A global dynamic optimization system for ultra-high-definition glass-based displays

Abstract

The present invention discloses a global dynamic optimization system for an ultra-high-definition glass-based display screen. The system operation process specifically includes the following steps: obtaining a real-time status data set of the display screen; generating an initial optimization parameter set based on a preset optimization strategy and a user behavior model; capturing user interaction signals and environmental change signals in real time; generating a dynamic correction coefficient set based on the user interaction signals and environmental change signals; performing global parameter fusion based on the initial optimization parameter set and the dynamic correction coefficient set to generate a target optimization instruction set; and generating an optimization effect evaluation table based on the optimization effect feedback. The present invention has the following advantages and effects: achieving collaborative optimization and thermal balance of global display parameters. Through multi-dimensional data fusion and collaborative calculation of global parameters, the system can balance the requirements of visual experience enhancement and thermal diffusion suppression in real time. While enhancing local contrast and optimizing color reproduction, it actively suppresses screen temperature rise through thermal balance constraints.

Description

Technical Field

[0001] The present invention relates to the field of display technology, and in particular to a global dynamic optimization system for an ultra-high-definition glass-based display screen. Background Art

[0002] Current dynamic optimization technologies for ultra-high-definition glass-based displays generally face a core bottleneck: Under the real-time coupling of multi-dimensional dynamic factors, such as user interaction, ambient light variations, and localized heat loads, existing systems struggle to achieve coordinated optimization of global display parameters and thermal balance. Traditional approaches typically employ independent closed-loop control strategies, such as global brightness adjustment based on ambient light, fixed-zone backlight control, or static color temperature compensation. While these solutions can partially improve display quality in isolated scenarios, they cannot address the complex interplay between localized heat accumulation caused by user gaze shifts, touch operations, and dynamic ambient light interference. Especially under prolonged high-load scenarios, localized screen temperature rise often conflicts with the need for display parameter adjustment: simply increasing local brightness leads to increased heat diffusion, while forced temperature control strategies compromise display quality. This limitation of decoupled parameter optimization makes it difficult for existing systems to simultaneously meet the requirements for visual consistency, color reproduction accuracy, and thermal stability in dynamic scenarios, becoming a key technical barrier to further improving the performance of ultra-high-definition glass-based displays. Summary of the Invention

[0003] The purpose of the present invention is to provide a global dynamic optimization system for an ultra-high-definition glass-based display screen to solve the problems raised in the background technology.

[0004] The above technical objectives of the present invention are achieved through the following technical solutions:

[0005] A global dynamic optimization system for an ultra-high-definition glass-based display screen, wherein the system operation process specifically includes the following steps:

[0006] S100, obtaining a real-time status data set of a display screen; wherein the real-time status data set includes brightness distribution data, color temperature gradient data, ambient light intensity data, and screen surface temperature data;

[0007] S200, generating an initial set of optimization parameters based on a preset optimization strategy and a user behavior model; wherein the preset optimization strategy includes a dynamic contrast enhancement rule, a color gamut adaptive matching rule, and a thermal balance constraint rule; the user behavior model is trained using historical operation data; and the initial set of optimization parameters includes a partition backlight intensity parameter, a pixel drive voltage parameter, and a color compensation coefficient matrix;

[0008] S300, capturing user interaction signals and environmental change signals in real time; wherein the user interaction signals include touch trajectory data, gaze area coordinates, and operation response duration, and the environmental change signals are synchronously collected by an ambient light sensor and an infrared thermal array;

[0009] S400, generating a dynamic correction coefficient set according to the user interaction signal and the environment change signal; wherein the dynamic correction coefficient set includes a brightness attenuation compensation coefficient, a color temperature offset correction factor, and a heat diffusion suppression parameter;

[0010] S500, performing global parameter fusion based on the initial optimization parameter set and the dynamic correction coefficient set to generate a target optimization instruction set; wherein the global parameter fusion includes weight superposition of backlight partitions, iterative adjustment of the gamma value of the pixel matrix, and color space remapping processing;

[0011] S600: Feedback an optimization effect evaluation table based on the optimization effect.

