Sub-pixel compensation method and device of display panel, display equipment and storage medium

Abstract

The invention relates to a sub-pixel compensation method and device of a display panel, display equipment and a storage medium. The method comprises the steps that current environment data of the environment where the display panel is located and historical use data corresponding to all sub-pixels in the display panel are acquired; based on a preset mapping relation, determining an environment compensation factor matched with the current environment data, the preset mapping relation being used for representing a mapping relation between the environment data and the environment compensation factor; inputting the historical use data and the current environment data into a pre-trained aging prediction model, and predicting to obtain an aging compensation factor corresponding to each sub-pixel; based on the environment compensation factor and the aging compensation factor, adjusting the basic compensation value corresponding to each sub-pixel to obtain a target compensation value corresponding to each sub-pixel; and compensating and displaying each sub-pixel in the to-be-displayed image based on the target compensation value corresponding to each sub-pixel. Therefore, the condition of compensation failure can be avoided.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of display, in particular to a sub-pixel compensation method and device of a display panel, a display device and a storage medium. BACKGROUND

[0002] Due to the manufacturing process of each sub-pixel in the display panel such as an organic light emitting display (OLED), there are small differences, which can easily lead to the problem of display unevenness caused by the inconsistent light emitting characteristics of each sub-pixel, such as Figure 1 As shown. In order to solve this problem, in the related art, a static compensation table is usually set in advance and stored in the driving chip, and then the input signal is compensated according to the static compensation table when the display panel displays. However, the compensation value in the static compensation table cannot be dynamically adjusted according to the environmental changes and pixel aging conditions, which can easily cause compensation failure. Therefore, how to accurately compensate each sub-pixel in the display panel has become a technical problem to be solved. SUMMARY

[0003] The present application provides a sub-pixel compensation method and device of a display panel, a display device and a storage medium to solve the problem of compensation failure in the existing sub-pixel compensation method.

[0004] In a first aspect, the present application provides a sub-pixel compensation method of a display panel, the method comprising: obtaining current environmental data of an environment in which the display panel is located and historical usage data corresponding to each sub-pixel in the display panel; determining an environmental compensation factor matched with the current environmental data based on a preset mapping relationship, wherein the preset mapping relationship is used to represent the mapping relationship between the environmental data and the environmental compensation factor; inputting the historical usage data and the current environmental data into a pre-trained aging prediction model to predict an aging compensation factor corresponding to each sub-pixel; adjusting a basic compensation value corresponding to each sub-pixel based on the environmental compensation factor and the aging compensation factor to obtain a target compensation value corresponding to each sub-pixel; compensating and displaying each sub-pixel in a to-be-displayed image based on the target compensation value corresponding to each sub-pixel.

[0005] Optionally, the inputting the historical usage data and the current environmental data into the pre-trained aging prediction model to predict the aging compensation factor corresponding to each sub-pixel comprises: inputting the historical usage data and the current environment data into the aging prediction model, wherein the historical usage data is at least one of normalized accumulated lighting time, average current and historical environment temperature, and the current environment data is at least one of normalized current temperature and current humidity; extracting long-term trend features corresponding to the historical usage data by using the aging prediction model, and splicing the long-term trend features with environment features corresponding to the current environment data to obtain fusion features; predicting the fusion features by using the aging prediction model to obtain aging compensation factors corresponding to each sub-pixel.

[0006] Optionally, before the historical usage data and the current environment data are input into the pre-trained aging prediction model to predict the aging compensation factors corresponding to each sub-pixel, the method further comprises: obtaining a plurality of labeled data corresponding to a plurality of sub-pixels, wherein each labeled data has historical usage data, current environment data and actual measured value of the aging compensation factor of the corresponding sub-pixel labeled therein; inputting the plurality of labeled data into a to-be-trained model for iterative training to obtain a predicted value of the aging compensation factor, and sequentially calculating a loss value between the predicted value of the aging compensation factor and the actual measured value of the aging compensation factor until the loss value gradually decreases and tends to be stable, stopping the iterative training to obtain the aging prediction model.

[0007] Optionally, the adjusting the basic compensation value corresponding to each sub-pixel based on the environment compensation factor and the aging compensation factor to obtain a target compensation value corresponding to each sub-pixel comprises: obtaining a preset basic compensation table, wherein the basic compensation table stores the basic compensation value corresponding to each sub-pixel; calculating the product of the basic compensation value corresponding to each sub-pixel, the environment compensation factor and the aging compensation factor, and determining the target compensation value corresponding to each sub-pixel according to the product calculation result.

[0008] Optionally, before the preset basic compensation table is obtained, the method further comprises: when the display panel is in a production stage, obtaining the luminance value of each sub-pixel; calculating the difference between the luminance value of each sub-pixel and a preset standard luminance value, and determining the basic compensation value of each sub-pixel according to the difference calculation result; storing the basic compensation value of each sub-pixel into the basic compensation table.

[0009] Optionally, the compensating each sub-pixel in the to-be-displayed image based on the target compensation value corresponding to each sub-pixel and displaying the to-be-displayed image comprises: obtaining an original input value of each sub-pixel in the to-be-displayed image; compensating the original input value of each sub-pixel based on the target compensation value corresponding to each sub-pixel to obtain a compensated image; displaying the compensated image.

