Control method of display panel, display device and related equipment

Abstract

This disclosure provides a control method, display device, and related equipment for a display panel. The display panel includes a touch structure, which includes multiple touch electrodes and multiple touch traces electrically coupled to the touch electrodes. The method includes: collecting capacitance data on the multiple touch traces; determining predicted display parameters of the display panel based on the capacitance data using a pre-trained display parameter prediction model; the display parameter prediction model is trained based on sample capacitance data under the constraint of sample environmental data, wherein the label of the sample capacitance data includes sample display parameters; and controlling the display panel to display based on the predicted display parameters. This eliminates the need for additional built-in sensors to collect environmental parameters, saving internal space in the display device and enabling real-time and accurate prediction of display parameters.

Description

Technical Field

[0001] This disclosure relates to the field of display technology, and in particular to a control method for a display panel, a display device, and related equipment. Background Technology

[0002] With the widespread use of touchscreens in display devices, screen display quality has a significant impact on user experience. In related technologies, environmental parameters are acquired through additional built-in sensors, and the display panel's parameters are adjusted accordingly. However, these additional built-in sensors increase the internal space occupied by the display device and cannot achieve real-time, precise adjustment of display parameters.

[0003] Therefore, how to accurately adjust the display parameters of the display panel in real time has become an urgent technical problem to be solved. Summary of the Invention

[0004] In view of this, the purpose of this disclosure is to provide a control method for a display panel, a display device, and related equipment to solve or partially solve the above-mentioned technical problems.

[0005] Based on the above objectives, the first aspect of this disclosure provides a method for controlling a display panel, the display panel including a touch structure, the touch structure including a plurality of touch electrodes and a plurality of touch traces electrically coupled to the plurality of touch electrodes, the method comprising:

[0006] Collect capacitance data from the multiple touch traces; Using a pre-trained display parameter prediction model, the predicted display parameters of the display panel are determined based on the capacitance data; the display parameter prediction model is trained based on sample capacitance data under the constraint of sample environmental data, and the labels of the sample capacitance data include sample display parameters; The display panel is controlled to display based on the predicted display parameters.

[0007] Based on the same inventive concept, a second aspect of this disclosure provides a display device, comprising: The display panel includes a touch structure disposed on one side of the light-emitting direction of the display panel. The touch structure includes multiple touch electrodes and multiple touch lines electrically coupled to the multiple touch electrodes. The control circuit includes a display control circuit and a touch control circuit, wherein: The touch control circuit is electrically coupled to the display control circuit and the plurality of touch traces, and is configured to: execute the method described in the first aspect to generate a display control signal; The display control circuit is electrically coupled to the display panel and is configured to control the display panel to display based on the display control signal.

[0008] Based on the same inventive concept, a third aspect of this disclosure proposes an electronic device including a memory, a processor, and a computer program stored in the memory and executable by the processor, wherein the processor implements the method described above when executing the computer program.

[0009] Based on the same inventive concept, a fourth aspect of this disclosure provides a non-transitory computer-readable storage medium that stores computer instructions for causing a computer to perform the methods described above.

[0010] Based on the same inventive concept, a fifth aspect of this disclosure provides a computer program product comprising computer program instructions that, when executed on a computer, cause the computer to perform the method described above.

[0011] As described above, this disclosure provides a control method, display device, and related equipment for a display panel. The display panel includes a touch structure, which comprises multiple touch electrodes and multiple touch traces electrically coupled to the touch electrodes. Capacitance data on the multiple touch traces is collected. A pre-trained display parameter prediction model is used to determine the predicted display parameters of the display panel based on the capacitance data. The display parameter prediction model is trained based on sample capacitance data under the constraint of sample environmental data, and the labels of the sample capacitance data include sample display parameters. The display panel is controlled to display based on the predicted display parameters. In this way, the predicted display parameters of the display panel are determined based on the capacitance data on multiple touch traces, eliminating the need for additional built-in sensors to collect environmental parameters, saving internal space in the display device, and avoiding the additional power consumption caused by sensor operation. Furthermore, the display parameter prediction model can quickly determine the predicted display parameters of the display panel, achieving real-time and accurate prediction of display parameters. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in this disclosure or related technologies, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a flowchart of a control method for a display panel according to an embodiment of the present disclosure; Figure 2 This is a schematic diagram of a method for predicting display parameters according to an embodiment of the present disclosure; Figure 3 This is a schematic diagram of a prediction system for display parameters according to an embodiment of the present disclosure; Figure 4 This is a schematic diagram of the data-driven modeling layer in an embodiment of this disclosure; Figure 5 This is a schematic diagram of the application mapping layer according to an embodiment of the present disclosure; Figure 6 This is a schematic diagram of the structure of a display device according to an embodiment of the present disclosure; Figure 7 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present disclosure. Detailed Implementation

[0014] To make the objectives, technical solutions, and advantages of this disclosure clearer, the following detailed description is provided in conjunction with specific embodiments and the accompanying drawings.

[0015] It should be noted that, unless otherwise defined, the technical or scientific terms used in the embodiments of this disclosure should have the ordinary meaning understood by one of ordinary skill in the art to which this disclosure pertains. The terms "first," "second," and similar terms used in the embodiments of this disclosure do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0016] Based on the background description, with the widespread application of touchscreens in high-end display devices such as smartphones, tablets, wearable devices, and flexible foldable screens, screen display performance has a significant impact on user experience. To provide ideal display performance under different environmental conditions, it is necessary to adjust display parameters (e.g., brightness, refresh rate, and temperature drift compensation for Gamma). In related technologies, additional built-in ambient light sensors or screen temperature sensors are typically used to acquire environmental data and determine display parameters based on this data. However, these additional built-in sensors increase the internal space occupied by the display device and cannot achieve real-time, precise adjustment of display parameters.

[0017] As mentioned above, how to accurately adjust the display parameters of the display panel in real time has become an important research question.

[0018] Based on the above description, such as Figure 1As shown in this embodiment, the control method for a display panel includes a touch structure, which comprises multiple touch electrodes and multiple touch traces electrically coupled to the multiple touch electrodes. The method includes: Step 101: Collect capacitance data on the multiple touch lines.

[0019] In practice, the capacitance data is static capacitance data collected on multiple touch traces without detecting any touch operation. Specifically, the capacitance data is the timing data of the capacitance on the touch traces.

[0020] Step 102: Using a pre-trained display parameter prediction model, determine the predicted display parameters of the display panel based on the capacitance data; the display parameter prediction model is trained based on sample capacitance data under the constraint of sample environmental data, and the labels of the sample capacitance data include sample display parameters.

[0021] In practice, the predicted display parameters include at least one of the following: predicted display brightness, predicted display refresh rate, and predicted display compensation value (predicted display Gamma compensation value).

[0022] The displayed parameter prediction model is obtained by training a Long Short-Term Memory (LSTM) network based on sample capacitance data under the constraints of sample environmental data.