[0012] By adopting the above technical solution and establishing a global display state perception system, it is possible to integrate multi-dimensional data such as brightness distribution, color temperature gradient, ambient light intensity, and screen surface temperature in real time to form a comprehensive and dynamically updated profile of the display's operation. This multimodal data fusion mechanism overcomes the limitations of traditional optimization solutions that rely solely on single-dimensional parameters, enabling the system to accurately identify areas of conflict between display quality and thermal stability. For example, in scenarios where strong ambient light and high screen temperature coexist, traditional methods often lead to parameter imbalances due to isolated adjustments of brightness or color temperature. However, by coupling and analyzing ambient light intensity and screen temperature data, this system can intelligently balance the need for brightness enhancement with the risk of thermal diffusion, thereby maintaining the visual experience while ensuring hardware safety. The generation of the initial optimization parameter set combines a preset optimization strategy with a user behavior model, adhering to the basic rules of display technology while incorporating user personalized preferences, achieving an upgrade from static rules to dynamic adaptation. The multi-level control variable design of the partitioned backlight intensity parameters, pixel drive voltage parameters, and color compensation coefficient matrix ensures comprehensive coverage of the display effect and avoids optimization blind spots caused by missing parameters. A real-time capture mechanism for user interaction signals and environmental change signals is also provided. , further giving the system dynamic response capabilities, so that the display parameters can be quickly adjusted following the instantaneous changes in user behavior and environmental conditions, effectively solving the problem of display effect degradation caused by response lag in traditional fixed strategies; in the process of global parameter fusion, the weight superposition of backlight partitions, iterative adjustment of the gamma value of the pixel matrix and the remapping of the color space form a collaborative optimization network, which eliminates the mutual interference between backlight, color and temperature adjustment through multi-parameter joint calculation. For example, when increasing the local backlight intensity, the system synchronously adjusts the gamma value of the corresponding area to compensate for the color deviation that may be caused by the brightness jump, and at the same time suppresses the heat diffusion. The control parameters limit the temperature rise rate of the area, thereby achieving dual optimization of display quality and thermal management; the generation of the target optimization instruction set converts abstract algorithm parameters into hardware executable instructions, ensuring the efficient connection between the software layer optimization logic and the physical layer driver equipment, and significantly reducing the system response delay; the introduction of the optimization effect evaluation table builds a closed-loop feedback mechanism. By continuously monitoring core indicators such as brightness uniformity error, color temperature deviation value and temperature rise suppression efficiency, the system can dynamically correct the parameter weights of the preset strategy and user model, forming self-diagnosis and continuous iterative optimization capabilities, and ensuring the long-term stability and reliability of the display performance.

[0013] Further configuration is that the S200 specifically includes the following steps:

[0014] S210: Segment the brightness distribution data into regions according to the dynamic contrast enhancement rule, calculate the local contrast gain value of each region, and generate a backlight intensity dynamic allocation table, specifically including:

[0015] The brightness distribution data in the real-time status dataset is divided into multiple backlight partitions according to a preset grid. The division of each partition is dynamically adjusted based on the gaze area coordinate distribution in the user behavior model.

[0016] For each backlight partition, extract the mean and standard deviation of its brightness distribution data, and calculate the local contrast gain value by combining the multi-directional incident light intensity in the ambient light intensity data:

[0017] According to the heat accumulation value of the corresponding partition in the screen surface temperature data, the local contrast gain value is dynamically attenuated and compensated to generate a backlight intensity dynamic allocation table;

[0018] S220: Based on the color gamut adaptive matching rule, perform difference analysis on the color temperature gradient data to generate a three-dimensional color compensation coefficient matrix, specifically including:

[0019] Extract the red, green, and blue sub-pixel color coordinate offsets of the color temperature gradient data from the color temperature gradient data in the real-time status data set, and construct a three-dimensional color difference mapping matrix in the color space;

[0020] The three-dimensional color difference mapping matrix is ​​compared pixel by pixel with the color temperature range of the preset standard color gamut, the color difference value is calculated, and a difference quantization table including a color difference weight factor is generated; wherein the step of generating the difference quantization table is:

[0021] According to the color preference data in the user behavior model, a color difference weight factor is assigned to the color difference value to generate a difference quantization table, where the color difference weight factor is positively correlated with the color adjustment frequency in the user's historical operations;

[0022] According to the temperature gradient of each pixel area in the screen surface temperature data, the color difference value of the high temperature area is nonlinearly scaled and corrected;

[0023] Multiply the color difference weight factor in the difference quantization table by the corrected color difference value to generate independent compensation coefficients for the RGB channels, specifically including:

[0024] For each pixel coordinate position, calculate the compensation coefficients of the red, green and blue channels respectively;

[0025] Integrate the red, green and blue channel compensation coefficients of each pixel position into a three-dimensional color compensation coefficient matrix according to spatial coordinates;

[0026] S230: Establishing a heat diffusion suppression model and generating a pixel voltage attenuation curve based on the thermal balance constraint rule, combined with screen surface temperature data and user interaction signals, specifically including:

[0027] Based on the screen surface temperature data in the real-time status dataset, a temperature field distribution map with pixel coordinates as variables is constructed. Furthermore, a heat source intensity distribution model is established based on the historical touch pressure distribution data stored in the user behavior model.

[0028] Based on the principles of thermodynamics, a heat conduction equation is established, and then the finite volume method is used to discretize and solve it, outputting the predicted value of the temperature change rate of each pixel unit;

[0029] According to the historical operation response time and touch trajectory data in the user behavior model, combined with the temperature change rate prediction value, a piecewise continuous pixel voltage attenuation curve is generated.

