Display screen refreshing control method and system based on power consumption control

Abstract

The invention discloses a display screen refreshing control method and system based on power consumption control. The method comprises the following steps: acquiring historical display data of at least one pixel region of a display screen; predicting a future display parameter corresponding to the pixel region according to the historical display data; determining a future power consumption parameter corresponding to the pixel region according to the future display parameter and a power consumption prediction model; and determining a display control instruction of the display screen at the future time point according to the future power consumption parameters corresponding to the at least two pixel areas. Therefore, accurate display screen dynamic energy-saving control based on pixel-level power consumption prediction can be achieved, the energy efficiency of the display screen is improved, the service life of the display screen is prolonged, and the risk of overheating or energy waste caused by the fact that a high-power-consumption area is not optimized is reduced.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a display screen refresh control method and system based on power consumption control. Background Technology

[0002] With the rapid proliferation of displays in various production control and consumer applications, users and manufacturers are increasingly focusing on improving energy efficiency and equipment lifespan through pixel-level dynamic energy-saving control. A key technical challenge is generating precise display control commands to avoid overheating or energy waste. Existing technologies typically acquire display data for the entire display area and control display parameters using fixed brightness adjustments or simple power consumption thresholds to meet basic energy-saving requirements. However, existing solutions lack the ability to predict future parameters from historical pixel data, perform detailed calculations of power consumption models, and dynamically analyze power consumption in adjacent areas. This makes it difficult to generate precise pixel-level display control commands, resulting in insufficient energy efficiency optimization. Failure to address high-power areas in a timely manner can lead to overheating, shortened lifespan, or energy waste, limiting the energy-saving performance and long-term reliability of the display. Therefore, existing technologies have shortcomings that urgently need to be addressed. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a display screen refresh control method and system based on power consumption control, which can realize accurate dynamic energy-saving control of the display screen based on pixel-level power consumption prediction, improve the energy efficiency and lifespan of the display screen, and reduce the risk of overheating or energy waste caused by unoptimized high power consumption areas.

[0004] To address the aforementioned technical problems, the first aspect of this invention discloses a display screen refresh control method based on power consumption control, the method comprising: Acquire historical display data for at least one pixel area of ​​the display screen; Based on the historical display data, predict the future display parameters corresponding to the pixel region; Based on the future display parameters and power consumption prediction model, determine the future power consumption parameters corresponding to the pixel region; The display control command for the display screen at a future time point is determined based on the future power consumption parameters corresponding to at least two of the pixel regions.

[0005] As an optional implementation, in the first aspect of the present invention, the historical display data includes component voltage data, brightness data, color data, dynamic change data of the image, and refresh data of the pixel area at multiple historical time points.

[0006] As an optional implementation, in the first aspect of the present invention, predicting the future display parameters corresponding to the pixel region based on the historical display data includes: Determine the region parameters corresponding to the pixel region; the region parameters include at least one of region location, region size, region number, and region hardware parameters; The prediction model corresponding to the region parameters is determined from multiple candidate models; The historical display data is input into the prediction model to obtain the future display parameters corresponding to the pixel area; the future display parameters include at least one of color ratio parameters, refresh rate parameters, voltage peak parameters, and dynamic change characteristic parameters.

[0007] As an optional implementation, in the first aspect of the present invention, the prediction model is an LSTM neural network model, which is trained through the following steps: Obtain historical display data sequences corresponding to multiple regions similar to the pixel region; The loss function is defined as the difference between the predicted display parameters at the next time point and the corresponding display data at the previous time point; the difference is the reciprocal of the matching degree between the predicted display parameters and the previous display data; the matching degree is obtained by the prediction output of a pre-trained display matching prediction model; the display matching prediction model is trained on a training dataset that includes multiple training display data and corresponding display parameter annotations. All the historical display data sequences are input into a preset base LSTM model for iterative training until the value of the loss function reaches its minimum, so as to obtain the trained prediction model.

[0008] As an optional implementation, in the first aspect of the present invention, determining the future power consumption parameters corresponding to the pixel region based on the future display parameters and the power consumption prediction model includes: For any pixel region, the future display parameters corresponding to the pixel region are input into the trained power prediction model corresponding to the pixel region to obtain the predicted power parameters; the power prediction model is trained using a training dataset that includes multiple training display parameters and corresponding power labels. Calculate the average of the predicted power consumption parameters of at least two pixel regions corresponding to the pixel region to obtain the adjacent power consumption parameters; Calculate the average power consumption parameters of the pixel region at at least two historical time points to obtain the historical power consumption parameters; Based on the adjacent power consumption parameters and the historical power consumption parameters, the predicted power consumption parameters are corrected to obtain the future power consumption parameters corresponding to the pixel region.

