Liquid crystal display anti-dazzle driving control method and system

Abstract

The invention relates to a liquid crystal display anti-dazzle driving control method and system. The method comprises the steps that current environment illumination data and liquid crystal display content data are collected; constructing a target light environment feature vector based on the environment illumination data and the liquid crystal display content data; user touch behavior information is obtained, a touch popularity map is constructed based on the user touch behavior information, and the user touch behavior information comprises a touch position, duration, frequency and a gesture type; inputting the target light environment feature vector and the touch heat map into a pre-trained driving model for analysis to obtain an anti-glare driving strategy corresponding to each display sub-region; and according to the anti-dazzle driving strategy, driving parameter adjustment is carried out on each sub-region of the liquid crystal display module so as to realize regional dynamic anti-dazzle control. The method has the effect of optimizing the watching experience of the user.

Description

Technical Field

[0001] This application relates to the technical field of liquid crystal displays, and in particular to a driving control method and system for anti-glare liquid crystal displays. Background Technology

[0002] Currently, liquid crystal display (LCD) technology is widely used in various fields such as televisions, mobile phones, automotive displays, and smart home devices, especially with the increasing demand for displays in high-brightness environments. LCDs dominate modern display devices due to their advantages such as sensitive operation and clear display effects. However, LCD modules often experience glare in complex lighting environments, such as direct sunlight or reflections from multiple light sources, leading to decreased image clarity and contrast, severely impacting the user's viewing experience and the accuracy of touch operations.

[0003] Existing anti-glare technologies mainly rely on hardware filters or physical coatings on the screen surface to reduce reflected light. However, these methods have the following limitations: First, hardware filters and coatings cannot adapt to different lighting environments and user operation needs, and their anti-glare effect is difficult to guarantee effectively in dynamic lighting environments.

[0004] The existing technical solutions mentioned above have the following drawbacks: most existing anti-glare technologies are static adjustments, which cannot be dynamically changed and optimized in real time under complex environments, affecting the user's viewing experience, and therefore there is room for improvement. Summary of the Invention

[0005] To optimize the user's viewing experience, this application provides a driving control method and system for anti-glare of liquid crystal displays.

[0006] The above-mentioned objective of this application is achieved through the following technical solution: A driving control method for anti-glare in liquid crystal displays, the driving control method for anti-glare in liquid crystal displays comprising: Collect current ambient light data and liquid crystal display content data, wherein the ambient light data includes ambient light intensity, light incident direction and reflection area image, and the liquid crystal display content data includes brightness distribution of each display area; A target light environment feature vector is constructed based on the ambient lighting data and the liquid crystal display content data; Obtain user touch behavior information and construct a touch heat map based on the user touch behavior information, wherein the user touch behavior information includes touch location, duration, frequency and gesture type; The target light environment feature vector and the touch thermal map are input into a pre-trained driving model for analysis to obtain the anti-glare driving strategy for each display sub-region. According to the anti-glare driving strategy, the driving parameters of each sub-region of the liquid crystal display module are adjusted to achieve regional dynamic anti-glare control.

[0007] By adopting the above technical solutions, and by collecting current ambient light data and liquid crystal display content data, the lighting conditions of the display environment and the brightness distribution of the display content can be obtained in real time. This provides accurate input data for subsequent anti-glare control, improving the real-time adaptability of the display effect. By constructing a target light environment feature vector based on the ambient light data and the liquid crystal display content data, multi-dimensional light environment information can be comprehensively analyzed, providing a comprehensive feature description for subsequent driving strategies and enhancing the system's adaptability to complex environments. By acquiring user touch behavior information and constructing a touch heat map based on it, user operation patterns and behavioral habits can be captured, thereby optimizing the impact of touch behavior on the display and improving the accuracy of touch operation. By inputting the target light environment feature vector and the touch heat map into a pre-trained driving model for analysis, the anti-glare strategy of each display sub-area can be dynamically adjusted based on the actual situation, thereby achieving precise control of parameters such as brightness and contrast of the display area, improving the display effect and user experience.

[0008] In one example, this application can be further configured such that: the acquisition of current ambient light data and liquid crystal display content data specifically includes: The current light intensity and incident light direction are collected using an ambient light sensor. The current screen reflection image data of the liquid crystal display module is acquired by a camera device, and based on the screen reflection image data, the high reflection area corresponding to the liquid crystal surface is identified by an image analysis algorithm to generate a reflection area image. Based on the real-time image displayed on the screen, the brightness distribution information of each display area is extracted and normalized to form the brightness distribution information of each display area of ​​the liquid crystal display content.

[0009] By adopting the above technical solutions, the ambient light sensor collects the current light intensity value and the direction of light incidence, enabling real-time acquisition of ambient light intensity and direction data. This provides accurate environmental information for anti-glare control, ensuring that the display effect can be adjusted promptly according to changes in lighting conditions. The camera device collects the current screen reflection image data of the liquid crystal display module, and based on this data, identifies high-reflection areas on the liquid crystal surface. This accurately detects high-reflection areas on the display screen that may affect visual perception, thereby optimizing the anti-glare strategy, reducing interference from reflected light, and improving the user's visual experience. Furthermore, by extracting and normalizing the brightness distribution information of each display area based on the real-time screen image, the brightness information of each display area can be standardized, providing a consistent numerical reference for subsequent anti-glare control, thus ensuring that the displayed content maintains the best visual effect under different lighting conditions.

[0010] In one example, this application can be further configured as follows: the construction of the target light environment feature vector based on the ambient lighting data and the liquid crystal display content data specifically includes: Spatial dimension encoding is performed on the illumination intensity, illumination incident direction and brightness distribution information corresponding to each display area to obtain the initial spatial illumination characteristics; Based on the reflection area image, display areas with reflection intensity exceeding a preset brightness threshold are identified, and regional features of the display areas with reflection intensity exceeding the preset brightness threshold are extracted. The regional features are then fused with the initial spatial illumination features to obtain fused features. The regional features include regional coverage, brightness anomaly distribution information, and edge gradient change features. By combining the trend of ambient light change over a continuous time period, the fused features are modeled in a time series to generate a target light environment feature vector containing spatial attributes and temporal evolution information.