[0030] By adopting the above technical solution, the dynamic contrast enhancement rule dynamically divides the backlight partitions according to the user's gaze area by the brightness distribution data, significantly improving the contrast performance of the visual focus area, while reducing the ineffective energy consumption of the non-gaze area; traditional fixed-partition backlight control often leads to resource waste due to the mismatch between the partition boundary and the user's focus area, while the present invention ensures the efficient allocation of backlight resources by real-time tracking of the gaze coordinates and dynamically adjusting the partition grid; the calculation of the local contrast gain value is not only based on the brightness mean and standard deviation, but also integrates multi-directional ambient light intensity data, which can effectively offset the interference of ambient light reflection on the display effect. For example, in a strong side light environment, the system analyzes the incident light angle and intensity to specifically enhance the backlight output of the corresponding area of ​​the screen, thereby maintaining the visibility of the picture; the gain attenuation compensation mechanism driven by the thermal accumulation value dynamically adjusts the backlight gain upper limit of the high-temperature area to avoid screen aging or thermal failure caused by excessive pursuit of contrast. risk; the generation of the three-dimensional color compensation coefficient matrix is ​​based on the precise quantification of the red, green and blue sub-pixel color coordinate offsets. Compared with traditional global color temperature adjustment, it can realize pixel-level color deviation detection and compensation; the association design of the color difference weight factor and the user's historical operation data makes the color compensation process closely fit the user's personalized preferences. For example, the color difference compensation intensity is automatically increased for users who frequently adjust the saturation; the nonlinear scaling strategy of the color difference value in the high-temperature area effectively suppresses the color drift caused by the temperature gradient, ensuring that the consistency of color restoration can be maintained in complex thermal environments; the thermal diffusion suppression model accurately predicts the local temperature rise trend caused by user interaction behavior by constructing a temperature field distribution map and a heat source intensity distribution model. For example, the temperature accumulation effect of the long-term touch operation area; based on the discretization solution of the heat conduction equation and the pixel-level temperature change rate prediction, the system can scientifically generate a piecewise continuous pixel voltage decay curve, achieving a balance between temperature control requirements and display stability.

[0031] A further configuration is that, in S210, dynamic attenuation compensation is performed on the local contrast gain value according to the heat accumulation value of the corresponding partition in the screen surface temperature data to generate a backlight intensity dynamic allocation table, including:

[0032] Extract the average temperature value of each backlight zone and calculate the temperature difference between it and the preset temperature threshold. If the temperature difference is greater than zero, modify the local contrast gain value based on the following logic:

[0033] The gain attenuation ratio is calculated by calculating the ratio of the temperature difference to the safe operating temperature range of the display screen, and multiplying the ratio by the thermal attenuation coefficient. The safe operating temperature range of the display screen is the difference between the maximum allowable operating temperature and a preset temperature threshold. The thermal attenuation coefficient is obtained by training with historical temperature rise data from the user behavior model and is used to adaptively adjust the thermal attenuation intensity under different usage scenarios.

[0034] Dynamically reducing the original local contrast gain value according to the gain attenuation ratio to ensure that the backlight intensity in the high temperature area does not exceed the thermal stability threshold;

[0035] The corrected local contrast gain value is written into the backlight intensity dynamic allocation table according to the partition number and associated with the corresponding backlight driver chip control address.

[0036] By adopting the above technical solution, the backlight gain is intelligently attenuated by dynamically adjusting the thermal attenuation coefficient through real-time calculation of the temperature difference between backlight zones. Training the thermal attenuation coefficient enables the system to adapt to temperature rise patterns in different usage scenarios. For example, in gaming scenarios, when the overall screen temperature rises due to high GPU load, the system automatically increases the attenuation ratio to match the thermal load change. This dynamic balance between temperature and backlight intensity not only extends the display's lifespan but also reduces the probability of hardware failure through preventative thermal management. The gain attenuation ratio calculation logic combines the display's safe operating temperature range with historical temperature rise data to ensure that the backlight intensity in high-temperature areas remains within the thermal stability threshold, while minimizing the negative impact on the display through optimization algorithms.

[0037] Further configuration is that the S200 specifically further includes the following steps:

[0038] The backlight intensity dynamic allocation table, the three-dimensional color compensation coefficient matrix and the pixel voltage attenuation curve are integrated into an initial optimization parameter set, specifically including:

[0039] Spatially aligning the local contrast gain values ​​of the partitions in the backlight intensity dynamic allocation table with the three-dimensional color compensation coefficient matrix to generate a multi-channel parameter mapping table;

[0040] Synchronize the pixel voltage decay curve with the multi-channel parameter mapping table to ensure that backlight intensity adjustment, color compensation and voltage decay are coordinated within the refresh cycle;

[0041] Based on the dynamic reflection suppression coefficient in the ambient light intensity data, the initial optimization parameter set is globally normalized to generate a binary control instruction sequence that can be directly input into the display driver chip.

[0042] By adopting the above technical solution, the generation of a multi-channel parameter mapping table solves the problem of display effect imbalance caused by spatial misalignment of parameters by spatially aligning backlight intensity and color compensation parameters; the timing synchronization mechanism prevents screen tearing or flickering caused by phase differences in parameter updates within the refresh cycle by coordinating the effective timing of backlight adjustment, color compensation and voltage attenuation; the global normalization processing driven by the dynamic reflection suppression coefficient can intelligently offset the impact of sudden changes in ambient light on display parameters. For example, under suddenly increased ambient light, the system automatically reduces the global brightness and enhances color compensation to maintain the visibility of the displayed content; the multi-parameter coordinated spatiotemporal consistency guarantee mechanism enables seamless connection of backlight, color and temperature control adjustments in time and space dimensions, thereby improving the consistency and stability of the overall optimization effect.

[0043] Further configuration is that the S300 specifically includes the following steps:

[0044] Recording the acceleration and pressure distribution of the touch track through the capacitive touch layer to generate a touch behavior feature vector; the touch behavior feature vector includes the normalization of the touch pressure mean, acceleration amplitude, and track curvature radius;

[0045] The eye tracking module is used to obtain the coordinate sequence of the user's gaze area, and the time decay model of the gaze heat map is constructed based on the timestamp.