[0009] As an optional implementation, in the first aspect of the present invention, the step of correcting the predicted power consumption parameters based on the adjacent power consumption parameters and the historical power consumption parameters to obtain the future power consumption parameters corresponding to the pixel region includes: Calculate the first parameter difference between the adjacent power consumption parameter and the predicted power consumption parameter; Calculate the second parameter difference between the historical power consumption parameter and the predicted power consumption parameter; Calculate the first product value between the first parameter difference and the first correction weight; Calculate the second product between the second parameter difference and the second correction weight; the second correction weight is less than the first correction weight. The product of the predicted power consumption parameter, the first product value, and the second product value is calculated to obtain the future power consumption parameter corresponding to the pixel region.

[0010] As an optional implementation, in the first aspect of the invention, determining the display control command for the display screen at a future time point based on future power consumption parameters corresponding to at least two of the pixel regions includes: From all the pixel regions, select multiple high-power regions where the future power consumption parameter is greater than a preset parameter threshold; Calculate the ratio of the total area of ​​all the high-power regions to the area of ​​the display screen; Determine whether the ratio is greater than a preset ratio threshold, and obtain the determination result; Based on the judgment result and the future power consumption parameters, the display control command for the display screen at a future point in time is determined.

[0011] As an optional implementation, in the first aspect of the present invention, determining the display control command for the display screen at a future point in time based on the judgment result and the future power consumption parameter includes: When the determination result is negative, a local refresh control instruction corresponding to a future time point is determined for the display screen; the local refresh control instruction is used to control the display screen to refresh at least one of the high power consumption areas with refresh parameters related to the corresponding future power consumption parameters; the refresh parameters are determined based on the future power consumption parameters and a preset correspondence between power consumption and refresh parameters; When the determination result is yes, an energy-saving frame insertion instruction corresponding to a future time point is determined for the display screen; the energy-saving frame insertion instruction is used to control the display screen to perform frame interpolation processing on the video data to be displayed based on the frame interpolation parameters; the frame interpolation parameters are determined based on the average power consumption parameter and the preset correspondence between power consumption and frame interpolation parameters; the average power consumption parameter is the average value of the future power consumption parameters corresponding to all the high power consumption regions.

[0012] A second aspect of this invention discloses a display screen refresh control system based on power consumption control, the system comprising: The acquisition module is used to acquire historical display data of at least one pixel area of ​​the display screen; The prediction module is used to predict the future display parameters corresponding to the pixel region based on the historical display data. The determining module is used to determine the future power consumption parameters corresponding to the pixel region based on the future display parameters and the power consumption prediction model. The control module is used to determine the display control command of the display screen at a future time point based on the future power consumption parameters corresponding to at least two of the pixel regions.

[0013] As an optional implementation, in a second aspect of the present invention, the historical display data includes component voltage data, brightness data, color data, dynamic change data of the image, and refresh data of the pixel area at multiple historical time points.

[0014] As an optional implementation, in a second aspect of the invention, the specific method by which the prediction module predicts the future display parameters corresponding to the pixel region based on the historical display data includes: Determine the region parameters corresponding to the pixel region; the region parameters include at least one of region location, region size, region number, and region hardware parameters; The prediction model corresponding to the region parameters is determined from multiple candidate models; The historical display data is input into the prediction model to obtain the future display parameters corresponding to the pixel area; the future display parameters include at least one of color ratio parameters, refresh rate parameters, voltage peak parameters, and dynamic change characteristic parameters.

[0015] As an optional implementation, in the second aspect of the invention, the prediction model is an LSTM neural network model, which is trained through the following steps: Obtain historical display data sequences corresponding to multiple regions similar to the pixel region; The loss function is defined as the difference between the predicted display parameters at the next time point and the corresponding display data at the previous time point; the difference is the reciprocal of the matching degree between the predicted display parameters and the previous display data; the matching degree is obtained by the prediction output of a pre-trained display matching prediction model; the display matching prediction model is trained on a training dataset that includes multiple training display data and corresponding display parameter annotations. All the historical display data sequences are input into a preset base LSTM model for iterative training until the value of the loss function reaches its minimum, so as to obtain the trained prediction model.

[0016] As an optional implementation, in a second aspect of the invention, the specific method by which the determining module determines the future power consumption parameters corresponding to the pixel region based on the future display parameters and the power consumption prediction model includes: For any pixel region, the future display parameters corresponding to the pixel region are input into the trained power prediction model corresponding to the pixel region to obtain the predicted power parameters; the power prediction model is trained using a training dataset that includes multiple training display parameters and corresponding power labels. Calculate the average of the predicted power consumption parameters of at least two pixel regions corresponding to the pixel region to obtain the adjacent power consumption parameters; Calculate the average power consumption parameters of the pixel region at at least two historical time points to obtain the historical power consumption parameters; Based on the adjacent power consumption parameters and the historical power consumption parameters, the predicted power consumption parameters are corrected to obtain the future power consumption parameters corresponding to the pixel region.