[0011] By employing the above technical solutions, spatial dimension encoding of the light intensity, light incident direction, and brightness distribution information corresponding to each display area enables the effective expression of the ambient lighting characteristics of the display area, thereby providing accurate spatial feature information for subsequent light environment analysis and control strategy formulation. Based on the reflection area image, display areas with reflection intensity exceeding a preset brightness threshold are identified, allowing for precise location of areas with high reflected light intensity on the display screen, thereby optimizing brightness adjustment in these areas and reducing the impact of reflected light on user vision. By fusing the area features with the initial spatial lighting features to obtain fused features, comprehensive analysis of spatial lighting characteristics can be achieved, improving the accuracy and flexibility of the anti-glare effect. By combining the ambient lighting change trend over a continuous time period and performing time-series modeling on the fused features, real-time response to dynamic changes in lighting can be achieved, ensuring that the liquid crystal display module can still provide optimal display performance under changing lighting conditions.

[0012] In one example, this application can be further configured as follows: the step of acquiring user touch behavior information and constructing a touch heat map based on the user touch behavior information specifically includes: Collect user touch location information, touch duration, touch operation frequency, and touch gesture type within a preset time window; Statistical analysis is performed on the touch behavior information corresponding to each display area of ​​the liquid crystal display module, and the initial touch activity value of each display area is calculated. Based on the touch gesture type, the initial touch activity value is adjusted by heat weight to obtain a weighted touch heat value; A two-dimensional spatially distributed touch heat map is constructed based on the weighted touch heat values. The touch heat map is used to indicate the operation priority distribution of different display areas in the liquid crystal display module.

[0013] By adopting the above technical solutions, and by collecting user touch position information, touch duration, touch operation frequency, and touch gesture type within a preset time window, the user's touch behavior patterns can be recorded in detail. This provides data support for personalized adjustments to anti-glare strategies and improves the responsiveness of touch behavior. Statistical analysis of touch behavior information in each display area of ​​the LCD module allows for the calculation of initial touch activity values ​​for each display area, assessing the activity level of each area and providing a basis for subsequent optimization. By applying a heat weighting correction to the initial touch activity value based on the touch gesture type, touch areas can be precisely adjusted according to different touch modes, ensuring that frequently used areas are prioritized for optimization. Furthermore, by constructing a two-dimensional spatially distributed touch heat map based on the weighted touch heat values, different operation priorities can be set for display areas according to dynamic changes in touch behavior, thereby improving the flexibility and accuracy of touch operations and enhancing the user experience.

[0014] In one example, this application can be further configured such that the driving control method for anti-glare liquid crystal display also includes: Construct a training sample set for modeling, which includes historical target light environment feature vectors, historical touch heat maps and corresponding historical anti-glare driving strategy labels; The training sample set is input into the constructed spatiotemporal graph neural network model for training. During the training process, the weights of the deep neural network model are optimized by minimizing the error between the target-driven strategy and the actual performance as the loss function until the model converges, thus obtaining the pre-trained driving model.

[0015] By adopting the above technical solution and constructing a training sample set for modeling, training data containing historical lighting environment data, touch thermal maps, and anti-glare driving strategy labels can be provided, offering high-quality data support for the training of deep learning models and thus improving the model's accuracy and generalization ability. By inputting the training sample set into the constructed spatiotemporal graph neural network model for training, the spatiotemporal graph neural network can simultaneously model in both spatial and temporal dimensions, ensuring the model can handle complex changes in lighting environment and user behavior patterns, thereby enhancing the model's adaptability. By minimizing the error between the target-driven strategy and actual performance as the loss function, model parameters can be continuously optimized during training, improving the model's response speed and accuracy to changes in real-time lighting environment and touch behavior. Through weight optimization during training until the model converges, an accurate and stable anti-glare driving model can be obtained, thus providing an efficient anti-glare control strategy in practical applications.

[0016] In one example, this application can be further configured as follows: inputting the target light environment feature vector and the touch thermal map into a pre-trained driving model for analysis to obtain the anti-glare driving strategy corresponding to each display sub-region, specifically including: The target light environment feature vector and the touch thermal map are preprocessed to obtain preprocessed input data, wherein the data preprocessing includes standardization, normalization and noise reduction. The preprocessed input data is input into the pre-trained driving model. The pre-trained driving model analyzes and displays the spatial relationship between regions through graph neural network structure analysis, and captures the dynamic change trend of ambient light and touch behavior through temporal modeling to obtain analysis results. Based on the analysis results, an anti-glare driving strategy is generated for each display sub-region, wherein the anti-glare driving strategy includes brightness adjustment, contrast adjustment and color temperature correction.

[0017] By employing the above technical solutions, and preprocessing the target light environment feature vector and the touch thermal map, the input data can be standardized, normalized, and denoised to ensure high quality and consistency, thereby improving the model's prediction accuracy and stability. By inputting the preprocessed input data into the pre-trained driving model, graph neural networks can be used to analyze the spatial relationships between display areas, improving the accuracy and flexibility of the anti-glare control strategy. Temporal modeling captures the dynamic trends of ambient light and touch behavior, enabling real-time response to changes in light intensity and user behavior, ensuring optimal display performance in different environments. By generating an anti-glare driving strategy based on the analysis results, the brightness, contrast, and color temperature correction of each display sub-region can be precisely adjusted, providing personalized and efficient display optimization strategies and improving the user's viewing experience.

[0018] In one example, this application can be further configured such that the driving control method for anti-glare liquid crystal display also includes: The ambient lighting data and the user touch behavior information are identified and analyzed to obtain the current usage scenario category; The anti-glare driving strategy is dynamically adjusted based on the current usage scenario category and user operation preference data.

[0019] By adopting the above technical solution, and by identifying and analyzing the ambient lighting data and the user touch behavior information, the current usage scenario category can be accurately identified, helping the system to optimize and adjust according to different environments and user behaviors, thereby improving the adaptability of the display effect. By dynamically adjusting the anti-glare driving strategy according to the current usage scenario category and user operation preference data, the display parameters can be automatically optimized according to different usage scenarios, ensuring the optimization of the anti-glare effect and improving the user's display experience in different scenarios.

[0020] The second objective of this invention is achieved through the following technical solution: A driving control system for anti-glare of liquid crystal displays, the driving control system for anti-glare of liquid crystal displays comprising: The data acquisition module is used to acquire current ambient light data and liquid crystal display content data. The ambient light data includes ambient light intensity, light incidence direction and reflection area image, and the liquid crystal display content data includes the brightness distribution of each display area. A light environment feature vector construction module is used to construct a target light environment feature vector based on the ambient lighting data and the liquid crystal display content data. The touch behavior acquisition module is used to acquire user touch behavior information and construct a touch heat map based on the user touch behavior information. The user touch behavior information includes touch position, duration, frequency and gesture type. The anti-glare strategy analysis module is used to input the target light environment feature vector and the touch thermal map into the pre-trained driving model for analysis, and obtain the anti-glare driving strategy corresponding to each display sub-region. The parameter adjustment module is used to adjust the driving parameters of each sub-region of the liquid crystal display module according to the anti-glare driving strategy, so as to realize regional dynamic anti-glare control.