[0046] Collect spectral intensity data of the ambient light sensor in the visible light and infrared bands, and eliminate instantaneous interference noise through the Kalman filter algorithm;

[0047] The multi-frame temperature distribution map of the synchronous infrared thermal array is used to calculate the movement trajectory and intensity change gradient of the ambient heat source using the optical flow method.

[0048] By adopting the above technical solutions, the generation of touch behavior feature vectors accurately identifies user operation intentions and interaction modes by analyzing the acceleration, pressure distribution and curvature radius of the touch trajectory. For example, a high-speed sliding trajectory may indicate an impending display content switch, and the system preloads optimization parameters in advance to reduce response delays. The time decay model of the gaze heat map dynamically constructs the user's visual focus migration pattern by weighting historical gaze coordinates and timestamp data, enabling the system to prioritize optimization of the current gaze area while retaining parameter adjustment margins for historical focus areas. The Kalman filter algorithm of the ambient light sensor effectively eliminates instantaneous interference noise. The optical flow analysis of the infrared thermal sensing array can accurately track the movement trajectory and intensity changes of external heat sources. The system can predict the local temperature rise trend of the screen and initiate suppression measures in advance. This multi-dimensional signal fusion perception capability enables the system to have a deep understanding of user intentions and environmental interference, providing high-confidence input data for dynamic optimization.

[0049] Further configuration is that the S400 specifically includes the following steps:

[0050] S410: Inputting the touch behavior feature vector into a first convolutional neural network and outputting a spatial distribution map of brightness attenuation compensation coefficients, specifically including:

[0051] Normalize the touch behavior feature vector;

[0052] The three-dimensional convolution layer extracts the spatiotemporal correlation features of the touch behavior. After the feature dimensions are compressed by the pooling layer, the fully connected layer outputs the brightness attenuation compensation coefficient corresponding to the backlight partition.

[0053] The first convolutional neural network is trained based on historical touch data, with the optimization goal of minimizing the error between the predicted brightness attenuation value and the actual backlight adjustment value;

[0054] Mapping the brightness attenuation compensation coefficient output by the first convolutional neural network into a spatial distribution map according to the backlight partition number;

[0055] S420: Matching the time decay model of the gaze heat map with the key areas of the currently displayed content, and generating a color temperature offset correction factor through an attention weight allocation algorithm, specifically including:

[0056] Extract high-contrast areas in the displayed content and the user's historical attention areas as key areas, and calculate the spatial matching score by combining the time decay weight of the gaze heat map with the key area mask;

[0057] Normalize the matching scores to generate attention weight distribution, and weight the current color temperature gradient data to obtain the color temperature offset correction factor matrix;

[0058] S430: Based on the movement trajectory of the ambient heat source, a thermodynamic simulation model is used to predict the local temperature rise trend of the screen and generate heat diffusion suppression parameters, specifically including:

[0059] According to the movement trajectory and intensity change gradient of the ambient heat source, a heat flux density distribution model of the screen surface is constructed to obtain the heat flux input density of each pixel unit;

[0060] For each pixel unit, the predicted temperature rise in the future time window is fitted based on its heat flux input density and historical temperature rise response curve. At the same time, the temperature rise compensation coefficient is added based on the touch operation frequency in the user behavior model.

[0061] If the corrected predicted temperature rise of the pixel unit exceeds the preset safety threshold, the thermal diffusion suppression parameter is calculated; specifically, the following steps are performed:

[0062] Calculate the difference between the corrected predicted temperature rise and the preset safety threshold to obtain the excess temperature rise;

[0063] Divide the excess temperature rise by the difference between the maximum allowable temperature rise and the preset safety threshold to obtain the normalized temperature rise risk ratio;

[0064] Finally, the heat diffusion suppression parameter is obtained by subtracting the temperature rise risk ratio from 1;

[0065] If the predicted temperature rise does not exceed the preset safety threshold, the heat diffusion suppression parameter is assigned to 1;

[0066] The thermal diffusion suppression parameters of all pixel units are integrated into a gradient mask matrix according to coordinates, and each element in the matrix corresponds to the thermal diffusion suppression parameter of a pixel;

[0067] The thermal diffusion suppression parameters of all pixels are integrated and a thermal diffusion suppression parameter gradient mask matrix is ​​generated according to the physical coordinates of the screen.

[0068] By adopting the above technical solution, the first convolutional neural network extracts the spatiotemporal correlation characteristics of touch behavior through a three-dimensional convolutional layer, capturing the inherent laws of complex interaction patterns, such as the synergistic effect of multi-touch operations or the continuous heat source characteristics of long-press operations; continuous training of historical touch data enables the neural network to adapt to the interaction habits of different users and gradually improve the prediction accuracy of the brightness attenuation compensation coefficient; the matching algorithm between the gaze heat map and the key areas of the displayed content dynamically allocates attention weights by calculating the spatial matching score, ensuring that high-priority areas receive more refined color temperature correction; the generation of thermal diffusion suppression parameters is based on the joint prediction of the heat flux density distribution model and the historical temperature rise response curve, which can accurately predict the temperature rise trend at the pixel level and formulate a suppression strategy; the temperature rise compensation coefficient design in high-frequency interaction areas strengthens the thermal diffusion suppression capability in touch-intensive areas to avoid touch failure or display abnormalities caused by local overheating.