[0023] Step 103: Control the display panel to display based on the predicted display parameters.

[0024] In practice, a display control signal is generated based on the predicted display parameters, and the display panel is controlled to display based on the display control signal.

[0025] In the above embodiments, the display panel includes a touch structure, which includes multiple touch electrodes and multiple touch traces electrically coupled to the touch electrodes. Capacitance data is collected from the multiple touch traces. Using a pre-trained display parameter prediction model, predicted display parameters of the display panel are determined based on the capacitance data. The display parameter prediction model is trained based on sample capacitance data under the constraint of sample environmental data, and the labels of the sample capacitance data include sample display parameters. The display panel is controlled to display based on the predicted display parameters. In this way, the predicted display parameters of the display panel are determined based on the capacitance data on multiple touch traces, eliminating the need for additional built-in sensors to collect environmental parameters, saving internal space in the display device, and avoiding the additional power consumption caused by sensor operation. Furthermore, the display parameter prediction model can quickly determine the predicted display parameters of the display panel, achieving real-time and accurate prediction of display parameters.

[0026] Figure 2This is a schematic diagram of a method for predicting display parameters according to an embodiment of this disclosure. Figure 2 As shown, the training phase of the display parameter prediction model includes: Step I, acquiring sample capacitance data, the labels of which include sample display parameters; Step II, acquiring sample environmental data (sample light intensity data, sample temperature data); inputting the sample capacitance data into a Long Short-Term Memory (LSTM) network to obtain a first prediction result, inputting the sample environmental data into a priori constraint network to obtain a second prediction result, and training the LSM network based on the first prediction result, the second prediction result, and the sample display parameters to obtain the display parameter prediction model. The application phase of the display parameter prediction model includes: Step III, inputting the capacitance data from multiple touch traces into the display parameter prediction model to obtain predicted display parameters.

[0027] Figure 3 This is a schematic diagram of a prediction system for display parameters according to an embodiment of this disclosure. Figure 3 As shown, the prediction system for display parameters includes: a mathematical modeling layer, a data-driven modeling layer, and an application mapping layer.

[0028] In the mathematical modeling layer, the capacitance data on multiple touch traces is essentially a parallel-plate capacitor, and the capacitance data on multiple touch traces is represented as follows: ,in, This refers to the capacitance data for multiple touch traces. The vacuum permittivity, The relative permittivity, This represents the relative area of ​​the touchscreen traces. This refers to the distance between touch control traces.

[0029] In the above formula, the relative permittivity It will change with environmental factors such as light intensity and temperature, that is ,in, For light intensity data, Given temperature data, the variation parameters of the capacitance data can be modeled as follows: ,in, For the changing parameters of capacitance data, This is a parameter representing the variation of the relative permittivity. This is a parameter representing the change in the relative area of ​​the touchscreen traces. This is a parameter representing the variation in the distance between touch traces.

[0030] Considering the diverse and complex scenarios in practical applications, the mathematical modeling layer should encompass dynamic scenarios such as indoor-to-outdoor transitions, tunnel-to-outdoor transitions, direct sunlight, and low-temperature environments. Taking the indoor-to-outdoor transition scenario, with the mobile phone as the terminal device, as an example, when the phone is moved from indoors to outdoors, the light intensity increases from 300 lux to 50,000 lux, and the ambient temperature changes from 22°C to -5°C. The phone's temperature change follows the exponential cooling law of heat conduction and convection, which can be described using Newton's law of cooling. ,in, For mobile phones in the first Temperature data at any given time The initial indoor temperature. The outdoor temperature under steady-state conditions. is the time constant.

[0031] Light intensity data changes dramatically from indoors to outdoors, which can be represented by a nonlinear step function: ,in, For mobile phones in the first Light intensity data at any given time The indoor light intensity in the initial state. Outdoor light intensity under steady-state conditions. This is the time required for the light intensity data to switch from an initial state to a stable state.

[0032] The mathematical model for changes in mobile phone screen brightness is the superposition of light intensity response and temperature response, expressed as: ,in, To predict display brightness, The indoor light intensity in the initial state. The maximum brightness increment driven by light intensity. The light intensity response coefficient is... For real-time light intensity data, This is a nonlinear light intensity response term. These are the temperature fitting coefficients. The initial indoor temperature. For real-time temperature data, For linear temperature correction.

[0033] refresh rate This is usually related to power consumption and temperature constraints need to be considered. ,in, To predict the display refresh rate, The nominal refresh rate, This is the temperature-induced refresh rate derating factor. This is the real-time temperature data displayed on the screen. This is the safe temperature threshold.

[0034] Gamma compensation value combined with changes in light intensity and temperature data: ,in, To predict the Gamma compensation value, This is the initial Gamma compensation value. These are the temperature fitting coefficients. The outdoor temperature under steady-state conditions. The initial indoor temperature. The brightness integration factor. Outdoor light intensity under steady-state conditions. The indoor light intensity is at its initial state.

[0035] Based on mathematical modeling, it is known that there are complex cross-nonlinear relationships between the capacitance data, environmental data (light intensity data, temperature data), and screen display parameters (display brightness, display refresh rate, and Gamma compensation value) of multiple touch traces. If traditional multidimensional lookup tables combined with manual control algorithms are used, technical problems such as data explosion, poor dynamic adaptation, and high maintenance costs will be encountered. However, display parameter prediction models can directly replace complex lookup tables through temporal feature learning and end-to-end mapping, achieving more efficient and accurate parameter control.

[0036] Figure 4 This is a schematic diagram of the data-driven modeling layer according to an embodiment of this disclosure. Figure 4 As shown, in the data-driven modeling layer, capacitance data from multiple touch traces are collected, and actual environmental data (light intensity data, temperature data) and corresponding screen display parameters (display brightness, display refresh rate, and Gamma compensation value) are recorded simultaneously to construct a calibration dataset. Unlike traditional static mapping methods, the Long Short-Term Memory (LSTM) network in this embodiment specifically models the time-series characteristics of capacitance data on touch traces under complex dynamic environments. In addition to using sample capacitance data from the touch traces as input, auxiliary feature sequences of sample environmental data (sample light intensity data and sample temperature data) are introduced to form a multi-channel input; screen display parameters (display brightness, display refresh rate, and Gamma compensation value) serve as output labels.

[0037] By capturing the temporal dynamics of capacitance changes, the Long Short-Term Memory (LSTM) network can remember causes and consequences, and by combining instantaneous fluctuations and trend lags, achieve optimal feedforward predictive control of screen display parameters for the next moment. Compared to control methods based on static thresholds or single-point measurements, the embodiments of this disclosure have stronger scene adaptability and dynamic response capabilities. After the display parameter prediction model is trained, only the capacitance test data of the current touch trace needs to be input during the inference phase to directly output the screen display parameters to be adjusted. Employing a multi-input training and single-input inference strategy, the training phase uses sample environmental data (sample light intensity data and sample temperature data) as prior constraints, making the model weight parameters of the display parameter prediction model implicitly contain the coupling relationship between these auxiliary features and capacitance; during the inference phase, high-precision output can be achieved by relying only on capacitance data from multiple touch traces, improving practicality and system integration.

