Dynamic adjustment method and device of grid voltage, storage medium and electronic equipment

Abstract

The invention relates to a grid voltage dynamic adjustment method and device, a storage medium and electronic equipment, and relates to the technical field of voltage adjustment, and the method comprises the steps: obtaining a to-be-detected light-emitting frequency band included in a to-be-detected OLED display screen and first RGB gamma fine tuning data corresponding to the to-be-detected light-emitting frequency band; performing feature selection on the first RGB gamma fine adjustment data to obtain a first associated feature required for dynamically adjusting a gate voltage corresponding to the to-be-detected light-emitting frequency band; based on a preset voltage range prediction model and the first correlation feature, determining a voltage adjustment range of the gate voltage of the to-be-detected light-emitting frequency band; and dynamically adjusting the grid voltage of the to-be-detected light-emitting frequency band according to the voltage adjustment range until all to-be-detected light-emitting frequency bands included in the to-be-detected OLED display screen are adjusted. The dynamic adjustment efficiency of the grid voltage is improved.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the technical field of voltage adjustment, and in particular, to a method for dynamically adjusting a gate voltage, a device for dynamically adjusting a gate voltage, a computer-readable storage medium, and an electronic device. Background Art

[0002] In existing voltage adjustment methods, the voltage adjustment range of a light-emitting band is determined according to the highest voltage of a gamma fine-tuning module of the light-emitting band. However, the voltage adjustment range obtained based on this method is too large, resulting in a low voltage adjustment efficiency for a single light-emitting band.

[0003] It should be noted that the information disclosed in the above background art is only used to enhance the understanding of the background of the present disclosure, and thus may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0004] An object of the present disclosure is to provide a method for dynamically adjusting a gate voltage, a device for dynamically adjusting a gate voltage, a computer-readable storage medium, and an electronic device, so as to at least overcome to some extent the problem of low voltage adjustment efficiency caused by limitations and defects of related technologies.

[0005] According to one aspect of the present disclosure, there is provided a method for dynamically adjusting a gate voltage, including:

[0006] Obtaining a to-be-detected light-emitting band included in a to-be-detected OLED display screen and first RGB gamma fine-tuning data corresponding to the to-be-detected light-emitting band;

[0007] Performing feature selection on the first RGB gamma fine-tuning data to obtain first correlation features required for dynamically adjusting the gate voltage corresponding to the to-be-detected light-emitting band;

[0008] Based on a preset voltage range prediction model and the first correlation features, determining a voltage adjustment range of the gate voltage of the to-be-detected light-emitting band;

[0009] Dynamically adjusting the gate voltage of the to-be-detected light-emitting band according to the voltage adjustment range until the adjustment of all to-be-detected light-emitting bands included in the to-be-detected OLED display screen is completed.

[0010] In an exemplary embodiment of the present disclosure, performing feature selection on the first RGB gamma fine-tuning data to obtain first correlation features required for dynamically adjusting the gate voltage corresponding to the to-be-detected light-emitting band includes:

[0011] Determine the first original data features included in the first RGB gamma fine-tuning data and the first original feature values corresponding to the first original data features;

[0012] Determine the first original brightness response value corresponding to the first original feature value, and calculate the first correlation coefficient between the first original feature value and the first original brightness response value;

[0013] Construct a first correlation coefficient matrix between the first original feature value and the first original brightness response value according to the first correlation coefficient;

[0014] Extract the first associated features required for dynamically adjusting the gate voltage corresponding to the to-be-detected light-emitting frequency band from the first original data features according to the first correlation coefficient matrix.

[0015] In an exemplary embodiment of the present disclosure, calculating the first correlation coefficient between the first original feature value and the first original brightness response value includes:

[0016] Determine the first feature mean of the first original feature value, and determine the first feature covariance and the first feature standard deviation of the first original feature value according to the first feature mean;

[0017] Determine the first brightness response mean of the first original brightness response value, and determine the first brightness response covariance and the first brightness response standard deviation of the first original brightness response value according to the first brightness response mean;

[0018] Determine the first correlation coefficient between the first original feature value and the first original brightness response value according to the first feature covariance, the first feature standard deviation, the first brightness response covariance, and the first brightness response standard deviation.

[0019] In an exemplary embodiment of the present disclosure, based on a preset voltage range prediction model and the first associated features, determining the voltage adjustment range of the gate voltage of the to-be-detected light-emitting frequency band includes:

[0020] Perform normalization processing on the first associated feature values of the first associated features to obtain first normalized feature values, and splice the first normalized feature values to obtain a first spliced feature;

[0021] Input the first spliced feature into the preset voltage range prediction model to obtain the voltage adjustment range of the gate voltage of the to-be-detected light-emitting frequency band.

[0022] In an exemplary embodiment of the present disclosure, the preset voltage range prediction model includes an input layer, a first feature hidden layer, a second feature hidden layer, …, an Nth feature hidden layer, and an output layer;

[0023] Wherein, inputting the first splicing feature into the preset voltage range prediction model to obtain the voltage scanning range of the gate voltage of the to-be-detected light-emitting band includes:

[0024] Based on the input layer receiving the first splicing feature and transmitting the first splicing feature to the first feature hidden layer;

[0025] Based on the first feature hidden layer extracting features from the first splicing feature to obtain a first feature extraction result, and based on the second feature hidden layer performing a non-linear transformation on the first feature extraction result to obtain a second feature extraction result;

[0026] Sequentially repeat the determination process of the second feature extraction result to obtain an Nth feature extraction result corresponding to the Nth feature hidden layer;

[0027] Based on the output layer predicting the voltage range for the Nth feature extraction result to obtain the voltage scanning range of the gate voltage of the to-be-detected light-emitting band.

[0028] In an exemplary embodiment of the present disclosure, the preset voltage range prediction model is obtained in the following manner:

[0029] Obtain the detected light-emitting bands included in the detected OLED display screen, the second RGB gamma fine-tuning data corresponding to the to-be-detected light-emitting band, and the target voltage range;

[0030] Perform feature selection on the second RGB gamma fine-tuning data to obtain a second correlation feature required for dynamically adjusting the gate voltage corresponding to the detected light-emitting band;

[0031] Input the second correlation feature into the neural network model to be trained to obtain a range prediction result of the gate voltage of the detected light-emitting band;

[0032] Construct a loss function according to the range prediction result and the target voltage range, and based on the loss function, adjust the parameters of the neural network model to be trained to obtain the preset voltage range prediction model.

[0033] In an exemplary embodiment of the present disclosure, dynamically adjusting the gate voltage of the to-be-detected light-emitting band according to the voltage adjustment range includes:

[0034] Extract the maximum voltage value from the voltage adjustment range, and determine the current gate voltage of the to-be-detected light-emitting band according to the maximum voltage value;

[0035] Collect the current brightness value of the to-be-detected light-emitting band under the current gate voltage, and determine whether the current brightness value meets a preset brightness condition;

[0036] When it is determined that the current brightness value meets the preset brightness condition, determine the optimal gate voltage value of the to-be-detected light-emitting band according to the current gate voltage, so as to dynamically adjust the gate voltage of the to-be-detected light-emitting band.