[0017] As an optional implementation, in a second aspect of the invention, the specific method by which the determining module corrects the predicted power consumption parameters based on the adjacent power consumption parameters and the historical power consumption parameters to obtain the future power consumption parameters corresponding to the pixel region includes: Calculate the first parameter difference between the adjacent power consumption parameter and the predicted power consumption parameter; Calculate the second parameter difference between the historical power consumption parameter and the predicted power consumption parameter; Calculate the first product value between the first parameter difference and the first correction weight; Calculate the second product between the second parameter difference and the second correction weight; the second correction weight is less than the first correction weight. The product of the predicted power consumption parameter, the first product value, and the second product value is calculated to obtain the future power consumption parameter corresponding to the pixel region.

[0018] As an optional implementation, in a second aspect of the invention, the control module determines the specific method of the display control command for the display screen at a future time point based on future power consumption parameters corresponding to at least two of the pixel regions, including: From all the pixel regions, select multiple high-power regions where the future power consumption parameter is greater than a preset parameter threshold; Calculate the ratio of the total area of ​​all the high-power regions to the area of ​​the display screen; Determine whether the ratio is greater than a preset ratio threshold, and obtain the determination result; Based on the judgment result and the future power consumption parameters, the display control command for the display screen at a future point in time is determined.

[0019] As an optional implementation, in a second aspect of the invention, the control module determines the specific manner of the display control command for the display screen at a future point in time based on the judgment result and the future power consumption parameters, including: When the determination result is negative, a local refresh control instruction corresponding to a future time point is determined for the display screen; the local refresh control instruction is used to control the display screen to refresh at least one of the high power consumption areas with refresh parameters related to the corresponding future power consumption parameters; the refresh parameters are determined based on the future power consumption parameters and a preset correspondence between power consumption and refresh parameters; When the determination result is yes, an energy-saving frame insertion instruction corresponding to a future time point is determined for the display screen; the energy-saving frame insertion instruction is used to control the display screen to perform frame interpolation processing on the video data to be displayed based on the frame interpolation parameters; the frame interpolation parameters are determined based on the average power consumption parameter and the preset correspondence between power consumption and frame interpolation parameters; the average power consumption parameter is the average value of the future power consumption parameters corresponding to all the high power consumption regions.

[0020] A third aspect of this invention discloses another display refresh control system based on power consumption control, the system comprising: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute some or all of the steps in the power consumption control-based display refresh control method disclosed in the first aspect of the present invention.

[0021] The fourth aspect of the present invention discloses a computer storage medium storing computer instructions, which, when invoked, are used to execute some or all of the steps in the power consumption control-based display refresh control method disclosed in the first aspect of the present invention.

[0022] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: This invention acquires historical display data of pixel areas of a display screen and predicts future display parameters. It then uses a power consumption prediction model to calculate future power consumption parameters and determines display control commands based on power consumption analysis of adjacent areas. This enables precise dynamic energy-saving control of the display screen based on pixel-level power consumption prediction, improving the energy efficiency and lifespan of the display screen and reducing the risk of overheating or energy waste caused by unoptimized high-power areas. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a flowchart illustrating a display refresh control method based on power consumption control disclosed in an embodiment of the present invention.

[0025] Figure 2 This is a schematic diagram of a display refresh control system based on power consumption control disclosed in an embodiment of the present invention.

[0026] Figure 3 This is a schematic diagram of another display refresh control system based on power consumption control disclosed in an embodiment of the present invention. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0028] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0029] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0030] This invention discloses a display screen refresh control method and system based on power consumption control. By acquiring historical display data of pixel areas of the display screen and predicting future display parameters, the method calculates future power consumption parameters using a power consumption prediction model, and determines display control commands based on power consumption analysis of adjacent areas. This enables precise dynamic energy-saving control of the display screen based on pixel-level power consumption prediction, improving display screen energy efficiency and lifespan, and reducing the risk of overheating or energy waste caused by unoptimized high-power areas. Detailed explanations follow.

[0031] Example 1 Please see Figure 1 , Figure 1 This is a flowchart illustrating a display screen refresh control method based on power consumption control, as disclosed in an embodiment of the present invention. Wherein, Figure 1 The described power consumption-based display refresh control method can be applied to data processing systems / data processing devices / data processing servers (wherein, the server includes a local processing server or a cloud processing server). For example... Figure 1 As shown, the power consumption-based display refresh control method may include the following operations: 101. Obtain historical display data for at least one pixel area of ​​the display screen.

[0032] Optionally, the historical display data includes component voltage data, brightness data, color data, dynamic image change data, and refresh data for the pixel area at multiple historical time points.

[0033] Optionally, the historical display data may include pixel brightness values, color distribution, refresh rate, or voltage fluctuation records, which are not limited in this invention.

[0034] 102. Based on historical display data, predict the future display parameters corresponding to the pixel area.

[0035] 103. Based on future display parameters and power consumption prediction models, determine the future power consumption parameters corresponding to the pixel area.