[0021] By adopting the above technical solutions, and by collecting current ambient light data and liquid crystal display content data, the lighting conditions of the display environment and the brightness distribution of the display content can be obtained in real time. This provides accurate input data for subsequent anti-glare control, improving the real-time adaptability of the display effect. By constructing a target light environment feature vector based on the ambient light data and the liquid crystal display content data, multi-dimensional light environment information can be comprehensively analyzed, providing a comprehensive feature description for subsequent driving strategies and enhancing the system's adaptability to complex environments. By acquiring user touch behavior information and constructing a touch heat map based on it, user operation patterns and behavioral habits can be captured, thereby optimizing the impact of touch behavior on the display and improving the accuracy of touch operation. By inputting the target light environment feature vector and the touch heat map into a pre-trained driving model for analysis, the anti-glare strategy of each display sub-area can be dynamically adjusted based on the actual situation, thereby achieving precise control of parameters such as brightness and contrast of the display area, improving the display effect and user experience.

[0022] In summary, this application includes the following beneficial technical effects: 1. By collecting current ambient light data and LCD display content data, the lighting conditions of the display environment and the brightness distribution of the display content can be obtained in real time, thereby providing accurate input data for subsequent anti-glare control and improving the real-time adaptability of the display effect; by constructing a target light environment feature vector based on the ambient light data and the LCD display content data, multi-dimensional light environment information can be comprehensively analyzed, thereby providing a comprehensive feature description for subsequent driving strategies and enhancing the system's adaptability to complex environments; 2. By acquiring user touch behavior information and constructing a touch heat map based on it, it is possible to capture user operation patterns and behavioral habits, thereby optimizing the impact of touch behavior on the display and improving the accuracy of touch operation; by inputting the target light environment feature vector and the touch heat map into a pre-trained driving model for analysis, it is possible to dynamically adjust the anti-glare strategy of each display sub-area based on the actual situation, thereby achieving precise control of parameters such as brightness and contrast of the display area, improving display effect and user experience. Attached Figure Description

[0023] Figure 1 This is a flowchart of a driving control method for anti-glare of a liquid crystal display according to an embodiment of this application; Figure 2 This is a flowchart illustrating the implementation of step S10 in a driving control method for anti-glare of a liquid crystal display according to an embodiment of this application. Figure 3 This is a flowchart illustrating the implementation of step S20 in a driving control method for anti-glare of a liquid crystal display according to an embodiment of this application. Figure 4This is a flowchart illustrating the implementation of step S30 in a driving control method for anti-glare of a liquid crystal display according to an embodiment of this application. Figure 5 This is a flowchart of step S40 in a driving control method for anti-glare of a liquid crystal display according to an embodiment of this application; Figure 6 This is another implementation flowchart of step S40 in a driving control method for anti-glare of a liquid crystal display in one embodiment of this application; Figure 7 This is another implementation flowchart of a driving control method for anti-glare liquid crystal display in one embodiment of this application; Figure 8 This is a schematic diagram of a driving control system for anti-glare liquid crystal display according to one embodiment of this application. Detailed Implementation

[0024] The present application will be further described in detail below with reference to the accompanying drawings.

[0025] In one embodiment, such as Figure 1 As shown, this application discloses a driving control method for anti-glare in liquid crystal displays, which specifically includes the following steps: S10: Collect current ambient light data and LCD display content data. The ambient light data includes ambient light intensity, light incident direction, and reflection area image. The LCD display content data includes the brightness distribution of each display area.

[0026] Specifically, the system uses an ambient light sensor to collect real-time data on the ambient light intensity and a light sensor to measure the incident direction of the light, providing detailed information about the external lighting. Simultaneously, a camera captures screen reflection data from the LCD module. Based on a reflection image analysis algorithm, it identifies areas on the LCD module surface with strong light reflection and generates a reflection area image. This image reflects the bright areas on the screen caused by light reflection. Furthermore, by extracting and normalizing the brightness information of each display area within the LCD content, the system obtains the brightness distribution information of each display area, ensuring the uniformity and accuracy of the displayed brightness. For example, when the LCD screen is in a strong light environment, such as under direct sunlight, the ambient light sensor accurately detects the increase in light intensity, while the camera captures the reflection areas on the screen, identifying areas with excessive brightness due to light reflection, such as those reflecting sunlight. Based on this data, the system can obtain real-time information on the current light intensity and reflection areas, providing crucial data for subsequent anti-glare control.

[0027] S20: Construct a target light environment feature vector based on ambient lighting data and liquid crystal display content data.

[0028] Specifically, by spatially encoding the collected ambient light intensity, illumination direction, and reflection area image data, preliminary spatial illumination features are generated. Simultaneously, brightness distribution information extracted from the liquid crystal display content is combined with the illumination data, and a target light environment feature vector is obtained through weighted fusion. This target light environment feature vector integrates multiple environmental information into a set of values, thus providing a multi-dimensional light environment feature, offering precise data input for the generation of subsequent driving strategies. Assuming the liquid crystal display module is in an outdoor scene with high ambient light intensity, illumination direction biased to the left, and relatively uniform brightness in the liquid crystal display area, the target light environment feature vector, through weighted fusion of illumination intensity, direction, and brightness distribution, can comprehensively express the current illumination state and display content, providing a comprehensive input value for the anti-glare driving model and guiding subsequent display optimization.

[0029] S30: Obtain user touch behavior information and construct a touch heat map based on the user touch behavior information, wherein the user touch behavior information includes touch location, duration, frequency and gesture type.

[0030] Specifically, the touchscreen's sensors record the location, duration, frequency, and type of user touches. This information is collected and stored in real time. Using this data, the touch activity level of different display areas can be analyzed. Gesture type data helps identify different operation modes and further generates a touch heatmap. This heatmap visually displays the touch frequency and priority of each area in the LCD module, helping to optimize the dynamic adjustment of the display area. For example, when a user frequently clicks on a specific area (such as the menu bar or button area) in an application, the touch location, duration, and frequency are recorded and combined with the gesture type (such as tap, swipe, double-tap, etc.) to construct a touch heatmap for that area. The system can then adjust the display area in real time based on this data, enhancing the brightness and contrast of frequently operated areas to ensure clarity and accuracy.

