Method for determining gamma data of OLED screen and display screen

Abstract

The invention provides a method for determining gamma data of an OLED (Organic Light Emitting Diode) screen and a display screen. The method comprises the following steps: constructing a first gamma calculation model; target gamma initial value data is obtained according to the target reference gamma data and the first gamma calculation model, the OLED screen is controlled to emit light based on the target gamma initial value data, the target reference gamma data is a reference value for calculating the target gamma initial value data, and the target gamma initial value data comprises gamma initial values of all registers for controlling the OLED screen to emit light. According to the method, the gamma data of the band0 register can be directly used as the reference value of the gamma value of each band to be input into the gamma calculation model, the gamma values of all the band registers are output at the same time, and ten brightness values can be adjusted within one time.

Description

Technical Field

[0001] The present application relates to the field of display technology, and in particular to a method for determining gamma data of an OLED screen and a display screen. Background Art

[0002] The OTP (One-Time-Programming) initial value algorithm in the OLED module is a one-time programming process that writes initial parameters or specific data into the OLED module. The current OTP initial value algorithm in the OLED module can only determine the gamma data in multiple band registers in sequence. This serial calculation method will cause the OTP adjustment time to be too long. In addition, the OTP adjustment time is greatly affected by the initial value of the gamma register, but the current difference between the initial value of the gamma register and the actual value after the OTP adjustment is successful is large, resulting in a large number of OTP adjustments and a long process time. Therefore, the OTP initial value algorithm in the OLED module in the prior art has a large number of adjustments and a long adjustment time. Summary of the invention

[0003] The main purpose of the present application is to provide a method for determining the gamma data of an OLED screen and a display screen, so as to at least solve the problem in the prior art that the OTP initial value algorithm in the OLED module has a large number of adjustments and a long adjustment time.

[0004] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for determining the gamma data of an OLED screen is provided, comprising: constructing a first gamma calculation model, wherein the first gamma calculation model is trained using multiple groups of training data, and each group of training data in the multiple groups of training data includes: historical reference gamma data and historical actual gamma data corresponding to the historical reference gamma data acquired within a historical time period, wherein the historical actual gamma data is real gamma data used to control the luminescence of the OLED screen at a historical moment, and the historical reference gamma data is a reference value used to calculate target gamma initial value data at a historical moment; according to the target reference gamma data and the first gamma calculation model, target gamma initial value data is obtained, and the OLED screen is controlled to emit light based on the target gamma initial value data, wherein the target reference gamma data is a reference value for calculating the target gamma initial value data, and the target gamma initial value data includes the gamma initial values ​​of all registers that control the luminescence of the OLED screen.

[0005] According to another aspect of the present application, a display screen is provided, the brightness of the display screen is determined based on the gamma data in each register, and the gamma data in each of the registers is determined using any one of the methods for determining the gamma data of the OLED screen.

[0006] Applying the technical solution of the present application, the method for determining the gamma data of the above-mentioned OLED screen first uses the reference value used to calculate the target gamma initial value data at a historical moment and the real gamma data used to control the OLED screen light emission at the corresponding historical moment to train to obtain a first gamma calculation model; then, according to the target reference gamma data and the first gamma calculation model, the target gamma initial value data is obtained, and the OLED screen light emission is controlled based on the target gamma initial value data, wherein the target reference gamma data is a reference value for calculating the target gamma initial value data, and the target gamma initial value data includes the gamma initial values ​​of all registers that control the OLED screen light emission. This method can directly input the gamma data of the band0 register as the reference value of the gamma value of each band into the gamma calculation model, and output the gamma values ​​of all band registers at the same time, so that ten brightnesses can be adjusted in twice the time, and the number of OTP adjustments is reduced, which greatly reduces the process time, and solves the problem that the OTP initial value algorithm in the OLED module in the prior art has a large number of adjustments and a long adjustment time. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] The drawings constituting part of the present application are used to provide a further understanding of the present application. The exemplary embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0008] Figure 1 A schematic flow chart of a method for determining gamma data of an OLED screen provided in accordance with an embodiment of the present application is shown;

[0009] Figure 2 A schematic structural diagram of a grayscale reactor model provided according to an embodiment of the present application is shown;

[0010] Figure 3 A schematic structural diagram of the intermediate layer composition of a grayscale reactor model provided according to an embodiment of the present application is shown;

[0011] Figure 4 A schematic flow chart of another method for determining gamma data of an OLED screen provided in accordance with an embodiment of the present application is shown;

[0012] Figure 5A schematic diagram showing the effect of a method for determining gamma data of an OLED screen provided in an embodiment of the present application is shown;

[0013] Figure 6 A schematic diagram showing the effect of another method for determining gamma data of an OLED screen provided in an embodiment of the present application is shown;

[0014] Figure 7 A schematic diagram showing the effect of another method for determining gamma data of an OLED screen provided in an embodiment of the present application is shown;

[0015] Figure 8 A schematic diagram showing the effect of another method for determining gamma data of an OLED screen provided in an embodiment of the present application is shown;

[0016] Fig. 9 A schematic diagram showing the effect of another method for determining gamma data of an OLED screen provided in an embodiment of the present application is shown;

[0017] Fig.10 A schematic diagram showing the effect of another method for determining gamma data of an OLED screen provided in an embodiment of the present application is shown;

[0018] Fig.11 A schematic structural diagram of a display screen provided according to an embodiment of the present application is shown.