[0037] In an exemplary embodiment of the present disclosure, determining whether the current brightness value meets a preset brightness condition includes:

[0038] Obtain the target brightness value of the to-be-detected light-emitting band under the current gate voltage, and determine whether the current brightness value meets the preset brightness condition according to the current brightness value and the target brightness value; wherein, if the current brightness value is greater than or equal to the target brightness value, it is determined that the current brightness value meets the preset brightness condition; if the current brightness value is less than the target brightness value, it is determined that the current brightness value does not meet the preset brightness condition.

[0039] In an exemplary embodiment of the present disclosure, determining the optimal gate voltage value of the to-be-detected light-emitting band according to the current gate voltage includes:

[0040] Determine the brightening compensation voltage of the to-be-detected light-emitting band under the condition of the target brightness value, and determine the optimal gate voltage value of the to-be-detected light-emitting band according to the brightening compensation voltage and the current gate voltage.

[0041] According to one aspect of the present disclosure, there is provided a device for dynamically adjusting a gate voltage, including:

[0042] A fine-tuning data acquisition module, configured to acquire a to-be-detected light-emitting band included in the to-be-detected OLED display screen and first RGB gamma fine-tuning data corresponding to the to-be-detected light-emitting band;

[0043] A first associated feature selection module, configured to perform feature selection on the first RGB gamma fine-tuning data to obtain a first associated feature required for dynamically adjusting the gate voltage corresponding to the to-be-detected light-emitting band;

[0044] A voltage adjustment range determination module, configured to determine a voltage adjustment range of the gate voltage of the to-be-detected light-emitting band based on a preset voltage range prediction model and the first associated feature;

[0045] A gate voltage dynamic adjustment module is configured to dynamically adjust the gate voltage of the to-be-detected light-emitting band according to the voltage adjustment range until the adjustment of all the to-be-detected light-emitting bands included in the to-be-detected OLED display screen is completed.

[0046] According to one aspect of the present disclosure, there is provided a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the dynamic adjustment method of the gate voltage described in any one of the above is implemented.

[0047] According to one aspect of the present disclosure, there is provided an electronic device, including:

[0048] a processor; and

[0049] a memory configured to store executable instructions of the processor;

[0050] wherein the processor is configured to execute the dynamic adjustment method of the gate voltage described in any one of the above by executing the executable instructions.

[0051] A dynamic adjustment method of a gate voltage provided by an embodiment of the present disclosure, on the one hand, obtains a to-be-detected light-emitting band included in a to-be-detected OLED display screen and first RGB gamma fine-tuning data corresponding to the to-be-detected light-emitting band; then performs feature selection on the first RGB gamma fine-tuning data to obtain first correlation features required for dynamically adjusting the gate voltage corresponding to the to-be-detected light-emitting band; further determines a voltage adjustment range of the gate voltage of the to-be-detected light-emitting band based on a preset voltage range prediction model and the first correlation features; and finally dynamically adjusts the gate voltage of the to-be-detected light-emitting band according to the voltage adjustment range until the adjustment of all the to-be-detected light-emitting bands included in the to-be-detected OLED display screen is completed; since the voltage adjustment range of the gate voltage can be determined based on the voltage range prediction model and the first correlation features, the voltage adjustment efficiency of a single light-emitting band can be improved on the basis of improving the accuracy of the obtained voltage adjustment range; on the other hand, since the voltage adjustment range of the gate voltage of the to-be-detected light-emitting band can be determined based on the obtained first correlation features, the calculation efficiency of the voltage adjustment range is improved.

[0052] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The accompanying drawings here are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the present disclosure, and are used together with the specification to explain the principles of the present disclosure. Obviously, the accompanying drawings in the following description are only some embodiments of the present disclosure, and those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts.

[0054] Figure 1 A schematic diagram showing an example of the voltage adjustment range in a related art solution.

[0055] Figure 2 A schematic flowchart showing a method for dynamically adjusting a gate voltage according to an exemplary embodiment of the present disclosure.

[0056] Figure 3 A schematic diagram showing the structure of a preset voltage range prediction model according to an exemplary embodiment of the present disclosure.

[0057] Figure 4 A schematic flowchart showing a method for the training process of a preset voltage range prediction model according to an exemplary embodiment of the present disclosure.

[0058] Figure 5 A schematic diagram showing the output layer classification based on the relationship between gamma fine-tuning data and dynamic L0 voltage distribution according to an exemplary embodiment of the present disclosure.

[0059] Figure 6 A schematic diagram showing an example of the dynamic L0 voltage adjustment range corresponding to each classification of the output layer according to an exemplary embodiment of the present disclosure.

[0060] Figure 7 A schematic diagram showing an example of the training set accuracy and test set accuracy under 750 iterations of calculation according to an exemplary embodiment of the present disclosure.

[0061] Figure 8 A schematic diagram showing an example of the training set loss curve and test set loss curve under 750 iterations of calculation according to an exemplary embodiment of the present disclosure.

[0062] Figure 9 A schematic diagram showing an example of the prediction result of the dynamic L0 voltage distribution range under a test set according to an exemplary embodiment of the present disclosure.

[0063] Figure 10 A schematic diagram showing an example of the obtained first correlation coefficient matrix according to an exemplary embodiment of the present disclosure.

[0064] Figure 11Schematic diagram showing an example of the two-dimensional distribution relationship between G data based on 7gray / 3gray and the dynamic L0 fixed voltage according to an example embodiment of the present disclosure.

[0065] Figure 12 Schematic diagram showing an example scenario of the specific calculation process of a voltage adjustment range according to an example embodiment of the present disclosure.

[0066] Figure 13 Schematic diagram showing an example structure of a dynamic adjustment device for a gate voltage according to an example embodiment of the present disclosure.

[0067] Figure 14 Schematic diagram showing an electronic device for implementing a method for dynamically adjusting a gate voltage according to an example embodiment of the present disclosure. Detailed implementation manners

[0068] Now, example embodiments will be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be more thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of the embodiments of the present disclosure. However, those skilled in the art will realize that the technical solutions of the present disclosure can be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. can be adopted. In other cases, well-known technical solutions are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0069] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0070] During the debugging process of an OLED (Organic Light-Emitting Diode) display module, there is usually a dilemma in the game between the black screen brightness debugging and the picture afterimage debugging under the condition of a million-to-one contrast; moreover, due to fluctuations in the product manufacturing process, it is also impossible to set a public L0 voltage scheme that takes into account all products. Based on the above problems, in some related technologies, an appropriate L0 voltage can be assigned to each product by scanning its own turn-on curve through a corresponding dynamic L0 voltage algorithm to ensure the balance between contrast and afterimage effect. Among them, the specific determination process of the L0 voltage is as follows: First, power on the OLED product and load the Band (emission frequency band) and the 0 gray-scale display picture in this OLED product; then, write the Gamma data voltage of the emission frequency band into the RGB registers all being 0 (at this time, the L0 voltage is VGMP (the highest voltage of the gamma fine-tuning module)), and collect the first brightness (Lv) value, and then compare the collected first brightness value with the target brightness value required for a million-to-one contrast to determine whether it exceeds the spec; finally, determine the optimal L0 voltage according to the comparison result between the first brightness value and the target brightness value. However, because this method requires multiple rounds of comparison and corresponding adjustments, the adjustment efficiency is relatively low.