[0031] S40: Input the target light environment feature vector and touch thermal map into the pre-trained driving model for analysis to obtain the anti-glare driving strategy corresponding to each display sub-region.

[0032] Specifically, the target light environment feature vector and touch heatmap generated from ambient lighting data and touch behavior are input into a pre-trained driving model. This model analyzes the lighting environment and touch behavior data, and combines this with machine learning algorithms to generate an anti-glare driving strategy for each display sub-region. The driving strategy optimizes the display effect based on the specific environmental characteristics and touch activity of the display area, reducing the interference of reflected light on the user's vision while ensuring the accuracy of user touch operations. Personalized anti-glare control schemes are generated for different display areas. For example, in a strong light environment, the target light environment feature vector of a display area may contain high light intensity values, while the touch heatmap of a certain area may show frequent user interaction behaviors, such as prolonged touches. After analysis, the driving model will generate an anti-glare strategy for that area, which may include increasing the brightness and contrast of that area to enhance the accuracy of user operations and reduce glare.

[0033] S50: Adjust the driving parameters of each sub-region of the liquid crystal display module according to the anti-glare driving strategy to achieve regional dynamic anti-glare control.

[0034] Specifically, the anti-glare driving strategy output by the driving model adjusts the driving parameters of each sub-region of the LCD module, including adjusting the display brightness, contrast, and color temperature of each region. Based on the target light environment feature vector and touch thermal map, each display area is precisely controlled to ensure maximum display performance under different ambient lighting conditions. Especially in areas with strong reflected light, brightness is automatically enhanced or contrast is adjusted to maintain high visibility and a comfortable user experience. For example, if the LCD module is in direct sunlight outdoors, and a certain display area has strong reflected light and high touch activity, the driving model may instruct that area to enhance brightness and optimize contrast, making touch operations in that area more accurate while reducing visual interference from strong light reflection.

[0035] By adopting the above technical solutions, and by collecting current ambient light data and liquid crystal display content data, the lighting conditions of the display environment and the brightness distribution of the display content can be obtained in real time. This provides accurate input data for subsequent anti-glare control, improving the real-time adaptability of the display effect. By constructing a target light environment feature vector based on the ambient light data and the liquid crystal display content data, multi-dimensional light environment information can be comprehensively analyzed, providing a comprehensive feature description for subsequent driving strategies and enhancing the system's adaptability to complex environments. By acquiring user touch behavior information and constructing a touch heat map based on it, user operation patterns and behavioral habits can be captured, thereby optimizing the impact of touch behavior on the display and improving the accuracy of touch operation. By inputting the target light environment feature vector and the touch heat map into a pre-trained driving model for analysis, the anti-glare strategy of each display sub-area can be dynamically adjusted based on the actual situation, thereby achieving precise control of parameters such as brightness and contrast of the display area, improving the display effect and user experience.

[0036] In one embodiment, such as Figure 2 As shown, in step S10, the current ambient light data and the liquid crystal display content data are collected, specifically including: S11: Collect the current light intensity value and the incident direction of light through an ambient light sensor.

[0037] Specifically, an ambient light sensor installed near the LCD module collects real-time data on the ambient light intensity. The sensor can detect light of different wavelengths and, based on light intensity and angle information, captures the incident direction of the light, providing data on ambient light intensity and direction. This data is used for subsequent display parameter adjustments to ensure optimized display performance under different lighting conditions. For example, in direct sunlight outdoors, the ambient light sensor will detect high light intensity, and the incident direction of the light may be biased towards the upper right. In this case, the system will adjust the display brightness based on this data, protecting the display area from excessive sunlight interference and preventing glare from affecting visual performance.

[0038] S12: Acquire the current screen reflection image data of the liquid crystal display module through a camera device, and based on the screen reflection image data, identify the high reflection area corresponding to the liquid crystal surface through an image analysis algorithm to generate a reflection area image.

[0039] Specifically, the camera captures images of the LCD module's screen and processes these images using image analysis algorithms to identify reflective areas on the display. These reflective areas are typically bright areas on the screen surface under strong light. The image analysis algorithm marks these areas by detecting brightness changes in the image, generating a reflective area image. This image shows the locations of areas in the LCD module that may cause glare, providing a spatial layout of the reflective areas. For example, in the central area of ​​the LCD module screen, sunlight causes reflective areas on the display. The image analysis algorithm identifies these areas and generates a reflective area image. The system can then adjust the brightness of these areas based on this reflective area image to reduce the impact of reflected light.

[0040] S13: Based on the real-time image displayed on the screen, extract the brightness distribution information of each display area and normalize it to form the brightness distribution information of each display area of ​​the liquid crystal display content.

[0041] Specifically, by capturing the screen display image in real time, brightness information for each display area is extracted. This brightness data represents the brightness of the displayed content in each area. Then, the brightness distribution of each area is normalized, adjusting the brightness values ​​to a uniform standard range, allowing for comparison and integration of brightness data from different areas. This brightness distribution information can be used for subsequent anti-glare strategy calculations to ensure consistent brightness of the LCD display under different ambient lighting conditions and optimize the user experience. For example, assuming the LCD module displays a text area and an image area, the system extracts the brightness information for both areas separately. After normalization, the brightness values ​​of the text and image areas are adjusted to the same standard range, ensuring that the display effect of these two areas does not differ due to changes in lighting conditions.

[0042] In one embodiment, such as Figure 3 As shown, in step S20, which involves constructing a target light environment feature vector based on ambient lighting data and liquid crystal display content data, the specific steps include: S21: Spatial dimension encoding is performed on the light intensity, light incident direction and brightness distribution information corresponding to each display area to obtain the initial spatial lighting characteristics.

[0043] Specifically, the illuminance, incident light direction, and brightness distribution information of each display area are converted into spatial dimension codes. By quantifying the illuminance of each display area and combining it with the spatial location of the light direction and brightness distribution, spatial illumination features related to the display area are generated. These features reflect the light environment of the display area and its potential impact on the displayed content, providing spatial dimension information support for subsequent anti-glare control strategies. Assuming there are multiple display areas on the LCD module screen, one area has a high illuminance under strong light illumination, while another area has a low illuminance under weak light illumination, the system converts the illuminance, incident light direction, and brightness distribution information of these two areas into corresponding spatial illumination features through spatial dimension coding, generating different initial spatial illumination features for each area.