[0019] The above drawings include the following reference numerals:

[0020] 100. Display panel. DETAILED DESCRIPTION

[0021] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0022] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0023] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] For the convenience of description, some nouns or terms involved in the embodiments of the present application are explained below:

[0025] One-time programmable time: One-Time Programmable Time, referred to as OTP time;

[0026] Grayscale reactor model: Gray Response Amplifier, referred to as GRA model.

[0027] As introduced in the background technology, the OTP initial value algorithm in the OLED module in the prior art needs to determine the initial value data of gamma one by one, and adjust the gamma value in the band register one by one, that is, if there are ten brightnesses that need to be adjusted, it is necessary to determine the initial gamma value of the band register in turn, and adjust the gamma value from the initial value to the target value in turn to control the display screen to display the corresponding brightness. It takes ten times the time to adjust the ten brightnesses. This will result in a long adjustment time. In addition, the initial gamma value of the band register determined by the OTP initial value algorithm in the OLED module in the prior art is quite different from the target value that is finally adjusted, which will result in a large number of OTP adjustments and a long process time.

[0028] In order to solve the problem in the prior art that the OTP initial value algorithm in the OLED module has a large number of adjustments and a long adjustment time, the embodiments of the present application provide a method for determining the gamma data of an OLED screen and a display screen.

[0029] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0030] In this embodiment, a method for determining the gamma data of an OLED screen running on a mobile terminal, a computer terminal or a similar computing device is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in an order different from that shown here.

[0031] Figure 1 FIG. 1 is a flow chart of a method for determining gamma data of an OLED screen according to an embodiment of the present application. Figure 2 As shown, the method comprises the following steps:

[0032] Step S101, constructing a first gamma calculation model, wherein the first gamma calculation model is obtained by training using multiple sets of training data, each set of training data in the multiple sets of training data includes: historical reference gamma data and historical actual gamma data corresponding to the historical reference gamma data acquired in a historical time period, the historical actual gamma data is the real gamma data used to control the light emission of the OLED screen at a historical moment, and the historical reference gamma data is the reference value used to calculate the target gamma initial value data at a historical moment;

[0033] Specifically, the band0 register in the OLED module is usually used to set the column address range of the OLED display. By setting the band0 register, the column address range of the OLED display can be specified, thereby controlling the position of the display content on the screen. The function of this register is to ensure that the display content can be correctly displayed at a specific position on the OLED display.

[0034] Among them, there are multiple band registers in the OLED module, namely band0~bandn, the historical reference gamma data is the gamma initial value data of the band0 register used to calculate the gamma values ​​of other band registers at the historical moment, and the historical actual gamma data is the real gamma data of the band1~bandn registers controlling the luminescence of the above OLED screen at the historical moment. By using the historical reference gamma data and the historical actual gamma data for training, the mapping relationship between the gamma initial value data of the band0 register and the real gamma data of the band1~bandn registers can be obtained.

[0035] In addition, the OTP initial value algorithm in the OLED module in the prior art needs to determine the initial value data of the gamma of the band register one by one, and adjust the gamma value in the band register one by one, that is, if there are ten brightnesses that need to be adjusted, it is necessary to determine the initial gamma value of the band register in turn, and adjust the gamma value from the initial value to the target value in turn to control the display screen to display the corresponding brightness. It takes ten times the time to adjust the ten brightnesses. This will result in a long adjustment time. In addition, the initial gamma value of the band register determined by the OTP initial value algorithm in the OLED module in the prior art is quite different from the target value that is finally adjusted, which will result in a large number of OTP adjustments and a long process time.

[0036] The first gamma calculation model can directly input the gamma data of the band0 register as the reference value of the gamma value of each band into the gamma calculation model, and output the gamma values ​​of all band registers at the same time. That is, when there are ten brightnesses that need to be adjusted, the first gamma calculation model inputs the gamma data of ten band0 registers, and outputs the gamma values ​​of ten band registers at the same time, so that ten brightnesses can be adjusted in twice the time. In addition, since the first gamma calculation model is trained based on historical reference gamma data and historical actual gamma data, the gamma output value obtained by using the first gamma calculation model will be closer to the target value to be adjusted in the end, which will reduce the number of OTP adjustments and greatly reduce the process time.

[0037] Before constructing the first gamma calculation model, the method further includes the following steps:

[0038] Step S201, obtaining operating parameters of the target OLED screen, wherein the operating parameters include at least one of the following: size, contrast, resolution, and refresh rate of the OLED screen;

[0039] Step S202, obtaining a second mapping relationship, wherein the second mapping relationship is a mapping relationship between the operating parameters of the OLED screen and the reference gamma data,

[0040] Step S203: determining the target reference gamma data corresponding to the operating parameters of the target OLED screen according to the operating parameters of the target OLED screen and the second mapping relationship.

[0041] Specifically, the reference gamma data of the band register can be accurately determined through the operating parameters of the OLED screen and the mapping relationship between the operating parameters of the OLED screen and the reference gamma data of the band register, wherein the reference gamma data is data pre-set according to the operating parameters of the OLED screen.

[0042] In the OLED module, the gamma data in the band0 register is used to control the brightness and color performance of the display. The gamma value is a nonlinear factor used to adjust the brightness and contrast of the display to make the display more realistic and natural. By adjusting the gamma value, the grayscale level and color saturation of the display can be improved, thereby improving the display effect and viewing experience.