[0038] Training of Long Short-Term Memory (LSTM) networks can be done on a personal computer (PC), but it is not limited to PCs. It can be extended to various hardware carriers such as embedded devices and cloud platforms as needed. Figure 5 This is a schematic diagram of the application mapping layer according to an embodiment of this disclosure. Figure 5 As shown, in the application mapping layer, after the display parameter prediction model is trained, its model parameters are compressed and quantized, and then stored in the memory unit of the integrated circuit (IC). During terminal operation, the touch chip collects capacitance data from multiple touch traces in real time, inputs it into the built-in display parameter prediction model, outputs the corresponding predicted display parameters, and generates display control signals based on these parameters. Through interaction between the touch chip and the display panel, automatic adjustment of display brightness, refresh rate, and Gamma compensation value is achieved.

[0039] In some embodiments, the capacitance data includes multiple capacitance data corresponding to multiple time points.

[0040] Step 102 includes: Step 1021: Using the display parameter prediction model, extract timing features from the capacitance data, and determine the predicted display parameters based on the timing features.

[0041] In practice, the display parameter prediction model includes an input layer, a long short-term memory layer, a fully connected layer, and a multi-task output layer. Capacitance data is input into the display parameter prediction model, and the hidden state is determined based on the model's forward pass. ,in, For the current moment The hidden state, For the previous moment The hidden state, For the Long Short-Term Memory layer at the current moment The state of cells, For the Long Short-Term Memory layer at the previous moment The cellular state.

[0042] The temporal features are determined based on the hidden state of the last time step. ,in, As a time series feature, These are the weight parameters (weight matrix) corresponding to the time-series features. In hidden state, These are the bias parameters (bias terms) corresponding to the time series features.

[0043] Predicted display parameters are determined based on temporal characteristics. These parameters include: predicted brightness parameters. Predicted refresh rate parameters and predicted compensation value parameters .

[0044] The above scheme utilizes a display parameter prediction model to extract time-series features from capacitance data, and then determines the predicted display parameters based on these features. In this way, the time-series features reflect the capacitance data characteristics of adjacent time points, enabling rapid and accurate determination of the predicted display parameters and achieving real-time, precise prediction of display parameters.

[0045] In some embodiments, step 1021 includes: Step 10211: Determine the predicted brightness parameters of the display panel based on the timing characteristics, brightness weight parameters, and brightness bias parameters.

[0046] In practice, the predicted brightness parameters of the display panel are determined based on timing characteristics, brightness weight parameters, and brightness bias parameters. ,in, This refers to the predicted brightness parameters of the display panel. For brightness weight parameters (brightness weight matrix). As a time series feature, This is the brightness bias parameter (brightness bias term).

[0047] Step 10212: Determine the predicted refresh rate parameters of the display panel based on the timing characteristics, refresh rate weight parameters, and refresh rate bias parameters.

[0048] In practice, the predicted refresh rate parameters of the display panel are determined based on timing characteristics, refresh rate weight parameters, and refresh rate offset parameters. ,in, This refers to the predicted refresh rate parameter (predicted refresh rate category score) for the display panel. This refers to the refresh rate weighting parameter (refresh rate weighting matrix). As a time series feature, This is the refresh rate offset parameter (refresh rate offset item).

[0049] Step 10213: Determine the predicted compensation value parameters of the display panel based on the time series characteristics, compensation value weight parameters, and compensation value bias parameters.

[0050] In practice, the predicted compensation value parameters for the display panel are determined based on the time-series characteristics, compensation value weight parameters, and compensation value bias parameters. ,in, The predicted compensation value parameter for the display panel. The compensation value weight parameters (compensation value weight matrix). As a time series feature, This is the compensation value bias parameter (compensation value bias term).

[0051] Step 10214: Use the predicted brightness parameter, the predicted refresh rate parameter, and the predicted compensation value parameter as the predicted display parameter.

[0052] In practice, the predicted brightness parameters will be used. Predicted refresh rate parameters and predicted compensation value parameters As a parameter for prediction display.

[0053] The above scheme determines the predicted brightness parameters of the display panel based on timing characteristics, brightness weight parameters, and brightness bias parameters. The predicted refresh rate parameters are also determined based on timing characteristics, refresh rate weight parameters, and refresh rate bias parameters. Finally, the predicted compensation value parameters are determined based on timing characteristics, compensation value weight parameters, and compensation value bias parameters. These predicted brightness, refresh rate, and compensation value parameters are then used as the predicted display parameters. In this way, the predicted brightness, refresh rate, and compensation value parameters can be determined based on timing characteristics, enabling comprehensive real-time prediction of display parameters.

[0054] In some embodiments, the training process of the display parameter prediction model includes: Step 104: Obtain the sample capacitance data and the sample environment data. The label of the sample capacitance data includes sample display parameters.

[0055] In practice, a touch sampling system, a display control system, and an environmental information acquisition system are constructed to simultaneously acquire sample capacitance data, sample environmental data (sample light intensity data and sample temperature data), and sample display parameters under different display states and environmental conditions.

[0056] During the training of the Long Short-Term Memory Network, the sample capacitance data on multiple touch lines are the main input information, the sample environmental data (sample light intensity data and sample temperature data) are the auxiliary input information, and the sample display parameters are the supervision labels.

[0057] The sample capacitance data consists of capacitance timing data across multiple touch traces. The sample capacitance data is represented as follows: ,in, For sample capacitance data, The time window length, For the first Capacitive feature vectors of multiple touch traces at each sampling time. Represents the real number field. This refers to the characteristic dimensions of multiple touch traces.

[0058] The sample environment data includes: sample light intensity data of the environment in which the display panel is located and sample temperature data of the display panel. The sample environment data is represented as follows: ,in, For sample environment data, This is sample light intensity data of the environment in which the display panel is located. This is the sample temperature data for the display panel.

[0059] The labels for the sample capacitance data include sample display parameters. These sample display parameters are expressed as follows: ,in, Display parameters for the sample. To display the brightness of the sample, To display the refresh rate for the sample, Provides compensation values ​​for the sample display. Sample display brightness. And sample display compensation value These are continuous values. The sample displays the refresh rate. For discrete speed settings, the sample display refresh rate is... The frequency range can be set to categories such as 60Hz, 90Hz, and 120Hz.