[0071] Furthermore, during the actual application process, restricted by the Gamma production capacity of the production line, due to the need to consider the characteristic distribution of all products in the existing adjustment range of the dynamic L0 voltage algorithm, the adjustment range is usually set relatively wide, resulting in a longer Tact time (adjustment event for a single emission frequency band). For example, as Figure 1 shown, the adjustment range needs to be set at 5.8V to 4.9V (step = 10); at the same time, due to the different PWM Duty (Pulse Width Modulation Duty) and Vint2 - VSS voltage difference between the high-brightness Band and the low-brightness Band, the L0 turn-on curves of different emission frequency bands also vary; therefore, it is usually necessary to collect the turn-on curves of 2 to 3 Bands to determine the specific adjustment range, further reducing the adjustment efficiency. Under this premise, it is extremely urgent to optimize the Tact time of the dynamic L0 algorithm by combining the broad L0 scan range and the L0 scan requirements of multiple Bands.

[0072] Based on this, in the exemplary embodiment of the present example, a method for dynamically adjusting the gate voltage is first provided. This method can run on a terminal device, a server, a server cluster, or a cloud server, etc.; of course, those skilled in the art can also run the method of the present disclosure on other platforms according to requirements, and no special limitation is made in this exemplary embodiment. Specifically, refer to Figure 2As shown, the method for dynamically adjusting the gate voltage may include the following steps:

[0073] Step S210. Obtain the to-be-detected light-emitting band included in the to-be-detected OLED display screen and the first RGB gamma fine-tuning data corresponding to the to-be-detected light-emitting band;

[0074] Step S220. Perform feature selection on the first RGB gamma fine-tuning data to obtain the first correlation feature required for dynamically adjusting the gate voltage corresponding to the to-be-detected light-emitting band;

[0075] Step S230. Based on a preset voltage range prediction model and the first correlation feature, determine the voltage adjustment range of the gate voltage of the to-be-detected light-emitting band;

[0076] Step S240. Dynamically adjust the gate voltage of the to-be-detected light-emitting band according to the voltage adjustment range until the adjustment of all the to-be-detected light-emitting bands included in the to-be-detected OLED display screen is completed.

[0077] In the above method for dynamically adjusting the gate voltage, on the one hand, obtain the to-be-detected light-emitting band included in the to-be-detected OLED display screen and the first RGB gamma fine-tuning data corresponding to the to-be-detected light-emitting band; then perform feature selection on the first RGB gamma fine-tuning data to obtain the first correlation feature required for dynamically adjusting the gate voltage corresponding to the to-be-detected light-emitting band; further, based on a preset voltage range prediction model and the first correlation feature, determine the voltage adjustment range of the gate voltage of the to-be-detected light-emitting band; finally, dynamically adjust the gate voltage of the to-be-detected light-emitting band according to the voltage adjustment range until the adjustment of all the to-be-detected light-emitting bands included in the to-be-detected OLED display screen is completed; since the voltage adjustment range of the gate voltage can be determined based on the voltage range prediction model and the first correlation feature, the voltage adjustment efficiency of a single light-emitting band can be improved on the basis of improving the accuracy of the obtained voltage adjustment range; on the other hand, since the voltage adjustment range of the gate voltage of the to-be-detected light-emitting band can be determined based on the obtained first correlation feature, the calculation efficiency of the voltage adjustment range is improved.

[0078] Hereinafter, the method for dynamically adjusting the gate voltage recorded in the exemplary embodiments of the present disclosure will be further explained and described with reference to the accompanying drawings.

[0079] First, the terms involved in the exemplary embodiments of the present disclosure will be explained and described.

[0080] OLED: Organic Light-Emitting Diode, an organic light-emitting diode.

[0081] DTFT: Driver Thin Film Transistor, the pixel driving thin film transistor.

[0082] L0 voltage: L0 Voltage, which indicates the gate voltage for writing the 0 gray level (i.e., black screen) into the pixel driving thin film transistor, that is, the voltage that needs to be dynamically adjusted in the present disclosure.

[0083] Image retention: When the OLED display screen is displaying an image, after a long-time static image display, the gray level inversion phenomenon caused by the hysteresis effect and the change in the number of interface trapped charges during the pixel high and low gray level switching process.

[0084] Contrast ratio: The ratio of the brightness of the brightest (white) and the darkest (black) parts of the display screen.

[0085] Neural network: A computational model that mimics the connection method between human brain neurons, consisting of a series of layers, each layer containing multiple neurons; at the same time, neurons are connected by weights and process information through activation functions.

[0086] Feedforward neural network: Feedforward Neural Network, the information flow direction is: input layer → hidden layer → output layer, that is, it has a unidirectional information flow and no reverse connection.

[0087] Backpropagation: An algorithm for training a neural network by calculating the gradient of the loss function with respect to the network parameters; in the actual application process, backpropagation starts from the output layer and propagates the error through the network in a reverse manner.

[0088] Secondly, the technical implementation principle of the exemplary embodiments of the present disclosure will be explained and described. Specifically, in the actual application process, the adjustment of the dynamic L0 voltage is an important means to balance the afterimage optimization and contrast of the OLED. The principle is to reduce the change in the number of interface trapped charges by reducing the difference in the retained data voltages of the high and low gray levels, and to self-adapt the L0 voltage between the display bands while meeting the contrast. At the same time, the existing dynamic L0 voltage algorithms have the following problems: there are significant differences between individual products; moreover, in order to meet the self-adaptation of L0 voltage for all products, the scanning voltage range of its L0 voltage algorithm is too wide and the gradient iteration time is too long, thus affecting the Tact Time (i.e., the adjustment time of a single OLED display screen). Based on this, the exemplary embodiments of the present disclosure propose a method for dynamically adjusting the gate voltage, which can adjust the L0 voltage of the OLED display screen based on a fully connected feedforward neural network model. In the actual application process, the FNN model can extract effective features strongly related to the L0 voltage based on the batch data (10k - 15k) in the trial production stage, and train the regression relationship between the L0 voltage and the features through the backpropagation algorithm of the deep neural network, so that in the production process of the OLED display module, only the Gamma Tuning Data (i.e., gamma fine-tuning data) of the screen body is required, and the FNN model is used to efficiently reduce the scanning range of the dynamic L0 voltage algorithm, thereby achieving the effect of reducing the Tact Time.

[0089] Further, the voltage range prediction model related to the exemplary embodiments of the present disclosure will be explained and described. Specifically, referring to Figure 3 as shown, the voltage range prediction model includes an input layer 301, a plurality of feature hidden layers (the first feature hidden layer, the second feature hidden layer,..., the Nth feature hidden layer) 302, and an output layer 303; among them, the specific functions performed by each model layer in the power range prediction process will be detailed later, and no further elaboration will be made here.

[0090] Hereinafter, the specific training process of the voltage range prediction model will be explained and described. Specifically, referring to Figure 4 as shown, the specific training process of the voltage range prediction model may include the following steps:

[0091] Step S410, obtaining the detected emission bands included in the detected OLED display screen, the second RGB gamma fine-tuning data corresponding to the to-be-detected emission bands, and the target voltage range;

[0092] Step S420, performing feature selection on the second RGB gamma fine-tuning data to obtain the second correlation features required for dynamically adjusting the gate voltage corresponding to the detected emission bands;

[0093] Step S430: Input the second associated feature into the neural network model to be trained, and obtain the prediction result of the gate voltage range of the detected emission band.