[0043] Among them, constructing the first gamma calculation model includes the following steps:

[0044] Step S301, obtaining an initial gamma calculation model, wherein the initial gamma calculation model is a model based on a grayscale reactor model;

[0045] Among them, the input data dimension of the above initial gamma calculation model is the same as the output data dimension.

[0046] Specifically, the input data dimension of the initial gamma calculation model is the same as the output data dimension, which can greatly reduce the process time of determining the gamma data, so that multiple brightnesses can be adjusted simultaneously in a very short time.

[0047] Step S302, obtaining historical reference gamma data and historical actual gamma data;

[0048] Step S303: input the historical reference gamma data and the historical actual gamma data into the initial gamma calculation model for iterative training, and determine the trained model as the first gamma calculation model.

[0049] Specifically, the Gray Response Amplifier (GRA) model is a grayscale processing technology widely used in OLED (Organic Light Emitting Diode) displays. The model can adjust the grayscale level of the pixels of the OLED display to achieve a more accurate and smooth grayscale performance, improve the display effect and picture quality. The GRA model can improve the color accuracy and brightness uniformity of the OLED display, making the display effect more realistic and delicate.

[0050] The historical reference gamma data and the historical actual gamma data are input into the initial gamma calculation model for iterative training, including the following steps:

[0051] Step S401, inputting the historical reference gamma data into the initial gamma calculation model to perform forward propagation calculation to obtain predicted initial gamma data;

[0052] Wherein, each set of training data includes a plurality of the above-mentioned historical reference gamma data, a plurality of the above-mentioned historical actual gamma data and a plurality of the above-mentioned predicted initial gamma data, the above-mentioned historical reference gamma data, the above-mentioned historical actual gamma data, the above-mentioned predicted initial gamma data and the above-mentioned register correspond one to one, the above-mentioned historical reference gamma data and the above-mentioned historical actual gamma data are input into the above-mentioned initial gamma calculation model for iterative training, and the trained model is determined as the above-mentioned first gamma calculation model, including:

[0053] Step S4011, performing error function calculation on each of the above-mentioned predicted initial gamma data and the corresponding above-mentioned historical actual gamma data to obtain multiple sub-calculation errors;

[0054] Step S4012, when all the sub-calculation errors are less than the preset error value, determining that the iterative training of the initial gamma calculation model is completed, and determining the initial gamma calculation model at this time as the first gamma calculation model;

[0055] Step S4013, when at least one of the above sub-calculation errors is greater than or equal to the above preset error value, back propagation calculation is performed on the above predicted initial gamma data to continue iterative training of the above initial gamma calculation model until all of the above sub-calculation errors are less than the above preset error value.

[0056] Specifically, the error function can be used to accurately judge the accuracy of the model, and the model can be continuously trained according to the accuracy of the model (i.e., continuous forward propagation and backward propagation). During the training process, the parameters and hyperparameters of the model can be continuously adjusted to improve the performance of the model.

[0057] Among them, the parameters and hyperparameters of the algorithm are to help the algorithm learn and adjust the performance of the model. Parameters refer to model parameters such as weights and biases obtained by the algorithm through learning, which directly affect the output of the model. Hyperparameters are parameters that need to be set manually before model training, such as learning rate, regularization parameters, etc. The selection of hyperparameters will directly affect the performance and training effect of the model. By adjusting parameters and hyperparameters, the model can be better fitted to the data, the generalization ability of the model can be improved, and better prediction results can be obtained. Therefore, the selection of parameters and hyperparameters requires careful debugging and optimization.

[0058] Step S402, performing loss function calculation on the predicted initial gamma data and the corresponding historical actual gamma data to obtain a calculation error, wherein the predicted initial gamma data and the historical actual gamma data correspond one to one;

[0059] Step S403, determining whether the iterative training of the initial gamma calculation model is completed according to the size of the calculation error.

[0060] Specifically, the error function can be used to accurately predict the accuracy of the model. The smaller the error, the higher the accuracy of the model.

[0061] Among them, according to the size of the above-mentioned calculation error, determining whether the iterative training of the above-mentioned initial gamma calculation model is completed, including: when the above-mentioned calculation error is less than the preset error value, determining that the iterative training of the above-mentioned initial gamma calculation model is completed, and determining the above-mentioned initial gamma calculation model at this time as the above-mentioned first gamma calculation model.

[0062] Specifically, since the purpose of the model is to make the predicted gamma data output by the model infinitely close to the actual gamma data, the actual gamma data is used as the standard. When the calculation error is less than the preset error value, it is proved that the accuracy of the initial gamma calculation model meets the standard requirements. At this time, the initial gamma calculation model is the first gamma calculation model.

[0063] The initial gamma calculation model includes an input layer, a hidden layer, and an output layer. According to the size of the calculation error, determining whether the iterative training of the initial gamma calculation model is completed also includes the following steps:

[0064] Step S4031, when the calculation error is greater than or equal to the preset error value, performing back propagation calculation on the predicted initial gamma data;

[0065] Step S4032, obtain an optimizer, and adjust the weights of each layer in the initial gamma calculation model based on the calculation error and the optimizer to continue iterative training of the initial gamma calculation model until the calculation error is less than the preset error value.

[0066] Specifically, when the calculation error is greater than or equal to the preset error value, it proves that the accuracy of the initial gamma calculation model at the current moment does not meet the requirements, so it is necessary to continue to train the initial gamma calculation model so that the accuracy of the initial gamma calculation model meets the standard requirements. In the process of training the initial gamma calculation model, the weights of each layer in the initial gamma calculation model are adjusted through back propagation calculation, and the parameters and hyperparameters of the model are adjusted using an optimizer, so as to optimize the performance of the model.

