Liquid crystal display drive control method and system

Abstract

The present invention proposes a liquid crystal display drive control method and system, the method comprising: obtaining a page loaded in the memory of a liquid crystal computer, calculating the maximum image motion degree of the page loaded in the memory of the liquid crystal computer by the difference between consecutive frames, and then adjusting the refresh rate of the liquid crystal display screen; obtaining the user's gaze point position and gaze time by eye tracking technology, and adjusting the brightness of the liquid crystal display screen according to the user's gaze point position and gaze time; combining the user's usage habits and the historical data of the display, using a machine learning algorithm to predict future display content and user behavior, and adjusting the brightness and refresh rate of the display based on the prediction results; recording the energy consumption data of the display in real time, comparing and analyzing the actual energy consumption with the expected energy consumption, and timely discovering abnormalities and making feedback adjustments. Through this method and the corresponding system, the energy consumption of the liquid crystal screen can be saved without affecting the user experience.

Description

Technical Field

[0001] The invention provides a liquid crystal display drive control method and system, belonging to the technical field of liquid crystal display drive. Background Art

[0002] Liquid Crystal Display (LCD) technology is a passive display technology that uses the physical properties of liquid crystals to control the arrangement of liquid crystal molecules through voltage or current, so that it has different optical properties and realizes image display. With the rapid development of electronic technology, liquid crystal display technology has been widely used in smart phones, tablet computers, televisions, computer monitors, automotive display systems and other fields due to its advantages such as low power consumption, high resolution, light weight and portability.

[0003] However, the refresh rate of existing LCD displays is always set to a fixed value and cannot be changed according to the user's display content. Alternatively, a whole LCD screen uses a uniform brightness, but the human eye is more sensitive to visually significant areas, so the brightness of non-significant areas can be reduced without significantly affecting the perceived quality, thereby saving energy. Alternatively, for office workers, their computers always have a fixed usage pattern, but the existing LCD drive control method cannot predict the user's usage behavior of the LCD computer to adjust the refresh rate and brightness. Summary of the invention

[0004] The present invention provides a liquid crystal display drive control method and system to solve the above-mentioned problems:

[0005] The present invention provides a liquid crystal display drive control method, the method comprising:

[0006] Obtaining a page loaded in the memory of the LCD computer, calculating a maximum image motion degree of the page loaded in the memory of the LCD computer by differences between consecutive frames, and adjusting a refresh rate of the LCD display based on the maximum image motion degree;

[0007] The user's gaze point position and gaze time are obtained through eye tracking technology, and the brightness of the LCD screen is adjusted according to the user's gaze point position and gaze time;

[0008] Combine the user's usage habits and the display's historical data, use machine learning algorithms to predict the LCD display's display content and user behavior, and adjust the display's brightness and refresh rate based on the prediction results;

[0009] Through the built-in energy consumption monitoring module, the energy consumption data of the display is recorded in real time, the actual energy consumption is compared and analyzed with the expected energy consumption, and energy consumption anomalies are discovered in time and feedback adjustments are made.

[0010] Further, obtaining a page loaded in the memory of the LCD computer, calculating the maximum image motion degree of the page loaded in the memory of the LCD computer by the difference between consecutive frames, and adjusting the refresh rate of the LCD display screen based on the maximum image motion degree, including:

[0011] Get the page loaded in the memory of the LCD computer, and get whether there is a dynamic page in the page display format. If there is a dynamic page, the page refresh rate is adjusted to the preset maximum refresh rate;

[0012] If the pages loaded into the memory of the LCD computer are static as a whole but dynamic in parts, the LCD screen is divided into multiple areas, and the refresh rate is controlled according to the page content and motion of each area. The sum of the absolute values ​​of the pixel value differences between two adjacent frames is calculated for each area through a frame difference model. Specifically, the frame difference model is:

[0013] ;

[0014] in, represents the difference between frames, Indicates at time At the moment, at coordinate The pixel value at Indicates at time At the moment, at coordinate The pixel value at

[0015] The refresh rate is set for each region according to the degree of inter-frame motion. Specifically, it is set through a refresh rate update model. The refresh rate update model is:

[0016] ;

[0017] in, Indicates the updated refresh rate, Indicates the preset minimum refresh rate. Indicates the preset maximum refresh rate. is the preset motion threshold, represents the sensitivity coefficient;

[0018] If the pages loaded into the memory of the LCD computer are all static pages, the maximum image motion degree of the pages loaded into the memory of the LCD computer is calculated by the difference between consecutive frames of the static pages. The maximum image motion degree is calculated by the frame difference model. The refresh rate of the LCD display is adjusted based on the maximum image motion degree. The refresh rate is calculated by the refresh rate update model.

[0019] Furthermore, the user's gaze point position and gaze time are obtained by using eye tracking technology, and the brightness of the liquid crystal display is adjusted according to the user's gaze point position and gaze time, including:

[0020] Setting a time threshold to define a gaze point, and capturing the user's eye movement data in real time through an eye tracker, wherein the eye movement data includes a gaze position and a gaze time;

[0021] Remove the noise data caused by device jitter and user rapid eye movement, merge close gaze points, and identify the user's long-term gaze behavior at the same location;

[0022] Get the attention weight of each fixation point, and use the predefined weighted model based on visual attention to calculate the target brightness value of each screen point. Specifically, the weighted model based on visual attention is:

[0023] ;

[0024] in, Indicates location The brightness value, Indicates the basic brightness of the screen. represents the number of fixations, Indicates The attention weight of each fixation point, Indicates The coordinates of the gaze point, represents the standard deviation of the Gaussian function corresponding to the first range enhancement, represents the standard deviation of the Gaussian function corresponding to the smooth transition of the second range, .

[0025] Furthermore, the display content and user behavior of the LCD screen are predicted using a machine learning algorithm in combination with the user's usage habits and the historical data of the display, and the brightness and refresh rate of the display are adjusted based on the prediction results, including:

[0026] Collecting the user's historical operation records, including mouse movement, clicks, keyboard input frequency and application usage time, and recording the timestamp of the user's historical operation records to establish time series data;

[0027] Capturing the current usage content of the display, including: open applications, window layout, and color brightness distribution, and obtaining hardware status data related to the display, including: current brightness setting, refresh rate, power consumption, and temperature change;

[0028] Processing missing data and abnormal values ​​in the user's historical operation records, and extracting useful features from the processed historical operation record data of the user, wherein the useful features include session duration, usage frequency of a specific application, and brightness change pattern;

[0029] Convert the extracted useful feature data into a format suitable for machine learning algorithms, including time series formatting;

[0030] Train the LSTM model with useful feature data formatted with time series, adjust model parameters to optimize performance, evaluate model performance through cross-validation, and adjust and improve the model;

[0031] Useful features are extracted from the current usage content of the display, and the useful features are input into the trained LSTM model to make real-time predictions on user behavior and display content, and the refresh rate and brightness of the screen are adjusted based on the predicted user behavior and display content.

[0032] Furthermore, the built-in energy consumption monitoring module records the energy consumption data of the display in real time, compares and analyzes the actual energy consumption with the expected energy consumption, and promptly detects energy consumption anomalies and makes feedback adjustments, including:

[0033] Acquire the refresh rate and brightness data of the screen adjusted based on the prediction, and calculate the energy consumption of the display based on the refresh rate and brightness data;

[0034] Monitor the energy consumption of the display in real time, compare and analyze the actual energy consumption with the expected energy consumption. If the actual energy consumption exceeds the preset threshold, collect user behavior again and retrain the LSTM model.