[0010] Optionally, the compensating each sub-pixel in the to-be-displayed image based on the target compensation value corresponding to each sub-pixel and displaying the to-be-displayed image comprises: calculating a product between the original input value of each sub-pixel and the target compensation value corresponding to each sub-pixel, and determining a target input value corresponding to each sub-pixel according to the product calculation result; combining the target input value corresponding to each sub-pixel to obtain the compensated image.

[0011] In a second aspect, an embodiment of the present application further provides a sub-pixel compensation device of a display panel, and the device comprises: a first obtaining module configured to obtain current environment data of an environment in which a display panel is located and historical use data corresponding to each sub-pixel in the display panel; a determining module configured to determine an environment compensation factor matched with the current environment data based on a preset mapping relationship, wherein the preset mapping relationship is used to represent a mapping relationship between environment data and an environment compensation factor; a predicting module configured to input the historical use data and the current environment data into a pre-trained aging prediction model to predict an aging compensation factor corresponding to each sub-pixel; an adjusting module configured to adjust a basic compensation value corresponding to each sub-pixel based on the environment compensation factor and the aging compensation factor to obtain a target compensation value corresponding to each sub-pixel; a compensating and displaying module configured to compensate each sub-pixel in a to-be-displayed image based on the target compensation value corresponding to each sub-pixel and display the to-be-displayed image.

[0012] In a third aspect, an embodiment of the present application further provides a display device, and the display device comprises a display panel and the sub-pixel compensation device of the display panel in the second aspect. The display panel and the sub-pixel compensation device of the display panel are electrically connected.

[0013] In a fourth aspect, an embodiment of the present application further provides a computer readable storage medium, and the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the sub-pixel compensation method of the display panel in the first aspect.

[0014] Compared with the prior art, the technical scheme provided by the embodiments of the present application has the following advantages: the method provided by the embodiments of the present application, by acquiring current environment data of an environment in which a display panel is located and historical use data corresponding to each sub-pixel in the display panel, determining an environment compensation factor matched with the current environment data based on a preset mapping relationship, wherein the preset mapping relationship is used to represent a mapping relationship between environment data and an environment compensation factor, inputting the historical use data and the current environment data into a pre-trained aging prediction model to predict an aging compensation factor corresponding to each sub-pixel, adjusting a basic compensation value corresponding to each sub-pixel based on the environment compensation factor and the aging compensation factor to obtain a target compensation value corresponding to each sub-pixel, and compensating and displaying each sub-pixel in a to-be-displayed image based on the target compensation value corresponding to each sub-pixel. In this way, the basic compensation value corresponding to each sub-pixel can be adjusted based on the environment compensation factor and the aging compensation factor, so that the compensation value of each sub-pixel can be dynamically adjusted according to the environmental change and the pixel aging condition, the compensation failure condition is avoided, and the purpose of accurate compensation of each sub-pixel in the display panel is achieved. BRIEF DESCRIPTION OF DRAWINGS

[0015] The accompanying drawings, which are incorporated into and form a part of the specification, illustrate one embodiment consistent with the present application and, together with the description, serve to explain the principles of the application.

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the accompanying drawings needed to be used in the embodiments or the prior art description will be briefly introduced as follows. Obviously, those skilled in the art can obtain other drawings from these drawings without any creative effort.

[0017] One or more embodiments are exemplarily illustrated by pictures in the drawings corresponding thereto, and these exemplary illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, unless otherwise specified. The drawings in the drawings do not constitute a proportional limitation.

[0018] Figure 1 A schematic diagram of display panel display unevenness in the prior art; Figure 2 A flowchart of a sub-pixel compensation method of a display panel provided by an embodiment of the present application; Figure 3 A structural diagram of a sub-pixel compensation system of a display panel provided by an embodiment of the present application; Figure 4 A flowchart of another sub-pixel compensation method of a display panel provided by an embodiment of the present application; Figure 5 A brightness uniformity simulation diagram before and after compensation provided in an embodiment of the present application; Figure 6 A schematic structural diagram of a sub-pixel compensation device for a display panel provided in an embodiment of the present application; Figure 7 A schematic structural diagram of a display device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0020] The disclosure below provides many different embodiments or examples for implementing different structures of the present application. In order to simplify the disclosure of the present application, the components and settings of specific examples are described below. Of course, these are merely examples and are not intended to limit the present application. In addition, the present application may repeat reference numbers and / or letters in different examples. Such repetition is for the purpose of simplicity and clarity and does not in itself indicate the relationship between the various embodiments and / or settings discussed.

[0021] See also Figure 2 , Figure 2 This is a flow chart of a sub-pixel compensation method for a display panel provided in an embodiment of the present application. Figure 2 As shown, the sub-pixel compensation method of the display panel may include the following steps: Step S201 : obtaining current environment data of the environment in which the display panel is located and historical usage data corresponding to each sub-pixel in the display panel.