[0060] Sample capacitance data, sample environment data (sample light intensity data and sample temperature data), and sample display parameters are preprocessed to obtain sample data. Specifically, DC removal and baseline drift calibration are performed on the sample capacitance data along multiple touch lines to obtain calibrated sample capacitance data. Abnormal spikes in the calibrated sample capacitance data are suppressed to obtain suppressed sample capacitance data. Multiple channel features in the suppressed sample capacitance data are normalized to obtain normalized sample capacitance data. The normalized sample capacitance data is then divided into multiple time-series windows using a sliding window of a preset length to obtain sample capacitance data for each time-series window. The sample environment data (sample light intensity data and sample temperature data) are aligned with the sample capacitance data for each time-series window to obtain sample input data. The sample display parameters corresponding to the sample input data at each time point are used as labels and written into the sample input data to obtain the sample data. The sample data is represented as follows: ,in, For sample data, For the first Individual sample capacitance data, For the first Individual sample environmental data, For the first Each sample displays parameters. This represents the total number of sample data.

[0061] In some approaches, sample data is divided into training, validation, and test sets. The training set is used to train the Long Short-Term Memory network, the validation set is used to validate the pre-trained display parameter prediction model, and the test set is used to test the pre-trained display parameter prediction model.

[0062] Specifically, the sample data is divided into a training set, a validation set, and a test set according to preset proportions. For example, the preset proportions for the training set are 70%, the validation set is 15%, and the test set is 15%.

[0063] Step 105: Input the sample capacitance data into a long short-term memory network, use the long short-term memory network to extract sample time-series features from the sample capacitance data, and determine the first prediction result based on the sample time-series features.

[0064] In specific implementation, this embodiment of the disclosure adopts a network structure of multi-input training and single-input inference. The training phase includes a long short-term memory network and a prior constraint network. The long short-term memory network only receives sample capacitance data from multiple touch lines, while the prior constraint network receives sample capacitance data and sample environmental data (sample light intensity data and sample temperature data) from multiple touch lines, and forms prior constraints on the long short-term memory network during the training phase.

[0065] The Long Short-Term Memory (LSTM) network consists of an input layer, an LSM layer, a fully connected layer, and a multi-task output layer. The LSM layer has two layers, each with 128 hidden units. The fully connected layer also has two layers; the first fully connected layer has an output dimension of 64, and the second fully connected layer is connected to the input layer. The internal state activation function of the LSM layer uses... The gating activation function of the long short-term memory layer adopts The activation function of the fully connected layer is adopted .

[0066] The sample capacitance data is input into a Long Short-Term Memory (LSTM) network. The LSM network is used to extract sample temporal features from the sample capacitance data, and a first prediction result is determined based on the sample temporal features. The first prediction result includes: a first predicted brightness, a first predicted refresh rate, and a first predicted compensation value.

[0067] Specifically, the forward pass of the Long Short-Term Memory (LSTM) network is represented as follows: ,in, For the current moment The hidden state, For the previous moment The hidden state, For the Long Short-Term Memory layer at the current moment The state of cells, For the Long Short-Term Memory layer at the previous moment Cellular state. Cellular state It is a memory channel in the Long Short-Term Memory network, used to store information across time periods.

[0068] For example, when a mobile phone is moved from indoors to outdoors, the light intensity increases from 300 lux to 50,000 lux, and the ambient temperature changes from 22°C to -5°C. Cellular state. This is a background assessment of the environment: the phone was just taken out of the room, and the temperature is continuously dropping, indicating it's not in a steady-state indoor environment. Hidden state. The assessment result of the current system is: the screen brightness of the phone should be increased now, but the compensation value and refresh rate should be adjusted according to the transition strategy first.

[0069] Hidden state of the last time step Determine the temporal characteristics of the samples. ,in, For the time series features of the samples, These are the weight parameters (weight matrix) corresponding to the temporal features of the samples. This is the hidden state at the last time step. These are the bias parameters (bias terms) corresponding to the temporal features of the samples. Temporal features of the samples This represents not a single-frame feature, but a temporal feature containing feature information from a previous period. For example, sample temporal features. This can indicate whether the screen is in a state of rising temperature or in a state of stable temperature.

[0070] Based on the sample time-series characteristics, brightness weight parameters, and brightness bias parameters, the predicted brightness parameters of the display panel are determined. ,in, For the first predicted brightness, For brightness weight parameters (brightness weight matrix). For the time series features of the samples, This is the brightness bias parameter (brightness bias term).

[0071] Based on the sample timing characteristics, refresh rate weight parameters, and refresh rate bias parameters, the predicted refresh rate parameters of the display panel are determined. ,in, The first predicted refresh rate, This refers to the refresh rate weighting parameter (refresh rate weighting matrix). For the time series features of the samples, This is the refresh rate offset parameter (refresh rate offset item).

[0072] Based on the sample time-series characteristics, compensation value weight parameters, and compensation value bias parameters, the predicted compensation value parameters for the display panel are determined. ,in, The first predicted compensation value, The compensation value weight parameters (compensation value weight matrix). For the time series features of the samples, This is the compensation value bias parameter (compensation value bias term).

[0073] Step 106: Input the sample environment data into the prior constraint network, and use the prior constraint network to extract prior features from the sample environment data.

[0074] In practice, the prior constraint network is only used during the training phase, and its input is the sample environment data. (Auxiliary input information). The prior constraint network is used to extract prior features from sample light intensity data and sample temperature data, and to constrain these prior features to the intermediate representation or output of the long short-term memory network. The prior constraint network consists of two fully connected layers.

[0075] The prior features are represented as follows: ,in, As prior features, The mapping function for the prior constraint network, This is sample environmental data.

[0076] Step 107: The sample temporal features and the prior features are fused to obtain fused features, and a second prediction result is determined based on the fused features.

[0077] In practice, to construct the joint prediction branch during the training phase, the temporal features and prior features of the samples are fused to obtain the fused features. ,in, As a feature of fusion, For the time series features of the samples, These are prior features.

[0078] The joint output from the training phase is generated based on the fused features, and this joint output is used as the second prediction result. The second prediction result includes: second predicted brightness, second predicted refresh rate, and second predicted compensation value. The second prediction result is expressed as: ,in, For the second predicted brightness, For the second predicted refresh rate, This is the second predicted compensation value. For the fusion prediction head during the training phase, This is a feature of fusion.

[0079] The second prediction result is only used for training constraints and is not part of the actual inference structure during the deployment of the explicit parameter prediction model. That is, the second prediction result is unrelated to determining the predicted explicit parameters using the explicit parameter prediction model.

[0080] Step 108: Determine the total loss function based on the first prediction result, the second prediction result, and the sample display parameters.

[0081] In practice, a first loss function is determined based on the first prediction result and the sample display parameters. A second loss function is determined based on the second prediction result and the sample display parameters. A prior loss function is determined based on the first and second prediction results. The first loss function, the second loss function, and the prior loss function are then weighted to obtain the total loss function.

[0082] Step 109: Update the model parameters of the Long Short-Term Memory Network based on the total loss function to obtain the display parameter prediction model.

[0083] In practice, the explicit parameter prediction model is obtained by updating the model parameters of the Long Short-Term Memory network based on the total loss function using the backpropagation algorithm. After the model training is complete, only the explicit parameter prediction model is retained for deployment.