[0036] Optionally, the future power consumption parameter can be the expected power consumption value or the peak power consumption, and the present invention does not limit it.

[0037] 104. Determine the display control command for the display screen at a future time point based on the future power consumption parameters corresponding to at least two pixel areas.

[0038] Optionally, the display control command can be a partial refresh or an energy-saving frame interpolation command, which is not limited in this invention.

[0039] As can be seen, the above-described embodiments of the invention acquire historical display data of the pixel area of ​​the display screen and predict future display parameters, calculate future power consumption parameters using a power consumption prediction model, and determine display control commands based on power consumption analysis of adjacent areas. This enables precise dynamic energy-saving control of the display screen based on pixel-level power consumption prediction, improves the energy efficiency and lifespan of the display screen, and reduces the risk of overheating or energy waste caused by unoptimized high-power areas.

[0040] As an optional embodiment, the step of predicting the future display parameters corresponding to the pixel region based on historical display data in the above steps includes: Determine the region parameters corresponding to the pixel region; The prediction model corresponding to the regional parameters is determined from multiple candidate models; Historical display data is input into the prediction model to obtain the future display parameters corresponding to the pixel area.

[0041] Optionally, the region parameters include at least one of the following: region location, region size, region number, and region hardware parameters.

[0042] Optionally, the location of this area can be a location in the screen coordinate system, which is not limited in this invention.

[0043] Optionally, future display parameters may include at least one of the following: color percentage parameter, refresh rate parameter, peak voltage parameter, and dynamic change characteristic parameter.

[0044] Optionally, the prediction model can be a long short-term memory network model, but this invention does not limit it.

[0045] As can be seen, through the above optional embodiments, by matching the corresponding prediction model according to the pixel region parameters and inputting historical display data to output future display parameters, accurate display parameter prediction based on region adaptation is achieved, improving the pertinence and accuracy of future parameter calculation and reducing the risk of prediction deviation caused by the universality of the model.

[0046] As an optional embodiment, the prediction model in the above steps is an LSTM neural network model, which is trained through the following steps: Obtain historical display data sequences corresponding to multiple regions similar to pixel regions; The loss function is defined to include the difference between the predicted display parameters for the next time point and the corresponding display data for the previous time point. All historical data sequences are input into a pre-defined base LSTM model for iterative training until the loss function reaches its minimum value, thus obtaining a well-trained prediction model.

[0047] Optionally, the difference is the reciprocal of the degree of matching between the predicted display parameters and the previous display data.

[0048] Optionally, the matching degree can be obtained by predicting the output of a pre-trained explicit matching prediction model.

[0049] Optionally, the display matching prediction model can be a classifier model or a neural network model with a CNN architecture.

[0050] Optionally, the display matching prediction model is trained using a training dataset that includes multiple training display data and corresponding display parameter annotations.

[0051] Optionally, the basic LSTM model can be a three-layer long short-term memory network with 256 hidden units in each layer, with an attention mechanism added, using the mean squared error loss function, and trained for 120 training epochs on 150,000 historical display data sequences, with the loss value converging to 0.002. This invention does not limit the scope of the model.

[0052] As can be seen, through the above optional embodiments, by training the LSTM model with the reciprocal of the matching degree between the predicted display parameters and the previous display data as the loss function, an accurate time series prediction model based on matching degree optimization is constructed, which improves the accuracy and robustness of future display parameter prediction and reduces the risk of prediction distortion caused by the simplicity of the loss function.

[0053] As an optional embodiment, the step above, determining the future power consumption parameters corresponding to the pixel region based on future display parameters and a power consumption prediction model, includes: For any pixel region, the future display parameters corresponding to that pixel region are input into the trained power prediction model corresponding to that pixel region to obtain the predicted power parameters. Calculate the average of the predicted power consumption parameters of at least two pixel regions corresponding to the pixel region to obtain the adjacent power consumption parameters; Calculate the average power consumption parameters of the pixel region at at least two historical time points to obtain the historical power consumption parameters; Based on adjacent power consumption parameters and historical power consumption parameters, the predicted power consumption parameters are corrected to obtain the future power consumption parameters corresponding to the pixel region.

[0054] Optionally, the power consumption prediction model is trained using a training dataset that includes multiple training display parameters and corresponding power consumption labels.

[0055] Optionally, the power consumption prediction model can be a four-layer fully connected neural network with 512 neurons in the first layer, 256 neurons in the second layer, 128 neurons in the third layer, and a power consumption value output by the fourth layer. The model uses the mean squared error loss function and is trained for 100 training epochs on 180,000 training data points. The prediction error is less than 5%. This invention does not impose any limitations on this model.

[0056] As can be seen, through the above optional embodiments, by inputting future display parameters into the corresponding power consumption prediction model to obtain predicted power consumption parameters, and combining them with adjacent and historical power consumption parameters to obtain future power consumption parameters, accurate power consumption quantification assessment based on multi-source correction is achieved, improving the reliability and stability of power consumption parameters and reducing the risk of power consumption deviation caused by single-model prediction.