[0069] Further configuration is that the S500 specifically includes the following steps:

[0070] S510: Weight superposition processing of backlight partitions, specifically including:

[0071] Extracting a backlight intensity dynamic allocation table from the initial optimization parameter set, and simultaneously obtaining a spatial distribution map of brightness attenuation compensation coefficients from the dynamic correction coefficient set;

[0072] Perform a region-by-region product operation on the local contrast gain value of the backlight partition and the brightness attenuation compensation coefficient of the corresponding partition to generate a fused backlight weight matrix;

[0073] Converting the fused backlight weight matrix into a backlight control signal waveform through the physical addressing mapping relationship of the backlight driver chip;

[0074] S520: Iteratively adjust the gamma value of the pixel matrix, specifically including:

[0075] Constructing a gamma correction parameter mapping table based on the independent compensation coefficients of the RGB channels in the three-dimensional color compensation coefficient matrix;

[0076] Extracting a color temperature offset correction factor matrix from the dynamic correction coefficient set, and performing channel alignment on the matrix with the gamma correction parameter mapping table;

[0077] The original gamma value is iteratively adjusted through a pixel-by-pixel weighted average algorithm to generate a dynamic gamma correction curve;

[0078] S530: Execute color space remapping processing, specifically including:

[0079] Inputting the dynamic gamma correction curve into a color management engine and combining it with a thermal diffusion suppression parameter gradient mask matrix to establish a color gamut constraint condition;

[0080] Perform nonlinear transformation on the RGB color space based on the color gamut constraint to generate a three-dimensional lookup table of the color space;

[0081] A bilinear interpolation algorithm is used to map the three-dimensional lookup table to the native color gamut space of the display screen to complete the recalibration of the color space;

[0082] S540: Generate a target optimization instruction set, specifically including:

[0083] The fused backlight weight matrix, dynamic gamma correction curve and recalibrated color space parameters are encoded synchronously in time sequence;

[0084] Based on the instruction set architecture of the display driver chip, the encoded parameters are converted into executable binary optimized instruction sequences;

[0085] The binary optimization instruction sequence is sent to the backlight controller, gamma correction module and color processing unit in real time through a high-speed serial interface to achieve coordinated optimization of display parameters.

[0086] By adopting the above technical solution, the fused backlight weight matrix achieves a dynamic balance between brightness and thermal management through zone-by-zone multiplication operations. When high brightness is required in high-temperature zones, the system limits the maximum gain value according to the thermal stability threshold and compensates for brightness loss through a color compensation mechanism. The gamma correction parameter mapping table is aligned with the channel of the color temperature offset correction factor to solve the problem of parameter coupling across color spaces. For example, red channel compensation needs to simultaneously consider the impact of color temperature offset on the overall white balance. The dynamic gamma curve generated by the pixel-by-pixel weighted averaging algorithm can adapt to local display characteristic differences. Color space remapping ensures that the conversion process does not exceed the physical limits of the native color gamut of the display through color gamut constraints. The combination of a three-dimensional lookup table and a bilinear interpolation algorithm greatly reduces computational complexity and meets real-time requirements. The timing synchronization encoding of the instruction set architecture eliminates timing jitter in parameter updates to ensure consistency in the actions of the backlight, gamma, and color units.

[0087] Further configuration is that the S600 specifically includes the following steps:

[0088] S610, collecting screen performance indicators after display parameter execution in real time; wherein the screen performance indicators include actual brightness uniformity error, color temperature deviation value and temperature rise suppression efficiency;

[0089] S620: Compare the screen performance index with a preset target threshold to generate an optimization effect evaluation table; the optimization effect evaluation table records the brightness error ratio, color temperature deviation level, and heat diffusion suppression success rate of each backlight partition.

[0090] By adopting the above technical solutions, the optimization effect evaluation table can provide intuitive optimization effect feedback and guide the direction of subsequent parameter adjustments.

[0091] In summary, the present invention has the following beneficial effects:

[0092] Achieve collaborative optimization and thermal balance of global display parameters; through multi-dimensional data fusion and collaborative calculation of global parameters, the system can balance the needs of improving visual experience and suppressing thermal diffusion in real time. While enhancing local contrast and optimizing color reproduction, it actively suppresses screen temperature rise through thermal balance constraints, ensuring the long-term coexistence of ultra-high-definition display effects and hardware security. BRIEF DESCRIPTION OF THE DRAWINGS

[0093] Figure 1 It is a schematic diagram of the main process of the embodiment;

[0094] Figure 2 Schematic diagram of the process of S200 in the embodiment;

[0095] Figure 3 This is a flow chart of performing dynamic attenuation compensation on the local contrast gain value according to the heat accumulation value of the corresponding partition in the screen surface temperature data in S210 in the embodiment to generate a dynamic backlight intensity allocation table;

[0096] Figure 4 Schematic diagram of the process of S400 in the embodiment. DETAILED DESCRIPTION

[0097] The present invention will be further described in detail below with reference to the accompanying drawings.

