. In related technologies, users typically need to replace their phone screen and avoid using high-brightness mode to prevent brightness degradation, which significantly impacts the user's screen experience. Summary of the Invention

[0003] Therefore, it is necessary to provide a method, apparatus, display device, and storage medium for de-aging compensation of display panels that can standardize the import process of brightness attenuation models in factory environments, effectively optimize the brightness and color uniformity of the display screen, and improve production efficiency, in order to address the above-mentioned technical problems.

[0004] In a first aspect, this application provides a method for de-aging compensation of a display panel, comprising:

[0005] Import the de-aging debugging model and control the display panel under test to display the target image. Collect the brightness and color data of the display panel under test under different test parameter conditions through the de-aging debugging model. The test parameters include grayscale, temperature, brightness level and continuous lighting time. The target image includes multiple display images with different display patterns and / or different grayscale.

[0006] A target de-aging model is established based on the de-aging debugging model, the brightness data, and the chromaticity data. The target de-aging model is used to perform de-aging compensation on abnormal display areas in the display panel to be tested. The abnormal display areas include areas with uneven brightness. The target de-aging model includes a compensation switch and a data burn-back switch.

[0007] Import the target de-aging model, turn on the compensation switch of the target de-aging model, and verify the de-aging compensation effect of the target de-aging model on the abnormal display area in the test display panel.

[0008] After a preset time, the data burn-back switch of the target de-aging model is turned on, and the compensation parameters of the target de-aging model are optimized.

[0009] In one embodiment, the de-aging debugging model is a deep belief network model, including an accumulation calculation sub-model and a compensation calculation sub-model;

[0010] The step of establishing a target de-aging model based on the de-aging adjustment model, the luminance data, and the chrominance data includes:

[0011] The brightness data and chromaticity data are analyzed by the cumulative calculation sub-model to obtain the lifespan curve of the display panel under test under different test parameter conditions;

[0012] The lifetime curve is processed by the compensation calculation sub-model to calculate the compensation parameters of the display panel under test.

[0013] Based on the mapping relationship between the luminance data, the chromaticity data, and the compensation parameters, the target de-aging model is established;

[0014] Preferably, the lifetime curves under different test parameter conditions include lifetime curves corresponding to the grayscale domain, lifetime curves corresponding to the time domain, lifetime curves corresponding to the temperature domain, and lifetime curves corresponding to the brightness level domain.

[0015] Preferably, the lifetime curves include the lifetime curves corresponding to R pixel units, B pixel units, and G pixel units;

[0016] Preferably, the compensation calculation sub-model includes compensation parameter calculation algorithms corresponding to different test parameter conditions. The corresponding life curve is processed by the compensation parameter calculation algorithm under the same test parameter conditions to calculate the compensation parameters of the display panel under test under the corresponding test parameter conditions.

[0017] Preferably, the cumulative calculation sub-model burns the lifetime curve to a preset storage space every preset time interval;

[0018] Preferably, the compensation calculation sub-model extracts the lifetime curve from the preset storage space and determines the compensation value based on the data usage ratio and the accumulated time value;

[0019] Preferably, the Block size in the deep belief network model is set to m×n, where m and n are both positive integers, and the maximum value of both m and n is 4.

[0020] In one embodiment, after establishing the target de-aging model based on the de-aging debugging model, the luminance data, and the chrominance data, the method further includes:

[0021] The bin file of the target de-aging model is integrated into the brightness unevenness defect compensation process. By writing the compensation parameters of the target de-aging model into the brightness unevenness defect compensation lookup table, de-aging compensation is performed on the abnormal display area in the display panel under test.

[0022] In one embodiment, verifying the de-aging compensation effect of the target de-aging model on abnormal display areas in the display panel under test includes:

[0023] Obtain the output data and prediction data of the target de-aging model;

[0024] Calculate the difference between the output data and the predicted data;

[0025] If the difference is greater than a preset difference threshold, it is determined that the target deaging model is abnormal;

[0026] If the difference is less than or equal to the preset difference threshold, the target deaging model is determined to be normal.

[0027] In one embodiment, after verifying the de-aging compensation effect of the target de-aging model on abnormal display areas in the test display panel, the method further includes:

[0028] When it is determined that the target de-aging model is abnormal, the display device under test that deployed the target de-aging model is marked, and a preset alarm process is executed, wherein the preset alarm process is used to prompt the marked display device under test that is abnormal.

[0029] In one embodiment, optimizing the compensation parameters of the target de-aging model includes:

[0030] Configure the accumulated data characteristics of the accumulated calculation sub-model;

[0031] Before performing the burn-in test on the display panel to be tested, the first color curve of the display panel to be tested is measured;

[0032] The display panel to be tested is subjected to a branding test, and the accumulated data features in the preset storage area are updated according to a preset cycle.

[0033] After performing a burn-in test on the display panel under test, the second color tone curve of the display panel under test is measured, and the burn-in characteristics are compared with the first color tone curve and the second color tone curve.