[0022] Specifically, the current environment data can include, but is not limited to, current temperature, current humidity, and the like. In obtaining the current environment data, real-time acquisition can be performed by using a temperature sensor, a humidity sensor, and the like integrated in the display panel. The historical usage data can include, but is not limited to, accumulated lighting duration, average current, and historical environment temperature, and the like. In obtaining the historical usage data, collection and recording can be performed by using a corresponding tool. For example, a temperature value collected by a temperature sensor in a preset time period in the past can be recorded to obtain a historical environment temperature; a current value collected by a current collection device in a preset time period in the past can be recorded to obtain an average current; and a driving duration of a driving chip in a preset time period in the past can be recorded to obtain an accumulated lighting duration. Of course, other manners can also be used to obtain the data, which is not limited in the embodiments of the present application.

[0023] In step S202, an environment compensation factor matched with the current environment data is determined based on a preset mapping relationship, where the preset mapping relationship is used to represent a mapping relationship between the environment data and the environment compensation factor.

[0024] Specifically, the preset mapping relationship can be used to represent a mapping relationship between the environment data and the environment compensation factor. The preset mapping relationship can be obtained by measuring experimental data. The environment compensation factor refers to a compensation factor required to avoid compensation failure caused by environment change.

[0025] After the preset mapping relationship is established, the current environment data can be compared with the environment parameters in the preset mapping relationship, so as to determine the environment compensation factor matched with the current environment data.

[0026] In step S203, the historical usage data and the current environment data are input into a pre-trained aging prediction model to predict an aging compensation factor corresponding to each sub-pixel.

[0027] Specifically, the aging prediction model can be any deep learning model, such as a Long Short-Term Memory (LSTM), a Convolutional Neural Networks (CNNs), a Recurrent Neural Networks (RNNs), and the like. The aging compensation factor refers to a compensation factor required to avoid compensation failure caused by pixel attenuation and aging.

[0028] In step S204, a basic compensation value corresponding to each sub-pixel is adjusted based on the environment compensation factor and the aging compensation factor to obtain a target compensation value corresponding to each sub-pixel.

[0029] Specifically, the basic compensation value corresponding to each sub-pixel is an original compensation value obtained during the production of the display panel, that is, a compensation value in a basic compensation table (Look-Up Table, LUT for short).

[0030] Step S205 : Compensate each sub-pixel in the image to be displayed based on the target compensation value corresponding to each sub-pixel, and then display the image.

[0031] After obtaining the target compensation value corresponding to each sub-pixel, each sub-pixel in the image to be displayed can be compensated based on the target compensation value corresponding to each sub-pixel to obtain a compensated image, which is then displayed.

[0032] Through the above method, the basic compensation value corresponding to each sub-pixel can be adjusted based on the environmental compensation factor and the aging compensation factor, so that the compensation value of each sub-pixel can be dynamically adjusted according to environmental changes and pixel aging, avoiding compensation failure and achieving the purpose of accurate compensation of each sub-pixel in the display panel.

[0033] In an optional embodiment, the above step S203, inputting the historical usage data and the current environment data into a pre-trained aging prediction model to predict the aging compensation factor corresponding to each sub-pixel, includes: Inputting historical usage data and current environmental data into an aging prediction model, wherein the historical usage data is at least one of normalized cumulative lighting time, average current, and historical ambient temperature, and the current environmental data is at least one of normalized current temperature and current humidity; The aging prediction model is used to extract the long-term trend features corresponding to the historical usage data, and the long-term trend features are combined with the environmental features corresponding to the current environmental data to obtain the fusion features; The aging prediction model is used to predict the fusion features and obtain the aging compensation factor corresponding to each sub-pixel.

[0034] Specifically, the aging prediction model can be a pre-trained LSTM model. When using the LSTM model to predict the aging compensation factor corresponding to each sub-pixel, historical usage data and current environmental data can be first input into the aging prediction model. The aging prediction model can then be used to extract long-term trend features corresponding to the historical usage data. These long-term trend features are then concatenated with environmental features corresponding to the current environmental data to obtain fused features. Finally, the fused features are predicted using the aging prediction model to obtain the aging compensation factor corresponding to each sub-pixel.

[0035] For example, for sub-pixel A in the image to be displayed, assume that its historical usage data (historical usage data for the past 7 days) is as shown in Table 1 below: Table 1

[0036] Current environment data: current temperature 27℃, current humidity 50%.

[0037] First, the historical usage data and the current environment data can be preprocessed, and the preprocessing result is (assuming that the maximum service life of the display panel is 100,000 hours, the maximum rated current is 10 mA, and the highest working temperature is 40℃): Historical feature normalization: cumulative lighting duration divided by the maximum service life of the display panel, the result is 0.00012-0.0002; average current divided by the maximum rated current, the result is 0.19-0.26; historical environment temperature divided by the highest working temperature, the result is 0.6-0.7; Current environment feature normalization: current temperature divided by 40℃, the result is 0.675; current humidity divided by 100%, the result is 50%.

[0038] Assuming that the long-term trend feature extracted by the LSTM model is [0.2, 0.5,...] (64-dimensional vector, [0.2, 0.5, …] is not a specific physical quantity, but an abstract numerical representation of the long-term aging trend of the sub-pixel by the LSTM model, the element 0.2 can correspond to “the long-term growth rate of cumulative lighting duration”, the larger the value, the faster the cumulative lighting duration grows in the past period of time, and the more obvious the aging trend; the element 0.5 can correspond to “the synergistic effect of average current and environment temperature”, the larger the value, the more obvious the acceleration effect of high current and high temperature combination on aging, etc.). Then, after concatenating the long-term trend feature [0.2, 0.5, …] with the current environment feature [0.675, 0.5], the aging compensation factor 0.32 is predicted by the LSTM model (this value can represent that the sub-pixel is aged by 32%).