[0098] As attached Figures 1 to 4 As shown;

[0099] This embodiment discloses a global dynamic optimization system for an ultra-high-definition glass-based display screen. The system operation process specifically includes the following steps:

[0100] S100, obtaining a real-time status data set of a display screen; wherein the real-time status data set includes brightness distribution data, color temperature gradient data, ambient light intensity data, and screen surface temperature data;

[0101] Brightness distribution data is collected through partitioned backlight sensors; color temperature gradient data is collected through a multi-spectral imaging unit that performs frame-by-frame spectral scanning of the display screen, extracts the color coordinate offsets of the red, green, and blue sub-pixels, and constructs a three-dimensional color temperature gradient matrix; ambient light intensity data is collected through a multi-directional ambient light sensor array that synchronously collects the spectral intensity of visible light and infrared bands; screen surface temperature data is collected through a high-density infrared thermal sensor grid that monitors the thermal radiation value of each pixel area in real time.

[0102] Specifically, the partitioned backlight sensor uses a high-sensitivity photodiode array with a 256×144 grid distribution, with each partition containing 16×16 pixels; the multispectral imaging unit integrates a CMOS sensor with a narrow-band filter; the multi-directional ambient light sensor adopts a six-way ring layout, with a visible light and infrared dual-channel spectral detector configured in each direction, with a sampling frequency of 1kHz; the high-density infrared thermal sensor grid is based on a 640×480 thermal imaging array of microbolometers, with a temperature resolution of 0.05°C and a spatial resolution of 0.1mm² / pixel.

[0103] S200, generating an initial set of optimization parameters based on a preset optimization strategy and a user behavior model; wherein the preset optimization strategy includes a dynamic contrast enhancement rule, a color gamut adaptive matching rule, and a thermal balance constraint rule; the user behavior model is trained using historical operation data; and the initial set of optimization parameters includes a partition backlight intensity parameter, a pixel drive voltage parameter, and a color compensation coefficient matrix;

[0104] S300, capturing user interaction signals and environmental change signals in real time; wherein the user interaction signals include touch trajectory data, gaze area coordinates, and operation response duration, and the environmental change signals are synchronously collected by the ambient light sensor and the infrared thermal array;

[0105] S400, generating a dynamic correction coefficient set according to the user interaction signal and the environment change signal; wherein the dynamic correction coefficient set includes a brightness attenuation compensation coefficient, a color temperature offset correction factor, and a heat diffusion suppression parameter;

[0106] S500, performing global parameter fusion based on the initial optimization parameter set and the dynamic correction coefficient set to generate a target optimization instruction set; wherein the global parameter fusion includes weight superposition of backlight partitions, iterative adjustment of the gamma value of the pixel matrix, and remapping of the color space;

[0107] S600: Feedback an optimization effect evaluation table based on the optimization effect.

[0108] Specifically, S200 includes the following steps:

[0109] S210: Segment the brightness distribution data into regions according to the dynamic contrast enhancement rule, calculate the local contrast gain value of each region, and generate a backlight intensity dynamic allocation table, specifically including:

[0110] The brightness distribution data in the real-time status dataset is divided into multiple backlight partitions according to a preset grid. The division of each partition is dynamically adjusted based on the gaze area coordinate distribution in the user behavior model.

[0111] For each backlight partition, extract the mean and standard deviation of its brightness distribution data, and calculate the local contrast gain value by combining the multi-directional incident light intensity in the ambient light intensity data:

[0112] Specifically, the local contrast gain value is calculated using the following formula:

[0113] G c =α·μ L / σ L +β·I amb / I max

[0114] Among them, G c is the local contrast gain value; μ L is the mean brightness of the backlight partition; σ L is the brightness standard deviation of the backlight partition; I amb is the ambient light intensity; I max is the maximum allowable backlight intensity; α and β are weight coefficients obtained based on user behavior model training;

[0115] According to the heat accumulation value of the corresponding partition in the screen surface temperature data, the local contrast gain value is dynamically attenuated and compensated to generate a dynamic backlight intensity allocation table;

[0116] S220: Based on the color gamut adaptive matching rule, perform difference analysis on the color temperature gradient data to generate a three-dimensional color compensation coefficient matrix, specifically including:

[0117] Extract the red, green, and blue sub-pixel color coordinate offsets of the color temperature gradient data from the color temperature gradient data in the real-time status data set, and construct a three-dimensional color difference mapping matrix in the color space;

[0118] The three-dimensional color difference mapping matrix is ​​compared pixel by pixel with the color temperature range of the preset standard color gamut, the color difference value is calculated, and a difference quantization table including a color difference weight factor is generated; wherein the steps for generating the difference quantization table are as follows:

[0119] According to the color preference data in the user behavior model, a color difference weight factor is assigned to the color difference value to generate a difference quantization table, where the color difference weight factor is positively correlated with the color adjustment frequency in the user's historical operations;

[0120] According to the temperature gradient of each pixel area in the screen surface temperature data, the color difference value of the high temperature area is nonlinearly scaled and corrected;

[0121] Specifically corrected by the following formula:

[0122] ΔE adj =ΔE·(1-λ·(T local -T base ) / (T maximum -T base )

[0123] Among them, T local is the local temperature; T base is the reference temperature threshold; T maximum is the maximum allowable temperature; λ is the thermal attenuation coefficient; ΔE is the color difference value before correction; ΔE adj is the corrected color difference value;

[0124] Multiply the color difference weight factor in the difference quantization table by the corrected color difference value to generate independent compensation coefficients for the RGB channels, specifically including:

[0125] For each pixel coordinate position, calculate the compensation coefficients of the red, green and blue channels respectively;

[0126] Integrate the red, green and blue channel compensation coefficients of each pixel position into a three-dimensional color compensation coefficient matrix according to spatial coordinates;

[0127] In a three-dimensional color compensation coefficient matrix:

[0128] The first dimension represents the row coordinate of the pixel;

[0129] The second dimension represents the column coordinate of the pixel;

[0130] The third dimension corresponds to the compensation coefficient values ​​of the red, green, and blue color channels respectively.