[0044] S22: Based on the reflection area image, identify the display area where the reflection intensity exceeds the preset brightness threshold, extract the regional features of the display area where the reflection intensity exceeds the preset brightness threshold, and fuse the regional features with the initial spatial illumination features to obtain the fused features. The regional features include regional coverage, brightness anomaly distribution information and edge gradient change features.

[0045] Specifically, image analysis algorithms identify display areas where the reflection intensity exceeds a preset brightness threshold based on the reflection area image. Regional features of these areas are extracted, including area coverage (the proportion of the reflective area in the overall display area), abnormal brightness distribution information (abnormal light distribution in the display area), and edge gradient change features (changes in reflected light at the edges). These regional features are then fused with previously obtained initial spatial illumination features to obtain a comprehensive fused feature, providing a complete description of the display area under the current lighting environment. For example, if a certain area of ​​the display screen produces strong reflection under sunlight, and the image analysis algorithm identifies that the reflection intensity of this area exceeds a preset brightness threshold, by extracting regional features such as a 30% reflective area coverage, significant fluctuations in abnormal brightness distribution, and obvious edge gradient changes, the system combines these features with the initial spatial illumination features to generate a fused feature for that area, allowing for further adjustments to the anti-glare strategy.

[0046] S23: Combine the trend of ambient light change over a continuous time period to perform time series modeling on the fused features, and generate a target light environment feature vector containing spatial attributes and temporal evolution information.

[0047] Specifically, by combining the changing trends of ambient light over a continuous time period, time-series modeling is performed on the fused features. This step, by capturing the dynamic changes in ambient light intensity, incident direction, and reflection area images over time, can predict the impact of future lighting conditions on the display area. The generated target light environment feature vector not only contains spatial attributes but also incorporates temporal evolution information, enabling the anti-glare system to dynamically optimize the display effect based on historical trends and future changes in lighting. For example, if the LCD module experiences sunlight exposure of varying intensities from morning to noon within a certain time period, the system can generate a light environment feature vector for that period based on previous lighting data and reflection area images, and combine it with future lighting trends to form a target light environment feature vector containing both spatial attributes and temporal evolution information. This allows the system to predict and adapt to future lighting changes, optimizing the display effect.

[0048] In one embodiment, such as Figure 4 As shown, in step S30, user touch behavior information is obtained, and a touch heat map is constructed based on the user touch behavior information, specifically including: S31: Collect the user's touch position information, touch duration, touch operation frequency, and touch gesture type within a preset time window.

[0049] Specifically, the touchscreen's sensor system collects real-time data on the user's touch location, duration, frequency, and gesture type within a preset time window. This information includes the specific location of the touch (e.g., the coordinates of the touch area), the duration of the touch (how long the touch point remains), the frequency of the touch (the number of touches per unit time), and different gesture types (e.g., single-finger tap, two-finger zoom, swipe, etc.). This data provides detailed raw data for subsequent touch behavior analysis and heatmap construction. For example, if a user frequently touches the left side of the LCD screen within 10 seconds, with each touch lasting 2 seconds and the gesture being a single-finger tap, the system will record this data in real-time. In the subsequent touch heatmap construction, the left side will be marked as a high-frequency touch area, and the system will generate touch behavior data for that area, taking into account the duration and gesture type of each touch event.

[0050] S32: Perform statistical analysis on the touch behavior information corresponding to each display area of ​​the liquid crystal display module, and calculate the initial touch activity value of each display area.

[0051] Specifically, the collected touch location information, touch duration, frequency, and gesture type are categorized and summarized by display area to calculate the touch activity value for each display area. The touch activity value reflects the frequency, duration, and intensity of user touches in that area. It is typically calculated using a weighted average to determine the impact of each touch behavior, ensuring the activity value accurately reflects the actual usage of each area. Areas with high activity usually correspond to more frequent user operations and therefore require priority adjustment to improve display quality and touch accuracy. For example, if a user touches the upper left corner 5 times in 10 seconds, each touch lasting 2 seconds; the lower right corner 2 times, each touch lasting 5 seconds; and the middle area 3 times, each touch lasting 3 seconds, the system calculates the touch activity value for each area based on this data. The upper left corner has a higher activity value, while the lower right corner has a lower activity value.

[0052] S33: Adjust the initial touch activity value based on the touch gesture type to obtain a weighted touch heat value.

[0053] Specifically, the initial touch activity value of each area is weighted according to different touch gesture types (such as single-finger tap, two-finger swipe, long press, etc.). Different gesture types have different importance in user interaction, and the system weights the initial activity value based on the degree of influence of these gestures. For example, a two-finger swipe or long press may indicate that the user has a higher demand for that area, and therefore gives it a higher weight. The final weighted touch heat value more accurately reflects the actual operation priority of each display area. Suppose that the user performs a single-finger tap 5 times in the middle area of ​​the LCD module, each lasting 2 seconds, and performs a two-finger swipe 3 times in the upper right corner area, each lasting 3 seconds. Because the two-finger swipe operation has a higher priority, the system will weight the activity value of the upper right corner area, making its weighted touch heat value higher than that of the left area, thus reflecting the importance of that area to the user's operation.

[0054] S34: Construct a two-dimensional spatially distributed touch heat map based on weighted touch heat values. The touch heat map is used to indicate the operation priority distribution of different display areas in the liquid crystal display module.

[0055] Specifically, a two-dimensional spatial distribution touch heat map of the liquid crystal display module is constructed based on the calculated weighted touch heat values. The touch heat map generates a visual image by combining the weighted touch heat values ​​with the spatial location of the display area, indicating the operation priority of different areas. For example, areas with frequent touches and longer durations are marked in red (high priority), while areas with fewer touches are marked in blue (low priority). This heat map helps optimize the display effect and touch response of the display area, making the user experience smoother and more precise. Assuming the system generates a touch heat map based on the weighted touch heat values, the upper left corner area is marked in red due to frequent touch operations, the middle area is marked in orange, and the lower right corner area is marked in blue due to fewer operations. In subsequent anti-glare control, the red area may receive more brightness optimization, while the blue area can receive less adjustment, thus ensuring that each area provides the best display effect and touch accuracy under different lighting conditions.

[0056] In one embodiment, such as Figure 5 As shown, the driving control method for anti-glare liquid crystal display further includes: S401: Construct a training sample set for modeling, which includes historical target light environment feature vectors, historical touch heat maps, and corresponding historical anti-glare driving strategy labels.