[0094] Step S440: Construct a loss function based on the range prediction result and the target voltage range, and adjust the parameters of the neural network model to be trained based on the loss function to obtain a preset voltage range prediction model.

[0095] Hereinafter, the specific training process of the voltage range prediction model will be further explained and described. Specifically, taking the neural network model to be trained as a fully connected feedforward neural network as an example, the specific training process will be explained and described. Among them, the fully connected feedforward neural network recorded here can be divided into three main parts: an input layer, a hidden layer, and an output layer. Each layer contains multiple neurons, and these neurons are connected to all neurons in the next layer. Among them, the input layer can be used to receive the original data input; the hidden layer can include one or more intermediate layers, which are used to extract features and learn the non-linear relationship of the data; the output layer can be used to generate the final prediction result based on the features extracted by the hidden layer. Further, the training principle of the FNN model is as follows: each neuron in each layer has associated weights and biases; among them, the weights determine the influence degree of the input factor, and the biases determine the threshold for neuron activation; at the same time, each neuron introduces non-linearity through an activation function, and the cost function is measured through backpropagation between layers to measure the difference between the predicted output and the true value, and thus iterate. Its iteration process is generally gradient descent to update the weights and biases of the neurons. Further, the parameters used in the model training process and the specific training process can refer to the following formulas (1)-(5):

[0096]

[0097] (h Θ (x)) i =i th output; Formula (2)

[0098]

[0099]

[0100] Among them, h Θ (x) refers to the K-dimensional vector output by each model layer of the FNN model, and the meaning of K is the number of units in the output layer; (h Θ (x)) i =i th output represents the vector on the i-th unit output by each model layer; Denotes the weight from the $i$-th unit in the $l$-th layer to the $j$-th unit in the $(l + 1)$-th layer in the weight matrix of the $l$-th model layer; Denotes the $n$-th feature in the $l$-th layer; Denotes the specific processing process of the model layer; $J(\Theta)$ is the loss function (i.e., the cost function), $M$ represents the number of samples in the training set, $K$ represents the number of units in the output layer (i.e., the number of classes), $L$ represents the total number of layers of the neural network (i.e., the input layer + hidden layers + output layer); $s_l$ represents that the number of neurons in the $l$-th layer is $s$; $\lambda$ represents the regularization coefficient, which can be used to control the strength of the regularization term; in the cost function described above, Denotes the regularization term, which can sum the squares of all weight parameters ($L2$ regularization) to penalize large weights; Denotes the true label of the $m$-th sample in the $k$-th class (i.e., the target voltage range); for example, if the $m$-th sample belongs to the 2nd class, then The rest are 0; ($h$ Θ (x m )) k Denotes the predicted label of the $m$-th sample in the $k$-th class (i.e., the predicted result of the gate voltage range); further, the specific meaning of the formula (5) described above is: if it is necessary to calculate the minimum value of the cost function, then it is necessary to calculate the partial derivative of the loss function with respect to the weight parameter for backpropagation to update the parameters.

[0101] It should also be further explained here that in the OLED dynamic $L0$ voltage algorithm, 10 kinds of $L0$ voltage range results can be screened out by collecting batch data (10k - 15k) during the trial production stage of the production line. Therefore, the output unit is defined as 10 (i.e., the value of $K$ is 10), and multi-class classification can be used for prediction during the training process; at the same time, the classification schematic diagram of the output layer based on the relationship between gamma fine-tuning data and dynamic $L0$ voltage distribution can be referred to Figure 5 as shown; the dynamic $L0$ voltage adjustment range corresponding to each classification of the output layer can be referred to Figure 6As shown. Further, in the actual application process, three-layer feature hidden layers can be adopted to extract the linear / nonlinear relationship between gamma fine-tuning data and dynamic L0 fixed voltage; at the same time, the ReLU activation function is adopted for the activation function here. Compared with the sigmoid activation function, the advantage of ReLU lies in its high computational rate and alleviating gradient disappearance. Therefore, the ReLU activation function is adopted in this training model; and the number of hidden units in each hidden layer is set to 128, 64, and 32 respectively to match a relatively large number of features. Further still, in the specific training process, 80% of the production line batch data can be extracted as the training set, and 20% as the test set to better verify the accuracy of the training model; moreover, training can also be carried out through the backpropagation algorithm and gradient descent, as Figure 7 As shown in the training set accuracy and test set accuracy under 750 iterations of calculation, it can be seen that it gradually converges to an accuracy above 0.95; as Figure 8 As shown in the training set loss curve and test set loss curve under 750 iterations of calculation, it can be seen that it gradually converges to a loss value below 0.3; as Figure 9 As shown in the prediction of the dynamic L0 voltage distribution range under the test set, it can be seen that it basically coincides with the true value. Therefore, it is proved that through this training model, the gamma fine-tuning data and the dynamic L0 voltage can be effectively established a regression relationship, thereby effectively reducing the dynamic L0 voltage range.

[0102] For the voltage range prediction model obtained based on the above training method, compared with multivariate linear regression and logistic regression, the prediction accuracy of the voltage range prediction model recorded in the exemplary embodiments of the present disclosure is much higher than that of a single multivariate linear regression or logistic regression, which proves that through this training model, the gamma tuning data and the dynamic L0 voltage can be effectively established a regression relationship, thereby effectively reducing the dynamic L0 voltage range. The specific comparison results can be referred to Table 1 below:

[0103] Table 1

[0104] Model Voltage Adjustment Range Prediction Accuracy (Based on the Same Test Set) Multivariable Linear Regression 0.83 Multinomial Logistic Regression 0.64 Voltage Range Prediction Model 0.96

[0105] Finally, after obtaining the voltage range prediction model, it can be deployed based on the production line production environment; among them, the production line production environment is Lua / c; at the same time, since the voltage range prediction model training is based on Python, the voltage range prediction model can be saved as a cross-platform general (supporting c++ / python) middleware file through the onnx Runtime module, and the FNN model can be called in the Lua environment by compiling the DLL with C++.

[0106] Next, in combination with Figures 2 - 9 For Figure 1Further explanation and illustration will be given to the method for dynamically adjusting the gate voltage shown in the figure. Specifically:

[0107] In step S110, the to-be-detected light-emitting band included in the to-be-detected OLED display screen and the first RGB gamma fine-tuning data corresponding to the to-be-detected light-emitting band are obtained.

[0108] Specifically, the to-be-detected light-emitting band recorded here refers to the Band included in the to-be-detected OLED display screen; the number of Bands included in each to-be-detected OLED display screen can be the same or different, and can be determined according to the specific situation of the display screen; at the same time, the first RGB gamma fine-tuning data recorded here can include the production line channel Channel of the to-be-detected light-emitting band and the high, medium, and low gray-scale data of the to-be-detected light-emitting band; among them, the high, medium, and low gray-scale data recorded here can include but are not limited to R_255, G_255, B_255, R_207, G_207, B_207, R_143, G_143, B_143, R_79, G_79, B_79, R_31, G_31, B_31, R_23, G_23, B_23, R_15, G_15, B_15, R_7, G_7, B_7, R_3, G_3, B_3, etc.; in the actual application process, other gray-scale data can also be selected according to the actual situation, and this example does not make special restrictions on this.