[0084] In this way, by using sample capacitance data from multiple touch lines as the main input information and sample environmental data (sample light intensity data and sample temperature data) as auxiliary prior information during the training phase, a joint training structure of long short-term memory network and prior constraint network is constructed. This allows the long short-term memory network to learn the influence of environmental data (light intensity data and temperature data) on display parameters during the training process, and to predict display parameters by relying solely on capacitance data from the touch lines during the deployment phase.

[0085] The above scheme acquires sample capacitance data and sample environment data. The label of the sample capacitance data includes sample display parameters. The sample capacitance data is input into a Long Short-Term Memory (LSTM) network, which extracts temporal features from the sample capacitance data and determines a first prediction result based on these features. The sample environment data is input into a prior constraint network, which extracts prior features from the sample environment data. The temporal features and prior features are fused to obtain fused features, and a second prediction result is determined based on these fused features. The total loss function is determined based on the first prediction result, the second prediction result, and the sample display parameters. The model parameters of the LSM network are updated based on the total loss function to obtain the display parameter prediction model. In this way, by using sample capacitance data as the primary input data and sample environment data as auxiliary prior data, and by constructing a joint training structure for the LSM network and the prior constraint network, the LSM network can learn the influence of environmental data on display parameters during training, enabling the trained display parameter prediction model to more accurately determine the predicted display parameters.

[0086] In some embodiments, the sample environment data includes: sample light intensity data of the environment in which the display panel is located and sample temperature data of the display panel.

[0087] In practice, the sample environment data is represented as follows: ,in, For sample environment data, This is sample light intensity data of the environment in which the display panel is located. This is the sample temperature data for the display panel.

[0088] The above approach uses sample environmental data including sample light intensity data of the environment in which the display panel is located and sample temperature data of the display panel. By using sample light intensity and temperature data as auxiliary prior data during the training phase, the Long Short-Term Memory (LSTM) network can learn the influence of light intensity and temperature data on display parameters, enabling the trained display parameter prediction model to more accurately determine the predicted display parameters.

[0089] In some embodiments, step 108 includes: Step 1081: Determine the first loss function based on the first prediction result and the sample display parameters.

[0090] In practice, the first prediction result includes: the first predicted brightness. First predicted refresh rate and the first predicted compensation value The sample display parameters include: sample display brightness. Sample display refresh rate And sample display compensation value .

[0091] Using the Mean Squared Error (MSE) algorithm, based on the first predicted brightness... and sample display brightness Determine the first luminance loss function Determine the first predicted refresh rate. Refresh rate of sample display The cross-entropy loss function is used as the first refresh rate loss function. Using the mean square error algorithm, based on the first predicted compensation value... And sample display compensation value Determine the first compensation value loss function For the first luminance loss function First refresh rate loss function and the first compensation value loss function After weighting, the first loss function is obtained. .

[0092] Step 1082: Determine the second loss function based on the second prediction result and the sample display parameters.

[0093] In practice, the second prediction result includes: the second predicted brightness. Second predicted refresh rate Second prediction compensation value The sample display parameters include: sample display brightness. Sample display refresh rate And sample display compensation value .

[0094] Using the mean square error algorithm, based on the second predicted brightness and sample display brightness Determine the second luminance loss function Determine the second predicted refresh rate. Refresh rate of sample display The cross-entropy loss function is used as the second refresh rate loss function. Using the mean square error algorithm, based on the second predicted compensation value... And sample display compensation value Determine the second compensation value loss function For the second brightness loss function Second refresh rate loss function Second compensation value loss function After weighting, the second loss function is obtained. .

[0095] Step 1083: Determine the prior loss function based on the first prediction result and the second prediction result.

[0096] In specific implementation, in order to enable the Long Short-Term Memory Network to absorb prior information from the sample environment data, the embodiments of this disclosure further construct a consistency loss function (prior loss function) between the first prediction result and the second prediction result.

[0097] The prior loss functions include: a first prior loss function and a second prior loss function. The first prior loss function is the consistency loss function for predicted brightness and predicted compensation value, while the second prior loss function is the consistency loss function for predicted refresh rate.

[0098] Based on the first predicted brightness Second predicted brightness First predicted compensation value Second prediction compensation value Determine the first prior loss function According to the first predicted refresh rate Second predicted refresh rate Determine the second prior loss function .

[0099] Step 1084: The first loss function, the second loss function, and the prior loss function are weighted to obtain the total loss function.

[0100] In specific implementation, the first loss function Second loss function and the prior loss function (first prior loss function) Second prior loss function The total loss function is obtained by weighting the loss values. The specific formula is as follows: , in, For the total loss function, For the first loss function, These are the weight coefficients corresponding to the second loss function. For the second loss function, These are the weight coefficients corresponding to the first prior loss function. Let the first prior loss function be... These are the weight coefficients corresponding to the second prior loss function. This is the second prior loss function.

[0101] Training the Long Short-Term Memory (LSTM) network using the total loss function ensures that the LTM network has the ability to directly predict the display parameters of the real labels; ensures that the fused features can make full use of the sample environment data; and ensures that the LTM network learns from the fused features. Thus, when using the display parameter prediction model to determine the predicted display parameters, relying only on the capacitance data of multiple touch lines can still approximate the prediction effect with prior information.

[0102] The above scheme determines a first loss function based on the first prediction result and the sample display parameters. This first loss function comprehensively reflects the accuracy of the first prediction result output by the Long Short-Term Memory (LSTM) network. A second loss function is then determined based on the second prediction result and the sample display parameters. This second loss function comprehensively reflects the accuracy of the second prediction result output by the prior constraint network. A prior loss function is then determined based on the first and second prediction results. This prior loss function comprehensively reflects the consistency between the first prediction result output by the LSM network and the second prediction result output by the prior constraint network, and can be used to constrain the LSM network. The first, second, and prior loss functions are weighted to obtain the total loss function. Thus, the total loss function comprehensively considers the prediction accuracy of the LSM network, the prediction accuracy of the prior constraint network, and the output consistency between the LSM network and the prior constraint network, making the total loss function more comprehensive and accurate.

[0103] In some embodiments, the first prediction result includes: a first predicted brightness, a first predicted refresh rate, and a first predicted compensation value; the sample display parameters include: sample display brightness, sample display refresh rate, and sample display compensation value.

[0104] Step 1081 includes: Step 1081A: Determine the first brightness loss function based on the first predicted brightness and the sample display brightness using the mean square error algorithm.

[0105] In practice, the mean square error algorithm is used to determine the first predicted brightness. and sample display brightness Determine the first luminance loss function. The specific formula is as follows: , in, Let be the first brightness loss function. This represents the total number of sample capacitance data. For the first The first predicted brightness corresponding to each sample capacitance data. For the first Each sample displays brightness.

[0106] Step 1081B: Determine the cross-entropy loss function between the first predicted refresh rate and the sample display refresh rate, and use the cross-entropy loss function as the first refresh rate loss function.