[0067] Among them, Figure 2 As shown, the input X of the neural network model includes m data, and the output value Ypre is obtained by forward propagation through multiple n layers of processing, where Ypre has the same dimension as X and also includes m data. The real value Yreal is used to compare the model output value Ypre with the loss function, and back propagation is performed according to the comparison result to train the neural network model, where Ypre is the predicted initial gamma data, Yreal is the actual gamma data, and layer1...layern are the first layer...nth layer of the neural network model respectively.

[0068] The hidden layer of the initial gamma calculation model includes a batch normalization layer, a linear layer, and an activation layer. The historical reference gamma data and the historical actual gamma data are input into the initial gamma calculation model for iterative training, which includes the following steps:

[0069] Step S501, normalizing the historical reference gamma data based on the batch normalization layer to obtain normalized gamma data;

[0070] Step S502, performing a nonlinear change on the normalized gamma data based on the linear layer to obtain nonlinearly changed gamma data;

[0071] Step S503, processing the gamma data after the nonlinear change based on the activation layer to perform iterative training.

[0072] Specifically, in a neural network, a batch normalization layer can accelerate the training process of the neural network, reduce the problem of gradient vanishing or gradient exploding, reduce the dependence of the neural network on the initial weights, improve the stability of the model, reduce the risk of overfitting, improve the generalization ability of the model, and make it easier for the neural network to converge to the optimal solution. The linear layer is a basic component in a neural network, which is used to perform linear transformation and feature extraction on the input data. It can realize the weighted summation of the input data to obtain a new feature representation, and can learn the relationship and pattern between the input data, thereby improving the expressiveness of the model. The activation function in the activation layer can introduce nonlinear factors, so that the neural network has stronger expressiveness, can enable the neural network to learn nonlinear relationships and patterns, improve the fitting ability of the model, and can solve the problem of gradient vanishing or gradient exploding, making the neural network training more stable and efficient.

[0073] Among them, Figure 3 As shown, the i-th layer of the neural network model consists of a normalization layer, a linear layer and an activation layer, and the neural network model has a total of n layers.

[0074] Step S102, obtaining target gamma initial value data according to the target reference gamma data and the above-mentioned first gamma calculation model, and controlling the luminescence of the above-mentioned OLED screen based on the above-mentioned target gamma initial value data, wherein the above-mentioned target reference gamma data is a reference value for calculating the target gamma initial value data, and the above-mentioned target gamma initial value data includes the gamma initial values ​​of all registers that control the luminescence of the above-mentioned OLED screen.

[0075] Specifically, the target reference gamma data is input into the first gamma calculation model, and the output target gamma initial value data is very close to the actual gamma value that ultimately controls the luminescence of the OLED screen, which greatly reduces the number and time of OTP adjustments.

[0076] Wherein, obtaining target gamma initial value data according to target reference gamma data and the above-mentioned first gamma calculation model includes the following steps:

[0077] Step S601, extracting model parameters of the first gamma calculation model;

[0078] Step S602, importing the model parameters of the first gamma calculation model into the OTP algorithm to obtain a second gamma calculation model, wherein the second gamma calculation model is a calculation model in the OTP algorithm having the same structure and parameters as the first gamma calculation model;

[0079] Among them, importing the model parameters of the above-mentioned first gamma calculation model into the OTP algorithm to obtain the second gamma calculation model includes: importing the forward propagation calculation parameters of the above-mentioned first gamma calculation model into the OTP algorithm to obtain the above-mentioned second gamma calculation model.

[0080] Specifically, the forward propagation calculation parameters of the neural network refer to the parameters used in the forward propagation process of the neural network, which are used to calculate the input data through the neurons of each layer and finally obtain the output result. These parameters include parameters such as the weight and bias of each layer, which are used to calculate the output of each layer. The back propagation calculation parameters refer to the parameters used in the back propagation process of the neural network, which are used to calculate the gradient according to the loss function and update the parameters of each layer to minimize the loss function. These parameters include parameters such as the gradient value and learning rate of each layer, which are used to calculate the updated value of the parameters of each layer.

[0081] Therefore, the forward propagation parameters are used to calculate the output of the neural network, while the back propagation parameters are used to update the parameters of the neural network to improve the performance of the model. The two play different but complementary roles in the training process of the neural network.

[0082] Since the first gamma calculation model is already a trained model, it is only necessary to input the forward propagation calculation parameters into the OTP algorithm to obtain a runnable second gamma calculation model without transmitting the back propagation calculation parameters to waste computing and storage resources.

[0083] Step S603: input the target reference gamma data as an input value into the second gamma calculation model, and obtain the output of the second gamma calculation model as the target gamma initial value data.

[0084] Specifically, the model parameters of the first gamma calculation model are imported into the OTP algorithm to directly obtain the second gamma calculation model that is the same as the first gamma calculation model. The model parameters of the first gamma calculation model are imported into the OTP algorithm to obtain the second gamma calculation model. In subsequent applications, there is no need to execute the OTP algorithm and the first gamma calculation model separately, but the gamma data of band0 is directly input into the OTP algorithm, and finally the initial gamma values ​​of band1 to bandn are obtained.