[0109] In step S120, feature selection is performed on the first RGB gamma fine-tuning data to obtain the first correlation feature required for dynamically adjusting the gate voltage corresponding to the to-be-detected light-emitting band.

[0110] Specifically, the specific determination process of the first correlation feature can be implemented in the following manner: Determine the first original data feature included in the first RGB gamma fine-tuning data and the first original feature value corresponding to the first original data feature; Determine the first original brightness response value corresponding to the first original feature value, and calculate the first correlation coefficient between the first original feature value and the first original brightness response value; Construct a first correlation coefficient matrix between the first original feature value and the first original brightness response value according to the first correlation coefficient; Extract the first correlation feature required for dynamically adjusting the gate voltage corresponding to the to-be-detected light-emitting frequency band from the first original data feature according to the first correlation coefficient matrix. Among them, the specific calculation process of the first correlation coefficient can be implemented in the following manner: Determine the first feature mean value of the first original feature value, and determine the first feature covariance and the first feature standard deviation of the first original feature value according to the first feature mean value; Determine the first brightness response mean value of the first original brightness response value, and determine the first brightness response covariance and the first brightness response standard deviation of the first original brightness response value according to the first brightness response mean value; Determine the first correlation coefficient between the first original feature value and the first original brightness response value according to the first feature covariance, the first feature standard deviation, the first brightness response covariance, and the first brightness response standard deviation.

[0111] Hereinafter, the specific screening process of the first correlation feature will be further explained and described. Specifically, the first original data feature recorded above may include the production line channel Channel and the high, medium, and low gray-scale data; The first original feature value may include the specific value of the production line channel Channel and the specific values of the high, medium, and low gray-scale data, such as R_255, G_255, B_255, R_207, G_207, B_207, R_143, G_143, B_143, R_79, G_79, B_79, R_31, G_31, B_31, R_23, G_23, B_23, R_15, G_15, B_15, R_7, G_7, B_7, R_3, G_3, B_3, etc.; The first original brightness response value can be determined according to the gamma curve. Further, through the analysis of the OLED dynamic L0 voltage algorithm, it is not difficult to find that the L0 turn-on adjustment process is a process of assigning different gamma data voltages to the screen body to determine whether to turn on; Therefore, the dynamic L0 voltage should have a certain correlation with the gamma adjustment data of different gray scales of the screen body. On this premise, 28 features such as the high, medium, and low gray scales and the production line channel corresponding to the Band are selected to analyze their linear relationship with the L0 fixed voltage; Through the heat map (i.e., as Figure 10From the first correlation coefficient matrix shown, it can be undoubtedly known that there is a strong linear relationship between the R / G pixel data values of 143gray / 79gray / 31gray / 23gray / 15gray / 7gray / 3gray and the dynamic L0 fixed voltage, and the lower the gray level, the stronger the linear relationship between the R / G pixel data values and the dynamic L0 fixed voltage; for a specific example diagram of the linear relationship, reference can be made to Figure 11 shown. Therefore, the R / G pixel data values of 143gray / 79gray / 31gray / 23gray / 15gray / 7gray / 3gray corresponding to the Band are preliminarily selected as the first associated feature of the Band.

[0112] In step S130, based on a preset voltage range prediction model and the first associated feature, determine the voltage adjustment range of the gate voltage of the to-be-detected light-emitting band.

[0113] Specifically, the specific determination process of the voltage adjustment range can be achieved in the following manner: perform normalization processing on the first associated feature value of the first associated feature to obtain a first normalized feature value, and splice the first normalized feature value to obtain a first spliced feature; input the first spliced feature into a preset voltage range prediction model to obtain the voltage adjustment range of the gate voltage of the to-be-detected light-emitting band. Among them, the normalization processing recorded here can also be understood as feature scaling; during the feature scaling process, all features can be adjusted to the same scale, enabling the training model to perform regression more effectively. The specific feature scaling process can include but is not limited to: First, calculate the mean; among them, the specific calculation process of the mean can be shown in the following formula (6):

[0114]

[0115] where, μ a is the mean of the a-th feature of m samples, M is the number of samples, and x ma is the value of the m-th sample on the a-th feature.

[0116] Secondly, calculate the standard deviation; specifically, the specific calculation process of calculating the standard deviation can be shown in the following formula (7):

[0117]

[0118] where, σ a is the standard deviation of the a-th feature.

[0119] Finally, perform normalization processing; specifically, the specific calculation process of normalization can be shown in the following formula (8):

[0120]

[0121] where x ma ' is the value after standardization.

[0122] In an exemplary embodiment, the first splicing feature is input into a preset gate voltage range prediction model for the light-emitting band to be detected to obtain the voltage scanning range of the gate voltage of the light-emitting band to be detected, which can be achieved in the following manner: the first splicing feature is received based on the input layer and passed to the first feature hidden layer; based on the first feature hidden layer, feature extraction is performed on the first splicing feature to obtain a first feature extraction result, and based on the second feature hidden layer, a non-linear transformation is performed on the first feature extraction result to obtain a second feature extraction result; the determination process of the second feature extraction result is sequentially repeated to obtain an Nth feature extraction result corresponding to the Nth feature hidden layer; based on the output layer, voltage range prediction is performed on the Nth feature extraction result to obtain the voltage scanning range of the gate voltage of the light-emitting band to be detected. Among them, for a scenario example diagram of the specific implementation principle, reference can be made to Figure 12 as shown.

[0123] In step S140, the gate voltage of the light-emitting band to be detected is dynamically adjusted according to the voltage adjustment range until the adjustment of all the light-emitting bands to be detected included in the OLED display screen to be detected is completed.

[0124] Specifically, the dynamic adjustment process can be achieved in the following manner: the maximum voltage value is extracted from the voltage adjustment range, and the current gate voltage of the light-emitting band to be detected is determined according to the maximum voltage value; the current brightness value of the light-emitting band to be detected at the current gate voltage is collected, and it is determined whether the current brightness value meets a preset brightness condition; when it is determined that the current brightness value meets the preset brightness condition, the optimal gate voltage value of the light-emitting band to be detected is determined according to the current gate voltage, so as to achieve dynamic adjustment of the gate voltage of the light-emitting band to be detected.

[0125] In an exemplary embodiment, determining whether the current brightness value meets a preset brightness condition can be achieved in the following manner: obtaining the target brightness value of the light-emitting band to be detected at the current gate voltage, and determining whether the current brightness value meets the preset brightness condition according to the current brightness value and the target brightness value; among them, if the current brightness value is greater than or equal to the target brightness value, it is determined that the current brightness value meets the preset brightness condition; if the current brightness value is less than the target brightness value, it is determined that the current brightness value does not meet the preset brightness condition.