[0035] The present invention provides a liquid crystal display drive control system, the system comprising:

[0036] A refresh rate adjustment module is used to obtain a page loaded in the memory of the LCD computer, calculate the maximum image motion degree of the page loaded in the memory of the LCD computer through the difference between consecutive frames, and adjust the refresh rate of the LCD display screen based on the maximum image motion degree;

[0037] A brightness adjustment module is used to obtain the user's gaze point position and gaze time through eye tracking technology, and adjust the brightness of the LCD screen according to the user's gaze point position and gaze time;

[0038] The module for predicting and adjusting the brightness and refresh rate of the display is used to combine the user's usage habits and the historical data of the display, use machine learning algorithms to predict the display content and user behavior of the LCD screen, and adjust the brightness and refresh rate of the display based on the prediction results;

[0039] The feedback adjustment module is used to record the energy consumption data of the display in real time through the built-in energy consumption monitoring module, compare and analyze the actual energy consumption with the expected energy consumption, promptly discover energy consumption anomalies and make feedback adjustments.

[0040] Furthermore, the refresh rate adjustment module includes:

[0041] The dynamic page adjustment module is used to obtain the page loaded in the memory of the LCD computer and obtain whether there is a dynamic page in the page display format. If there is a dynamic page, the page refresh rate is adjusted to the preset maximum refresh rate;

[0042] The overall static and local dynamic page adjustment module, if the pages loaded into the memory of the LCD computer are overall static but partially dynamic, the LCD screen is divided into multiple areas, and the refresh rate is controlled according to the page content and motion of each area. For each area, the sum of the absolute values ​​of the pixel value differences between two adjacent frames is calculated by the frame difference model. Specifically, the frame difference model is:

[0043] ;

[0044] in, represents the difference between frames, Indicates at time At the moment, at coordinate The pixel value at Indicates at time At the moment, at coordinate The pixel value at

[0045] The refresh rate is set for each region according to the degree of inter-frame motion. Specifically, it is set through a refresh rate update model. The refresh rate update model is:

[0046] ;

[0047] in, Indicates the updated refresh rate, Indicates the preset minimum refresh rate. Indicates the preset maximum refresh rate. is the preset motion threshold, represents the sensitivity coefficient;

[0048] A static page adjustment module is used to calculate the maximum image motion degree of the pages loaded in the memory of the LCD computer by the difference between consecutive frames of the static pages if all the pages loaded in the memory of the LCD computer are static pages. The maximum image motion degree is calculated by the frame difference model. The refresh rate of the LCD display is adjusted based on the maximum image motion degree. The refresh rate is calculated by the refresh rate update model.

[0049] Furthermore, the brightness adjustment module includes:

[0050] A module for capturing user's eye movement data, which is used to set a time threshold to define a gaze point, and to capture the user's eye movement data in real time through an eye tracker, wherein the eye movement data includes a gaze position and a gaze time;

[0051] The pre-processing module is used to remove the noise data caused by device jitter and user rapid eye movement, merge close gaze points, and identify the user's long-term gaze behavior at the same location;

[0052] The module for calculating the target brightness value is used to obtain the attention weight of each gaze point and calculate the target brightness value of each screen point using a predefined weighted model based on visual attention. Specifically, the weighted model based on visual attention is:

[0053] ;

[0054] in, Indicates location The brightness value, Indicates the basic brightness of the screen. represents the number of fixations, Indicates The attention weight of each fixation point, Indicates The coordinates of the gaze point, represents the standard deviation of the Gaussian function corresponding to the first range enhancement, represents the standard deviation of the Gaussian function corresponding to the smooth transition of the second range, .

[0055] Furthermore, the module for predicting and adjusting the brightness and refresh rate of the display includes:

[0056] A user history data collection module is used to collect the user's historical operation records, which include mouse movement, clicks, keyboard input frequency and application usage time, and to record the timestamp of the user's historical operation records to establish time series data;

[0057] A capture module is used to capture the current usage content of the display, the current usage content includes: open applications, window layout and color brightness distribution, and obtain hardware status data related to the display, including: current brightness setting, refresh rate, power consumption and temperature change;

[0058] A training preprocessing module is used to process missing data and abnormal values ​​in the user's historical operation records, and extract useful features from the processed historical operation record data of the user, wherein the useful features include session duration, usage frequency of a specific application, and brightness change pattern;

[0059] The conversion module is used to convert the extracted useful feature data into a format suitable for machine learning algorithms, including time series formatting;

[0060] The tuning module is used to train the LSTM model with useful feature data formatted in time series, adjust model parameters to optimize performance, evaluate model performance through cross-validation, and adjust and improve the model;

[0061] The prediction module is used to extract useful features from the current usage content of the display, input the useful features into the trained LSTM model, make real-time predictions on user behavior and display content, and adjust the refresh rate and brightness of the screen based on the predicted user behavior and display content.

[0062] Furthermore, the feedback adjustment module includes:

[0063] A real-time energy consumption acquisition module is used to acquire the refresh rate and brightness data of the screen adjusted based on the prediction, and calculate the energy consumption of the display based on the refresh rate and brightness data;

[0064] Update the training module to monitor the energy consumption of the display in real time, compare and analyze the actual energy consumption with the expected energy consumption. If the actual energy consumption exceeds the preset threshold, re-collect user behavior and re-train the LSTM model.

[0065] Beneficial effects of the present invention: Dynamic adjustment of refresh rate and brightness, combined with machine learning prediction technology and real-time energy consumption monitoring, significantly reducing power consumption and improving energy efficiency while ensuring display effects; automatic adjustment to adapt to user sight and operating habits makes the display effect more comfortable and smooth, reducing eye fatigue and poor visual experience; the system realizes intelligent equipment management with minimal human intervention; and can respond and adjust quickly to maintain the performance and energy efficiency of the display;

[0066] The real-time analysis and feedback adjustment mechanism of the energy consumption monitoring module ensures that the system can respond quickly when abnormal energy consumption is identified, correct unnecessary power consumption, and keep energy consumption within a reasonable range; it not only optimizes hardware power consumption, but also improves the overall effect in user interaction and experience. Through intelligent system management, a more sustainable way of using electricity can be achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 A schematic diagram of a liquid crystal display driving control method according to the present invention. DETAILED DESCRIPTION

[0068] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0069] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. The embodiments described are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0070] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0071] One embodiment of the present invention provides a liquid crystal display drive control method, the method comprising:

[0072] Obtaining a page loaded in the memory of the LCD computer, calculating a maximum image motion degree of the page loaded in the memory of the LCD computer by differences between consecutive frames, and adjusting a refresh rate of the LCD display based on the maximum image motion degree;

[0073] The user's gaze point position and gaze time are obtained through eye tracking technology, and the brightness of the LCD screen is adjusted according to the user's gaze point position and gaze time;

[0074] Combine the user's usage habits and the display's historical data, use machine learning algorithms to predict the LCD display's display content and user behavior, and adjust the display's brightness and refresh rate based on the prediction results;

[0075] Through the built-in energy consumption monitoring module, the energy consumption data of the display is recorded in real time, the actual energy consumption is compared and analyzed with the expected energy consumption, and energy consumption anomalies are discovered in time and feedback adjustments are made.