[0131] S230: Establish a heat diffusion suppression model and generate a pixel voltage attenuation curve based on thermal equilibrium constraint rules, combined with screen surface temperature data and user interaction signals. Specifically, the following steps are performed:

[0132] Based on the screen surface temperature data in the real-time status dataset, a temperature field distribution map with pixel coordinates as variables is constructed. Furthermore, a heat source intensity distribution model is established based on the historical touch pressure distribution data stored in the user behavior model.

[0133] Based on the principles of thermodynamics, a heat conduction equation is established, and then the finite volume method is used to discretize and solve it, outputting the predicted value of the temperature change rate of each pixel unit;

[0134] Specifically:

[0135] Construct the partial differential equation for heat conduction:

[0136] ,

[0137] Where k is the thermal conductivity of the display glass substrate; P is the pixel driving power, which is calculated from the pixel driving current and voltage in the real-time status data set; C p is the specific heat capacity of the display material; ρ is the density of the display material; Represents the spatial second-order derivative of the temperature field, which is used to describe the thermal diffusion effect; Indicates the rate of change of the temperature field over time. By quantifying the speed of temperature change, it predicts the temperature rise trend of each area of ​​the screen in the future, thereby dynamically adjusting the pixel driving parameters to suppress display distortion caused by heat diffusion;

[0138] Based on the historical operation response time and touch trajectory data in the user behavior model and the predicted value of the temperature change rate, a piecewise continuous pixel voltage attenuation curve is generated.

[0139] Specifically, in S210, according to the heat accumulation value of the corresponding partition in the screen surface temperature data, dynamic attenuation compensation is performed on the local contrast gain value to generate a backlight intensity dynamic allocation table, including:

[0140] Extract the average temperature value of each backlight zone and calculate the temperature difference between it and the preset temperature threshold. If the temperature difference is greater than zero, modify the local contrast gain value based on the following logic:

[0141] The gain attenuation ratio is calculated by calculating the ratio of the temperature difference to the display's safe operating temperature range and multiplying it by the thermal attenuation coefficient. The display's safe operating temperature range is the difference between the maximum allowable operating temperature and the preset temperature threshold. The thermal attenuation coefficient is trained using historical temperature rise data from the user behavior model and is used to adaptively adjust the thermal attenuation intensity under different usage scenarios.

[0142] Dynamically reduce the original local contrast gain value according to the gain attenuation ratio to ensure that the backlight intensity in the high temperature area does not exceed the thermal stability threshold;

[0143] Specifically:

[0144] G c_adj =G c ·(1-η·ΔT / (T max -T threshold )

[0145] Where ΔT is the temperature difference; T max T is the maximum operating temperature allowed by the display; threshold is the preset temperature threshold; η is the thermal attenuation coefficient; G c is the local contrast gain value before correction; G c_adj is the corrected local contrast gain value.

[0146] The corrected local contrast gain value is written into the backlight intensity dynamic allocation table according to the partition number and associated with the corresponding backlight driver chip control address.

[0147] Example 1

[0148] Based on the user gaze heat map, we determined that 80% of the gaze points were concentrated in the 200×200 area in the center of the screen, so we doubled the grid density in the center area.

[0149] μ in one of the backlight zones L 1500 nits,σ L 30nits, I amb 300 lux, I max is 2000 nits, α is 0.6, β is 0.4;

[0150] After calculation, G c is 30.06;

[0151] The backlight partition T maximum is 50℃, T threshold is 40℃,η is 0.8;

[0152] G c_adj =30.06×[1-0.8×(43-40) / (50-40)]=22.85;

[0153] Example 2

[0154] The color difference value of one pixel is ΔE=5, the user's historical adjustment frequency of green accounts for 60%, and the color difference weight factor is given as 0.8; if the local temperature T local At 45°C, T base is 40℃,λ is 0.5; then

[0155] ΔE adj =5×[1-0.5×(45-40) / (50-40)]=3.75;

[0156] The final compensation coefficient K_green=3.75×0.8=3.0.

[0157] Example 3

[0158] Using the COMSOL Multiphysics solver, a transient analysis of the temperature field distribution was performed, predicting that the temperature rise rate in a high-power consumption area would reach 0.8°C / s within the next 5 minutes.

[0159] Generate a segmented continuous pixel voltage attenuation curve. For example, when the temperature is greater than 42°C, the pixel driving voltage decreases by 0.2V for every 1°C increase in temperature.

[0160] Specifically, S200 further includes the following steps:

[0161] The backlight intensity dynamic allocation table, the three-dimensional color compensation coefficient matrix, and the pixel voltage attenuation curve are integrated into the initial optimization parameter set, specifically including:

[0162] Spatially aligning the local contrast gain values ​​of the partitions in the backlight intensity dynamic allocation table with the three-dimensional color compensation coefficient matrix to generate a multi-channel parameter mapping table;

[0163] Synchronize the pixel voltage decay curve with the multi-channel parameter mapping table to ensure that backlight intensity adjustment, color compensation and voltage decay are coordinated within the refresh cycle;

[0164] Based on the dynamic reflection suppression coefficient in the ambient light intensity data, the initial optimization parameter set is globally normalized to generate a binary control instruction sequence that can be directly input into the display driver chip.