[0057] As an optional embodiment, the step described above, correcting the predicted power consumption parameters based on adjacent power consumption parameters and historical power consumption parameters to obtain the future power consumption parameters corresponding to the pixel region, includes: Calculate the first parameter difference between adjacent power consumption parameters and the predicted power consumption parameter; Calculate the difference between the second parameter of the historical power consumption parameters and the predicted power consumption parameters; Calculate the first product between the first parameter difference and the first correction weight; Calculate the second product between the second parameter difference and the second correction weight; optionally, the second correction weight is less than the first correction weight. The future power consumption parameters corresponding to the pixel region are obtained by calculating the product of the predicted power consumption parameters, the first product value, and the second product value.

[0058] As can be seen, through the above optional embodiments, by calculating the difference between the predicted power consumption and the adjacent / historical power consumption and correcting the predicted power consumption with different weights, the future power consumption parameters are obtained, thereby achieving accurate power consumption correction based on difference weighting, improving the balance and accuracy of power consumption parameter calculation, and reducing the risk of power consumption assessment distortion caused by improper weight allocation.

[0059] As an optional embodiment, the step described above, determining the display control command for the display screen at a future time point based on future power consumption parameters corresponding to at least two pixel regions, includes: Select multiple high-power regions from all pixel regions whose future power consumption parameters are greater than a preset parameter threshold; Calculate the ratio of the total area of ​​all high-power regions to the total area of ​​the display screen; Determine whether the ratio is greater than a preset ratio threshold, and obtain the determination result; Based on the judgment results and future power consumption parameters, determine the display control command for the display screen at a future point in time.

[0060] As can be seen, through the above optional embodiments, the area ratio of high-power areas is calculated to determine whether the threshold is exceeded, and the display control command of the display screen at a future time point is determined based on the judgment result. This realizes an energy-saving strategy based on area ratio and power consumption, improves the flexibility and effectiveness of dynamic power consumption management of the display screen, and reduces the risk of insufficient energy saving or decreased display quality due to a single control strategy.

[0061] As an optional embodiment, the step above, determining the display control command for the display screen at a future point in time based on the judgment result and future power consumption parameters, includes: If the result is negative, determine the partial refresh control command for the display screen at a future point in time; If the judgment result is yes, determine the energy-saving frame insertion instruction corresponding to the future time point of the display screen.

[0062] Optionally, the partial refresh control command is used to control the display to refresh at least one high-power area with refresh parameters related to the corresponding future power consumption parameters.

[0063] Optionally, the refresh parameters are determined based on future power consumption parameters and the preset correspondence between power consumption and refresh parameters.

[0064] Optionally, the energy-saving frame insertion command is used to control the display screen to perform frame interpolation processing on the video data to be displayed based on the interpolation parameters.

[0065] Optionally, the frame interpolation parameters are determined based on the average power consumption parameters and the preset correspondence between power consumption and frame interpolation parameters.

[0066] Optionally, the average power consumption parameter is the average of the future power consumption parameters corresponding to all high power consumption regions.

[0067] Optionally, the correspondence between the power consumption and refresh parameters or frame interpolation parameters mentioned above can be predetermined or modeled by the operator based on experimental data or experience. This correspondence can be a mathematical fitting model or a parameter mapping table. Specifically, this correspondence can be used to limit the refresh rate to a lower level for areas with higher power consumption, or to limit the number of black frames inserted, the proportion of low-power frames inserted, or the frequency of insertion to a higher average power consumption.

[0068] As can be seen, through the above optional embodiments, it is determined whether it is necessary to perform frame interpolation processing of the entire video based on the judgment result, and local refresh or energy-saving frame insertion control instructions are generated based on the predicted power consumption of different pixel areas. This realizes a hierarchical energy-saving strategy based on the area ratio and power consumption, improves the flexibility and effect of dynamic power consumption management of the display screen, and reduces the risk of insufficient energy saving or decreased display quality due to a single control strategy.

[0069] Example 2 Please see Figure 2 , Figure 2 This is a schematic diagram of a display screen refresh control system based on power consumption control, as disclosed in an embodiment of the present invention. Figure 2The described power-consumption-based display refresh control system can be applied to data processing systems / data processing equipment / data processing servers (including local processing servers or cloud processing servers). For example... Figure 2 As shown, the power consumption-based display refresh control system may include: The acquisition module 201 is used to acquire historical display data of at least one pixel area of ​​the display screen.

[0070] The prediction module 202 is used to predict the future display parameters corresponding to the pixel area based on historical display data.

[0071] The determination module 203 is used to determine the future power consumption parameters corresponding to the pixel area based on the future display parameters and the power consumption prediction model.