[0076] The working principle and effect of the above technical solution are: refresh rate adjustment based on image motion, page frame difference analysis, calculating the degree of image motion by comparing consecutive frames loaded on the LCD screen, involving the use of algorithms to detect pixel changes and quantify motion intensity; dynamically adjusting the screen refresh rate based on the calculated maximum image motion degree, higher motion intensity requires a higher refresh rate to ensure visual smoothness, while the refresh rate can be reduced in static or low motion to save power consumption; using eye tracking technology to capture the user's gaze point position and gaze time. This technology detects the user's pupil position and movement path to understand the screen area that the user is paying attention to in real time; dynamically adjust the brightness of the area according to the specific area the user is looking at, and by reducing the brightness of the unfocused area, energy can be saved while improving the visibility and contrast of the area of ​​interest to the user; collect and analyze the user's historical usage data and the history of the content displayed on the screen, use machine learning algorithms to predict user behavior and display requirements for a period of time in the future, and adjust the brightness and refresh rate in advance based on the predicted results to optimize power usage. This forward-looking adjustment can optimize display parameters and reduce unnecessary power consumption; the built-in energy consumption monitoring module records the display's consumption data in real time, monitors parameters including current, voltage, overhead time, etc., compares actual energy consumption with energy consumption in the expected model, identifies any abnormal energy consumption patterns, and automatically adjusts through a feedback mechanism to ensure that the device runs in an energy-saving state, and performs inspections and corrections. Through real-time and predictive adjustments, the display significantly reduces energy consumption while meeting user experience needs, extending battery life (for portable devices) and reducing overall power costs; adaptive optimization based on user activity and screen content improves visual quality. For example, dynamic images are always displayed smoothly, and the brightness of important content areas is appropriately adjusted, which enhances user satisfaction; the equipment has the ability to self-regulate and learn, and can continuously optimize its own operating parameters to provide the best display effect according to user behavior habits and environmental changes; through more efficient energy management, the burden on the environment is reduced, which is in line with the development trend of green technology; automatic adjustment significantly reduces the need for users to manually change display settings, making operation smoother and more convenient, and through intelligent perception, prediction and adjustment, it closely combines user experience and energy management to achieve advanced LCD display drive control.

[0077] An embodiment of the present invention obtains a page loaded in a memory of a liquid crystal computer, calculates a maximum image motion degree of the page loaded in the memory of the liquid crystal computer by differences between consecutive frames, and adjusts a refresh rate of a liquid crystal display screen based on the maximum image motion degree, including:

[0078] Get the page loaded in the memory of the LCD computer, and get whether there is a dynamic page in the page display format. If there is a dynamic page, the page refresh rate is adjusted to the preset maximum refresh rate;

[0079] If the pages loaded into the memory of the LCD computer are static as a whole but dynamic in parts, the LCD screen is divided into multiple areas, and the refresh rate is controlled according to the page content and motion of each area. The sum of the absolute values ​​of the pixel value differences between two adjacent frames is calculated for each area through a frame difference model. Specifically, the frame difference model is:

[0080] ;

[0081] in, represents the difference between frames, Indicates at time At the moment, at coordinate The pixel value at Indicates at time At the moment, at coordinate The pixel value at

[0082] The refresh rate is set for each region according to the degree of inter-frame motion. Specifically, it is set through a refresh rate update model. The refresh rate update model is:

[0083] ;

[0084] in, Indicates the updated refresh rate, Indicates the preset minimum refresh rate. Indicates the preset maximum refresh rate. is the preset motion threshold, represents the sensitivity coefficient, >0;

[0085] If the pages loaded into the memory of the LCD computer are all static pages, the maximum image motion degree of the pages loaded into the memory of the LCD computer is calculated by the difference between consecutive frames of the static pages. The maximum image motion degree is calculated by the frame difference model. The refresh rate of the LCD display is adjusted based on the maximum image motion degree. The refresh rate is calculated by the refresh rate update model.

[0086] The working principle and effect of the above technical solution are as follows: This technical solution aims to optimize the refresh rate of the LCD display screen by identifying the dynamic characteristics of the page and adjusting the refresh rate of each area accordingly, so as to improve the visual effect and optimize energy consumption; first, detect whether the page loaded in the LCD computer memory is a dynamic page; if the page as a whole is dynamic, the refresh rate is directly adjusted to the preset maximum refresh rate to ensure the visual effect; if the page is static as a whole but contains local dynamic areas, the LCD screen is divided into multiple small areas, and each area evaluates the degree of motion by calculating the difference in pixel values ​​between two adjacent frames, and uses the frame difference model to set the refresh rate of each area based on the degree of inter-frame motion in the area using the refresh rate update model; for completely static pages, the refresh rate of the screen is adjusted by calculating the overall inter-frame difference, that is, the maximum degree of image motion, and the refresh rate update model is also used for calculation. In dynamic images, maintaining a high refresh rate ensures a smooth visual experience, while in static images, the refresh rate is dynamically adjusted according to demand; appropriately reducing the refresh rate for static areas can significantly reduce power consumption, extend the battery life of the device or reduce operating costs; when users use a small screen to play videos, asynchronous refresh rate adjustments in different areas allow the device to achieve more fine-grained power consumption optimization while maintaining the necessary display quality. The frame difference model determines the degree of motion by calculating the pixel difference between frames. Calculating the sum of absolute differences is an effective way to measure the intensity of change. It is simple and has a moderate amount of calculation, which is suitable for real-time processing. The S-shaped curve of the Sigmoid function naturally optimizes the change of the refresh rate so that it does not appear suddenly and avoids flickering; through the parameters and Settings, the system can adjust its sensitivity and response speed according to different scenarios, which is very flexible; by setting and Ensure that the refresh rate changes within a reasonable range to avoid unclear display caused by too low refresh rate or unnecessary power consumption caused by too high refresh rate; achieve dual optimization of visual effects and energy consumption by accurately controlling the refresh rate of different pages and areas; Control Input Variables Output results when changes The impact of The value will cause the function to More sensitive to changes, smaller changes can cause significant change; It also affects the steepness of the curve. A higher value means a steeper curve and a faster transition; a lower A higher value means a smoother transition. Increase, the page content will quickly approach the , which is suitable for scenarios that require fast response to dynamic content; when Reduce, The changes will be slower and smoother, which is suitable for scenes that prioritize stability and prevent visual discomfort caused by frequent changes.

[0087] In one embodiment of the present invention, the user's gaze point position and gaze time are obtained through eye tracking technology, and the brightness of the liquid crystal display screen is adjusted according to the user's gaze point position and gaze time, including:

[0088] Setting a time threshold to define a gaze point, and capturing the user's eye movement data in real time through an eye tracker, wherein the eye movement data includes a gaze position and a gaze time;

[0089] Remove the noise data caused by device jitter and user rapid eye movement, merge close gaze points, and identify the user's long-term gaze behavior at the same location;

[0090] Get the attention weight of each fixation point, and use the predefined weighted model based on visual attention to calculate the target brightness value of each screen point. Specifically, the weighted model based on visual attention is:

[0091] ;

[0092] in, Indicates location The brightness value, Indicates the basic brightness of the screen. represents the number of fixations, Indicates The attention weight of each fixation point, Indicates The coordinates of the gaze point, represents the standard deviation of the Gaussian function corresponding to the first range enhancement, represents the standard deviation of the Gaussian function corresponding to the smooth transition of the second range, .