[0034] Generate corresponding compensation parameters based on the branding characteristics and the accumulated data features;

[0035] The target de-aging model is activated to verify the de-aging compensation effect of the compensation parameters on the branded area;

[0036] When it is determined that the de-aging compensation effect of the compensation parameter is abnormal, the compensation parameter shall be optimized and adjusted.

[0037] Preferably, the accumulated data feature is a current feature.

[0038] Secondly, this application also provides an anti-aging compensation device for a display panel, comprising:

[0039] The data collection module is used to import the de-aging debugging model and control the display panel under test to display the target image. The de-aging debugging model collects the brightness and color data of the display panel under test under different test parameters. The test parameters include grayscale, temperature, brightness level and continuous lighting time. The target image includes multiple display images with different display patterns and / or different grayscale.

[0040] The model building module is used to build a target de-aging model based on the brightness data and the chromaticity data. The target de-aging model is used to perform de-aging compensation on abnormal display areas in the display panel under test. The abnormal display areas include areas with uneven brightness. The target de-aging model includes a compensation switch and a data burn-back switch.

[0041] The compensation test module is used to import the target de-aging model, turn on the compensation switch of the target de-aging model, and verify the de-aging compensation effect of the target de-aging model on the abnormal display area in the display panel under test.

[0042] The data burn-back module is used to turn on the data burn-back switch of the target de-aging model after a preset time, and optimize the compensation parameters of the target de-aging model according to the de-aging compensation effect.

[0043] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the de-aging compensation method for the display panel described in the first aspect.

[0044] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the de-aging compensation method for the display panel described in the first aspect.

[0045] Fifthly, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the de-aging compensation method for the display panel described in the first aspect.

[0046] In summary, this application proposes a method, apparatus, display device, and storage medium for de-aging compensation of display panels, comprising: importing a de-aging debugging model and controlling the display panel under test to display target images with different display patterns and / or different grayscale levels; collecting brightness and chromaticity data of the display panel under test under different test parameter conditions through the de-aging debugging model; establishing a target de-aging model based on the de-aging debugging model, brightness data, and chromaticity data; importing the target de-aging model, activating the compensation switch of the target de-aging model, and verifying the de-aging compensation effect of the target de-aging model on abnormal display areas in the display panel under test; and after a preset time, activating the data burn-back switch of the target de-aging model and optimizing the compensation parameters of the target de-aging model. This invention, by standardizing the import process of the de-aging model, can effectively improve the "burn-in" problem of display panels. Attached Figure Description

[0047] Figure 1 This is a diagram illustrating the application environment of an anti-aging compensation method for a display panel in one embodiment.

[0048] Figure 2 This is a flowchart illustrating an anti-aging compensation method for a display panel in one embodiment.

[0049] Figure 3 This is a schematic diagram of the target image displayed on the display panel to be tested in one embodiment;

[0050] Figure 4 This is a schematic diagram of the operation logic of the cumulative calculation model in one embodiment;

[0051] Figure 5 This is a schematic diagram of the operating logic of the compensation calculation model in one embodiment;

[0052] Figure 6 This is a flowchart illustrating the steps involved in establishing a target DBI model in one embodiment.

[0053] Figure 7 This is a schematic diagram of the steps for optimizing compensation parameters in one embodiment;

[0054] Figure 8 This is a structural block diagram of the anti-aging compensation device of a display device in one embodiment;

[0055] Figure 9 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0056] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0057] Before describing the technical solutions provided in the embodiments of this application, in order to facilitate understanding of the embodiments of this application, this application first specifically explains the problems existing in the related technologies:

[0058] In related technologies, displays are prone to screen burn-in when displaying high-brightness images for extended periods. Screen burn-in refers to permanent image retention that occurs after a display device has been displaying static images for a long time. The main cause of screen burn-in is uneven aging of the display materials, leading to display abnormalities such as brightness unevenness defects (mura). A common method to solve screen burn-in is to achieve brightness equalization of the display module based on de-burn-in (DBI) compensation schemes. However, in factory production and testing environments, there is no standardized execution procedure for de-burn-in compensation, and the DBI compensation scheme in display devices is prone to failure. This forces users to avoid prolonged use of high-brightness screens, resulting in inconvenience and failing to meet user needs.

[0059] The anti-aging compensation method for display panels provided in this application embodiment can be applied to, for example... Figure 1 The application environment shown. Among them, Figure 1 An aging test apparatus is provided for performing aging tests on a display panel under test. In this embodiment, aging test refers to a test process that simulates the long-term high-load operation of a product to detect potential faults and performance degradation. In practical applications, by controlling the display device under test to simulate long-term high-brightness display, potential problems such as brightness decay and color deviation in the display panel can be exposed in advance.

[0060] The aging test apparatus includes a computer device 110, a lamp-lighting platform 120, a horizontal stage 130, a calibration component 140, and a camera component 150. The computer device 110 is communicatively connected to the lamp-lighting platform 120, the horizontal stage 130, the calibration component 140, and the camera component 150. This aging test apparatus is used to perform aging tests on display panels and imports corresponding de-aging models into the display panels via the computer device 110 to implement the de-aging compensation method provided in this embodiment.