[0126] In an exemplary embodiment, determining the optimal gate voltage value of the luminous frequency band to be detected based on the current gate voltage can be achieved in the following way: determining the brightness compensation voltage of the luminous frequency band to be detected under the target brightness value condition, and determining the optimal gate voltage value of the luminous frequency band to be detected based on the brightness compensation voltage and the current gate voltage.

[0127] The following will further explain and illustrate the dynamic adjustment process of the gate voltage. Specifically, the dynamic adjustment process of the gate voltage may include the following steps:

[0128] S001, powering on the OLED display screen to be detected, and loading the luminous frequency band Band to be detected included in the OLED display screen to be detected and the first RGB gamma fine-tuning data corresponding to the luminous frequency band to be detected;

[0129] S002, performing feature selection on the first RGB gamma fine-tuning data of the luminous frequency band to be detected, obtaining a first associated feature, and loading a voltage range prediction model to determine a voltage adjustment range of the gate voltage of the luminous frequency band to be detected;

[0130] S003, determine the Max value from the voltage adjustment range, and set the L0 voltage to: L0 voltage = Max value - Step;

[0131] S004, collecting the current brightness value at this moment, and comparing the brightness value with the target brightness value under the million degree comparison requirement, to determine whether the current brightness value exceeds the target brightness value Spec; if so, jump to step S005; if not, jump to step S003;

[0132] Step S005, obtaining the optimal value VL0 of the L0 voltage under the luminous frequency band to be detected;

[0133] Step S006, considering the reliability brightness compensation, the best value of VL0 is: VL0 = VL0 + Offset;

[0134] Step S007, determine whether all the luminous frequency bands to be detected have been debugged; if so, end; if not, jump to step S001.

[0135] So far, the dynamic adjustment method of the gate voltage described in the exemplary embodiments of the present disclosure has been fully implemented. Based on the foregoing content, it can be known that the dynamic adjustment method of the gate voltage described in the exemplary embodiments of the present disclosure has at least the following advantages: on the one hand, by training the regression relationship between the L0 voltage and the features through the backpropagation algorithm of the fully connected feedforward neural network model, it is realized that during the production process of the OLED display module, only the Gamma Tuning Data of the screen body is required, and the FNN model is used to efficiently reduce the scanning range of the dynamic L0 voltage algorithm, thereby achieving the effect of reducing the Tact Time; on the other hand, the dynamic adjustment method of the gate voltage described in the exemplary embodiments of the present disclosure can ensure that each screen quickly finds the optimal solution for the balance between its own contrast and afterimage; moreover, the dynamic adjustment of the L0 voltage can be realized without additional hardware costs and additional processes, and the process is simple and flexible.

[0136] The following is an embodiment of the device of the present disclosure, which can be used to execute the embodiment of the method of the present disclosure. For the details not disclosed in the embodiment of the device of the present disclosure, please refer to the embodiment of the method of the present disclosure.

[0137] The exemplary embodiments of the present disclosure also provide a device for dynamically adjusting the gate voltage. Specifically, referring to Figure 13 as shown, the device for dynamically adjusting the gate voltage may include a fine-tuning data acquisition module 1310, a first associated feature selection module 1320, a voltage adjustment range determination module 1330, and a gate voltage dynamic adjustment module 1340. Among them:

[0138] The fine-tuning data acquisition module 1310 can be used to acquire the to-be-detected light-emitting frequency band included in the to-be-detected OLED display screen and the first RGB gamma fine-tuning data corresponding to the to-be-detected light-emitting frequency band;

[0139] The first associated feature selection module 1320 can be used to perform feature selection on the first RGB gamma fine-tuning data to obtain the first associated features required for dynamically adjusting the gate voltage corresponding to the to-be-detected light-emitting frequency band;

[0140] The voltage adjustment range determination module 1330 can be used to determine the voltage adjustment range of the gate voltage of the to-be-detected light-emitting frequency band based on a preset voltage range prediction model and the first associated features;

[0141] The gate voltage dynamic adjustment module 1340 can be used to dynamically adjust the gate voltage of the to-be-detected light-emitting frequency band according to the voltage adjustment range until the adjustment of all the to-be-detected light-emitting frequency bands included in the to-be-detected OLED display screen is completed.

[0142] In an exemplary embodiment of the present disclosure, feature selection is performed on the first RGB gamma fine-tuning data to obtain first associated features required for dynamically adjusting the gate voltage corresponding to the to-be-detected emission frequency band, including: determining first original data features included in the first RGB gamma fine-tuning data and first original feature values corresponding to the first original data features; determining first original brightness response values corresponding to the first original feature values, and calculating a first correlation coefficient between the first original feature values and the first original brightness response values; constructing a first correlation coefficient matrix between the first original feature values and the first original brightness response values according to the first correlation coefficient; and extracting, from the first original data features, first associated features required for dynamically adjusting the gate voltage corresponding to the to-be-detected emission frequency band according to the first correlation coefficient matrix.

[0143] In an exemplary embodiment of the present disclosure, calculating the first correlation coefficient between the first original feature values and the first original brightness response values includes: determining a first feature mean of the first original feature values, and determining a first feature covariance and a first feature standard deviation of the first original feature values according to the first feature mean; determining a first brightness response mean of the first original brightness response values, and determining a first brightness response covariance and a first brightness response standard deviation of the first original brightness response values according to the first brightness response mean; and determining the first correlation coefficient between the first original feature values and the first original brightness response values according to the first feature covariance, the first feature standard deviation, the first brightness response covariance, and the first brightness response standard deviation.

[0144] In an exemplary embodiment of the present disclosure, based on a preset voltage range prediction model and the first associated features, determining a voltage adjustment range of the gate voltage of the to-be-detected emission frequency band includes: performing normalization processing on first associated feature values of the first associated features to obtain first normalized feature values, and splicing the first normalized feature values to obtain a first spliced feature; and inputting the first spliced feature into the preset voltage range prediction model to obtain the voltage adjustment range of the gate voltage of the to-be-detected emission frequency band.

[0145] In an exemplary embodiment of the present disclosure, the preset voltage range prediction model includes an input layer, a first feature hidden layer, a second feature hidden layer, …, an Nth feature hidden layer, and an output layer; wherein, inputting the first spliced feature into the preset voltage range prediction model to obtain the voltage scanning range of the gate voltage of the to-be-detected light-emitting band includes: receiving, by the input layer, the first spliced feature and transmitting the first spliced feature to the first feature hidden layer; performing feature extraction on the first spliced feature by the first feature hidden layer to obtain a first feature extraction result, and performing a non-linear transformation on the first feature extraction result by the second feature hidden layer to obtain a second feature extraction result; sequentially repeating the determination process of the second feature extraction result to obtain an Nth feature extraction result corresponding to the Nth feature hidden layer; and performing voltage range prediction on the Nth feature extraction result by the output layer to obtain the voltage scanning range of the gate voltage of the to-be-detected light-emitting band.

[0146] In an exemplary embodiment of the present disclosure, the preset voltage range prediction model is obtained by the following method: acquiring the detected light-emitting bands included in the detected OLED display screen, the second RGB gamma fine-tuning data corresponding to the to-be-detected light-emitting bands, and the target voltage range; performing feature selection on the second RGB gamma fine-tuning data to obtain second correlation features required for dynamically adjusting the gate voltage corresponding to the detected light-emitting bands; inputting the second correlation features into a neural network model to be trained to obtain a range prediction result of the gate voltage of the detected light-emitting bands; constructing a loss function according to the range prediction result and the target voltage range, and adjusting the parameters of the neural network model to be trained based on the loss function to obtain the preset voltage range prediction model.