[0093] Sure and You need to determine the distance between the user and the screen, the screen size, and the resolution, which will affect the range of visual perception details; smaller A higher value means a more concentrated and localized brightness enhancement, which is suitable for situations where you need to focus on specific details, while a larger The value provides a smooth and wide transition, avoiding abrupt bright and dark boundaries. Example 1: Small display scene Pixels: This setting is suitable for smaller laptop monitors, where the user usually sits at a distance of about 50-60 cm. This smaller standard deviation is suitable for enhancing small areas near the user's gaze point. Pixels: This value is used for larger visual transitions, ensuring that the brightness is smoothly spread to a larger area around the gaze point to prevent uneven edges. Example 2: Large screen or projector scene Pixels: This setting is based on the usage of indoor large-screen displays or projectors, considering that users are usually far away from the screen. It is therefore set large to create a noticeable but unobtrusive brightness boost near its fixation point; Pixels: Provides a wider transition effect, ensuring that brightness changes flow more naturally as the user moves their focus on larger screens.

[0094] The working principle and effect of the above technical solution are as follows: the eye tracker captures the user's eye movement data in real time, including the gaze position and gaze time, which are used to analyze the user's attention distribution on the screen; removes noise data caused by device jitter and user rapid eye movements (such as scanning and jumping). Through filtering technology and time threshold setting, stable gaze points are retained; gaze points that are close in time and space are merged to identify the user's long-term gaze behavior at the same location to avoid multiple point misidentification caused by slight visual drift; the attention weight of each gaze point is calculated based on its attributes in time and persistence. Gaze points with long duration and accurate positioning are given higher weights because they can better reflect the user's interest; a weighted model based on visual attention is used to calculate the brightness value of each position on the screen; Gaussian function: two Gaussian functions are used to enhance the brightness near the gaze point, respectively. For a more focused, noticeable brightness boost, while It is used to produce a smooth transition effect to ensure visual comfort; the basic brightness provides a basic brightness level for the screen to ensure that the screen can maintain moderate brightness even when there is no gaze point. Dynamically adjust the screen brightness to highlight the area where the user pays attention, improve visual perception, enhance content presentation, and reduce unnecessary visual fatigue; reduce the brightness in the area where the user does not pay attention, optimize energy consumption, and ensure that the central area of ​​vision maintains appropriate brightness; by identifying and responding to the user's gaze behavior, personalized visual assistance is achieved, which is very suitable for tasks that require long-term gaze or multi-tasking operation environments; focusing the brightness in the area where the user pays attention helps to reduce the interference of irrelevant information next to it, thereby improving concentration and efficiency; smooth transition, using the combination of double Gaussian functions to ensure that the brightness transition is natural, avoiding discomfort and visual distraction caused by excessive contrast between light and dark; provides an intelligent screen brightness management method, through detailed visual attention analysis, improves visual effects and energy efficiency, suitable for a variety of application scenarios such as office, graphic design, entertainment, etc.; basic brightness provides a consistent brightness level to ensure that the screen remains visible without a clear gaze point. This is to avoid relying entirely on the user's gaze point and causing the unfocused area to become too dim; weighted Gaussian function is a two-dimensional Gaussian function that describes how brightness spreads outward from the point of gaze. and Represent the standard deviation of the Gaussian function, which defines the size of the brightness impact range, Smaller, used to achieve highlight enhancement around the focus point to make the center more noticeable. The weight of each fixation point reflects the user's attention intensity on a certain area, ensuring that the position with long or frequent fixation time gets higher brightness boost; 0.5 is used to control the contribution value of the second Gaussian function so that it is properly balanced with the total effect of the first Gaussian function; by multiplying by 0.5, the neutralization effect can be visually ensured, making the impact of the smooth transition softer and avoiding excessive edge effect; it helps to form a natural brightness transition and reduce visual distraction or dizziness, especially when the user's perspective shifts quickly; dynamically adjusts the brightness based on the fixation point to improve the personalization and response sensitivity of the screen display; highlights the center area to help guide the user's attention, improve work efficiency and visual experience. Using the dual Gaussian function model, the effects of different ranges are superimposed to ensure a natural brightness transition and avoid the stimulation of abrupt brightness changes on the vision; the brightness of non-focus areas is intelligently adjusted to achieve energy saving goals; the formula is designed to balance visibility and comfort, and to improve the user experience through intelligent brightness adjustment.

[0095] An embodiment of the present invention combines the user's usage habits and the historical data of the display, uses a machine learning algorithm to predict the display content and user behavior of the liquid crystal display screen, and adjusts the brightness and refresh rate of the display based on the prediction results, including:

[0096] Collecting the user's historical operation records, including mouse movement, clicks, keyboard input frequency and application usage time, and recording the timestamp of the user's historical operation records to establish time series data;

[0097] Capturing the current usage content of the display, including: open applications, window layout, and color brightness distribution, and obtaining hardware status data related to the display, including: current brightness setting, refresh rate, power consumption, and temperature change;

[0098] Processing missing data and abnormal values ​​in the user's historical operation records, and extracting useful features from the processed historical operation record data of the user, wherein the useful features include session duration, usage frequency of a specific application, and brightness change pattern;

[0099] Convert the extracted useful feature data into a format suitable for machine learning algorithms, including time series formatting;

[0100] Train the LSTM model with useful feature data formatted with time series, adjust model parameters to optimize performance, evaluate model performance through cross-validation, and adjust and improve the model;

[0101] Useful features are extracted from the current usage content of the display, and the useful features are input into the trained LSTM model to make real-time predictions on user behavior and display content, and the refresh rate and brightness of the screen are adjusted based on the predicted user behavior and display content.

[0102] The working principle and effect of the above technical solution are as follows: user historical operation record collection, user interaction data collection, including mouse movement, clicks, keyboard input frequency and the duration of use of each application; record the timestamp when the operation occurs and organize it into time series data to support timing analysis; obtain information about the current display content, such as open applications, window layout and color brightness distribution, and collect hardware-related data, including current brightness settings, refresh rate, power consumption and temperature changes; perform missing value processing and outlier detection and correction on user historical operation records; extract key features from the cleaned data, such as session duration, application usage frequency and brightness change pattern; convert the extracted useful features into a format suitable for machine learning applications, especially time series format, to facilitate model training; use the formatted time series data to train the long short-term memory (LSTM) model; adjust the parameters of the model, evaluate and optimize the model performance through cross-validation and other technologies to improve prediction accuracy; extract features from the current use content of the display and input them into the trained LSTM model; the model predicts the user's possible behavior and display content trends in real time, and makes intelligent adjustment suggestions for the refresh rate and brightness of the screen. By dynamically adjusting the screen based on user behavior prediction, the display effect is optimized to improve the user's visual comfort; the settings when high refresh rate or high brightness is not needed are reduced to reduce eye fatigue; the device energy consumption is intelligently adjusted according to the predicted usage pattern to extend the device life and battery life; for example, the brightness and refresh rate are reduced when the user is inactive for a long time to save energy; personalized screen settings are provided according to the user's habits and current operating environment to improve operating efficiency; the user experience in different applications, such as games, high-brightness working environments and low-light environments, can be flexibly adjusted to the best settings; unnecessary power consumption is reduced through intelligent display management, and the heat load and wear and tear of hardware are reduced; the display can respond to the user's usage habits and environment more intelligently to provide users with optimized visual performance and device usage experience. Such a system shows high flexibility and adaptability in a dynamic environment, ultimately leading to more efficient device operation and more lasting user satisfaction.