[0061] In this embodiment, the horizontal stage 130 is used to place the display panel to be tested at a certain angle, for example, keeping the display module of the display panel to be tested horizontal, so that the target image displayed by the display module can be accurately captured when capturing the display screen of the display panel to be tested. Furthermore, the horizontal stage 130 can adjust the placement angle of the display panel to be tested according to the control commands below the computer device 110, so that the camera component 150 can completely capture the target image displayed by the display module of the display panel.

[0062] The lighting platform 120 is connected to the display panel to be tested, which is placed on the horizontal platform 130. When the test begins, the lighting platform 120 is used to light up all the display modules of the display panel to be tested. After the display modules are lit up, the computer device 110 inputs a picture with a special pattern to the display panel to be tested so that the display panel to be tested displays the target image.

[0063] The calibration component 140 includes a position detection sensor for locating the position information of the display panel under test on the horizontal stage 130 and sending the position information of the display panel under test to the computer device 110. The computer device 110 determines whether to start the aging test based on the position information of the display panel under test. In one embodiment, when the position information of the display panel under test belongs to a preset position area, the computer device 110 determines to start the aging test. The preset position area can be configured according to the needs of the actual application scenario; for example, the preset position area can be configured to be located in the horizontal placement area of ​​the horizontal stage 130.

[0064] The camera assembly 150 includes an industrial camera, etc., used to capture the display screen of the display panel under test. The display screen is then transmitted to the computer device 110 for analysis of the brightness and color data of the display panel under test.

[0065] In one embodiment, such as Figure 2 As shown, a method for de-aging compensation of a display panel is provided, which is applied to... Figure 1 Taking the aging test apparatus in the example, the following steps are included:

[0066] S201, import the de-aging debugging model and control the display panel under test to display the target image. Collect the brightness and color data of the display panel under test under different test parameter conditions through the de-aging debugging model. The test parameters include gray scale, temperature, display brightness value (DBV) and continuous lighting time. The target image includes multiple display images with different display patterns and / or different gray scales.

[0067] In this embodiment, before starting the aging test, a DBI debugging model is first imported into the display panel under test. The DBI debugging model collects a large amount of model training data, providing a foundation for training the subsequent compensation parameter calculation algorithm. The DBI debugging model can employ a Deep Belief Network (DBN) model. A DBN model, as a probabilistic generative model, is composed of multiple layers of Restricted Boltzmann Machines (RBMs). In this embodiment, the DBI debugging model can capture the inherent characteristics of the brightness and chromaticity data of the display panel under test through unsupervised learning (enabling the compensation switch), and then optimize the network performance through supervised fine-tuning (enabling the data burn-in switch). This embodiment learns the aging pattern of the panel under test through the DBI debugging model, predicts performance degradation, and determines the compensation parameters.

[0068] In this embodiment, the specific control steps for controlling the display panel to display the target image can refer to the specific control steps of the lighting platform and computer equipment of the aging test experimental apparatus in the foregoing embodiments. That is, the lighting platform illuminates the display module of the display panel, and the computer equipment transmits the target image to the display panel.

[0069] In this embodiment, the target screen can be a display screen with a special display pattern and / or different grayscale values. The display pattern can be a checkerboard pattern, a gradient image, or similar patterns. For example, the target screen can be... Figure 3 The image shown includes a special display pattern and different grayscale values. In this embodiment, the specific type of display pattern in the target image and the actual situation of the gradient grayscale values ​​can be configured according to the needs of the actual application scenario. The gradient grayscale values ​​can gradually change from grayscale level 0 to grayscale level 255 to ensure that the aging-out debugging model can measure the brightness and chromaticity of each grayscale level. It should be understood that, as... Figure 3 As shown, the grayscale values ​​can also be gradually changed from 255, 192, 128 to 64.

[0070] In this embodiment, brightness data includes brightness decay data, and chromaticity data includes color shift data. While controlling the display panel under test to display the target image, the lighting platform continuously illuminates the display panel to simulate a long-term display scenario. During the aging test, test parameters such as grayscale, temperature, brightness level, and continuous illumination time are configured to simulate the brightness decay and color shift of the display panel under real-world conditions. The brightness data collected by the aging-de-aging debugging model in this embodiment can generate brightness decay curves under various test parameter conditions. The chromaticity data collected by the aging-de-aging debugging model in this embodiment can generate color shift curves under various test parameter conditions.

[0071] Based on the above steps, by simulating various real-world application scenarios of the display panel under test, and considering the brightness decay and color shift characteristics under different DBV, grayscale, temperature, and time test conditions, it is possible to ensure the simulation of real-world application environments. This guarantees that the DBI model can be built with reference to multiple test conditions, ensuring the DBI model's detection efficiency and compensation effect for display anomalies under various test environments. Furthermore, this implementation uses a DBN model structure to form a DBI debugging model, and then uses the DBI debugging model to collect brightness and chromaticity data. This allows for efficient and accurate pre-training of the target DBI model, resulting in a target DBI model capable of accurately performing de-aging compensation.