[0039] In the above manner, the pre-trained aging prediction model can be used to accurately predict the aging compensation factor corresponding to each sub-pixel, so that the aging compensation factor corresponding to each sub-pixel is used to eliminate the compensation failure problem caused by pixel decay and aging.

[0040] In an optional embodiment, before the step S203 of inputting the historical usage data and the current environment data into the pre-trained aging prediction model to predict the aging compensation factor corresponding to each sub-pixel, the method further comprises: Obtaining a plurality of labeled data corresponding to a plurality of sub-pixels, wherein the historical usage data, the current environment data, and the measured value of the aging compensation factor of the corresponding sub-pixel are labeled in each labeled data; The plurality of labeled data are sequentially input to the to-be-trained model for iterative training to obtain the aging compensation factor prediction value, and the loss value between the aging compensation factor prediction value and the aging compensation factor measured value is sequentially calculated until the loss value gradually decreases and tends to be stable, the iterative training is stopped, and the aging prediction model is obtained.

[0041] Specifically, in the process of training the aging prediction model, a plurality of labeled data corresponding to a plurality of sub-pixels can be obtained first, wherein the historical use data, the current environment data and the aging compensation factor measured value of the corresponding sub-pixel are labeled in each labeled data. Then, the plurality of labeled data are sequentially input to the to-be-trained model for iterative training to obtain the aging compensation factor prediction value, and the loss value between the aging compensation factor prediction value and the aging compensation factor measured value is sequentially calculated until the loss value gradually decreases and tends to be stable, the iterative training is stopped, and the aging prediction model is obtained.

[0042] For example, a large amount of labeled data of sub-pixels (such as 1000 sub-pixels) can be collected, and the labeled data of each sub-pixel includes historical use data (such as cumulative lighting time, average current, historical environment temperature) in the past 7 days, current environment data (temperature, humidity, etc.), and an actually measured aging compensation factor measured value. The aging compensation factor measured value can be obtained by measuring the brightness attenuation rate by a luminometer or the threshold voltage change amount detected by a voltage detection device, and then normalized.

[0043] Then, the original labeled data is preprocessed, such as cleaning (such as removing outliers), normalization (such as normalizing the cumulative lighting time to the interval [0, 1]), feature engineering (such as extracting combined features such as “cumulative lighting time x environment temperature”), etc. Among them, the historical feature normalization: such as dividing the cumulative lighting time by the maximum service life of the display panel (such as 100,000 hours), dividing the average current by the maximum rated current (such as 10 mA), dividing the historical environment temperature by the highest working temperature (such as 40°C), and scaling the value to the range of 0-1. Current environment feature normalization: such as dividing the current temperature by 40°C and the current humidity by 100%, scaling the value to the range of 0-1. Label normalization: scaling the measured brightness attenuation rate (such as from 1000 nits to 800 nits, attenuation rate 20%) to the range of 0-1 (i.e. 0.2).

[0044] Then, a suitable to-be-trained model (the LSTM model architecture is used in this scheme, which can be integrated in the display driving chip) is selected, the input layer dimension of which corresponds to the feature quantity of the historical use data + current environment data, and the output layer dimension corresponds to the aging compensation factor of each sub-pixel.

[0045] Finally, the pre-processed labeled data (such as labeled data of 32 sub-pixels per training) can be used to train the to-be-trained model, wherein a loss function can be a mean square error (MSE) function used to measure the loss value between the predicted value of the aging compensation factor and the measured value of the aging compensation factor, and the weight of the to-be-trained model is adjusted through back propagation until the to-be-trained model converges to a stable MSE value with the measured value of the aging compensation factor, and the iteration training is stopped, and the aging prediction model is obtained.

[0046] In this way, the aging prediction model can be trained, and the corresponding aging compensation factor of each sub-pixel can be predicted based on the trained aging prediction model.

[0047] In an optional embodiment, the step S204 of adjusting the base compensation value corresponding to each sub-pixel based on the environmental compensation factor and the aging compensation factor to obtain the target compensation value corresponding to each sub-pixel comprises: obtaining a preset base compensation table, wherein the base compensation table stores the base compensation value corresponding to each sub-pixel; calculating the product of the base compensation value corresponding to each sub-pixel, the environmental compensation factor, and the aging compensation factor, and determining the target compensation value corresponding to each sub-pixel according to the product calculation result.

[0048] Specifically, the base compensation value corresponding to each sub-pixel can be adjusted in combination with the environmental compensation factor and the aging compensation factor to dynamically generate the target compensation value. Specifically, the following formula can be used to achieve this: , wherein represents the target compensation value corresponding to the sub-pixel , wherein represents the base compensation value corresponding to the sub-pixel , wherein represents the environmental compensation factor, represents the aging compensation factor corresponding to the sub-pixel represents the current temperature, represents the current humidity, represents the current environmental data, represents the historical usage data.