[0085] The initial values ​​of the OTP algorithm in the OLED module are used to initialize and calibrate the OLED module. These initial values ​​include the brightness, contrast, color and other parameters of the OLED. By adjusting these initial values, the OLED display effect can be made clearer, more accurate and more stable. The purpose of these initial values ​​is to ensure the consistency and stability of the OLED display effect, so that it can achieve the best display effect in different environments.

[0086] The OTP (One-Time-Programming) initial value algorithm in the OLED module is a one-time programming process used to write initial parameters or specific data into the OLED module. This algorithm is usually designed and implemented by the manufacturer of the OLED module, and its specific implementation method may vary depending on the different OLED module models and manufacturers. Generally speaking, this algorithm will write the initial parameters or specific data into the OTP memory of the OLED module to ensure that the OLED module can work properly and have the preset characteristics when it leaves the factory. This process is usually completed during the manufacturing process, and once completed, the data cannot be modified or erased, so it is called one-time programming.

[0087] There is a certain relationship between the OTP adjustment time and the initial value of the gamma register. This is because the OTP adjustment time and the initial value of the gamma register are used to adjust the parameters of the display screen, thereby affecting the display effect. Generally speaking, the initial value of the gamma register affects the brightness and contrast of the display screen, while the OTP adjustment time affects the response speed and stability of the display screen. Therefore, there is a certain correlation between the two. By adjusting the initial value of the gamma register, the display effect can be affected, thereby indirectly affecting the demand for the OTP adjustment time. Therefore, the relationship between the adjustment time and the initial value of the gamma register needs to be analyzed and adjusted according to the specific display screen and requirements.

[0088] Among them, there are multiple target reference gamma data, there are multiple target gamma initial value data, the target reference gamma data correspond to the target gamma initial value data one by one, each of the target gamma initial value data is the gamma initial value of the corresponding register, the target reference gamma data is input as an input value into the second gamma calculation model, and the output of the second gamma calculation model is the target gamma initial value data, including: all the target gamma reference data are input into the second gamma calculation model at the same time, so that the second gamma calculation model simultaneously outputs all the target gamma initial value data.

[0089] Specifically, this can use twice the time to obtain all target gamma initial value data at the same time, greatly saving process time.

[0090] Wherein, controlling the OLED screen to emit light based on the target gamma initial value data comprises the following steps:

[0091] Step S701, inputting the above target gamma initial value data into the OTP algorithm;

[0092] Among them, the above-mentioned target gamma initial value data of different registers are different.

[0093] Specifically, different band registers may have different uses or functions, so their gamma initial value data will also be different. Gamma values ​​are usually used to adjust the brightness and contrast of the display to ensure the accuracy and clarity of the image display. Different band registers may require different gamma initial value data to meet specific display requirements or application scenarios. Therefore, even adjacent band registers may have different gamma initial value data.

[0094] Wherein, an absolute value of a difference between the target gamma initial value data of one of the registers and the corresponding target gamma data is less than or equal to a preset absolute value.

[0095] Specifically, since the second gamma calculation model is the same model as the first gamma calculation model, and the first gamma calculation model is trained using reference gamma data and actual gamma data, the target gamma initial value data of the register obtained using the second gamma calculation model is very close to the target gamma data ultimately used to control the light emission of the OLED screen, which will greatly reduce the number of OTP adjustments and the adjustment time.

[0096] Step S702, using the above-mentioned OTP algorithm and based on the above-mentioned target gamma initial value data corresponding to each of the above-mentioned registers, the gamma data of each of the above-mentioned registers is adjusted to obtain the target gamma data corresponding to the above-mentioned register, and the above-mentioned target gamma data is used to control the above-mentioned OLED screen to display the target brightness.

[0097] Specifically, the second gamma calculation model is used to obtain only the initial gamma value data of the register, and the OTP algorithm is also needed to adjust the initial gamma value data to obtain the target gamma data that ultimately controls the target brightness displayed by the OLED screen. Since the target gamma initial value data is very close to the target gamma data that is ultimately used to control the luminescence of the OLED screen, the number of OTP adjustments and the adjustment time will be greatly reduced.

[0098] The OTP algorithm is used to adjust the gamma data of each of the registers based on the target gamma initial value data corresponding to each of the registers to obtain the target gamma data corresponding to the registers, including the following steps:

[0099] Step S7021, obtaining the target display brightness of the OLED screen;

[0100] Step S7022, obtaining a first mapping relationship, where the first mapping relationship is a correspondence between the display brightness of the OLED screen and the gamma data of each of the registers;

[0101] Step S7023, determining the target gamma data corresponding to each of the above registers according to the target display brightness of the above OLED screen and the above first mapping relationship.

[0102] Specifically, since the gamma data in the band0 register is used to control the brightness and color performance of the display screen, and is used to adjust the brightness and contrast of the display, by adjusting the gamma value, the grayscale level and color saturation of the display screen can be improved, thereby improving the display effect and viewing experience. Therefore, it is necessary to first determine the target display brightness required by the OLED screen in order to determine the final gamma data value required by each band register, and use this gamma value as a standard to adjust the gamma data in the band register.

[0103] Among them, the above method also includes: obtaining multiple data adjustment times, the above data adjustment times correspond one-to-one to the above registers, the above data adjustment times are the adjustment times for adjusting the gamma data of the above registers using the above OTP algorithm and based on the corresponding above target gamma initial value data, and the above data adjustment time is less than or equal to the preset time.

[0104] Specifically, since the target gamma initial value data is very close to the target gamma data ultimately used to control the luminescence of the OLED screen, the number of OTP adjustments and the adjustment time will be greatly reduced, that is, the OTP adjustment time using the above embodiment is much shorter than the OTP adjustment time in the prior art.