[0072] The control module 204 is used to determine the display control command of the display screen at a future time point based on the future power consumption parameters corresponding to at least two pixel areas.

[0073] As can be seen, the above-described embodiments of the invention acquire historical display data of the pixel area of ​​the display screen and predict future display parameters, calculate future power consumption parameters using a power consumption prediction model, and determine display control commands based on power consumption analysis of adjacent areas. This enables precise dynamic energy-saving control of the display screen based on pixel-level power consumption prediction, improves the energy efficiency and lifespan of the display screen, and reduces the risk of overheating or energy waste caused by unoptimized high-power areas.

[0074] As an optional embodiment, the historical display data includes component voltage data, brightness data, color data, dynamic image change data, and refresh data of the pixel area at multiple historical time points.

[0075] As can be seen, the above optional embodiments limit the content of historical display data, enabling this solution to achieve power consumption control based on more comprehensive and accurate historical display data, assisting in the realization of accurate dynamic energy-saving control of the display screen based on pixel-level power consumption prediction, and improving the energy efficiency and lifespan of the display screen.

[0076] As an optional embodiment, the specific method by which the prediction module predicts the future display parameters corresponding to a pixel region based on historical display data includes: Determine the region parameters corresponding to the pixel region; optionally, the region parameters include at least one of the following: region location, region size, region number, and region hardware parameters. The prediction model corresponding to the regional parameters is determined from multiple candidate models; Historical display data is input into the prediction model to obtain the future display parameters corresponding to the pixel area; the future display parameters include at least one of the following: color ratio parameter, refresh rate parameter, voltage peak parameter, and dynamic change characteristic parameter.

[0077] As can be seen, through the above optional embodiments, by matching the corresponding prediction model according to the pixel region parameters and inputting historical display data to output future display parameters, accurate display parameter prediction based on region adaptation is achieved, improving the pertinence and accuracy of future parameter calculation and reducing the risk of prediction deviation caused by the universality of the model.

[0078] As an optional embodiment, the prediction model is an LSTM neural network model, which is trained through the following steps: Obtain historical display data sequences corresponding to multiple regions similar to pixel regions; The loss function is defined as the difference between the predicted display parameters at the next time point and the corresponding display data at the previous time point; optionally, the difference is the reciprocal of the matching degree between the predicted display parameters and the previous display data; the matching degree is obtained by the prediction output of a pre-trained display matching prediction model; the display matching prediction model is trained on a training dataset that includes multiple training display data and corresponding display parameter annotations. All historical data sequences are input into a pre-defined base LSTM model for iterative training until the loss function reaches its minimum value, thus obtaining a well-trained prediction model.

[0079] As can be seen, through the above optional embodiments, by training the LSTM model with the reciprocal of the matching degree between the predicted display parameters and the previous display data as the loss function, an accurate time series prediction model based on matching degree optimization is constructed, which improves the accuracy and robustness of future display parameter prediction and reduces the risk of prediction distortion caused by the simplicity of the loss function.

[0080] As an optional embodiment, the determining module determines the specific method by which it determines the future power consumption parameters corresponding to a pixel region based on future display parameters and a power consumption prediction model, including: For any pixel region, the future display parameters corresponding to the pixel region are input into the trained power prediction model corresponding to the pixel region to obtain the predicted power parameters; optionally, the power prediction model is trained using a training dataset that includes multiple training display parameters and corresponding power labels. Calculate the average of the predicted power consumption parameters of at least two pixel regions corresponding to the pixel region to obtain the adjacent power consumption parameters; Calculate the average power consumption parameters of the pixel region at at least two historical time points to obtain the historical power consumption parameters; Based on adjacent power consumption parameters and historical power consumption parameters, the predicted power consumption parameters are corrected to obtain the future power consumption parameters corresponding to the pixel region.

[0081] As can be seen, through the above optional embodiments, by inputting future display parameters into the corresponding power consumption prediction model to obtain predicted power consumption parameters, and combining them with adjacent and historical power consumption parameters to obtain future power consumption parameters, accurate power consumption quantification assessment based on multi-source correction is achieved, improving the reliability and stability of power consumption parameters and reducing the risk of power consumption deviation caused by single-model prediction.

[0082] As an optional embodiment, the specific method by which the determining module corrects the predicted power consumption parameters based on adjacent power consumption parameters and historical power consumption parameters to obtain the future power consumption parameters corresponding to the pixel region includes: Calculate the first parameter difference between adjacent power consumption parameters and the predicted power consumption parameter; Calculate the difference between the second parameter of the historical power consumption parameters and the predicted power consumption parameters; Calculate the first product between the first parameter difference and the first correction weight; Calculate the second product between the second parameter difference and the second correction weight; optionally, the second correction weight is less than the first correction weight. The future power consumption parameters corresponding to the pixel region are obtained by calculating the product of the predicted power consumption parameters, the first product value, and the second product value.