[0057] Specifically, firstly, historical data of the liquid crystal display module under different ambient lighting conditions is collected, including historical target light environment feature vectors such as light intensity, light direction, and reflection area images; historical touch thermal maps; data recording user touch positions, frequencies, durations, and gesture types; and corresponding historical anti-glare driving strategy labels, such as brightness adjustment, contrast optimization, and color temperature correction control strategies for the display area. This data will be labeled according to different display environments and user behaviors and organized into a training sample set for subsequent model training. The training sample set will serve as input data for the spatiotemporal graph neural network, helping the model learn the mapping relationship from the light environment and touch behavior to anti-glare strategies. For example, assuming a summer outdoor scene with high reflection intensity of the liquid crystal display module, and the touch thermal map showing frequent touches on a certain display area, the system records the light environment characteristics, touch behavior data, and the actual anti-glare strategies adopted in this scene (such as brightness enhancement and contrast adjustment). This data will become part of the training sample set. Similar data will cover different scenarios and user operations to train the model, enabling it to make accurate anti-glare adjustments under various lighting conditions.

[0058] S402: Input the training sample set into the constructed spatiotemporal graph neural network model for training. During the training process, optimize the weights of the deep neural network model by minimizing the error between the target-driven strategy and the actual performance as the loss function until the model converges, and obtain the pre-trained driving model.

[0059] Specifically, firstly, a spatiotemporal graph neural network model is constructed, employing a graph convolutional network as its basic structure and combining it with a long short-term memory network to process time-series data. The spatiotemporal graph neural network learns the spatial relationships between display areas through graph convolutional operations, while the LSTM module is responsible for processing and capturing the temporal evolution features of ambient lighting and touch behavior data. The model's input consists of two parts: historical target lighting environment feature vectors, including data such as light intensity, light direction, and reflection area images; and historical touch heatmaps, including touch location, frequency, and duration information. These data are input into the graph neural network, processed through multiple graph convolutional layers to progressively extract spatial features, and further learned in the LSTM module to learn the temporal dependencies of the data, ultimately predicting an anti-glare driving strategy suitable for the current lighting environment and touch behavior, such as brightness adjustment, contrast adjustment, and color temperature correction. During training, the network weights are optimized by minimizing the error between the target anti-glare strategy and the actual performance as the loss function. The loss function primarily measures the difference between the predicted anti-glare strategy and actual user feedback, such as the degree of improvement in display effect and the accuracy of user touch operations. Using backpropagation and gradient descent algorithms, the model's weights are continuously updated in each training iteration until the loss function converges to its minimum, indicating that the model has learned the relationship between a suitable anti-glare strategy and lighting and touch behavior. In one embodiment, such as Figure 6 As shown, in step S40, the target light environment feature vector and touch thermal map are input into a pre-trained driving model for analysis to obtain the anti-glare driving strategy corresponding to each display sub-region, specifically including: S41: Perform data preprocessing on the target light environment feature vector and touch thermal map to obtain preprocessed input data. The data preprocessing includes standardization, normalization and noise reduction.

[0060] Specifically, the target light environment feature vector and touch heatmap are preprocessed. First, standardization is performed, adjusting the value of each input feature to a uniform range (e.g., between 0 and 1) to ensure consistent magnitude across all input features and prevent any single feature from excessively influencing the model. Second, normalization is performed, adjusting the mean to 0 and the standard deviation to 1, ensuring consistent data distribution and facilitating faster model convergence. Finally, noise reduction is applied to remove outliers or noise, such as sudden, atypical touch behaviors or extreme ambient lighting conditions, ensuring data quality, reducing unnecessary interference, and improving the accuracy of subsequent analysis. For example, when the LCD module is touched under different lighting conditions, some areas may have higher ambient light intensity, and some areas in the touch heatmap may contain occasional abnormal touch data (e.g., accidental touches). Standardization and normalization transform all data to the same scale, and noise reduction removes inaccurate outliers, ensuring more accurate and consistent data display for each region during subsequent analysis.

[0061] S42: Input the pre-processed input data into the pre-trained driving model. The pre-trained driving model analyzes and displays the spatial relationship between regions through graph neural network structure analysis, and captures the dynamic change trend of ambient light and touch behavior through temporal modeling to obtain the analysis results.

[0062] Specifically, the preprocessed input data (including the target light environment feature vector and touch thermal map) is fed into a pre-trained driving model. This model employs a graph neural network structure, which can effectively analyze the spatial relationships between display areas, such as the influence of illumination between display areas and the interactivity of touch operations. Simultaneously, it combines temporal modeling techniques to capture the dynamic trends of ambient light and touch behavior over time. Through graph neural network analysis, the model can understand the mutual influence between display areas, and through temporal modeling, it can capture the temporal dependency between illumination changes and touch behavior. Finally, after analysis and processing by the network, an anti-glare driving strategy corresponding to each display sub-region is generated. For example, when certain areas of the LCD module are exposed to strong sunlight, the system uses a graph neural network to analyze the light intensity and the spatial relationship between display areas, identifying which areas need brightness adjustment. Simultaneously, the LSTM model analyzes the changing trends of ambient light over a period of time, combines this with the user's touch behavior, and predicts future changes in illumination and touch patterns, thereby generating a personalized anti-glare strategy for each region.

[0063] S43: Based on the analysis results, generate an anti-glare driving strategy for each display sub-region, wherein the anti-glare driving strategy includes brightness adjustment, contrast adjustment and color temperature correction.

[0064] Specifically, based on the analysis results generated by the driving model, corresponding anti-glare driving strategies are formulated for each display sub-region. These strategies include: brightness adjustment, which increases or decreases the brightness of the display area to ensure users can clearly see the displayed content even in strong light environments; contrast adjustment, which optimizes the contrast of the display area to make images and text more vivid and maintain clarity even in complex lighting conditions; and color temperature correction, which adjusts the color temperature of the display area to ensure natural colors and reduce color shift under varying lighting conditions. These anti-glare driving strategies are implemented separately for each display sub-region to achieve optimal display effects and user experience. For example, under strong sunlight, the upper left area of ​​the LCD module is subject to high reflection. After analysis, the system generates an anti-glare strategy for this area, increasing brightness and adjusting contrast, and performing color temperature correction in this area to make the image display more vivid and clear, allowing for more precise touch operation. In areas with less reflection, the system may only need to adjust contrast or color temperature, thus avoiding unnecessary brightness adjustments and improving the overall display effect.

[0065] In one embodiment, such as Figure 7 As shown, the driving control method for anti-glare liquid crystal display further includes: S60: Identify and analyze ambient lighting data and user touch behavior information to obtain the current usage scenario category.