[0072] S202, establish a target de-aging model based on the de-aging debugging model, brightness data and chromaticity data. The target de-aging model is used to de-age compensation for abnormal display areas in the display panel to be tested. Abnormal display areas include areas with uneven brightness. The target de-aging model includes a compensation switch and a data burn-back switch.

[0073] In this embodiment, based on the DBN network structure of the DBI debugging model and the luminance and chromaticity data of the display panel under test under various test conditions collected by the DBI debugging model, multiple compensation parameter calculation algorithms corresponding to different test conditions can be trained. Each compensation parameter calculation algorithm can determine the corresponding compensation parameter based on the luminance and chromaticity data. The compensation parameters are used to adjust for luminance attenuation and color shift. By combining the above compensation parameter calculation algorithms with the DBN network architecture, a target DBI model capable of achieving DBI compensation can be established.

[0074] In this embodiment, the target DBI model is configured with three switches: a master switch, a compensation switch, and a data burn-back switch.

[0075] When the main switch is turned on, the target DBI model starts and performs model initialization, training, and inference. When the main switch is on, the compensation switch and / or data re-training switch can also be activated. When the main switch is off, both the compensation switch and the data re-training switch are off. In practical applications, during the pre-training phase of the target DBI model, both the compensation switch and the data re-training switch are kept off; only the main switch is turned on to start the DBN network for unsupervised learning to collect sample data.

[0076] When the compensation switch is activated, the target DBI model continuously monitors the deviation between the output value and the expected value. If the deviation exceeds a preset threshold, such as a brightness error greater than 5%, the target DBI model is deemed abnormal. In one embodiment, when the target DBI model malfunctions, an alarm can be triggered on the display panel or the production line alarm mechanism can be activated to investigate the abnormal display panel. In other words, the compensation switch of the target DBI model primarily enables real-time dynamic adjustment of the DBN network output to compensate for the impact of external factors (such as changes in ambient temperature or hardness aging) on ​​the performance of the target DBI model. When the compensation switch is activated, the target DBI model can automatically adjust the display signal based on the current brightness decay trend of the relevant area of ​​the display panel to maintain the display brightness of the relevant area at the target brightness. The target brightness is the brightness required to be displayed in the relevant area.

[0077] When the data burn-back switch is enabled, newly acquired data is fed back to the DBN network to fine-tune the model parameters of the target DBI model, such as weights or biases. In other words, the data burn-back switch for the target DBI model controls the feedback update process of the training data.

[0078] It's important to know that when the compensation switch is enabled, the target DBI model can be used to determine abnormal display areas based on the chromaticity and luminance data of relevant areas of the display panel, and generate compensation parameters for the corresponding pixels within those abnormal display areas. These compensation parameters can be luminance or chromaticity values. In practical applications, the luminance value can be a grayscale value.

[0079] Based on the above steps, this embodiment establishes a target DBI model capable of detecting abnormal display areas and performing aging compensation, using sample data (chromaticity data and luminance data) collected under various test parameter conditions from a DBN network. This significantly increases the detection sensitivity of the DBI model. Furthermore, because test parameters such as DBV data, temperature data, and grayscale data are considered during sample data collection, the target DBI model can adapt to various factory aging test environments, achieving accurate compensation for the display panel.

[0080] S203, import the target de-aging model, turn on the compensation switch of the target de-aging model, and verify the de-aging compensation effect of the target de-aging model on the abnormal display area in the test display panel.

[0081] In this embodiment, during the factory aging test, the target DBI model is imported into the display panel to be tested, and the compensation switch of the target DBI model is turned on. The de-aging compensation effect of the target DBI model on the abnormal display area in the display panel to be tested is determined by the output value and the predicted value of the target DBI model.

[0082] S204 After a preset time, turn on the data burn-back switch of the target de-aging model and optimize the compensation parameters of the target de-aging model.

[0083] In practical applications, if the collected data is not filtered, or if the target DBI model is not yet stable before starting the data burn-in, noise or incorrect labels may be introduced during the burn-in process, leading to overfitting or parameter drift in the target DBI model. For example, during aging tests on the display panel under test, if the DBN network burns in display panel data containing temporary faults, it may mislead the optimization direction of the target DBI model. Burning in unfiltered anomalous data (such as brightness spikes caused by hardware failures) can lead to incorrect model learning patterns. Burning in data during the pre-training phase (e.g., before RBM layer-by-layer training is complete) will impair the feature extraction capabilities of the target DBI model. When the distribution of new data and the original training data is inconsistent, backpropagation will force parameter adjustments to fit the new data, resulting in the loss of original features.

[0084] In this embodiment, by activating the compensation switch of the target deaging model after a preset time interval, and then activating the data burn-back switch of the target deaging model, the problem of incorrect optimization direction of the target DBI model is ensured during the model pre-training stage, fine-tuning stage, and deployment stage, which greatly guarantees the reliability and accuracy of the target DBI model.