[0105] The method for determining the gamma data of the above-mentioned OLED screen of the present application first uses the reference value used to calculate the target gamma initial value data at a historical moment and the real gamma data used to control the OLED screen light emission at the corresponding historical moment to train to obtain a first gamma calculation model; then, according to the target reference gamma data and the first gamma calculation model, the target gamma initial value data is obtained, and the OLED screen light emission is controlled based on the target gamma initial value data, wherein the target reference gamma data is a reference value for calculating the target gamma initial value data, and the target gamma initial value data includes the gamma initial values ​​of all registers that control the OLED screen light emission. This method can directly input the gamma data of the band0 register as the reference value of the gamma value of each band into the gamma calculation model, and output the gamma values ​​of all band registers at the same time, so that ten brightnesses can be adjusted in twice the time, and the number of OTP adjustments is reduced, which greatly reduces the process time, and solves the problem of a large number of adjustments and a long adjustment time of the OTP initial value algorithm in the OLED module in the prior art.

[0106] Figure 4 FIG. 1 is a flow chart of another method for determining the gamma data of an OLED screen. Figure 4 As shown, the above method first performs data analysis through the OTP algorithm to obtain historical reference gamma data and the corresponding historical actual gamma data, and then batch imports the historical reference gamma data and the corresponding historical actual gamma data into the MySQL lightweight database system to obtain the gamma data table, and then reads the data in the gamma data table and establishes a Ctorch framework algorithm model with different structures for each project to train the GRA algorithm model, and then iterates the training of the GRA algorithm model to obtain the trained GRA algorithm model as the first gamma calculation model. The model parameters of the first gamma calculation model are exported to the OTP program, and the GRA algorithm model with the same structure in the OTP is obtained as the second gamma calculation model, and then the gamma reference data of band0 is input into the second gamma calculation model, and the model output is the gamma initial value data of band1 to bandn.

[0107] Figures 5 to 10 They are schematic diagrams showing the effects of a method for determining the gamma data of an OLED screen, and a large amount of data is used to verify the effects of the method for determining the gamma data of the OLED screen.

[0108] like Figure 5As shown, when the grayscale value is 0, the data whose error between the target gamma initial value data and the target gamma data of the band1 register is in the range of <5 accounts for 87% of the overall test data, the data whose error between the target gamma initial value data and the target gamma data of the band1 register is in the range of greater than 5 and less than 10 accounts for 12.86% of the overall test data, the data whose error between the target gamma initial value data and the target gamma data of the band1 register is in the range of greater than 10 and less than 15 accounts for 0.15% of the overall test data, and the data whose error between the target gamma initial value data and the target gamma data of the band1 register is in the range of greater than 15 accounts for 0% of the overall test data.

[0109] like Figure 6 As shown, when the grayscale value is 1, the data whose error between the target gamma initial value data and the target gamma data of the band1 register is in the range of <5 accounts for 99.25% of the overall test data, the data whose error between the target gamma initial value data and the target gamma data of the band1 register is in the range of greater than 5 and less than 10 accounts for 0.75% of the overall test data, and the data whose error between the target gamma initial value data and the target gamma data of the band1 register is in the range of greater than 10 accounts for 0% of the overall test data.

[0110] like Figure 7 As shown, when the grayscale value is 2, the data whose error between the target gamma initial value data and the target gamma data of the band1 register is in the range of <5 accounts for 98.95% of the overall test data, the data whose error between the target gamma initial value data and the target gamma data of the band1 register is in the range of greater than 5 and less than 10 accounts for 1.05% of the overall test data, and the data whose error between the target gamma initial value data and the target gamma data of the band1 register is in the range of greater than 10 accounts for 0% of the overall test data.

[0111] like Figure 8 As shown, when the grayscale value is 3, the data whose error between the target gamma initial value data and the target gamma data of the band1 register is in the range of <5 accounts for 95.37% of the overall test data, the data whose error between the target gamma initial value data and the target gamma data of the band1 register is in the range of greater than 5 and less than 10 accounts for 4.63% of the overall test data, and the data whose error between the target gamma initial value data and the target gamma data of the band1 register is in the range of greater than 10 accounts for 0% of the overall test data.

[0112] like Fig. 9As shown, when the grayscale value is 4, the data whose error between the target gamma initial value data and the target gamma data of the band1 register is in the range of <5 accounts for 99.25% of the overall test data, the data whose error between the target gamma initial value data and the target gamma data of the band1 register is in the range of greater than 5 and less than 10 accounts for 0.75% of the overall test data, and the data whose error between the target gamma initial value data and the target gamma data of the band1 register is in the range of greater than 10 accounts for 0% of the overall test data.

[0113] like Fig.10 As shown, when the grayscale value is 5, the data whose error between the target gamma initial value data and the target gamma data of the band1 register is in the range of <5 accounts for 98.8% of the overall test data, the data whose error between the target gamma initial value data and the target gamma data of the band1 register is in the range of greater than 5 and less than 10 accounts for 1.2% of the overall test data, and the data whose error between the target gamma initial value data and the target gamma data of the band1 register is in the range of greater than 10 accounts for 0% of the overall test data.