[0066] Specifically, by analyzing collected ambient lighting data, such as light intensity, light direction, and reflection area images, as well as user touch behavior information, such as touch location, duration, frequency, and gesture type, the system can identify the current usage scenario category. Through pattern recognition algorithms, combined with historical and real-time data, the system can automatically determine whether the current scene is indoors or outdoors, whether the lighting environment is strong light or low light, and whether the user's operation is simple touch or complex. These features are then mapped to predefined usage scenario categories, such as "outdoor strong light environment," "indoor low light environment," and "driving mode." This information helps in adjusting anti-glare strategies to better adapt the display effect to the actual usage scenario. For example, suppose a user is using a mobile phone interface with an LCD display module in a bright outdoor environment with high ambient light intensity, and the user frequently touches the upper left corner area. Through analysis, the system identifies this usage scenario as an "outdoor strong light environment" and the user's operating habits as frequently clicking a certain area. The system will then generate a corresponding anti-glare adjustment strategy for that area based on this scenario category.

[0067] S70: Dynamically adjust the anti-glare driving strategy based on the current usage scenario category and user operation preference data.

[0068] Specifically, based on the identified current usage scenario category, such as outdoor bright light, indoor, and night mode, as well as user operation preference data, such as frequently touched areas and gesture types, the system dynamically adjusts the anti-glare driving strategy. For different usage scenarios, the system optimizes parameters such as display brightness, contrast, and color temperature. For example, in an "outdoor bright light environment," the system may enhance display brightness and contrast to improve display clarity; in "night mode," the system may reduce eye fatigue by reducing brightness and adjusting color temperature. Furthermore, based on user touch preference data, the system also makes personalized adjustments according to the activity level of the touch area and gesture type, improving the touch responsiveness and display effect of the display area to ensure the best user experience in different environments and operating modes. For example, in an "indoor low light environment," the brightness of the LCD module can be appropriately reduced to reduce the interference of reflected light on the user's vision, while increasing contrast to ensure clarity. In "outdoor high-light environment", the system will enhance the brightness of the display area and dynamically adjust the brightness and contrast of the area that the user frequently operates on the screen to improve the accuracy of the user's touch and reduce visual interference caused by light reflection.

[0069] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0070] In one embodiment, a driving control system for anti-glare of a liquid crystal display is provided, which corresponds one-to-one with the driving control method for anti-glare of a liquid crystal display described in the above embodiment. For example... Figure 8 As shown, the anti-glare driving control system for a liquid crystal display includes a data acquisition module, a light environment feature vector construction module, a touch behavior acquisition module, an anti-glare strategy analysis module, and a parameter adjustment module. Detailed descriptions of each functional module are as follows: The data acquisition module is used to collect current ambient light data and LCD display content data. The ambient light data includes ambient light intensity, light incidence direction and reflection area image, and the LCD display content data includes the brightness distribution of each display area. The light environment feature vector construction module is used to construct the target light environment feature vector based on ambient lighting data and LCD display content data. The touch behavior acquisition module is used to acquire user touch behavior information and construct a touch heat map based on the user touch behavior information. The user touch behavior information includes touch location, duration, frequency and gesture type. The anti-glare strategy analysis module is used to input the target light environment feature vector and touch thermal map into the pre-trained driving model for analysis, and obtain the anti-glare driving strategy corresponding to each display sub-region. The parameter adjustment module is used to adjust the driving parameters of each sub-region of the liquid crystal display module according to the anti-glare driving strategy, so as to realize regional dynamic anti-glare control.

[0071] Optionally, the data acquisition module includes: The optical sensing acquisition submodule is used to acquire the current light intensity value and the light incident direction through an ambient light sensor; The camera acquisition submodule is used to acquire the current screen reflection image data of the liquid crystal display module through a camera device, and based on the screen reflection image data, to identify the high reflection area corresponding to the liquid crystal surface through an image analysis algorithm and generate a reflection area image. The extraction submodule is used to extract the brightness distribution information of each display area based on the real-time image displayed on the screen and normalize it to form the brightness distribution information of each display area of ​​the liquid crystal display content.

[0072] Optionally, the light environment feature vector construction module includes: The encoding submodule is used to spatially encode the light intensity, light incident direction and brightness distribution information of each display area to obtain the initial spatial lighting features. The fusion submodule is used to identify display areas with reflection intensity exceeding a preset brightness threshold based on the reflection area image, extract the regional features of the display areas with reflection intensity exceeding the preset brightness threshold, and fuse the regional features with the initial spatial illumination features to obtain fused features. The regional features include regional coverage, brightness anomaly distribution information, and edge gradient change features. The modeling submodule is used to combine the ambient light change trend over a continuous time period to perform time series modeling on the fused features, generating a target light environment feature vector that includes spatial attributes and temporal evolution information.

[0073] Optionally, the touch behavior acquisition module includes: The touch capture submodule is used to collect information on the user's touch position, touch duration, touch operation frequency, and touch gesture type within a preset time window; The statistical analysis submodule is used to perform statistical analysis on the touch behavior information corresponding to each display area of ​​the LCD module and calculate the initial touch activity value of each display area. The correction submodule is used to correct the initial touch activity value based on the touch gesture type to obtain a weighted touch heat value. The touch heat map construction submodule is used to construct a two-dimensional spatial distribution touch heat map based on weighted touch heat values. The touch heat map is used to indicate the operation priority distribution of different display areas in the liquid crystal display module.

[0074] Optionally, the drive control system for anti-glare liquid crystal display also includes: The sample construction module is used to build a training sample set for modeling. The training sample set includes historical target light environment feature vectors, historical touch heat maps and corresponding historical anti-glare driving strategy labels. The model training module is used to input the training sample set into the constructed spatiotemporal graph neural network model for training. During the training process, the weights of the deep neural network model are optimized by minimizing the error between the target-driven strategy and the actual performance as the loss function until the model converges, thus obtaining the pre-trained driving model.

[0075] Optional, the anti-glare strategy analysis module includes: The preprocessing submodule is used to preprocess the target light environment feature vector and touch thermal map to obtain preprocessed input data. The data preprocessing includes standardization, normalization and noise reduction. The model analysis submodule is used to input the pre-processed input data into the pre-trained driving model. The pre-trained driving model uses graph neural network structure analysis to display the spatial relationship between regions and uses temporal modeling to capture the dynamic change trend of ambient lighting and touch behavior to obtain analysis results. The strategy generation submodule is used to generate an anti-glare driving strategy for each display sub-region based on the analysis results. The anti-glare driving strategy includes brightness adjustment, contrast adjustment, and color temperature correction.