[0147] In an exemplary embodiment of the present disclosure, dynamically adjusting the gate voltage of the to-be-detected light-emitting band according to the voltage adjustment range includes: extracting the maximum voltage value from the voltage adjustment range, and determining the current gate voltage of the to-be-detected light-emitting band according to the maximum voltage value; collecting the current brightness value of the to-be-detected light-emitting band at the current gate voltage, and determining whether the current brightness value meets a preset brightness condition; when it is determined that the current brightness value meets the preset brightness condition, determining the optimal gate voltage value of the to-be-detected light-emitting band according to the current gate voltage, so as to implement dynamic adjustment of the gate voltage of the to-be-detected light-emitting band.

[0148] In an exemplary embodiment of the present disclosure, determining whether the current brightness value meets a preset brightness condition includes: obtaining a target brightness value of the to-be-detected light-emitting band at the current gate voltage, and determining whether the current brightness value meets the preset brightness condition according to the current brightness value and the target brightness value; wherein, if the current brightness value is greater than or equal to the target brightness value, it is determined that the current brightness value meets the preset brightness condition; if the current brightness value is less than the target brightness value, it is determined that the current brightness value does not meet the preset brightness condition.

[0149] In an exemplary embodiment of the present disclosure, determining the optimal gate voltage value of the to-be-detected light-emitting band according to the current gate voltage includes: determining a lighting compensation voltage of the to-be-detected light-emitting band under the condition of the target brightness value, and determining the optimal gate voltage value of the to-be-detected light-emitting band according to the lighting compensation voltage and the current gate voltage.

[0150] The specific details of each module in the above gate voltage dynamic adjustment device have been described in detail in the corresponding gate voltage dynamic adjustment method, so they will not be repeated here.

[0151] It should be noted that although several modules or units of a device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of the two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0152] In addition, although the steps of the methods in the present disclosure are described in a specific order in the drawings, this does not require or imply that these steps must be executed in that specific order, or that all the steps shown must be executed to achieve the desired result. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step for execution, and / or one step may be decomposed into multiple steps for execution, etc.

[0153] In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is further provided. Those skilled in the art can understand that various aspects of the present disclosure can be implemented as a system, a method, or a program product. Therefore, various aspects of the present disclosure can be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software aspects, which can be collectively referred to as a circuit, a module, or a system here.

[0154] The following refers to Figure 14The electronic device 1400 according to this embodiment of the present disclosure will be described. Figure 14 The illustrated electronic device 1400 is merely an example and should not impose any limitations on the functions and scope of use of the embodiments of the present disclosure.

[0155] As Figure 14 shown, the electronic device 1400 is presented in the form of a general-purpose computing device. The components of the electronic device 1400 may include, but are not limited to: at least one of the above-mentioned processing units 1410, at least one of the above-mentioned storage units 1420, a bus 1430 connecting different system components (including the storage unit 1420 and the processing unit 1410), and a display unit 1440.

[0156] Among them, the storage unit stores program code, and the program code can be executed by the processing unit 1410, so that the processing unit 1410 executes the steps according to various exemplary embodiments of the present disclosure described in the above "Exemplary Method" section of this specification. For example, the processing unit 1410 may execute steps S210 as Figure 2 shown: obtaining a to-be-detected emission frequency band included in the to-be-detected OLED display screen and first RGB gamma fine-tuning data corresponding to the to-be-detected emission frequency band; step S220: performing feature selection on the first RGB gamma fine-tuning data to obtain a first associated feature required for dynamically adjusting the gate voltage corresponding to the to-be-detected emission frequency band; step S230: determining a voltage adjustment range of the gate voltage of the to-be-detected emission frequency band based on a preset voltage range prediction model and the first associated feature; step S240: dynamically adjusting the gate voltage of the to-be-detected emission frequency band according to the voltage adjustment range until the adjustment of all the to-be-detected emission frequency bands included in the to-be-detected OLED display screen is completed.

[0157] The storage unit 1420 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 14201 and / or a cache storage unit 14202, and may further include a read-only storage unit (ROM) 14203. Among them, the storage unit 1420 may further include a program / utility 14204 having a set (at least one) of program modules 14205. Such program modules 14205 include, but are not limited to: an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include the implementation of a network environment. The bus 1430 may represent one or more of several types of bus structures, including a storage unit bus or a storage unit controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any bus structure in a variety of bus structures.

[0158] The electronic device 1400 can also communicate with one or more external devices 1500 (such as keyboards, pointing devices, Bluetooth devices, etc.), and can also communicate with one or more devices that enable users to interact with the electronic device 1400, and / or communicate with any device that enables the electronic device 1400 to communicate with one or more other computing devices (such as routers, modems, etc.). Such communication can be carried out through the input / output (I / O) interface 1450. Moreover, the electronic device 1400 can also communicate with one or more networks (such as local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) through the network adapter 14140. As shown in the figure, the network adapter 14140 communicates with other modules of the electronic device 1400 through the bus 1430. It should be understood that although not shown in the figure, other hardware and / or software modules can be used in combination with the electronic device 1400, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0159] Furthermore, through the description of the above embodiments, those skilled in the art can easily understand that the exemplary embodiments described herein can be implemented by software, or can be implemented by a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, USB flash drive, mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, server, terminal device, or network device, etc.) to execute the method according to the embodiments of the present disclosure.

[0160] In an exemplary embodiment of the present disclosure, there is also provided a computer-readable storage medium, on which there is a program product capable of implementing the above method of this specification. In some possible implementation manners, various aspects of the present disclosure can also be implemented in the form of a program product, which includes program code. When the program product runs on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary embodiments described in the above exemplary method part of this specification.

[0161] A program product for implementing the above method according to an embodiment of the present disclosure may be a portable compact disc read-only memory (CD-ROM) and includes program code, and can run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto. In this document, a readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. The program product may employ any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. The readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the readable storage medium (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0162] A computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which the readable program code is carried. Such a propagated data signal may take various forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The readable signal medium may also be any readable medium other than the readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0163] The program code contained on the readable medium may be transmitted by any appropriate medium, including but not limited to wireless, wired, optical fiber cable, RF, etc., or any suitable combination of the above.

[0164] The program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and also including conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, executed as a stand-alone software package, partially on the user computing device and partially on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0165] In addition, the above-mentioned drawings are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present disclosure, rather than for limiting purposes. It is easily understood that the processes shown in the above-mentioned drawings do not indicate or limit the chronological order of these processes. Additionally, it is also easily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0166] Those skilled in the art will readily conceive of other embodiments of the present disclosure after considering the specification and practicing the invention herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include known common knowledge or conventional technical means in the technical field not invented by the present disclosure. The specification and embodiments are only regarded as exemplary, and the true scope and spirit of the present disclosure are pointed out by the claims.