[0114] It can be seen from the above test data that the error between the target gamma initial value data of the band register obtained by the method for determining the gamma data of the above-mentioned OLED screen and the target gamma data is generally controlled within the range of less than 5, and the error of a small amount of data is within the range of greater than 5 and less than 10. It can be determined that the initial gamma value obtained by the determination method of the present application will be closer to the target value to be finally adjusted, which will reduce the number of OTP adjustments and the adjustment time, and greatly reduce the process time.

[0115] In this embodiment, a display screen is also provided. Fig.11 A schematic diagram of a display screen provided by an embodiment of the present invention, such as Fig.11 As shown, the display screen further includes a display panel 100. The brightness of the display screen is determined according to the gamma data in each register, and the gamma data in each of the above registers is determined by using any of the above methods for determining the gamma data of the OLED screen.

[0116] In addition to the OLED main screen, other bands in the OLED module may include touch screen, fingerprint reader, camera, speaker, microphone and other components. These components can be integrated with the OLED main screen to form a complete OLED module for use in mobile phones, tablets, smart watches and other devices.

[0117] The brightness of the display screen of the present application is determined according to the gamma data in each register, and the gamma data in each register is determined by any of the above-mentioned methods for determining the gamma data of the OLED screen. The display screen can directly input the gamma data of the band0 register as the reference value of the gamma value of each band into the gamma calculation model, and output the gamma values ​​of all band registers at the same time, so that ten brightnesses can be adjusted in twice the time, and the number of OTP adjustments is reduced, which greatly reduces the process time, and solves the problem that the OTP initial value algorithm in the OLED module in the prior art has a large number of adjustments and a long adjustment time.

[0118] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0119] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

[0120] 1) The method for determining the gamma data of the above-mentioned OLED screen of the present application first uses the reference value used to calculate the target gamma initial value data at a historical moment and the real gamma data used to control the OLED screen light emission at the corresponding historical moment to train to obtain the first gamma calculation model; then, according to the target reference gamma data and the first gamma calculation model, the target gamma initial value data is obtained, and the OLED screen light emission is controlled based on the target gamma initial value data, wherein the target reference gamma data is a reference value for calculating the target gamma initial value data, and the target gamma initial value data includes the gamma initial values ​​of all registers that control the OLED screen light emission. This method can directly input the gamma data of the band0 register as the reference value of the gamma value of each band into the gamma calculation model, and output the gamma values ​​of all band registers at the same time, so that ten brightnesses can be adjusted in twice the time, and the number of OTP adjustments is reduced, which greatly reduces the process time, and solves the problem that the OTP initial value algorithm in the OLED module in the prior art has a large number of adjustments and a long adjustment time.

[0121] 2) The brightness of the above-mentioned display screen of the present application is determined according to the gamma data in each register, and the gamma data in each of the above-mentioned registers is determined by any of the above-mentioned methods for determining the gamma data of the OLED screen. The display screen can directly input the gamma data of the band0 register as the reference value of the gamma value of each band into the gamma calculation model, and output the gamma values ​​of all band registers at the same time. Ten brightness levels can be adjusted in twice the time, and the number of OTP adjustments is reduced, which greatly reduces the process time and solves the problem that the OTP initial value algorithm in the OLED module in the prior art has a large number of adjustments and a long adjustment time.

[0122] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for determining gamma data of an OLED screen, characterized in that: include: Constructing a first gamma calculation model, wherein the first gamma calculation model is obtained by training using multiple sets of training data, each set of training data in the multiple sets of training data includes: historical reference gamma data and historical actual gamma data corresponding to the historical reference gamma data acquired in a historical time period, wherein the historical actual gamma data is real gamma data used to control the light emission of the OLED screen at a historical moment, and the historical reference gamma data is a reference value used to calculate target gamma initial value data at a historical moment; According to the target reference gamma data and the first gamma calculation model, the target gamma initial value data is obtained, and the OLED screen is controlled to emit light based on the target gamma initial value data, wherein the target reference gamma data is a reference value for calculating the target gamma initial value data, and the target gamma initial value data includes the gamma initial values ​​of all registers that control the OLED screen to emit light.

2. The determination method according to claim 1, characterized in that: Construct the first gamma calculation model, including: Acquire an initial gamma calculation model, wherein the initial gamma calculation model is a model based on a grayscale reactor model; Obtain historical reference gamma data and historical actual gamma data; The historical reference gamma data and the historical actual gamma data are input into the initial gamma calculation model for iterative training, and the trained model is determined as the first gamma calculation model.

3. The determination method according to claim 2, characterized in that: Inputting the historical reference gamma data and the historical actual gamma data into the initial gamma calculation model for iterative training includes: Inputting the historical reference gamma data into the initial gamma calculation model for forward propagation calculation to obtain predicted initial gamma data; Perform loss function calculation on the predicted initial gamma data and the corresponding historical actual gamma data to obtain a calculation error, wherein the predicted initial gamma data and the historical actual gamma data correspond one to one; According to the size of the calculation error, it is determined whether the iterative training of the initial gamma calculation model is completed.

4. The determination method according to claim 3, characterized in that: Determining whether the iterative training of the initial gamma calculation model is completed according to the size of the calculation error includes: When the calculation error is less than the preset error value, it is determined that the iterative training of the initial gamma calculation model is completed, and the initial gamma calculation model at this time is determined as the first gamma calculation model.

5. The determination method according to claim 3, characterized in that: The initial gamma calculation model includes an input layer, a hidden layer, and an output layer. According to the size of the calculation error, determining whether the iterative training of the initial gamma calculation model is completed includes: When the calculation error is greater than or equal to a preset error value, performing back propagation calculation on the predicted initial gamma data; Obtain an optimizer, and adjust the weights of each layer in the initial gamma calculation model based on the calculation error and the optimizer to continue iterative training of the initial gamma calculation model until the calculation error is less than the preset error value.