[0103] In one embodiment of the present invention, the energy consumption data of the display is recorded in real time through a built-in energy consumption monitoring module, and the actual energy consumption is compared and analyzed with the expected energy consumption, so as to timely find energy consumption abnormalities and make feedback adjustments, including:

[0104] Acquire the refresh rate and brightness data of the screen adjusted based on the prediction, and calculate the energy consumption of the display based on the refresh rate and brightness data;

[0105] Monitor the energy consumption of the display in real time, compare and analyze the actual energy consumption with the expected energy consumption. If the difference between the actual energy consumption and the expected energy consumption exceeds the preset threshold, collect user behavior again and retrain the LSTM model. The working principle and effect of the above technical solution are: Obtain the refresh rate and brightness data of the screen in real time, estimate the energy consumption of the current display through these data, and use appropriate formulas and models to calculate the expected power consumption based on the set refresh rate and brightness; monitor the actual energy consumption of the display in real time, which can be obtained through the connected power consumption monitoring device or the system's built-in power consumption evaluation module; compare and analyze the actual energy consumption with the expected energy consumption obtained through predictive adjustment; define the threshold of energy consumption difference. When the difference between the actual energy consumption and the expected energy consumption exceeds this threshold, the system detects that there may be room for optimization or inaccurate prediction; when the energy consumption difference exceeds the threshold, record the anomaly and possible influencing factors. Re-collect user behavior data, including the latest operation records and display usage status, to capture new usage patterns or changes; retrain the LSTM model with updated data, which may include using a larger data set or introducing new features to improve the accuracy of the model; generate new predictions through the updated model, dynamically adjust screen settings, and further optimize the system's energy performance. Improve energy efficiency. By precisely controlling the refresh rate and brightness of the screen, the rational use of electricity is achieved and unnecessary energy consumption is reduced. The optimized energy efficiency of the system helps to extend battery life and reduce energy costs. The system can self-correct and optimize according to the deviation between actual energy consumption and prediction, so that the system can maintain optimal performance in different usage environments and conditions. Dynamic update and adjustment models maintain the system's sensitivity to changes in usage habits and environmental changes. By reducing unnecessary device usage costs and enhancing device response, the user experience is optimized to a new level, and users can get longer device life and better device performance without losing visual quality. Promote environmental protection and sustainable development. Reduce total power consumption and carbon footprint through intelligent energy management strategies. Effective energy management not only reduces waste of resources, but also reduces potential damage to the device due to excessive temperature. It not only improves the energy management capabilities of the device, but also provides users with a smarter and more efficient use experience. This cycle of intelligent adjustment and optimization ensures the long-term effectiveness and adaptability of the system.

[0106] One embodiment of the present invention provides a liquid crystal display drive control system, the system comprising:

[0107] A refresh rate adjustment module is used to obtain a page loaded in the memory of the LCD computer, calculate the maximum image motion degree of the page loaded in the memory of the LCD computer through the difference between consecutive frames, and adjust the refresh rate of the LCD display screen based on the maximum image motion degree;

[0108] A brightness adjustment module is used to obtain the user's gaze point position and gaze time through eye tracking technology, and adjust the brightness of the LCD screen according to the user's gaze point position and gaze time;

[0109] The module for predicting and adjusting the brightness and refresh rate of the display is used to combine the user's usage habits and the historical data of the display, use machine learning algorithms to predict the display content and user behavior of the LCD screen, and adjust the brightness and refresh rate of the display based on the prediction results;

[0110] The feedback adjustment module is used to record the energy consumption data of the display in real time through the built-in energy consumption monitoring module, compare and analyze the actual energy consumption with the expected energy consumption, promptly discover energy consumption anomalies and make feedback adjustments.

[0111] The working principle and effect of the above technical solution are: refresh rate adjustment based on image motion, page frame difference analysis, calculating the degree of image motion by comparing consecutive frames loaded on the LCD screen, involving the use of algorithms to detect pixel changes and quantify motion intensity; dynamically adjusting the screen refresh rate based on the calculated maximum image motion degree, higher motion intensity requires a higher refresh rate to ensure visual smoothness, while the refresh rate can be reduced in static or low motion to save power consumption; using eye tracking technology to capture the user's gaze point position and gaze time. This technology detects the user's pupil position and movement path to understand the screen area that the user is paying attention to in real time; dynamically adjust the brightness of the area according to the specific area the user is looking at, and by reducing the brightness of the unfocused area, energy can be saved while improving the visibility and contrast of the area of ​​interest to the user; collect and analyze the user's historical usage data and the history of the content displayed on the screen, use machine learning algorithms to predict user behavior and display requirements for a period of time in the future, and adjust the brightness and refresh rate in advance based on the predicted results to optimize power usage. This forward-looking adjustment can optimize display parameters and reduce unnecessary power consumption; the built-in energy consumption monitoring module records the display's consumption data in real time, monitors parameters including current, voltage, overhead time, etc., compares actual energy consumption with energy consumption in the expected model, identifies any abnormal energy consumption patterns, and automatically adjusts through a feedback mechanism to ensure that the device runs in an energy-saving state, and performs inspections and corrections. Through real-time and predictive adjustments, the display significantly reduces energy consumption while meeting user experience needs, extending battery life (for portable devices) and reducing overall power costs; adaptive optimization based on user activity and screen content improves visual quality. For example, dynamic images are always displayed smoothly, and the brightness of important content areas is appropriately adjusted, which enhances user satisfaction; the equipment has the ability to self-regulate and learn, and can continuously optimize its own operating parameters to provide the best display effect according to user behavior habits and environmental changes; through more efficient energy management, the burden on the environment is reduced, which is in line with the development trend of green technology; automatic adjustment significantly reduces the need for users to manually change display settings, making operation smoother and more convenient, and through intelligent perception, prediction and adjustment, it closely combines user experience and energy management to achieve advanced LCD display drive control.

[0112] In one embodiment of the present invention, the refresh rate adjustment module includes:

[0113] The dynamic page adjustment module is used to obtain the page loaded in the memory of the LCD computer and obtain whether there is a dynamic page in the page display format. If there is a dynamic page, the page refresh rate is adjusted to the preset maximum refresh rate;

[0114] The overall static and local dynamic page adjustment module, if the pages loaded into the memory of the LCD computer are overall static but partially dynamic, the LCD screen is divided into multiple areas, and the refresh rate is controlled according to the page content and motion of each area. For each area, the sum of the absolute values ​​of the pixel value differences between two adjacent frames is calculated by the frame difference model. Specifically, the frame difference model is:

[0115] ;

[0116] in, represents the difference between frames, Indicates at time At the moment, at coordinate The pixel value at Indicates at time At the moment, at coordinate The pixel value at

[0117] The refresh rate is set for each region according to the degree of inter-frame motion. Specifically, it is set through a refresh rate update model. The refresh rate update model is:

[0118] ;

[0119] in, Indicates the updated refresh rate, Indicates the preset minimum refresh rate. Indicates the preset maximum refresh rate. is the preset motion threshold, represents the sensitivity coefficient;

[0120] A static page adjustment module is used to calculate the maximum image motion degree of the pages loaded in the memory of the LCD computer by the difference between consecutive frames of the static pages if all the pages loaded in the memory of the LCD computer are static pages. The maximum image motion degree is calculated by the frame difference model. The refresh rate of the LCD display is adjusted based on the maximum image motion degree. The refresh rate is calculated by the refresh rate update model.