[0085] It should be noted that in some feasible embodiments, the decision to enable the data retraining switch can also be determined by monitoring the data usage at each stage of the target DBI model. For example, the data retraining switch can be enabled when it is determined that anomalous data has been filtered, the pre-training phase of the target DBI model has been completed, and the distribution of new data is consistent with that of the original training data. The activation conditions for the data retraining switch can be adaptively configured while ensuring the effectiveness of the target DBI model.

[0086] In summary, the anti-aging compensation method for display panels proposed in this embodiment is mainly based on the deployment of the DBI model on the display panel side in the factory production testing environment after steps S201-S204. While ensuring that the target DBI model can output compensation parameters stably and reliably, the dynamic optimization (data burn-back switch) of the target DBI model on the display panel side is realized through the DBN network structure. This ensures the efficiency of aging testing of the display panel in the factory environment, as well as the anti-aging effect of the display panel, and meets the user's functional requirements for the display panel.

[0087] like Figure 6 As shown, a target de-aging model is established based on the de-aging adjustment model, luminance data, and chrominance data, including:

[0088] S601 analyzes the brightness and chromaticity data through an accumulation calculation sub-model to obtain the lifespan curve of the display panel under test under different test parameter conditions.

[0089] In this embodiment, the DBI debugging model includes, for example... Figure 4 The cumulative calculation sub-model shown and, for example Figure 5 The compensation calculation sub-model is shown. The accumulation calculation sub-model continuously collects pixel data, temperature data, and brightness level data from the display panel under test as it displays the target image according to corresponding test parameters. The pixel data includes R pixels, B pixels, and G pixels. In practical applications, the accumulation calculation sub-model can be implemented using multi-layer RBM stacking. Each RBM layer learns features of different aging stages, such as brightness decay and color shift. Through layer-by-layer pre-training of the RBMs, aging features can be captured in stages. Finally, the accumulation calculation sub-model sums the features obtained from each layer to form a global description of the aging trajectory, thus obtaining the lifespan curve of the display panel under test under different test parameter conditions.

[0090] In feasible embodiments, the lifetime curves under different test parameter conditions include lifetime curves corresponding to the grayscale domain, the time domain, the temperature domain, and the brightness level domain. This embodiment divides the lifetime curves by grayscale, time, temperature, and brightness level domains, allowing for the establishment of compensation parameter calculation algorithms corresponding to the grayscale, time, temperature, and brightness levels respectively when building the target DBI model. It should be noted that the compensation parameter calculation algorithms can calculate the display look-up table (LUT) separately.

[0091] In feasible embodiments, the lifetime curves include lifetime curves corresponding to R pixel units, B pixel units, and G pixel units. By establishing lifetime curves for R, G, and B pixels respectively, compensation parameters for all points of the display module of the display panel can be calculated, thereby achieving global compensation for the display panel.

[0092] In feasible embodiments, the compensation calculation sub-model includes compensation parameter calculation algorithms corresponding to different test parameter conditions. The corresponding lifetime curve is processed using the compensation parameter calculation algorithms under the same test parameter conditions to calculate the compensation parameters of the display panel under test under the corresponding test parameter conditions. This embodiment, by constructing multiple compensation parameter calculation algorithms corresponding to different test parameter conditions, makes the target DBI model applicable to various environments, ensuring the detection and compensation effects of the target DBI model for abnormal areas.

[0093] S602 processes the lifespan curve through a compensation calculation sub-model to calculate the compensation parameters of the display panel under test.

[0094] In this embodiment, the compensation calculation sub-model can accurately predict the performance degradation of the display panel under test by analyzing the lifetime curve, including brightness degradation and color shift. The compensation calculation sub-model dynamically adjusts the display parameters based on the brightness degradation and color shift to obtain compensation parameters for abnormal display areas, thereby compensating for the performance degradation in those areas.

[0095] In this embodiment, the compensation calculation sub-model determines the compensation value based on the data usage ratio and the accumulated time value. The data usage ratio refers to the frequency of use of various test parameters during the DBN model training process. For example, the frequency / percentage of grayscale usage during DBN model training. The accumulated time value refers to the total running time of the DBN model.

[0096] In this embodiment, the calculation algorithm for the compensation calculation sub-model can be a weighted accumulation algorithm.

[0097] S603 establishes a target de-aging model based on the mapping relationship between luminance data, chrominance data and compensation parameters.

[0098] In this embodiment, after acquiring and analyzing the lifetime curve from luminance and chrominance data based on the accumulation calculation sub-model and the compensation calculation sub-model, and calculating the compensation parameters, a target de-aging model can be established based on the mapping relationship between luminance and chrominance data and compensation parameters, i.e., the compensation parameter calculation algorithm.

[0099] In this embodiment, the target de-aging model is generated based on the DBN network. The generation scheme for the target de-aging model can be determined with reference to the actual structure of the DBN network.