[0107] In practice, the first predicted refresh rate is determined. Refresh rate of sample display The cross-entropy loss function is used as the first refresh rate loss function. The specific formula is as follows: , in, For the first refresh rate loss function, This represents the total number of sample capacitance data. The number of refresh rate categories, For the first Each sample displays the refresh rate. For the first The first predicted refresh rate corresponding to the sample capacitance data belongs to the [number]th [number]. Predicted probability of refresh rate.

[0108] Step 1081C: Determine the first compensation value loss function based on the first predicted compensation value and the sample display compensation value using the mean square error algorithm.

[0109] In practice, the mean square error algorithm is used to determine the compensation value based on the first prediction. And sample display compensation value Determine the loss function for the first compensation value. The specific formula is as follows: , in, The loss function is the first compensation value. This represents the total number of sample capacitance data. For the first The first predicted compensation value corresponding to each sample capacitance data. For the first Each sample displays the compensation value.

[0110] Step 1081D: The first brightness loss function, the first refresh rate loss function, and the first compensation value loss function are weighted to obtain the first loss function.

[0111] In specific implementation, the first luminance loss function First refresh rate loss function and the first compensation value loss function After weighting, the first loss function is obtained. The specific formula is as follows: , in, For the first loss function, The first weighting coefficient corresponds to the first brightness loss function. Let be the first brightness loss function. The second weighting coefficient corresponds to the first refresh rate loss function. For the first refresh rate loss function, The third weighting coefficient corresponds to the loss function of the first compensation value. This is the loss function for the first compensation value.

[0112] The above scheme employs a mean squared error algorithm to determine a first brightness loss function based on the first predicted brightness and the sample displayed brightness. This first brightness loss function reflects the accuracy of the first predicted brightness output by the Long Short-Term Memory (LSTM) network. A cross-entropy loss function is determined between the first predicted refresh rate and the sample displayed refresh rate, and this cross-entropy loss function is used as the first refresh rate loss function, reflecting the accuracy of the first predicted refresh rate output by the LSTM network. A first compensation value loss function is determined using a mean squared error algorithm based on the first predicted compensation value and the sample displayed compensation value, reflecting the accuracy of the first predicted compensation value output by the LSTM network. The first brightness loss function, the first refresh rate loss function, and the first compensation value loss function are weighted to obtain the first loss function. Thus, the first loss function comprehensively reflects the accuracy of the first predicted result output by the LSTM network.

[0113] In some embodiments, the second prediction result includes: a second predicted brightness, a second predicted refresh rate, and a second predicted compensation value; the sample display parameters include: sample display brightness, sample display refresh rate, and sample display compensation value.

[0114] Step 1082 includes: Step 1082A: Determine the second brightness loss function based on the second predicted brightness and the sample display brightness using the mean square error algorithm.

[0115] In practice, the mean square error algorithm is used to determine the second predicted brightness. and sample display brightness Determine the second luminance loss function. The specific formula is as follows: , in, The second brightness loss function, This represents the total number of sample capacitance data. For the first The second predicted brightness corresponding to each sample capacitance data. For the first Each sample displays brightness.

[0116] Step 1082B: Determine the cross-entropy loss function between the second predicted refresh rate and the sample display refresh rate, and use the cross-entropy loss function as the second refresh rate loss function.

[0117] In practice, the second predicted refresh rate is determined. Refresh rate of sample display The cross-entropy loss function is used as the second refresh rate loss function. The specific formula is as follows: , in, For the second refresh rate loss function, This represents the total number of sample capacitance data. The number of refresh rate categories, For the first Each sample displays the refresh rate. For the first The second predicted refresh rate corresponding to the sample capacitance data belongs to the [number]th [number]. Predicted probability of refresh rate.

[0118] Step 1082C: Determine the second compensation value loss function based on the second predicted compensation value and the sample displayed compensation value using the mean square error algorithm.

[0119] In practice, the mean square error algorithm is used to determine the second predicted compensation value. And sample display compensation value Determine the loss function for the second compensation value. The specific formula is as follows: , in, The second compensation value loss function, This represents the total number of sample capacitance data. For the first The second predicted compensation value corresponding to each sample capacitance data. For the first Each sample displays the compensation value.

[0120] Step 1082D: The second brightness loss function, the second refresh rate loss function, and the second compensation value loss function are weighted to obtain the second loss function.

[0121] In specific implementation, the second luminance loss function Second refresh rate loss function Second compensation value loss function After weighting, a second loss function is obtained. The specific formula is as follows: , in, For the second loss function, The fourth weighting coefficient corresponds to the second brightness loss function. The second brightness loss function, This is the fifth weighting coefficient corresponding to the second refresh rate loss function. For the second refresh rate loss function, The sixth weight coefficient corresponds to the second compensation value loss function. This is the loss function for the second compensation value.

[0122] The above scheme employs a mean squared error algorithm to determine a second brightness loss function based on the second predicted brightness and the sample displayed brightness. This second brightness loss function reflects the accuracy of the second predicted brightness output by the prior constraint network. A cross-entropy loss function is determined between the second predicted refresh rate and the sample displayed refresh rate, and this cross-entropy loss function is used as the second refresh rate loss function, reflecting the accuracy of the second predicted refresh rate output by the prior constraint network. A second compensation value loss function is determined using a mean squared error algorithm based on the second predicted compensation value and the sample displayed compensation value, reflecting the accuracy of the second predicted compensation value output by the prior constraint network. The second brightness loss function, the second refresh rate loss function, and the second compensation value loss function are weighted to obtain the second loss function. Thus, the second loss function comprehensively reflects the accuracy of the second prediction result output by the prior constraint network.

[0123] In some embodiments, the first prediction result includes: a first predicted brightness, a first predicted refresh rate, and a first predicted compensation value; the second prediction result includes: a second predicted brightness, a second predicted refresh rate, and a second predicted compensation value.

[0124] Step 1083 includes: Step 1083A: Determine the first prior loss function based on the first predicted brightness, the second predicted brightness, the first predicted compensation value, and the second predicted compensation value.

[0125] In specific implementation, based on the first predicted brightness Second predicted brightness First predicted compensation value Second prediction compensation value Determine the first prior loss function. The specific formula is as follows: , in, Let the first prior loss function be... This represents the total number of sample capacitance data. For the first The first predicted brightness corresponding to each sample capacitance data. For the first The second predicted brightness corresponding to each sample capacitance data. For the first The first predicted compensation value corresponding to each sample capacitance data. For the first The second predicted compensation value corresponding to each sample capacitance data.

[0126] Step 1083B: Determine the second prior loss function based on the first predicted refresh rate and the second predicted refresh rate.

[0127] In practice, based on the first predicted refresh rate Second predicted refresh rate Determine the second prior loss function. The specific formula is as follows: , in, The second prior loss function, This represents the total number of sample capacitance data. For the first The predicted probability of the second predicted refresh rate corresponding to each sample capacitance data. For the first The predicted probability of the first predicted refresh rate corresponding to each sample capacitance data.