[0121] The working principle and effect of the above technical solution are as follows: This technical solution aims to optimize the refresh rate of the LCD display screen by identifying the dynamic characteristics of the page and adjusting the refresh rate of each area accordingly, so as to improve the visual effect and optimize energy consumption; first, detect whether the page loaded in the LCD computer memory is a dynamic page; if the page as a whole is dynamic, the refresh rate is directly adjusted to the preset maximum refresh rate to ensure the visual effect; if the page is static as a whole but contains local dynamic areas, the LCD screen is divided into multiple small areas, and each area evaluates the degree of motion by calculating the difference in pixel values ​​between two adjacent frames, and uses the frame difference model to set the refresh rate of each area based on the degree of inter-frame motion in the area using the refresh rate update model; for completely static pages, the refresh rate of the screen is adjusted by calculating the overall inter-frame difference, that is, the maximum degree of image motion, and the refresh rate update model is also used for calculation. In dynamic images, maintaining a high refresh rate ensures a smooth visual experience, while in static images, the refresh rate is dynamically adjusted according to demand; appropriately reducing the refresh rate for static areas can significantly reduce power consumption, extend the battery life of the device or reduce operating costs; when users use a small screen to play videos, asynchronous refresh rate adjustments in different areas allow the device to achieve more fine-grained power consumption optimization while maintaining the necessary display quality. The frame difference model determines the degree of motion by calculating the pixel difference between frames. Calculating the sum of absolute differences is an effective way to measure the intensity of change. It is simple and has a moderate amount of calculation, which is suitable for real-time processing. The S-shaped curve of the Sigmoid function naturally optimizes the change of the refresh rate so that it does not appear suddenly and avoids flickering; through the parameters and Settings, the system can adjust its sensitivity and response speed according to different scenarios, which is very flexible; by setting and Ensure that the refresh rate changes within a reasonable range to avoid unclear display caused by too low refresh rate or unnecessary power consumption caused by too high refresh rate; achieve dual optimization of visual effects and energy consumption by accurately controlling the refresh rate of different pages and areas; Control Input Variables Output results when changes The impact of The value will cause the function to More sensitive to changes, smaller changes can cause significant change; It also affects the steepness of the curve. A higher value means a steeper curve and a faster transition; a lower A higher value means a smoother transition. Increase, the page content will quickly approach the , which is suitable for scenarios that require fast response to dynamic content; when Reduce, The changes will be slower and smoother, which is suitable for scenes that prioritize stability and prevent visual discomfort caused by frequent changes.

[0122] In one embodiment of the present invention, the brightness adjustment module includes:

[0123] A module for capturing user's eye movement data, which is used to set a time threshold to define a gaze point, and to capture the user's eye movement data in real time through an eye tracker, wherein the eye movement data includes gaze position and gaze time;

[0124] The pre-processing module is used to remove the noise data caused by device jitter and user rapid eye movement, merge close gaze points, and identify the user's long-term gaze behavior at the same location;

[0125] The module for calculating the target brightness value is used to obtain the attention weight of each gaze point and calculate the target brightness value of each screen point using a predefined weighted model based on visual attention. Specifically, the weighted model based on visual attention is:

[0126] ;

[0127] in, Indicates location The brightness value, Indicates the basic brightness of the screen. represents the number of fixations, Indicates The attention weight of each fixation point, Indicates The coordinates of the gaze point, represents the standard deviation of the Gaussian function corresponding to the first range enhancement, represents the standard deviation of the Gaussian function corresponding to the smooth transition of the second range, .

[0128] The working principle and effect of the above technical solution are as follows: the eye tracker captures the user's eye movement data in real time, including the gaze position and gaze time, which are used to analyze the user's attention distribution on the screen; removes noise data caused by device jitter and user rapid eye movements (such as scanning and jumping). Through filtering technology and time threshold setting, stable gaze points are retained; gaze points that are close in time and space are merged to identify the user's long-term gaze behavior at the same location to avoid multiple point misidentification caused by slight visual drift; the attention weight of each gaze point is calculated based on its attributes in time and persistence. Gaze points with long duration and accurate positioning are given higher weights because they can better reflect the user's interest; a weighted model based on visual attention is used to calculate the brightness value of each position on the screen; Gaussian function: two Gaussian functions are used to enhance the brightness near the gaze point, respectively. For a more focused, noticeable brightness boost, while It is used to produce a smooth transition effect to ensure visual comfort; the basic brightness provides a basic brightness level for the screen to ensure that the screen can maintain moderate brightness even when there is no focus point. Dynamically adjust the screen brightness to highlight the area where the user pays attention, improve visual perception, enhance content presentation, and reduce unnecessary visual fatigue; reduce the brightness in the area where the user does not pay attention, optimize energy consumption, and ensure that the central area of ​​the vision maintains appropriate brightness; by identifying and responding to the user's gaze behavior, personalized visual assistance is achieved, which is very suitable for tasks that require long-term gaze or multi-tasking operation environments; focusing the brightness on the area where the user pays attention helps reduce the interference of irrelevant information next to it, thereby improving concentration and efficiency; smooth transition, using the combination of double Gaussian functions to ensure natural brightness transition, avoiding discomfort and visual distraction caused by excessive light-dark contrast; provides an intelligent screen brightness management method, through detailed visual attention analysis, improves visual effects and energy efficiency, suitable for a variety of application scenarios such as office, graphic design, entertainment, etc.

[0129] In one embodiment of the present invention, the module for predicting and adjusting the brightness and refresh rate of the display includes:

[0130] A user history data collection module is used to collect the user's historical operation records, which include mouse movement, clicks, keyboard input frequency and application usage time, and to record the timestamp of the user's historical operation records to establish time series data;

[0131] A capture module is used to capture the current usage content of the display, the current usage content includes: open applications, window layout and color brightness distribution, and obtain hardware status data related to the display, including: current brightness setting, refresh rate, power consumption and temperature change;

[0132] A training preprocessing module is used to process missing data and abnormal values ​​in the user's historical operation records, and extract useful features from the processed historical operation record data of the user, wherein the useful features include session duration, usage frequency of a specific application, and brightness change pattern;

[0133] The conversion module is used to convert the extracted useful feature data into a format suitable for machine learning algorithms, including time series formatting;

[0134] The tuning module is used to train the LSTM model with useful feature data formatted in time series, adjust model parameters to optimize performance, evaluate model performance through cross-validation, and adjust and improve the model;

[0135] The prediction module is used to extract useful features from the current usage content of the display, input the useful features into the trained LSTM model, make real-time predictions on user behavior and display content, and adjust the refresh rate and brightness of the screen based on the predicted user behavior and display content.