[0049] for adjusting the display brightness / color of the sub-pixel . from the base compensation table generated during the production phase. Each sub-pixel in the display panel shares the ​​, which is determined by the current temperature T and the current humidity H, and is used to offset the decay caused by the environment change. Different sub-pixels in the display panel correspond to different , which are determined by the historical use data of the sub-pixel and the current environmental data , and are used to offset the decay caused by long-term aging.

[0050] In this way, the target compensation value corresponding to each sub-pixel can be accurately determined based on the basic compensation value, the environmental compensation factor and the aging compensation factor corresponding to each sub-pixel, and the subsequent compensation and display of each sub-pixel in the to-be-displayed image based on the target compensation value corresponding to each sub-pixel are facilitated.

[0051] In an optional embodiment, before the above step of obtaining the preset basic compensation table, the method further includes: obtaining the luminance value of each sub-pixel when the display panel is in the production stage; calculating the difference between the luminance value of each sub-pixel and the preset standard luminance value, and determining the basic compensation value of each sub-pixel according to the difference calculation result; storing the basic compensation value of each sub-pixel into the basic compensation table.

[0052] Specifically, in the process of generating the basic compensation table, the luminance value of each sub-pixel can be obtained when the display panel is in the production stage, then the difference between the luminance value of each sub-pixel and the preset standard luminance value is calculated, and the basic compensation value of each sub-pixel is determined according to the difference calculation result, and finally the basic compensation value of each sub-pixel is stored into the basic compensation table. In this way, the basic compensation table can be obtained, and the basic compensation value of each sub-pixel can be conveniently obtained by querying during the subsequent use of the display panel.

[0053] In an optional embodiment, the above step S204 of compensating and displaying each sub-pixel in the to-be-displayed image based on the target compensation value corresponding to each sub-pixel includes: obtaining the original input value of each sub-pixel in the to-be-displayed image; compensating the original input value of each sub-pixel based on the target compensation value corresponding to each sub-pixel to obtain a compensated image; displaying the compensated image.

[0054] Specifically, the above to-be-displayed image can be composed of multiple sub-pixels (for example, in an 8-bit display, the original input value of each sub-pixel in the RGB channel corresponds to 0-255, representing the luminance of the sub-pixel). The core of compensation is to adjust the original input value of each sub-pixel, so that the final displayed luminance / color meets the expectation (offsets the influence of aging and environment). ​

[0055] After obtaining the target compensation value corresponding to each sub-pixel, the original input value of each sub-pixel in the image to be displayed can be obtained, and then the original input value of each sub-pixel is compensated based on the target compensation value corresponding to each sub-pixel to obtain a compensated image, and then the compensated image is displayed, so that the final display brightness / color meets the expectation (offsets the effects of aging and environment).

[0056] In an optional embodiment, the step of compensating the original input value of each sub-pixel based on the target compensation value corresponding to each sub-pixel to obtain a compensated image comprises: calculating the product between the original input value of each sub-pixel and the target compensation value corresponding to each sub-pixel, and determining the target input value corresponding to each sub-pixel according to the product calculation result; combining the target input value corresponding to each sub-pixel to obtain a compensated image.

[0057] Specifically, the product between the original input value of each sub-pixel and the target compensation value corresponding to each sub-pixel can be calculated, and the target input value corresponding to each sub-pixel can be determined according to the product calculation result, and then the target input value corresponding to each sub-pixel is combined to obtain a compensated image, so that the compensated image can be displayed, and the final display brightness / color meets the expectation.