[0083] As can be seen, through the above optional embodiments, by calculating the difference between the predicted power consumption and the adjacent / historical power consumption and correcting the predicted power consumption with different weights, the future power consumption parameters are obtained, thereby achieving accurate power consumption correction based on difference weighting, improving the balance and accuracy of power consumption parameter calculation, and reducing the risk of power consumption assessment distortion caused by improper weight allocation.

[0084] As an optional embodiment, the control module determines the specific method of the display control command for the display screen at a future time point based on the future power consumption parameters corresponding to at least two pixel regions, including: Select multiple high-power regions from all pixel regions whose future power consumption parameters are greater than a preset parameter threshold; Calculate the ratio of the total area of ​​all high-power regions to the total area of ​​the display screen; Determine whether the ratio is greater than a preset ratio threshold, and obtain the determination result; Based on the judgment results and future power consumption parameters, determine the display control command for the display screen at a future point in time.

[0085] As can be seen, through the above optional embodiments, the area ratio of high-power areas is calculated to determine whether the threshold is exceeded, and the display control command of the display screen at a future time point is determined based on the judgment result. This realizes an energy-saving strategy based on area ratio and power consumption, improves the flexibility and effectiveness of dynamic power consumption management of the display screen, and reduces the risk of insufficient energy saving or decreased display quality due to a single control strategy.

[0086] As an optional embodiment, the control module determines the specific method of the display control command for the display screen at a future point in time based on the judgment result and future power consumption parameters, including: If the result is negative, determine the local refresh control instruction corresponding to the future time point of the display screen; optionally, the local refresh control instruction is used to control the display screen to refresh at least one high power consumption area with refresh parameters related to the corresponding future power consumption parameters; the refresh parameters are determined based on the future power consumption parameters and the preset correspondence between power consumption and refresh parameters. If the judgment result is yes, determine the energy-saving frame insertion instruction corresponding to the future time point of the display screen; optionally, the energy-saving frame insertion instruction is used to control the display screen to perform frame interpolation processing on the video data to be displayed based on the frame interpolation parameters; the frame interpolation parameters are determined according to the average power consumption parameter and the preset correspondence between power consumption and frame interpolation parameters; the average power consumption parameter is the average value of the future power consumption parameters corresponding to all high power consumption areas.

[0087] As can be seen, through the above optional embodiments, it is determined whether it is necessary to perform frame interpolation processing of the entire video based on the judgment result, and local refresh or energy-saving frame insertion control instructions are generated based on the predicted power consumption of different pixel areas. This realizes a hierarchical energy-saving strategy based on the area ratio and power consumption, improves the flexibility and effect of dynamic power consumption management of the display screen, and reduces the risk of insufficient energy saving or decreased display quality due to a single control strategy.

[0088] Example 3 Please see Figure 3 , Figure 3 This is another display refresh control system based on power consumption control disclosed in the embodiments of the present invention. Figure 3 The described power-consumption-based display refresh control system is applied in data processing systems / data processing equipment / data processing servers (wherein, the server includes a local processing server or a cloud processing server). For example... Figure 3 As shown, the power consumption-based display refresh control system may include: Memory 301 storing executable program code; Processor 302 coupled to memory 301; The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the power consumption control-based display refresh control method described in Embodiment 1.

[0089] Example 4 This invention discloses a computer read storage medium that stores a computer program for electronic data interchange, wherein the computer program causes a computer to execute the steps of the power consumption control-based display refresh control method described in Embodiment 1.

[0090] Example 5 This invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform the steps of the power consumption control-based display refresh control method described in Embodiment 1.

[0091] The foregoing has described specific embodiments of this specification; other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims may be performed in a different order than those shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily have to follow the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0092] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0093] For ease of description, the above devices are described in terms of function, divided into various units. Of course, in implementing this specification, the functions of each unit can be implemented in one or more software and / or hardware components.

[0094] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0095] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0096] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0097] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0098] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0099] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0100] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, 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-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0101] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0102] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0103] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0104] Finally, it should be noted that the display refresh control method and system based on power consumption control disclosed in the embodiments of the present invention are merely preferred embodiments of the present invention, and are only used to illustrate the technical solutions of the present invention, and not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A display screen refresh control method based on power consumption control, characterized in that, The method includes: Acquire historical display data for at least one pixel area of ​​the display screen; Based on the historical display data, predict the future display parameters corresponding to the pixel region; Based on the future display parameters and power consumption prediction model, determine the future power consumption parameters corresponding to the pixel region; The display control command for the display screen at a future time point is determined based on the future power consumption parameters corresponding to at least two of the pixel regions.

2. The display screen refresh control method based on power consumption control according to claim 1, characterized in that, The historical display data includes component voltage data, brightness data, color data, dynamic image change data, and refresh data of the pixel area at multiple historical time points.