[0136] The working principle and effect of the above technical solution are as follows: user historical operation record collection, user interaction data collection, including mouse movement, clicks, keyboard input frequency and the duration of use of each application; record the timestamp when the operation occurs and organize it into time series data to support timing analysis; obtain information about the current display content, such as open applications, window layout and color brightness distribution, and collect hardware-related data, including current brightness settings, refresh rate, power consumption and temperature changes; perform missing value processing and outlier detection and correction on user historical operation records; extract key features from the cleaned data, such as session duration, application usage frequency and brightness change pattern; convert the extracted useful features into a format suitable for machine learning applications, especially time series format, to facilitate model training; use the formatted time series data to train the long short-term memory (LSTM) model; adjust the parameters of the model, evaluate and optimize the model performance through cross-validation and other technologies to improve prediction accuracy; extract features from the current use content of the display and input them into the trained LSTM model; the model predicts the user's possible behavior and display content trends in real time, and makes intelligent adjustment suggestions for the refresh rate and brightness of the screen. By dynamically adjusting the screen based on user behavior prediction, the display effect is optimized to improve the user's visual comfort; the settings when high refresh rate or high brightness is not needed are reduced to reduce eye fatigue; the device energy consumption is intelligently adjusted according to the predicted usage pattern to extend the device life and battery life; for example, the brightness and refresh rate are reduced when the user is inactive for a long time to save energy; personalized screen settings are provided according to the user's habits and current operating environment to improve operating efficiency; the user experience in different applications, such as games, high-brightness working environments and low-light environments, can be flexibly adjusted to the best settings; unnecessary power consumption is reduced through intelligent display management, and the heat load and wear and tear of hardware are reduced; the display can respond to the user's usage habits and environment more intelligently to provide users with optimized visual performance and device usage experience. Such a system shows high flexibility and adaptability in a dynamic environment, ultimately leading to more efficient device operation and more lasting user satisfaction.

[0137] In one embodiment of the present invention, the feedback adjustment module includes:

[0138] A real-time energy consumption acquisition module is used to acquire the refresh rate and brightness data of the screen adjusted based on the prediction, and calculate the energy consumption of the display based on the refresh rate and brightness data;

[0139] Update the training module to monitor the energy consumption of the display in real time, compare and analyze the actual energy consumption with the expected energy consumption. If the actual energy consumption exceeds the preset threshold, re-collect user behavior and re-train the LSTM model.

[0140] The working principle and effect of the above technical solution are as follows: Real-time acquisition of screen refresh rate and brightness data, estimation of current display energy consumption through these data, and calculation of expected power consumption based on set refresh rate and brightness using appropriate formulas and models; real-time monitoring of actual display energy consumption, which can be obtained through connected power consumption monitoring equipment or system built-in power consumption assessment module; comparison and analysis of actual energy consumption with expected energy consumption obtained through predictive adjustment; definition of energy consumption difference threshold, when the difference between actual energy consumption and expected energy consumption exceeds this threshold, the system detects that there may be room for optimization or inaccurate prediction; when energy consumption difference exceeds the threshold, record abnormalities and possible influencing factors. Re-collect user behavior data, including the latest operation records and display usage status, to capture new usage patterns or changes; retrain LSTM model with updated data, which may include using larger data sets or introducing new features to improve model accuracy; generate new predictions through updated models, dynamically adjust screen settings, and further optimize system energy consumption performance. Improve energy efficiency. By precisely controlling the refresh rate and brightness of the screen, the rational use of electricity is achieved and unnecessary energy consumption is reduced. The optimized energy efficiency of the system helps to extend battery life and reduce energy costs. The system can self-correct and optimize according to the deviation between actual energy consumption and prediction, so that the system can maintain optimal performance in different usage environments and conditions. Dynamic update and adjustment models maintain the system's sensitivity to changes in usage habits and environmental changes. By reducing unnecessary device usage costs and enhancing device response, the user experience is optimized to a new level, and users can get longer device life and better device performance without losing visual quality. Promote environmental protection and sustainable development. Reduce total power consumption and carbon footprint through intelligent energy management strategies. Effective energy management not only reduces waste of resources, but also reduces potential damage to the device due to excessive temperature. It not only improves the energy management capabilities of the device, but also provides users with a smarter and more efficient use experience. This cycle of intelligent adjustment and optimization ensures the long-term effectiveness and adaptability of the system.

[0141] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A liquid crystal display driving control method, characterized in that: The method comprises: Obtaining a page loaded in the memory of the LCD computer, calculating a maximum image motion degree of the page loaded in the memory of the LCD computer by differences between consecutive frames, and adjusting a refresh rate of the LCD display based on the maximum image motion degree; The user's gaze point position and gaze time are obtained through eye tracking technology, and the brightness of the LCD screen is adjusted according to the user's gaze point position and gaze time, including: Setting a time threshold to define a gaze point, and capturing the user's eye movement data in real time through an eye tracker, wherein the eye movement data includes a gaze position and a gaze time; Remove the noise data caused by device jitter and user rapid eye movement, merge close gaze points, and identify the user's long-term gaze behavior at the same location; Get the attention weight of each fixation point, and use the predefined weighted model based on visual attention to calculate the target brightness value of each screen point. Specifically, the weighted model based on visual attention is: ； Among them, L(x,y) represents the brightness value of the position (x,y), represents the basic brightness of the screen, n represents the number of gaze points, represents the attention weight of the i-th fixation point, ( , ) represents the coordinates of the i-th fixation point, represents the standard deviation of the Gaussian function corresponding to the first range enhancement, represents the standard deviation of the Gaussian function corresponding to the smooth transition of the second range, > , j represents the brightness unit constant, the value of j is 1, and the unit is Stay consistent; Combine the user's usage habits and the display's historical data, use machine learning algorithms to predict the LCD display's display content and user behavior, and adjust the display's brightness and refresh rate based on the prediction results; Through the built-in energy consumption monitoring module, the energy consumption data of the display is recorded in real time, the actual energy consumption is compared and analyzed with the expected energy consumption, and energy consumption anomalies are discovered in time and feedback adjustments are made.

2. A liquid crystal display driving control method according to claim 1, characterized in that: Obtaining a page loaded in a memory of a liquid crystal computer, calculating a maximum image motion degree of the page loaded in the memory of the liquid crystal computer by a difference between consecutive frames, and adjusting a refresh rate of the liquid crystal display based on the maximum image motion degree, including: Get the page loaded in the memory of the LCD computer, and get whether there is a dynamic page in the page display format. If there is a dynamic page, the page refresh rate is adjusted to the preset maximum refresh rate; If the pages loaded into the memory of the LCD computer are static as a whole but dynamic in parts, the LCD screen is divided into multiple areas, and the refresh rate is controlled according to the page content and motion of each area. The sum of the absolute values ​​of the pixel value differences between two adjacent frames is calculated for each area through a frame difference model. Specifically, the frame difference model is: ； Where D represents the difference between frames, represents the pixel value at coordinate (x, y) at time t. represents the pixel value at coordinate (x, y) at time t-1, The refresh rate is set for each region according to the degree of inter-frame motion. Specifically, it is set through a refresh rate update model. The refresh rate update model is: ； Among them, R represents the updated refresh rate, Indicates the preset minimum refresh rate. Indicates the preset maximum refresh rate. is the preset motion threshold, γ represents the sensitivity coefficient; If the pages loaded into the memory of the LCD computer are all static pages, the maximum image motion degree of the pages loaded into the memory of the LCD computer is calculated by the difference between consecutive frames of the static pages. The maximum image motion degree is calculated by the frame difference model. The refresh rate of the LCD display is adjusted based on the maximum image motion degree. The refresh rate is calculated by the refresh rate update model.