[0058] As an optional embodiment, the sub-pixel compensation method of the display panel can be applied to Figure 3 the sub-pixel compensation system of the display panel shown in the figure. The system comprises a dynamic compensation module and a driving chip, wherein the dynamic compensation module comprises an environment self-adapting module and an aging prediction model. The environment self-adapting module integrates a temperature sensor and a humidity sensor inside the display panel to collect environmental data (temperature T, humidity H) in real time, and dynamically adjusts the basic compensation value according to the environmental parameters. The environment self-adapting module establishes a mapping relationship between the environmental parameters and the environmental compensation factors through experiments, avoiding compensation failure caused by environmental changes. The aging prediction model inputs include historical usage data of each sub-pixel (such as cumulative lighting time, average current, environmental temperature), and current environmental data, and outputs the aging compensation factor of each sub-pixel. The model can accurately predict the pixel decay degree under different usage conditions. The driving chip comprises an input image analysis module, a basic compensation value query module, a dynamic compensation module, and a compensated image output module. Among them, the input image analysis module can analyze the original input matrix of the sub-pixel level from the input image (i.e. the image to be displayed above) to obtain the original input value of each sub-pixel. For example, for an image with a resolution of WxH, each pixel position (x, y) corresponds to 3 sub-pixels (R, G, B), and the original input value of each sub-pixel can be represented as I raw , R (x, y), Iraw,G (x,y),I raw,B (x, y) (both are integers from 0 to 255). The basic compensation value query module can query the basic compensation value sub-pixel by sub-pixel, and for each sub-pixel (x, y) (such as the sub-pixel of the R channel), read its corresponding C from the basic compensation table LUT. base (x,y). The purpose of the basic compensation table is to generate a LUT by measuring the initial brightness of each sub-pixel during production to offset the initial deviation of the sub-pixel. The LUT is usually stored in the driver chip of the display, and the C value of each sub-pixel can be quickly queried. base The dynamic compensation module can calculate the total compensation value of each sub-pixel, and adjust the basic compensation value corresponding to each sub-pixel in combination with the environmental compensation factor and the aging compensation factor to dynamically generate the target compensation value. This can be achieved using the following formula: ; in, Represents sub-pixel The corresponding target compensation value, Represents sub-pixel The corresponding basic compensation value, represents the environmental compensation factor, Represents sub-pixel The corresponding aging compensation factor, Indicates the current temperature. Indicates the current humidity. Indicates the current environment data. Represents historical usage data. Then, the original input value of each sub-pixel is multiplied by the total compensation value to obtain the compensated sub-pixel value I comp (x,y), which can be implemented using the following formula: I comp (x,y)=I raw (x,y)×C(x,y); Among them, I comp (x,y) represents sub-pixel The corresponding target input value, I raw (x,y) represents sub-pixel The corresponding original input value, Represents sub-pixel The corresponding target compensation value. The target compensation value C(x,y) is used to adjust the original input value to offset the brightness attenuation caused by aging and the environment. For example, if the brightness of a sub-pixel is attenuated by 30% due to aging (β=1.43) and the environment causes attenuation of 10% (α=1.11), the basic compensation C base=1.0, then C=1.0x1.11x1.43≈1.59. If the original input value is 100, the compensated value is 100x1.59=159, and the displayed brightness will be restored to the standard level (offsetting 30%+10% attenuation). Since the compensated I comp (x,y) must be limited within the dynamic range of the display (e.g. 0-255 for an 8-bit display), and if the calculation result exceeds 255, take 255; if it is lower than 0, take 0. The compensated image output module can output the compensated image, which can combine all the sub-pixel I comp (x,y) into a compensated image signal (such as a sub-pixel matrix of R, G, B channels), and send it to the pixel driving circuit of the display. The driving circuit controls the light-emitting element (such as the organic layer of OLED) of each sub-pixel to make the displayed image brightness uniform and color accurate, offsetting the effects of aging and the environment. comp

[0059] In an optional embodiment, the sub-pixel compensation process of the display panel is as shown in Figure 4 which specifically includes the following steps: Step S401, initialization phase.

[0060] In the production phase, the sub-pixel brightness is measured, the basic compensation table LUT is generated and stored in the driving chip, and in the initialization phase, the basic compensation value in the basic compensation table LUT is obtained.

[0061] Step S402, real-time environmental data acquisition.

[0062] The current environmental data (temperature T, humidity H, etc.) is acquired by the built-in temperature sensor and humidity sensor.

[0063] Step S403, aging compensation factor update.

[0064] Periodically input the historical usage data (cumulative lighting duration, average current, historical environmental data) of each sub-pixel into the aging prediction model, and output the aging compensation factor.

[0065] Step S404, compensation value calculation.

[0066] The target compensation value of each sub-pixel is calculated using the above formula.

[0067] Step S405, compensating and displaying each sub-pixel in the image to be displayed.

[0068] ​To verify the effectiveness of the present scheme, simulation can be performed using Matlab. The simulation conditions are: a display panel of 1080x1920 is simulated, and the simulation target is: the uniformity of the display panel, which can be the standard deviation of the pixel brightness of the display picture, and the smaller the value means the more uniform the brightness. The basic compensation table is: generated by randomly generated brightness data (simulate Mura). Environmental changes: temperature from -20℃ to 85℃, humidity from 20% to 90%. Aging simulation: cumulative use of 1000 hours, average temperature 40℃. The final simulation results are shown in Table Two as follows: Table Two

[0069] And, the compensation before and after the brightness uniformity simulation diagram of 1000hrs (cumulative use of 1000hrs), the current temperature is 45℃, and the temperature is 30%RH is as shown in Figure 5

[0070] Therefore, the sub-pixel compensation method of the display panel has the following beneficial effects: (1) Adapt to environmental changes: real-time adjustment of compensation through environmental sensors ensures display uniformity in different temperature and humidity environments.

[0071] (2) Accurate aging compensation: combined with the prediction model of deep learning, the aging degree of each sub-pixel is accurately tracked, avoiding compensation failure due to pixel aging.

[0072] (3) Improve display quality: the uniformity index (standard deviation / mean) of the display panel after compensation is reduced from 0.15 of the traditional method to below 0.05.

[0073] (4) Prolong the service life of the screen: reduce pixel overdrive through dynamic compensation to avoid local aging aggravation.

[0074] (5) Low cost: only need to add low-cost temperature and humidity sensors, and the algorithm can run on existing driving chips without additional hardware.

[0075] Referring to Figure 6 , Figure 6 A structure diagram of a sub-pixel compensation device of a display panel provided by the embodiments of the present application is shown in Figure 6 The sub-pixel compensation device 600 of the display panel includes: A first acquisition module 601 for acquiring current environmental data of the environment in which the display panel is located and historical use data corresponding to each sub-pixel in the display panel; A determination module 602 for determining an environmental compensation factor matched with the current environmental data based on a preset mapping relationship, wherein the preset mapping relationship is used to represent the mapping relationship between the environmental data and the environmental compensation factor;​ The prediction module 603 is configured to input the historical use data and the current environment data into a pre-trained aging prediction model to predict an aging compensation factor corresponding to each sub-pixel. The adjustment module 604 is configured to adjust a basic compensation value corresponding to each sub-pixel based on the environment compensation factor and the aging compensation factor to obtain a target compensation value corresponding to each sub-pixel. The compensation and display module 605 is configured to compensate and display each sub-pixel in the to-be-displayed image based on the target compensation value corresponding to each sub-pixel.