[0100] In feasible embodiments, such as Figure 4 and Figure 5 As shown, the cumulative calculation sub-model burns the lifetime curve to a preset storage space at preset intervals. This preset storage space includes the SRAM and Flash memory in the display panel. The compensation calculation sub-model extracts the lifetime curve from the preset storage space to calculate the compensation parameters. In practical applications, the burning interval of the cumulative calculation sub-model can be set to 300 seconds (s) or other values.

[0101] In a feasible embodiment, the block size in the deep belief network (DBN) model is set to m×n, where m and n are both positive integers, and the maximum value of both m and n is 4. In this embodiment, the block size of the DBN model is set to 4×4 or smaller, which can significantly improve the effect of removing text and other markings on the display panel under test.

[0102] Based on the above steps, the target DBI model can be established through the DBN network model. The target DBI model establishes corresponding compensation parameter calculation algorithm channels for RGB multi-pixel channels, which can calculate the compensation parameters for the corresponding R pixels, G pixels and B pixels respectively, so as to achieve whole-area compensation for the display module.

[0103] In one embodiment, after establishing a target de-aging model based on the de-aging adjustment model, brightness data, and chromaticity data, the de-aging compensation method for the display panel further includes:

[0104] The target de-aging model's bin file is integrated into the brightness unevenness defect compensation process. By writing the compensation parameters of the target de-aging model into the brightness unevenness defect compensation lookup table, de-aging compensation is achieved for abnormal display areas in the display panel under test.

[0105] In this embodiment, after integrating the bin file of the target DBI model into the brightness unevenness defect compensation process, the compensation parameter calculation algorithm in the target DBI model can generate lookup table (LUT) parameters corresponding to various test parameter conditions, so as to directly realize the automatic adjustment of the display signal in the Demura process, that is, to realize the de-aging compensation of abnormal display areas in the display panel under test.

[0106] In one embodiment, such as Figure 7 As shown, the compensation parameters for optimizing the target de-aging model include:

[0107] S701, configure the accumulated data characteristics of the accumulated calculation sub-model.

[0108] S702, before performing a burn-in test on the display panel to be tested, measures the first color curve of the display panel to be tested.

[0109] S703 performs a burn-in test on the display panel under test and updates the accumulated data features in the preset storage area according to a preset cycle.

[0110] S704, after performing a burn-in test on the display panel to be tested, measures the second color tone curve of the display panel to be tested, and compares the burn-in characteristics based on the first color tone curve and the second color tone curve.

[0111] S705 generates corresponding compensation parameters based on the branding characteristics and accumulated data features.

[0112] S706, Start the target de-aging model to verify the de-aging compensation effect of the compensation parameters on the branded area.

[0113] S707: When it is determined that the de-aging compensation effect of the compensation parameters is abnormal, the compensation parameters are optimized and adjusted.

[0114] In this embodiment, the accumulated data feature can be the current feature. The optimization process of the compensation parameters of the target de-aging model can be summarized as follows: a burn-in experiment is performed with only the accumulated current feature data to screen out the compensation parameters that have poor compensation effect during the burn-in experiment, and these compensation parameters are dynamically adjusted to ensure that the compensation parameters output by the target DBI model can effectively compensate for abnormal display areas in the display panel under test.

[0115] By configuring the accumulated data characteristics stored in Flash using the accumulated calculation sub-model, i.e., setting the accumulated calculation sub-model to current mode, the accumulated calculation sub-model values ​​can be stored in Flash as current characteristics. Before starting the burn-in test, initial parameters are measured, i.e., the first gamma curve of the display panel under test before burn-in, to facilitate subsequent comparison of burn-in characteristics. The aging test device is controlled to perform burn-in tests on the display panel under test, and the current characteristic data in Flash is continuously updated during the burn-in test. At this time, no compensation parameters are generated, and brightness is measured periodically. After the burn-in test is completed, the second gamma curve of the display panel after burn-in is measured and compared with the first gamma curve to obtain the burn-in characteristics, i.e., brightness decay characteristics and color shift characteristics, which can also be understood as obtaining the lifespan curve. A corresponding current pair compensation value lookup table (LUT) is generated based on the burn-in characteristics and accumulated data characteristics. The compensation switch of the target DBI model is turned on, and the current-to-compensation lookup table (LUT) is input into the DBN network to verify the compensation effect of the compensation parameter. The specific verification steps can refer to the specific steps for verifying the compensation effect when the compensation switch is turned on in the previous embodiment, which will not be repeated here. For compensation parameters with poor compensation effect, that is, the difference between the output value and the predicted value is greater than the preset threshold, adaptive optimization is performed to achieve dynamic optimization of the compensation parameters for the target DBI model.

[0116] In a more detailed embodiment, the steps of the display panel de-aging compensation method can be summarized as follows:

[0117] The first step is to import the DBI debugging model and collect the brightness and color data of the display device under test under different test parameters for different gray levels and special patterns.

[0118] The second step involves establishing compensation parameter calculation algorithms for various test parameter conditions based on the brightness and chromaticity data collected from the DBI debugging model. A target DBI model is then built based on the DBN network, and the bin file of the target DBI model is integrated into the Demura process to achieve automatic compensation for abnormal display areas in the display panel under test.