3. A liquid crystal display driving control method according to claim 1, characterized in that: Combined with the user's usage habits and the display's historical data, the machine learning algorithm is used to predict the LCD display's display content and user behavior. Based on the prediction results, the display's brightness and refresh rate are adjusted, including: Collecting the user's historical operation records, including mouse movement, clicks, keyboard input frequency and application usage time, and recording the timestamp of the user's historical operation records to establish time series data; Capturing the current usage content of the display, including: open applications, window layout, and color brightness distribution, and obtaining hardware status data related to the display, including: current brightness setting, refresh rate, power consumption, and temperature change; Processing missing data and abnormal values ​​in the user's historical operation records, and extracting useful features from the processed historical operation record data of the user, wherein the useful features include session duration, usage frequency of a specific application, and brightness change pattern; Convert the extracted useful feature data into a format suitable for machine learning algorithms, including time series formatting; Train the LSTM model with useful feature data formatted with time series, adjust model parameters to optimize performance, evaluate model performance through cross-validation, and adjust and improve the model; Useful features are extracted from the current usage content of the display, and the useful features are input into the trained LSTM model to make real-time predictions on user behavior and display content, and the refresh rate and brightness of the screen are adjusted based on the predicted user behavior and display content.

4. A liquid crystal display driving control method according to claim 1, characterized in that: The built-in energy consumption monitoring module records the energy consumption data of the display in real time, compares and analyzes the actual energy consumption with the expected energy consumption, and promptly detects energy consumption anomalies and makes feedback adjustments, including: Acquire the refresh rate and brightness data of the screen adjusted based on the prediction, and calculate the energy consumption of the display based on the refresh rate and brightness data; Monitor the energy consumption of the display in real time, compare and analyze the actual energy consumption with the expected energy consumption. If the actual energy consumption exceeds the preset threshold, collect user behavior again and retrain the LSTM model.

5. A liquid crystal display drive control system, characterized in that: The system comprises: A refresh rate adjustment module is used to obtain a page loaded in the memory of the LCD computer, calculate the maximum image motion degree of the page loaded in the memory of the LCD computer through the difference between consecutive frames, and adjust the refresh rate of the LCD display screen based on the maximum image motion degree; The brightness adjustment module is used to obtain the user's gaze point position and gaze time through eye tracking technology, and adjust the brightness of the LCD screen according to the user's gaze point position and gaze time, including: A module for capturing user's eye movement data, which is used to set a time threshold to define a gaze point, and to capture the user's eye movement data in real time through an eye tracker, wherein the eye movement data includes a gaze position and a gaze time; The pre-processing module is used to remove the noise data caused by device jitter and user rapid eye movement, merge close gaze points, and identify the user's long-term gaze behavior at the same location; The module for calculating the target brightness value is used to obtain the attention weight of each gaze point and calculate the target brightness value of each screen point using a predefined weighted model based on visual attention. Specifically, the weighted model based on visual attention is: ； Among them, L(x,y) represents the brightness value of the position (x,y), represents the basic brightness of the screen, n represents the number of gaze points, represents the attention weight of the i-th fixation point, ( , ) represents the coordinates of the i-th fixation point, represents the standard deviation of the Gaussian function corresponding to the first range enhancement, represents the standard deviation of the Gaussian function corresponding to the smooth transition of the second range, > , j represents the brightness unit constant, the value of j is 1, and the unit is Stay consistent; The module for predicting and adjusting the brightness and refresh rate of the display is used to combine the user's usage habits and the historical data of the display, use machine learning algorithms to predict the display content and user behavior of the LCD screen, and adjust the brightness and refresh rate of the display based on the prediction results; The feedback adjustment module is used to record the energy consumption data of the display in real time through the built-in energy consumption monitoring module, compare and analyze the actual energy consumption with the expected energy consumption, promptly discover energy consumption anomalies and make feedback adjustments.

6. A liquid crystal display drive control system according to claim 5, characterized in that: The refresh rate adjustment module comprises: The dynamic page adjustment module is used to obtain the page loaded in the memory of the LCD computer and obtain whether there is a dynamic page in the page display format. If there is a dynamic page, the page refresh rate is adjusted to the preset maximum refresh rate; The overall static and local dynamic page adjustment module, if the pages loaded into the memory of the LCD computer are overall static but partially dynamic, the LCD screen is divided into multiple areas, and the refresh rate is controlled according to the page content and motion of each area. For each area, the sum of the absolute values ​​of the pixel value differences between two adjacent frames is calculated by the frame difference model. Specifically, the frame difference model is: ； Where D represents the difference between frames, represents the pixel value at coordinate (x, y) at time t. represents the pixel value at coordinate (x, y) at time t-1, The refresh rate is set for each region according to the degree of inter-frame motion. Specifically, it is set through a refresh rate update model. The refresh rate update model is: ； Among them, R represents the updated refresh rate, Indicates the preset minimum refresh rate. Indicates the preset maximum refresh rate. is the preset motion threshold, γ represents the sensitivity coefficient; A static page adjustment module is used to calculate the maximum image motion degree of the pages loaded in the memory of the LCD computer by the difference between consecutive frames of the static pages if all the pages loaded in the memory of the LCD computer are static pages. The maximum image motion degree is calculated by the frame difference model. The refresh rate of the LCD display is adjusted based on the maximum image motion degree. The refresh rate is calculated by the refresh rate update model.

7. A liquid crystal display drive control system according to claim 5, characterized in that: The module for predicting and adjusting the brightness and refresh rate of the display comprises: A user history data collection module is used to collect the user's historical operation records, which include mouse movement, clicks, keyboard input frequency and application usage time, and to record the timestamp of the user's historical operation records to establish time series data; A capture module is used to capture the current usage content of the display, the current usage content includes: open applications, window layout and color brightness distribution, and obtain hardware status data related to the display, including: current brightness setting, refresh rate, power consumption and temperature change; A training preprocessing module is used to process missing data and abnormal values ​​in the user's historical operation records, and extract useful features from the processed historical operation record data of the user, wherein the useful features include session duration, usage frequency of a specific application, and brightness change pattern; The conversion module is used to convert the extracted useful feature data into a format suitable for machine learning algorithms, including time series formatting; The tuning module is used to train the LSTM model with useful feature data formatted in time series, adjust model parameters to optimize performance, evaluate model performance through cross-validation, and adjust and improve the model; The prediction module is used to extract useful features from the current usage content of the display, input the useful features into the trained LSTM model, make real-time predictions on user behavior and display content, and adjust the refresh rate and brightness of the screen based on the predicted user behavior and display content.

8. A liquid crystal display drive control system according to claim 5, characterized in that: The feedback adjustment module comprises: A real-time energy consumption acquisition module is used to acquire the refresh rate and brightness data of the screen adjusted based on the prediction, and calculate the energy consumption of the display based on the refresh rate and brightness data; Update the training module to monitor the energy consumption of the display in real time, compare and analyze the actual energy consumption with the expected energy consumption. If the actual energy consumption exceeds the preset threshold, re-collect user behavior and re-train the LSTM model.

Images