[0128] Step 1083C: Use the first prior loss function and the second prior loss function as the prior loss function.

[0129] In practical implementation, the first prior loss function Second prior loss function As a prior loss function.

[0130] Using the above scheme, a first prior loss function is determined based on the first predicted brightness, the second predicted brightness, the first predicted compensation value, and the second predicted compensation value. The first prior loss function reflects the consistency between the first and second predicted brightness, and also reflects the consistency between the first and second predicted compensation values. A second prior loss function is determined based on the first and second predicted refresh rates. The second prior loss function accurately reflects the consistency between the first and second predicted refresh rates. Both the first and second prior loss functions are used as the primary prior loss function. In this way, the prior loss function can comprehensively reflect the consistency between the first predicted result output by the Long Short-Term Memory (LSTM) network and the second predicted result output by the prior constraint network, and can be used to constrain the LSM network.

[0131] In some embodiments, after step 1084, the method further includes: Step 1084A: Obtain the weight parameters and regularization coefficients.

[0132] Step 1084B: Based on the weight parameters and the regularization coefficients, the total loss function is modified to obtain the modified total loss function.

[0133] In practice, the weight parameters are obtained. and regularization coefficient According to the weight parameters and regularization coefficient The total loss function is then modified to obtain the modified total loss function. The specific formula is as follows: , in, The corrected total loss function, For the total loss function, The regularization coefficient is . These are the weight parameters.

[0134] The above method yields the weight parameters and regularization coefficients. Based on these parameters, the total loss function is modified to obtain the corrected total loss function. Thus, by adding a weighted regularization term, the total loss function can be modified to suppress fitting.

[0135] In the above embodiments, the display panel includes a touch structure, which includes multiple touch electrodes and multiple touch traces electrically coupled to the touch electrodes. Capacitance data is collected from the multiple touch traces. Using a pre-trained display parameter prediction model, predicted display parameters of the display panel are determined based on the capacitance data. The display parameter prediction model is trained based on sample capacitance data under the constraint of sample environmental data, and the labels of the sample capacitance data include sample display parameters. The display panel is controlled to display based on the predicted display parameters. In this way, the predicted display parameters of the display panel are determined based on the capacitance data on multiple touch traces, eliminating the need for additional built-in sensors to collect environmental parameters, saving internal space in the display device, and avoiding the additional power consumption caused by sensor operation. Furthermore, the display parameter prediction model can quickly determine the predicted display parameters of the display panel, achieving real-time and accurate prediction of display parameters.

[0136] It should be noted that the method of this disclosure embodiment can be executed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario, where multiple devices cooperate to complete the task. In such a distributed scenario, one of these devices may execute only one or more steps of the method of this disclosure embodiment, and the multiple devices will interact with each other to complete the method described.

[0137] It should be noted that the above description describes some embodiments of this disclosure. Other embodiments are within the scope of the appended claims of this disclosure. In some cases, the actions or steps described in the claims of this disclosure may be performed in a different order than that shown in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0138] Based on the same inventive concept, corresponding to any of the above-described embodiments, this disclosure also provides a display device.

[0139] refer to Figure 6 The display device 200 includes: The display panel 210 includes a touch structure 211 disposed on one side of the light emission direction of the display panel 210. The touch structure 211 includes a plurality of touch electrodes 2111 and a plurality of touch lines 2112 electrically coupled to the plurality of touch electrodes 2111. Control circuit 220 includes display control circuit 221 and touch control circuit 222, wherein: The touch control circuit 222 is electrically coupled to the display control circuit 221 and the plurality of touch traces 2112, and is configured to: execute the method described in any of the above embodiments to generate a display control signal; The display control circuit 221 is electrically coupled to the display panel 210 and is configured to control the display panel 210 to display based on the display control signal.

[0140] In specific implementation, the touch control circuit 222 can be a touch chip that integrates the control methods corresponding to the display panel. For example... Figure 5 As shown, after the display parameter prediction model is trained, its model parameters are compressed and quantized, and then stored in the touch chip's storage unit. During terminal operation, the touch chip collects capacitance data from multiple touch traces 2112 in real time, inputs it into the built-in display parameter prediction model, outputs the corresponding predicted display parameters, and generates display control signals based on these parameters. The touch chip interacts with the display panel 210, controlling the display panel 210 to display information based on the display control signals.

[0141] For ease of description, the above apparatus is described in terms of its functions, divided into various modules. Of course, in implementing this disclosure, the functions of each module can be implemented in one or more software and / or hardware.

[0142] The apparatus of the above embodiments is used to implement the control method of the corresponding display panel in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0143] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this disclosure also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the control method of the display panel described in any of the above embodiments.

[0144] Figure 7 This embodiment illustrates a more specific hardware structure of an electronic device, which may include a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, memory 1020, input / output interface 1030, and communication interface 1040 are interconnected internally via the bus 1050.

[0145] The processor 1010 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0146] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.

[0147] The input / output interface 1030 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components within the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touchscreens, microphones, various sensors, etc., while output devices may include displays, speakers, vibrators, indicator lights, etc.

[0148] The communication interface 1040 is used to connect the communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB (Universal Serial Bus), network cable, etc.) or wireless means (such as mobile network, WIFI (Wireless Fidelity), Bluetooth, etc.).

[0149] Bus 1050 includes a pathway for transmitting information between various components of the device, such as processor 1010, memory 1020, input / output interface 1030, and communication interface 1040.

[0150] It should be noted that although the above-described device only shows the processor 1010, memory 1020, input / output interface 1030, communication interface 1040, and bus 1050, in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the embodiments of this specification, and not necessarily all the components shown in the figures.

[0151] The electronic devices described above are used to implement the control methods of the corresponding display panels in any of the foregoing embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0152] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this disclosure also provides a non-transitory computer-readable storage medium that stores computer instructions for causing the computer to execute the control method of the display panel as described in any of the above embodiments.

[0153] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0154] The computer instructions stored in the storage medium of the above embodiments are used to cause the computer to execute the control method of the display panel as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0155] Based on the same inventive concept, corresponding to any of the above embodiments, this application also provides a computer program product, including computer program instructions. When the computer program instructions are run on a computer, the computer causes the computer to execute the control method of the display panel as described in any of the above embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0156] It is understood that before using the technical solutions of the various embodiments in this disclosure, users will be informed of the type, scope of use, and usage scenarios of the personal information involved in an appropriate manner, and user authorization will be obtained.

[0157] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose, based on the prompt message, whether to provide personal information to the software or hardware such as electronic devices, applications, servers, or storage media performing the operations of this disclosed technical solution.

[0158] As an optional but not limited implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0159] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0160] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of this disclosure is limited to these examples; within the framework of this disclosure, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of the embodiments of this disclosure as described above, which are not provided in detail for the sake of brevity.