6. The determination method according to claim 3, characterized in that: Each set of training data includes a plurality of the historical reference gamma data, a plurality of the historical actual gamma data, and a plurality of the predicted initial gamma data, the historical reference gamma data, the historical actual gamma data, the predicted initial gamma data and the register correspond to each other one by one, the historical reference gamma data and the historical actual gamma data are input into the initial gamma calculation model for iterative training, and the trained model is determined as the first gamma calculation model, including: Perform error function calculation on each of the predicted initial gamma data and the corresponding historical actual gamma data to obtain multiple sub-calculation errors; When all the sub-calculation errors are less than a preset error value, determining that the iterative training of the initial gamma calculation model is completed, and determining the initial gamma calculation model at this time as the first gamma calculation model; When at least one of the sub-calculation errors is greater than or equal to the preset error value, back-propagation calculation is performed on the predicted initial gamma data to continue iterative training of the initial gamma calculation model until all of the sub-calculation errors are less than the preset error value.

7. The determination method according to claim 2, characterized in that: The input data dimension and output data dimension of the initial gamma calculation model are the same.

8. The determination method according to claim 2, characterized in that: The hidden layer of the initial gamma calculation model includes a batch normalization layer, a linear layer and an activation layer, and the historical reference gamma data and the historical actual gamma data are input into the initial gamma calculation model for iterative training, including: Normalizing the historical reference gamma data based on the batch normalization layer to obtain normalized gamma data; Performing a nonlinear change on the normalized gamma data based on the linear layer to obtain nonlinearly changed gamma data; The nonlinearly changed gamma data is processed based on the activation layer to perform iterative training.

9. The determination method according to claim 1, characterized in that: According to the target reference gamma data and the first gamma calculation model, target gamma initial value data is obtained, including: Extracting model parameters of the first gamma calculation model; Importing the model parameters of the first gamma calculation model into the OTP algorithm to obtain a second gamma calculation model, wherein the second gamma calculation model is a calculation model in the OTP algorithm with the same structure and parameters as the first gamma calculation model; The target reference gamma data is input as an input value into the second gamma calculation model, and the output of the second gamma calculation model is the target gamma initial value data.

10. The determination method according to claim 9, characterized in that: Importing the model parameters of the first gamma calculation model into the OTP algorithm to obtain a second gamma calculation model, including: The forward propagation calculation parameters of the first gamma calculation model are imported into the OTP algorithm to obtain the second gamma calculation model.

11. The determination method according to claim 9, characterized in that: There are a plurality of target reference gamma data, there are a plurality of target gamma initial value data, the target reference gamma data correspond to the target gamma initial value data one by one, each of the target gamma initial value data is the gamma initial value of the corresponding register, the target reference gamma data is input as an input value into the second gamma calculation model, and the output of the second gamma calculation model is the target gamma initial value data, including: All of the target gamma reference data are simultaneously input into the second gamma calculation model, so that the second gamma calculation model simultaneously outputs all of the target gamma initial value data.

12. The determination method according to claim 1, characterized in that: Controlling the OLED screen to emit light based on the target gamma initial value data includes: Inputting the target gamma initial value data into the OTP algorithm; The OTP algorithm is used to adjust the gamma data of each register based on the target gamma initial value data corresponding to each register to obtain the target gamma data corresponding to the register, and the target gamma data is used to control the target brightness displayed by the OLED screen.

13. The determination method according to claim 12, characterized in that: The OTP algorithm is used and based on the target gamma initial value data corresponding to each register, the gamma data of each register is adjusted to obtain the target gamma data corresponding to the register, including: Obtaining the target display brightness of the OLED screen; Acquire a first mapping relationship, where the first mapping relationship is a correspondence between the display brightness of the OLED screen and the gamma data of each of the registers; According to the target display brightness of the OLED screen and the first mapping relationship, the target gamma data corresponding to each of the registers is determined.

14. The determination method according to claim 12, characterized in that: The target gamma initial value data of different registers are different.

15. The determination method according to claim 12, characterized in that: An absolute value of a difference between the target gamma initial value data of one of the registers and the corresponding target gamma data is less than or equal to a preset absolute value.

16. The determination method according to claim 12, characterized in that: The method further comprises: Acquire multiple data adjustment times, the data adjustment times corresponding to the registers one by one, the data adjustment times are the adjustment times for adjusting the gamma data of the registers using the OTP algorithm and based on the corresponding target gamma initial value data, and the data adjustment time is less than or equal to a preset time.

17. The determination method according to claim 1, characterized in that: Before constructing the first gamma calculation model, the method further includes: Obtaining operating parameters of the target OLED screen, wherein the operating parameters include at least one of the following: size, contrast, resolution, and refresh rate of the OLED screen; Acquire a second mapping relationship, where the second mapping relationship is a mapping relationship between an operating parameter of the OLED screen and reference gamma data, According to the operating parameters of the target OLED screen and the second mapping relationship, the target reference gamma data corresponding to the operating parameters of the target OLED screen is determined.

18. A display screen, characterized in that: The brightness of the display screen is determined based on the gamma data in each register, and the gamma data in each register is determined by the method for determining the gamma data of the OLED screen described in any one of claims 1 to 17.

Images