Claims

1. A method for dynamically adjusting a gate voltage, characterized in that: include: Acquire a light-emitting frequency band to be detected included in the OLED display screen to be detected and first RGB gamma fine-tuning data corresponding to the light-emitting frequency band to be detected; Performing feature selection on the first RGB gamma fine-tuning data to obtain a first associated feature required for dynamically adjusting the gate voltage corresponding to the light-emitting frequency band to be detected; Based on a preset voltage range prediction model and a first associated feature, determining a voltage adjustment range of a gate voltage of the light emitting frequency band to be detected; The gate voltage of the light emitting frequency band to be detected is dynamically adjusted according to the voltage adjustment range until the adjustment of all the light emitting frequency bands to be detected included in the light emitting frequency band to be detected of the OLED display screen to be detected is completed.

2. The method for dynamically adjusting gate voltage according to claim 1, characterized in that: Feature selection is performed on the first RGB gamma fine-tuning data to obtain a first associated feature required for dynamically adjusting the gate voltage corresponding to the light-emitting frequency band to be detected, including: Determine a first original data feature included in the first RGB gamma fine-tuning data and a first original feature value corresponding to the first original data feature; Determine a first original brightness response value corresponding to the first original eigenvalue, and calculate a first correlation coefficient between the first original eigenvalue and the first original brightness response value; Constructing a first correlation coefficient matrix between the first original eigenvalue and the first original brightness response value according to the first correlation coefficient; A first correlation feature required for dynamically adjusting a gate voltage corresponding to the luminous frequency band to be detected is extracted from the first original data feature according to the first correlation coefficient matrix.

3. The method for dynamically adjusting gate voltage according to claim 2, characterized in that: Calculating a first correlation coefficient between the first original eigenvalue and the first original brightness response value includes: Determine a first characteristic mean of the first original eigenvalue, and determine a first characteristic covariance and a first characteristic standard deviation of the first original eigenvalue according to the first characteristic mean; Determine a first brightness response mean of the first original brightness response value, and determine a first brightness response covariance and a first brightness response standard deviation of the first original brightness response value according to the first brightness response mean; A first correlation coefficient between the first original eigenvalue and the first original luminance response value is determined according to the first eigencovariance, the first eigenstandard deviation, the first luminance response covariance, and the first luminance response standard deviation.

4. The method for dynamically adjusting gate voltage according to claim 1, characterized in that: Determining a voltage adjustment range of a gate voltage of the light emitting frequency band to be detected based on a preset voltage range prediction model and a first associated feature includes: Standardizing the first associated feature values ​​of the first associated features to obtain first standardized feature values, and concatenating the first standardized feature values ​​to obtain a first concatenated feature; The first splicing feature is input into a preset voltage range prediction model to obtain a voltage adjustment range of the gate voltage of the light-emitting frequency band to be detected.

5. The method for dynamically adjusting gate voltage according to claim 4, characterized in that: The preset voltage range prediction model includes an input layer, a first feature hidden layer, a second feature hidden layer, ..., an Nth feature hidden layer and an output layer; The first splicing feature is input into a preset voltage range prediction model to obtain a voltage scanning range of the gate voltage of the light-emitting frequency band to be detected, including: receiving the first concatenated feature based on the input layer, and transmitting the first concatenated feature to a first feature hidden layer; Performing feature extraction on the first concatenated feature based on the first feature hidden layer to obtain a first feature extraction result, and performing nonlinear transformation on the first feature extraction result based on the second feature hidden layer to obtain a second feature extraction result; Repeat the process of determining the second feature extraction result in sequence to obtain an Nth feature extraction result corresponding to the Nth feature hidden layer; The voltage range of the Nth feature extraction result is predicted based on the output layer to obtain the voltage scanning range of the gate voltage of the luminous frequency band to be detected.

6. The method for dynamically adjusting gate voltage according to claim 1, characterized in that: The preset voltage range prediction model is obtained in the following manner: Acquire the detected light-emitting frequency band included in the detected OLED display screen, the second RGB gamma fine-tuning data corresponding to the light-emitting frequency band to be detected, and the target voltage range; Performing feature selection on the second RGB gamma fine-tuning data to obtain a second associated feature required for dynamically adjusting the gate voltage corresponding to the detected light-emitting frequency band; Inputting the second associated feature into the neural network model to be trained to obtain a range prediction result of the gate voltage of the detected luminous frequency band; A loss function is constructed according to the range prediction result and the target voltage range, and parameters of the neural network model to be trained are adjusted based on the loss function to obtain a preset voltage range prediction model.

7. The method for dynamically adjusting gate voltage according to claim 1, characterized in that: Dynamically adjusting the gate voltage of the light-emitting frequency band to be detected according to the voltage adjustment range includes: Extracting a maximum voltage value from the voltage adjustment range, and determining a current gate voltage of the light-emitting frequency band to be detected according to the maximum voltage value; Collecting the current brightness value of the light-emitting frequency band to be detected under the current gate voltage, and determining whether the current brightness value meets a preset brightness condition; When it is determined that the current brightness value meets the preset brightness condition, the optimal gate voltage value of the light-emitting frequency band to be detected is determined according to the current gate voltage, so as to dynamically adjust the gate voltage of the light-emitting frequency band to be detected.

8. The method for dynamically adjusting gate voltage according to claim 7, characterized in that: Determining whether the current brightness value meets a preset brightness condition includes: Obtain the target brightness value of the luminous band to be detected under the current gate voltage, and determine whether the current brightness value meets the preset brightness condition based on the current brightness value and the target brightness value; wherein, if the current brightness value is greater than or equal to the target brightness value, it is determined that the current brightness value meets the preset brightness condition; if the current brightness value is less than the target brightness value, it is determined that the current brightness value does not meet the preset brightness condition.

9. The method for dynamically adjusting gate voltage according to claim 7, characterized in that: Determining the optimal gate voltage value of the light-emitting frequency band to be detected according to the current gate voltage includes: The lighting compensation voltage of the light-emitting frequency band to be detected under the target brightness value condition is determined, and the optimal gate voltage value of the light-emitting frequency band to be detected is determined according to the lighting compensation voltage and the current gate voltage.

10. A gate voltage dynamic adjustment device, characterized in that: include: A fine-tuning data acquisition module, used to acquire the luminous frequency band to be detected included in the OLED display screen to be detected and the first RGB gamma fine-tuning data corresponding to the luminous frequency band to be detected; A first correlation feature selection module, used for performing feature selection on the first RGB gamma fine-tuning data to obtain a first correlation feature required for dynamically adjusting the gate voltage corresponding to the light-emitting frequency band to be detected; A voltage adjustment range determination module, used to determine the voltage adjustment range of the gate voltage of the light-emitting frequency band to be detected based on a preset voltage range prediction model and a first associated feature; The gate voltage dynamic adjustment module is used to dynamically adjust the gate voltage of the light-emitting frequency band to be detected according to the voltage adjustment range until the adjustment of all the light-emitting frequency bands to be detected included in the OLED display screen to be detected is completed.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for dynamically adjusting the gate voltage according to any one of claims 1 to 9 is implemented.

12. An electronic device, characterized in that: include: processor; as well as A memory, configured to store executable instructions of the processor; The processor is configured to execute the method for dynamically adjusting the gate voltage according to any one of claims 1 to 9 by executing the executable instructions.

Images