[0076] Further, the prediction module 603 comprises: The input sub-module is configured to input the historical use data and the current environment data into the aging prediction model, wherein the historical use data is at least one of the normalized accumulated lighting duration, the average current and the historical environment temperature, and the current environment data is at least one of the normalized current temperature and the current humidity. The extraction and splicing sub-module is configured to extract a long-term trend feature corresponding to the historical use data by using the aging prediction model, and splice the long-term trend feature with an environment feature corresponding to the current environment data to obtain a fusion feature. The prediction sub-module is configured to predict the fusion feature by using the aging prediction model to obtain the aging compensation factor corresponding to each sub-pixel.

[0077] Further, the sub-pixel compensation device 600 of the display panel further comprises: The second acquisition module is configured to acquire a plurality of label data corresponding to a plurality of sub-pixels, wherein each label data labels the historical use data, the current environment data and the measured value of the aging compensation factor of the corresponding sub-pixel. The training module is configured to input the plurality of label data into a to-be-trained model for iterative training to obtain a predicted value of the aging compensation factor, and sequentially calculate a loss value between the predicted value of the aging compensation factor and the measured value of the aging compensation factor until the loss value gradually decreases and tends to be stable, and stop the iterative training to obtain the aging prediction model.

[0078] Further, the adjustment module 604 comprises: The first acquisition sub-module is configured to acquire a preset basic compensation table, wherein the basic compensation table stores the basic compensation value corresponding to each sub-pixel. The first calculation sub-module is configured to calculate the product of the basic compensation value corresponding to each sub-pixel, the environment compensation factor and the aging compensation factor, and determine the target compensation value corresponding to each sub-pixel according to the product calculation result.

[0079] Further, the adjustment module 604 further comprises: A second acquisition submodule is used to acquire the brightness value of each sub-pixel when the display panel is in the production stage; A second calculation submodule is used to calculate the difference between the brightness value of each sub-pixel and a preset standard brightness value, and determine a basic compensation value for each sub-pixel based on the difference calculation result; The storage submodule is used to store the basic compensation value of each sub-pixel in the basic compensation table.

[0080] Furthermore, the compensation and display module 605 includes: A third acquisition submodule is used to obtain the original input value of each sub-pixel in the image to be displayed; a compensation submodule, configured to compensate the original input value of each subpixel based on the target compensation value corresponding to each subpixel to obtain a compensated image; The display submodule is used to display the compensated image.

[0081] Furthermore, the compensation submodule includes: a calculation unit, configured to calculate the product of the original input value of each sub-pixel and the target compensation value corresponding to each sub-pixel, and determine the target input value corresponding to each sub-pixel based on the product calculation result; The combining unit is used to combine the target input values ​​corresponding to the sub-pixels to obtain a compensated image.

[0082] It should be noted that the sub-pixel compensation device 600 of the display panel can implement the sub-pixel compensation method of the display panel provided by any of the aforementioned method embodiments and can achieve the same technical effects, which will not be described in detail here.

[0083] See also Figure 7 , Figure 7 A schematic diagram of the structure of a display device provided in an embodiment of the present application is shown in FIG. Figure 7 As shown, the display device 700 includes: a display panel 701 and a sub-pixel compensation device 702 of the display panel in the aforementioned embodiment; The display panel 701 and the sub-pixel compensation device 702 of the display panel are electrically connected.

[0084] It should be noted that the display device 700 can be any device such as a mobile phone, a computer, a television, and a wearable device that is provided with a display panel 701, without limitation.

[0085] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the sub-pixel compensation method for a display panel provided in any of the aforementioned method embodiments is implemented.

[0086] The apparatus embodiments described above are only illustrative, and units described as separate units can or can not be physically separate, and units shown as units can or can not be physical units, i.e., can be located in one place, or can be distributed to multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiment.

[0087] Through the above description of the embodiments, those skilled in the art can clearly understand that the embodiments can be implemented by means of software plus a general hardware platform, and of course can also be implemented by hardware. Based on such understanding, the above technical solutions can be embodied in the form of a software product, and the computer software product can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in the embodiments or some parts of the embodiments.

[0088] It should be understood that the terms used herein are for the purpose of describing particular example embodiments only and are not intended to be limiting. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. The terms "comprises", "comprising", "includes", "including" and "has" are inclusive and therefore specify the presence of stated features, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, steps, operations, elements, components, and / or groups thereof. The method steps, processes, and operations described herein are not to be construed as necessarily requiring their performance in the particular order in which they are described, unless specifically indicated as such. It is also to be understood that additional or alternative steps can be employed.