[0119] The third step is to import the target DBI model into the display panel to be tested and turn on the compensation switch of the target DBI model. Based on the output value and prediction value of the target DBI model, it is determined whether the target DBI model is abnormal, and the display panel with the abnormal target DBI model is intercepted through alarms and other means.

[0120] The fourth step is to turn on the data burn-back switch of the target DBI model after a preset time, and dynamically optimize the target DBI model based on the newly collected data on the display panel to improve the display optimization effect of the target DBI model.

[0121] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0122] Based on the same inventive concept, this application also provides a display panel de-aging compensation device for implementing the aforementioned display panel de-aging compensation method. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations of one or more display panel de-aging compensation device embodiments provided below can be found in the limitations of the display panel de-aging compensation method described above, and will not be repeated here.

[0123] In one embodiment, such as Figure 8 As shown, an aging compensation device 800 for a display panel is provided, comprising: a data collection module 810, a model building module 820, a compensation testing module 830, and a data burn-back module 840, wherein:

[0124] The data collection module 810 is used to import the de-aging debugging model and control the display panel under test to display the target image. The de-aging debugging model collects the brightness and color data of the display panel under test under different test parameter conditions. The test parameters include grayscale, temperature, brightness level and continuous lighting time. The target image includes multiple display images with different display patterns and / or different grayscale.

[0125] The model building module 820 is used to build a target de-aging model based on the brightness data and the chromaticity data. The target de-aging model is used to perform de-aging compensation on abnormal display areas in the display panel to be tested. The abnormal display areas include areas with uneven brightness. The target de-aging model includes a compensation switch and a data burn-back switch.

[0126] The compensation test module 830 is used to import the target de-aging model, turn on the compensation switch of the target de-aging model, and verify the de-aging compensation effect of the target de-aging model on the abnormal display area in the display panel under test.

[0127] The data burn-back module 840 is used to turn on the data burn-back switch of the target de-aging model after a preset time, and optimize the compensation parameters of the target de-aging model according to the de-aging compensation effect.

[0128] In one embodiment, the model building module 820 is specifically used to analyze the brightness data and the chromaticity data through the cumulative calculation sub-model to obtain the lifespan curve of the display panel under test under different test parameter conditions; process the lifespan curve through the compensation calculation sub-model to calculate the compensation parameters of the display panel under test; and establish the target de-aging model according to the mapping relationship between the brightness data, the chromaticity data and the compensation parameters.

[0129] In one embodiment, the model building module 820 is specifically used to integrate the bin file of the target de-aging model into the brightness unevenness defect compensation process, so as to realize the de-aging compensation of the abnormal display area in the display panel under test by writing the compensation parameters of the target de-aging model into the brightness unevenness defect compensation lookup table.

[0130] In one embodiment, the compensation test module 830 is specifically used to acquire the output data and prediction data of the target deaging model; calculate the difference between the output data and the prediction data; determine that the target deaging model is abnormal if the difference is greater than a preset difference threshold; and determine that the target deaging model is normal if the difference is less than or equal to the preset difference threshold.

[0131] The data burn-back module 840 is specifically used to configure the accumulated data characteristics of the accumulated calculation sub-model; before performing a burn-in test on the display panel under test, it measures the first hue curve of the display panel under test; it performs a burn-in test on the display panel under test and updates the accumulated data characteristics in the preset storage area according to a preset cycle; after performing a burn-in test on the display panel under test, it measures the second hue curve of the display panel under test and compares the burn-in characteristics based on the first hue curve and the second hue curve; it generates corresponding compensation parameters based on the burn-in characteristics and the accumulated data characteristics; it starts the target de-aging model to verify the de-aging compensation effect of the compensation parameters on the burn-in area; and when it is determined that the de-aging compensation effect of the compensation parameters is abnormal, it optimizes and adjusts the compensation parameters.

[0132] Each module in the aforementioned aging compensation device for the display panel can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0133] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 9 As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a method for de-aging compensation of a display panel. The display unit of the computer device forms a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0134] Those skilled in the art will understand that Figure 9 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0135] In one embodiment, a display device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the aforementioned method embodiments.

[0136] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the aforementioned method embodiments.

[0137] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the foregoing method embodiments.

[0138] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0139] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0140] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for de-aging compensation of a display panel, characterized in that, include: Import the de-aging debugging model and control the display panel under test to display the target image. Collect the brightness and color data of the display panel under test under different test parameter conditions through the de-aging debugging model. The test parameters include grayscale, temperature, brightness level and continuous lighting time. The target image includes multiple display images with different display patterns and / or different grayscale. A target de-aging model is established based on the de-aging debugging model, the brightness data, and the chromaticity data. The target de-aging model is used to perform de-aging compensation on abnormal display areas in the display panel to be tested. The abnormal display areas include areas with uneven brightness. The target de-aging model includes a compensation switch and a data burn-back switch. Import the target de-aging model, turn on the compensation switch of the target de-aging model, and verify the de-aging compensation effect of the target de-aging model on the abnormal display area in the test display panel. After a preset time, the data burn-back switch of the target de-aging model is turned on, and the compensation parameters of the target de-aging model are optimized.