[0161] Additionally, to simplify the description and discussion, and to avoid obscuring the embodiments of this disclosure, the provided drawings may or may not show well-known power / ground connections to integrated circuit (IC) chips and other components. Furthermore, the apparatus may be shown in block diagram form to avoid obscuring the embodiments of this disclosure, and this also takes into account the fact that the details of implementation of these block diagram apparatuses are highly dependent on the platform on which the embodiments of this disclosure will be implemented (i.e., these details should be fully understood by those skilled in the art). While specific details (e.g., circuits) have been set forth to describe exemplary embodiments of this disclosure, it will be apparent to those skilled in the art that the embodiments of this disclosure can be implemented without these specific details or with variations thereof. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0162] Although this disclosure has been described in conjunction with specific embodiments thereof, many substitutions, modifications, and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0163] This disclosure is intended to cover all such substitutions, modifications, and variations that fall within the broad scope of this disclosure. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this disclosure should be included within the protection scope of this disclosure.

Claims

1. A method for controlling a display panel, the display panel including a touch structure, the touch structure including a plurality of touch electrodes and a plurality of touch traces electrically coupled to the plurality of touch electrodes, the method comprising: Collect capacitance data from the multiple touch traces; Using a pre-trained display parameter prediction model, the predicted display parameters of the display panel are determined based on the capacitance data; the display parameter prediction model is trained based on sample capacitance data under the constraint of sample environmental data, and the labels of the sample capacitance data include sample display parameters; The display panel is controlled to display based on the predicted display parameters.

2. The method according to claim 1, wherein, The capacitance data includes multiple capacitance data corresponding to multiple time points; The step of using a pre-trained display parameter prediction model to determine the predicted display parameters of the display panel based on the capacitance data includes: Using the display parameter prediction model, timing features are extracted from the capacitance data, and the predicted display parameters are determined based on the timing features.

3. The method according to claim 2, wherein, Determining the prediction display parameters based on the temporal features includes: Based on the timing characteristics, brightness weight parameters, and brightness bias parameters, the predicted brightness parameters of the display panel are determined. Based on the timing characteristics, refresh rate weight parameters, and refresh rate bias parameters, the predicted refresh rate parameters of the display panel are determined. Based on the aforementioned temporal characteristics, compensation value weight parameters, and compensation value bias parameters, the predicted compensation value parameters for the display panel are determined. The predicted brightness parameter, the predicted refresh rate parameter, and the predicted compensation value parameter are used as the predicted display parameters.

4. The method according to claim 1, wherein, The training process of the display parameter prediction model includes: Acquire the sample capacitance data and the sample environment data, wherein the label of the sample capacitance data includes sample display parameters; The sample capacitance data is input into a long short-term memory network, and the long short-term memory network is used to extract sample temporal features from the sample capacitance data. Based on the sample temporal features, a first prediction result is determined. The sample environment data is input into the prior constraint network, and the prior constraint network is used to extract prior features from the sample environment data. The temporal features of the samples and the prior features are fused to obtain fused features, and a second prediction result is determined based on the fused features; The total loss function is determined based on the first prediction result, the second prediction result, and the sample display parameters; The explicit parameter prediction model is obtained by updating the model parameters of the Long Short-Term Memory network based on the total loss function.

5. The method according to claim 4, wherein, The sample environment data includes: sample light intensity data of the environment in which the display panel is located and sample temperature data of the display panel.

6. The method according to claim 4, wherein, The step of determining the total loss function based on the first prediction result, the second prediction result, and the sample display parameters includes: A first loss function is determined based on the first prediction result and the sample display parameters; The second loss function is determined based on the second prediction result and the sample display parameters; Determine the prior loss function based on the first prediction result and the second prediction result; The total loss function is obtained by weighting the first loss function, the second loss function, and the prior loss function.

7. The method according to claim 6, wherein, The first prediction result includes: a first predicted brightness, a first predicted refresh rate, and a first predicted compensation value; the sample display parameters include: sample display brightness, sample display refresh rate, and sample display compensation value; The step of determining the first loss function based on the first prediction result and the sample display parameters includes: A first brightness loss function is determined based on the first predicted brightness and the sample displayed brightness using a mean square error algorithm. Determine the cross-entropy loss function between the first predicted refresh rate and the sample display refresh rate, and use the cross-entropy loss function as the first refresh rate loss function; The first compensation value loss function is determined based on the first predicted compensation value and the sample display compensation value using the mean square error algorithm. The first brightness loss function, the first refresh rate loss function, and the first compensation value loss function are weighted to obtain the first loss function.

8. The method according to claim 6, wherein, The second prediction result includes: second predicted brightness, second predicted refresh rate, and second predicted compensation value; the sample display parameters include: sample display brightness, sample display refresh rate, and sample display compensation value. The step of determining the second loss function based on the second prediction result and the sample display parameters includes: A second brightness loss function is determined based on the second predicted brightness and the sample display brightness using a mean square error algorithm. Determine the cross-entropy loss function between the second predicted refresh rate and the sample display refresh rate, and use the cross-entropy loss function as the second refresh rate loss function; The second compensation value loss function is determined based on the second predicted compensation value and the sample displayed compensation value using the mean square error algorithm. The second brightness loss function, the second refresh rate loss function, and the second compensation value loss function are weighted to obtain the second loss function.

9. The method according to claim 6, wherein, The first prediction result includes: a first predicted brightness, a first predicted refresh rate, and a first predicted compensation value; the second prediction result includes: a second predicted brightness, a second predicted refresh rate, and a second predicted compensation value. The step of determining the prior loss function based on the first prediction result and the second prediction result includes: A first prior loss function is determined based on the first predicted brightness, the second predicted brightness, the first predicted compensation value, and the second predicted compensation value. The second prior loss function is determined based on the first predicted refresh rate and the second predicted refresh rate; The first prior loss function and the second prior loss function are used as the prior loss functions.

10. The method according to claim 6, wherein, After obtaining the total loss function by weighting the first loss function, the second loss function, and the prior loss function, the method further includes: Obtain the weight parameters and regularization coefficients; The total loss function is modified based on the weight parameters and the regularization coefficients to obtain the modified total loss function.

11. A display device, comprising: The display panel includes a touch structure disposed on one side of the light-emitting direction of the display panel. The touch structure includes multiple touch electrodes and multiple touch lines electrically coupled to the multiple touch electrodes. The control circuit includes a display control circuit and a touch control circuit, wherein: The touch control circuit is electrically coupled to the display control circuit and the plurality of touch traces, and is configured to: execute the method according to any one of claims 1 to 10 to generate a display control signal; The display control circuit is electrically coupled to the display panel and is configured to control the display panel to display based on the display control signal.

12. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor, when executing the program, implements the method as claimed in any one of claims 1 to 10.

13. A non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method according to any one of claims 1 to 10.

14. A computer program product comprising computer program instructions that, when executed on a computer, cause the computer to perform the method as described in any one of claims 1 to 10.

Images