[0089] The above description is merely illustrative of the application and should not be taken as limiting. Numerous modifications and variations underlying the general principles of the applications can be made by those of ordinary skill in the art without departing from the spirit or scope of the application. Therefore, the application is not to be limited to the embodiments described herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A sub-pixel compensation method for a display panel, characterized in that: The method comprises: Acquire current environment data of the environment in which the display panel is located and historical usage data corresponding to each sub-pixel in the display panel; Determining an environmental compensation factor that matches the current environmental data based on a preset mapping relationship, wherein the preset mapping relationship is used to represent a mapping relationship between the environmental data and the environmental compensation factor; Inputting the historical usage data and the current environment data into a pre-trained aging prediction model to predict an aging compensation factor corresponding to each sub-pixel; Adjusting the basic compensation value corresponding to each sub-pixel based on the environmental compensation factor and the aging compensation factor to obtain a target compensation value corresponding to each sub-pixel; Based on the target compensation value corresponding to each sub-pixel, each sub-pixel in the image to be displayed is compensated and displayed.

2. The sub-pixel compensation method for a display panel according to claim 1, wherein: Inputting the historical usage data and the current environment data into a pre-trained aging prediction model to predict an aging compensation factor corresponding to each sub-pixel includes: Inputting the historical usage data and the current environmental data into the aging prediction model, wherein the historical usage data is at least one of the normalized cumulative lighting duration, average current, and historical ambient temperature, and the current environmental data is at least one of the normalized current temperature and current humidity; Extracting long-term trend features corresponding to the historical usage data using the aging prediction model, and combining the long-term trend features with environmental features corresponding to the current environmental data to obtain fusion features; The fusion feature is predicted using the aging prediction model to obtain an aging compensation factor corresponding to each sub-pixel.

3. The sub-pixel compensation method for a display panel according to claim 2, wherein: Before inputting the historical usage data and the current environment data into a pre-trained aging prediction model to predict an aging compensation factor corresponding to each sub-pixel, the method further includes: Acquire a plurality of annotated data corresponding to a plurality of sub-pixels, wherein each annotated data is annotated with historical usage data, current environment data, and a measured value of an aging compensation factor of the corresponding sub-pixel; The multiple labeled data are sequentially input into the model to be trained for iterative training to obtain the predicted value of the aging compensation factor, and the loss value between the predicted value of the aging compensation factor and the measured value of the aging compensation factor is sequentially calculated until the loss value gradually decreases and tends to be stable. The iterative training is stopped to obtain the aging prediction model.

4. The sub-pixel compensation method for a display panel according to claim 1, wherein: The adjusting the basic compensation value corresponding to each sub-pixel based on the environmental compensation factor and the aging compensation factor to obtain the target compensation value corresponding to each sub-pixel includes: Obtaining a preset basic compensation table, wherein the basic compensation table stores a basic compensation value corresponding to each sub-pixel; The product of the basic compensation value corresponding to each sub-pixel, the environmental compensation factor and the aging compensation factor is calculated, and the target compensation value corresponding to each sub-pixel is determined according to the product calculation result.

5. The sub-pixel compensation method for a display panel according to claim 4, wherein: Before obtaining the preset basic compensation table, the method further includes: When the display panel is in a production stage, obtaining a brightness value of each sub-pixel; Calculating the difference between the brightness value of each sub-pixel and a preset standard brightness value, and determining a basic compensation value for each sub-pixel based on the difference calculation result; The basic compensation value of each sub-pixel is stored in the basic compensation table.

6. The sub-pixel compensation method for a display panel according to claim 1, wherein: The compensating and displaying each sub-pixel in the image to be displayed based on the target compensation value corresponding to each sub-pixel includes: Obtaining the original input value of each sub-pixel in the image to be displayed; Based on the target compensation value corresponding to each sub-pixel, the original input value of each sub-pixel is compensated to obtain a compensated image; The compensated image is displayed.

7. The sub-pixel compensation method for a display panel according to claim 6, wherein: The method of compensating the original input value of each sub-pixel based on the target compensation value corresponding to each sub-pixel to obtain a compensated image includes: Calculating the product of the original input value of each sub-pixel and the target compensation value corresponding to each sub-pixel, and determining the target input value corresponding to each sub-pixel according to the product calculation result; The target input values ​​corresponding to the sub-pixels are combined to obtain the compensated image.

8. A sub-pixel compensation device for a display panel, characterized in that: The device comprises: A first acquisition module is configured to acquire current environment data of an environment in which a display panel is located and historical usage data corresponding to each sub-pixel in the display panel; a determination module, configured to determine an environmental compensation factor that matches the current environmental data based on a preset mapping relationship, wherein the preset mapping relationship is used to represent a mapping relationship between the environmental data and the environmental compensation factor; a prediction module, configured to input the historical usage data and the current environment data into a pre-trained aging prediction model to predict an aging compensation factor corresponding to each sub-pixel; an adjustment module, configured to adjust a basic compensation value corresponding to each sub-pixel based on the environmental compensation factor and the aging compensation factor to obtain a target compensation value corresponding to each sub-pixel; The compensation and display module is used to compensate and display each sub-pixel in the image to be displayed based on the target compensation value corresponding to each sub-pixel.

9. A display device, characterized in that: The display device comprises: a display panel and the sub-pixel compensation device of the display panel according to claim 8; Wherein, the display panel and the sub-pixel compensation device of the display panel are electrically connected.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the sub-pixel compensation method for a display panel according to any one of claims 1 to 7 is implemented.

Images