3. The display refresh control method based on power consumption control according to claim 1, characterized in that, The step of predicting the future display parameters corresponding to the pixel region based on the historical display data includes: Determine the region parameters corresponding to the pixel region; the region parameters include at least one of region location, region size, region number, and region hardware parameters; The prediction model corresponding to the region parameters is determined from multiple candidate models; The historical display data is input into the prediction model to obtain the future display parameters corresponding to the pixel area; the future display parameters include at least one of color ratio parameters, refresh rate parameters, voltage peak parameters, and dynamic change characteristic parameters.

4. The display refresh control method based on power consumption control according to claim 3, characterized in that, The prediction model is an LSTM neural network model, which is trained through the following steps: Obtain historical display data sequences corresponding to multiple regions similar to the pixel region; The loss function is defined as the difference between the predicted display parameters at the next time point and the corresponding display data at the previous time point; the difference is the reciprocal of the matching degree between the predicted display parameters and the previous display data; the matching degree is obtained by the prediction output of a pre-trained display matching prediction model; the display matching prediction model is trained on a training dataset that includes multiple training display data and corresponding display parameter annotations. All the historical display data sequences are input into a preset base LSTM model for iterative training until the value of the loss function reaches its minimum, so as to obtain the trained prediction model.

5. The display refresh control method based on power consumption control according to claim 1, characterized in that, The step of determining the future power consumption parameters corresponding to the pixel region based on the future display parameters and power consumption prediction model includes: For any pixel region, the future display parameters corresponding to the pixel region are input into the trained power prediction model corresponding to the pixel region to obtain the predicted power parameters; the power prediction model is trained using a training dataset that includes multiple training display parameters and corresponding power labels. Calculate the average of the predicted power consumption parameters of at least two pixel regions corresponding to the pixel region to obtain the adjacent power consumption parameters; Calculate the average power consumption parameters of the pixel region at at least two historical time points to obtain the historical power consumption parameters; Based on the adjacent power consumption parameters and the historical power consumption parameters, the predicted power consumption parameters are corrected to obtain the future power consumption parameters corresponding to the pixel region.

6. The display refresh control method based on power consumption control according to claim 5, characterized in that, The step of correcting the predicted power consumption parameters based on the adjacent power consumption parameters and the historical power consumption parameters to obtain the future power consumption parameters corresponding to the pixel region includes: Calculate the first parameter difference between the adjacent power consumption parameter and the predicted power consumption parameter; Calculate the second parameter difference between the historical power consumption parameter and the predicted power consumption parameter; Calculate the first product value between the first parameter difference and the first correction weight; Calculate the second product between the second parameter difference and the second correction weight; the second correction weight is less than the first correction weight. The product of the predicted power consumption parameter, the first product value, and the second product value is calculated to obtain the future power consumption parameter corresponding to the pixel region.

7. The display refresh control method based on power consumption control according to claim 1, characterized in that, The step of determining the display control command for the display screen at a future time point based on future power consumption parameters corresponding to at least two of the pixel regions includes: From all the pixel regions, select multiple high-power regions where the future power consumption parameter is greater than a preset parameter threshold; Calculate the ratio of the total area of ​​all the high-power regions to the area of ​​the display screen; Determine whether the ratio is greater than a preset ratio threshold, and obtain the determination result; Based on the judgment result and the future power consumption parameters, the display control command for the display screen at a future point in time is determined.

8. The display refresh control method based on power consumption control according to claim 7, characterized in that, The step of determining the display control command for the display screen at a future point in time based on the judgment result and the future power consumption parameters includes: When the determination result is negative, a local refresh control instruction corresponding to a future time point is determined for the display screen; the local refresh control instruction is used to control the display screen to refresh at least one of the high power consumption areas with refresh parameters related to the corresponding future power consumption parameters; the refresh parameters are determined based on the future power consumption parameters and a preset correspondence between power consumption and refresh parameters; When the determination result is yes, an energy-saving frame insertion instruction corresponding to a future time point is determined for the display screen; the energy-saving frame insertion instruction is used to control the display screen to perform frame interpolation processing on the video data to be displayed based on the frame interpolation parameters; the frame interpolation parameters are determined based on the average power consumption parameter and the preset correspondence between power consumption and frame interpolation parameters; the average power consumption parameter is the average value of the future power consumption parameters corresponding to all the high power consumption regions.

9. A display screen refresh control system based on power consumption control, characterized in that, The system includes: The acquisition module is used to acquire historical display data of at least one pixel area of ​​the display screen; The prediction module is used to predict the future display parameters corresponding to the pixel region based on the historical display data. The determining module is used to determine the future power consumption parameters corresponding to the pixel region based on the future display parameters and the power consumption prediction model. The control module is used to determine the display control command of the display screen at a future time point based on the future power consumption parameters corresponding to at least two of the pixel regions.

10. A display screen refresh control system based on power consumption control, characterized in that, The system includes: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the display refresh control method based on power consumption control as described in any one of claims 1-8.

Images