2. The method according to claim 1, characterized in that, The de-aging debugging model is a deep belief network model, which includes an accumulation calculation sub-model and a compensation calculation sub-model. The step of establishing a target de-aging model based on the de-aging adjustment model, the luminance data, and the chrominance data includes: The brightness data and chromaticity data are analyzed by the cumulative calculation sub-model to obtain the lifespan curve of the display panel under test under different test parameter conditions; The lifetime curve is processed by the compensation calculation sub-model to calculate the compensation parameters of the display panel under test. Based on the mapping relationship between the luminance data, the chromaticity data, and the compensation parameters, the target de-aging model is established; Preferably, the lifetime curves under different test parameter conditions include lifetime curves corresponding to the grayscale domain, lifetime curves corresponding to the time domain, lifetime curves corresponding to the temperature domain, and lifetime curves corresponding to the brightness level domain. Preferably, the lifetime curves include the lifetime curves corresponding to R pixel units, B pixel units, and G pixel units; Preferably, the compensation calculation sub-model includes compensation parameter calculation algorithms corresponding to different test parameter conditions. The corresponding life curve is processed by the compensation parameter calculation algorithm under the same test parameter conditions to calculate the compensation parameters of the display panel under test under the corresponding test parameter conditions. Preferably, the cumulative calculation sub-model burns the lifetime curve to a preset storage space every preset time interval; Preferably, the compensation calculation sub-model extracts the lifetime curve from the preset storage space and determines the compensation value based on the data usage ratio and the accumulated time value; Preferably, the Block size in the deep belief network model is set to m×n, where m and n are both positive integers, and the maximum value of both m and n is 4.

3. The method according to claim 1, characterized in that, After establishing the target de-aging model based on the de-aging adjustment model, the luminance data, and the chrominance data, the method further includes: The bin file of the target de-aging model is integrated into the brightness unevenness defect compensation process. By writing the compensation parameters of the target de-aging model into the brightness unevenness defect compensation lookup table, de-aging compensation is performed on the abnormal display area in the display panel under test.

4. The method according to claim 1, characterized in that, The verification of the de-aging compensation effect of the target de-aging model on the abnormal display area in the test display panel includes: Obtain the output data and prediction data of the target de-aging model; Calculate the difference between the output data and the predicted data; If the difference is greater than a preset difference threshold, it is determined that the target deaging model is abnormal; If the difference is less than or equal to the preset difference threshold, the target deaging model is determined to be normal.

5. The method according to claim 4, characterized in that, After verifying the de-aging compensation effect of the target de-aging model on the abnormal display area in the test display panel, the method further includes: When it is determined that the target de-aging model is abnormal, the display device under test that deployed the target de-aging model is marked, and a preset alarm process is executed, wherein the preset alarm process is used to prompt the marked display device under test that is abnormal.

6. The method according to claim 2, characterized in that, The compensation parameters for optimizing the target de-aging model include: Configure the accumulated data characteristics of the accumulated calculation sub-model; Before performing the burn-in test on the display panel to be tested, the first color curve of the display panel to be tested is measured; The display panel to be tested is subjected to a branding test, and the accumulated data features in the preset storage area are updated according to a preset cycle. After performing a burn-in test on the display panel under test, the second color tone curve of the display panel under test is measured, and the burn-in characteristics are compared with the first color tone curve and the second color tone curve. Generate corresponding compensation parameters based on the branding characteristics and the accumulated data features; The target de-aging model is activated to verify the de-aging compensation effect of the compensation parameters on the branded area; When it is determined that the de-aging compensation effect of the compensation parameter is abnormal, the compensation parameter shall be optimized and adjusted. Preferably, the accumulated data feature is a current feature.

7. An anti-aging compensation device for a display panel, characterized in that, include: The data collection module is used to import the de-aging debugging model and control the display panel under test to display the target image. The de-aging debugging model collects the brightness and color data of the display panel under test under different test parameters. The test parameters include grayscale, temperature, brightness level and continuous lighting time. The target image includes multiple display images with different display patterns and / or different grayscale. The model building module is used to build a target de-aging model based on the brightness data and the chromaticity data. The target de-aging model is used to perform de-aging compensation on abnormal display areas in the display panel under test. The abnormal display areas include areas with uneven brightness. The target de-aging model includes a compensation switch and a data burn-back switch. The compensation test module is used to import the target de-aging model, turn on the compensation switch of the target de-aging model, and verify the de-aging compensation effect of the target de-aging model on the abnormal display area in the display panel under test. The data burn-back module is used to turn on the data burn-back switch of the target de-aging model after a preset time, and optimize the compensation parameters of the target de-aging model according to the de-aging compensation effect.

8. A display device comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the de-aging compensation method for the display panel according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the de-aging compensation method for the display panel according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the de-aging compensation method for the display panel as described in any one of claims 1 to 6.

Images