[0076] Optionally, the drive control system for anti-glare liquid crystal display also includes: The scene recognition module is used to identify and analyze ambient lighting data and user touch behavior information to obtain the current usage scene category; The adjustment module is used to dynamically adjust the anti-glare driving strategy based on the current usage scenario category and user operation preference data.

[0077] Specific limitations regarding the driving control system for anti-glare liquid crystal displays can be found in the above description of the driving control method for anti-glare liquid crystal displays, and will not be repeated here. Each module in the aforementioned driving control system for anti-glare liquid crystal displays can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0078] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.

[0079] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application 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. Such 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 this application, and should all be included within the protection scope of this application.

Claims

1. A method for driving and controlling a liquid crystal display to prevent glare, characterized by, The liquid crystal display anti-glare driving control method comprises the steps of: Collecting current ambient light data and liquid crystal display content data, wherein the ambient light data comprises ambient light intensity, light incidence direction and reflection area image, and the liquid crystal display content data comprises brightness distribution of each display area; Based on the ambient light data and the liquid crystal display content data, a target light environment feature vector is constructed; User touch behavior information is obtained, and a touch heat map is constructed based on the user touch behavior information, wherein the user touch behavior information comprises touch position, duration, frequency and gesture type; The target light environment feature vector and the touch heat map are input into a pre-trained driving model for analysis to obtain an anti-glare driving strategy corresponding to each display sub-area of the liquid crystal display module; According to the anti-glare driving strategy, the driving parameters of each sub-area of the liquid crystal display module are adjusted to realize dynamic anti-glare control in different areas.

2. The driving control method for anti-glare liquid crystal display according to claim 1, characterized in that, The collection of current ambient light data and liquid crystal display content data specifically comprises: The current light intensity value and light incidence direction are collected by an ambient light sensor; The current screen reflection image data of the liquid crystal display module is collected by a camera device, and based on the screen reflection image data, a high reflection area corresponding to the liquid crystal surface is identified by an image analysis algorithm to generate a reflection area image; Based on the real-time display image of the screen, the brightness distribution information of each display area is extracted and normalized to form the brightness distribution information of each display area of the liquid crystal display content.

3. The method of claim 1, wherein the method is a method of driving and controlling a liquid crystal display device for preventing glare. The construction of the target light environment feature vector based on the ambient light data and the liquid crystal display content data specifically comprises: The light intensity, light incidence direction and brightness distribution information corresponding to each display area are spatially dimensionally encoded to obtain an initial spatial light feature; Based on the reflection area image, display areas with reflection intensity exceeding a preset brightness threshold are identified, the area features of the display areas with reflection intensity exceeding the preset brightness threshold are extracted, and the area features and the initial spatial light feature are fused to obtain a fused feature, wherein the area features comprise area coverage, brightness abnormal distribution information and edge gradient change feature; The fused feature is time series modeled in combination with the ambient light change trend in a continuous time period to generate a target light environment feature vector containing spatial attributes and time evolution information.

4. The method of claim 1, wherein the method is a method of driving and controlling a liquid crystal display device for preventing glare. The acquisition of user touch behavior information and the construction of a touch heat map based on the user touch behavior information specifically comprise: Touch position information, touch duration, touch operation frequency and touch gesture type of the user within a preset time window are collected; The corresponding touch behavior information of each display area of the liquid crystal display module is statistically analyzed to calculate the initial touch activity value of each display area; The initial touch activity value is corrected by a heat weight based on the touch gesture type to obtain a weighted touch heat value; A two-dimensional spatial distribution touch heat map is constructed based on the weighted touch heat value, and the touch heat map is used to indicate the operation priority distribution of different display areas of the liquid crystal display module.

5. The method of claim 1, wherein the method is a method of driving and controlling a liquid crystal display device for preventing glare. The liquid crystal display anti-glare driving control method further comprises: a training sample set for modeling is constructed, the training sample set comprising a historical target light environment feature vector, a historical touch heat map, and a corresponding historical anti-glare driving strategy label; the training sample set is input into the constructed spatio-temporal graph neural network model for training, and in the training process, the error between the target driving strategy and the actual performance is minimized as a loss function to optimize the weights of the deep neural network model until the model converges, obtaining the pre-trained driving model.

6. The method of claim 1, wherein the method is a method of driving and controlling a liquid crystal display device for preventing glare. The target light environment feature vector and the touch heat map are input into the pre-trained driving model for analysis to obtain an anti-glare driving strategy corresponding to each display sub-region, specifically comprising: data preprocessing is performed on the target light environment feature vector and the touch heat map to obtain preprocessed input data, wherein the data preprocessing comprises standardization, normalization, and noise reduction processing; the preprocessed input data is input into the pre-trained driving model, the pre-trained driving model analyzes the spatial relationship between display regions through a graph neural network structure, captures the dynamic change trend of environmental light and touch behavior through time series modeling, and obtains an analysis result; according to the analysis result, an anti-glare driving strategy corresponding to each display sub-region is generated, wherein the anti-glare driving strategy comprises brightness adjustment, contrast adjustment, and color temperature correction.

7. The method of claim 1, wherein the method is a method of driving and controlling a liquid crystal display device for preventing glare. The liquid crystal display anti-glare driving control method further comprises: the environmental light data and the user touch behavior information are identified and analyzed to obtain a current use scenario category; the anti-glare driving strategy is dynamically adjusted according to the current use scenario category and user operation preference data.

8. A drive control system for liquid crystal display anti-glare, characterized by, The liquid crystal display anti-glare driving control system comprises: a data acquisition module for acquiring current environmental light data and liquid crystal display content data, wherein the environmental light data comprises environmental light intensity, light incidence direction, and reflection area image, and the liquid crystal display content data comprises brightness distribution of each display region; a light environment feature vector construction module for constructing a target light environment feature vector based on the environmental light data and the liquid crystal display content data; a touch behavior acquisition module for acquiring user touch behavior information and constructing a touch heat map based on the user touch behavior information, wherein the user touch behavior information comprises touch position, duration, frequency, and gesture type; an anti-glare strategy analysis module for inputting the target light environment feature vector and the touch heat map into a pre-trained driving model for analysis to obtain an anti-glare driving strategy corresponding to each display sub-region; a parameter adjustment module for adjusting driving parameters of each sub-region of a liquid crystal display module according to the anti-glare driving strategy to realize dynamic anti-glare control in sub-regions.

Images