[0165] Specifically, S300 includes the following steps:

[0166] The acceleration and pressure distribution of the touch track are recorded through the capacitive touch layer to generate a touch behavior feature vector; the touch behavior feature vector includes the touch pressure mean, acceleration amplitude and normalized track curvature radius;

[0167] The eye tracking module is used to obtain the coordinate sequence of the user's gaze area, and the time decay model of the gaze heat map is constructed in combination with the timestamp; specifically:

[0168] The user's eye movement data is captured using an infrared camera, and the pupil center coordinates and gaze dwell time are extracted. The pupil center coordinates are mapped to the physical coordinate space of the display screen to generate a gaze area coordinate sequence. The start time and duration of each gaze point are marked with associated timestamps.

[0169] The time decay model of the gaze heat map is constructed based on the timestamp, and the exponential decay function is used to calculate the weight value of each gaze point:

[0170] Finally, the weight values ​​of each gaze point are superimposed according to the spatial coordinates to generate a dynamically updated gaze heat map;

[0171] Collect spectral intensity data of the ambient light sensor in the visible light and infrared bands, and eliminate instantaneous interference noise through the Kalman filter algorithm;

[0172] The multi-frame temperature distribution map of the synchronous infrared thermal array is used to calculate the movement trajectory and intensity change gradient of the ambient heat source using the optical flow method.

[0173] Example 4

[0174] The capacitive touch layer records the touch track at a sampling rate of 1000 Hz and calculates the curvature radius;

[0175] The eye tracking module uses the Tobii 4C module, which outputs a sequence of gaze point coordinates;

[0176] The optical flow method detected that the ambient heat source on the right side moved at a speed of 0.5 m / s, with a heat flux density gradient of ΔQ = 10 W / m²·s.

[0177] Specifically, S400 includes the following steps:

[0178] S410: Input the touch behavior feature vector into the first convolutional neural network, and output a spatial distribution map of the brightness attenuation compensation coefficient, specifically including:

[0179] Normalize the touch behavior feature vector;

[0180] The three-dimensional convolution layer extracts the spatiotemporal correlation features of the touch behavior. After the feature dimensions are compressed by the pooling layer, the fully connected layer outputs the brightness attenuation compensation coefficient corresponding to the backlight partition.

[0181] Specifically, the structure of the first convolutional neural network is as follows:

[0182] Input layer: receives spatiotemporal feature tensors;

[0183] 3D convolutional layer: extracts the spatiotemporal correlation features of touch behavior, with a convolution kernel size of (3×3×3);

[0184] Pooling layer: uses maximum pooling to compress feature dimensions;

[0185] Fully connected layer: outputs the brightness attenuation compensation coefficient corresponding to the screen backlight partition;

[0186] The first convolutional neural network is trained based on historical touch data, with the optimization goal of minimizing the error between the predicted brightness attenuation value and the actual backlight adjustment value;

[0187] Mapping the brightness attenuation compensation coefficient output by the first convolutional neural network into a spatial distribution map according to the backlight partition number;

[0188] S420: Matching the time decay model of the gaze heat map with the key areas of the currently displayed content, and generating a color temperature offset correction factor through an attention weight allocation algorithm, specifically including:

[0189] Extract high-contrast areas in the displayed content and the user's historical attention areas as key areas, and calculate the spatial matching score by combining the time decay weight of the gaze heat map with the key area mask;

[0190] Normalize the matching scores to generate attention weight distribution, and weight the current color temperature gradient data to obtain the color temperature offset correction factor matrix;

[0191] S430: Based on the movement trajectory of the ambient heat source, a thermodynamic simulation model is used to predict the local temperature rise trend of the screen and generate heat diffusion suppression parameters, specifically including:

[0192] According to the movement trajectory and intensity change gradient of the ambient heat source, a heat flux density distribution model of the screen surface is constructed to obtain the heat flux input density of each pixel unit;

[0193] For each pixel unit, the predicted temperature rise in the future time window is fitted based on its heat flux input density and historical temperature rise response curve. At the same time, the temperature rise compensation coefficient is added based on the touch operation frequency in the user behavior model.

[0194] Specifically:

[0195] ΔC pred_adj =ΔC pred ·(1+γ·N touch )

[0196] Among them, N touch is the touch operation frequency; γ is the compensation weight; ΔC pred is the predicted temperature rise before correction; ΔC pred_adj is the predicted temperature rise after correction;

[0197] If the corrected predicted temperature rise of the pixel unit exceeds the preset safety threshold, the thermal diffusion suppression parameter is calculated; specifically, the following steps are performed:

[0198] Calculate the difference between the corrected predicted temperature rise and the preset safety threshold to obtain the excess temperature rise;

[0199] Divide the excess temperature rise by the difference between the maximum allowable temperature rise and the preset safety threshold to obtain the normalized temperature rise risk ratio;

[0200] Finally, the thermal diffusion suppression parameter is obtained by subtracting the temperature rise risk ratio from 1;

[0201] The specific formula is as follows:

[0202] δ=1-(ΔC pred_adj -C threshold ) / (C max -C threshold )

[0203] Among them, C threshold is the preset safety threshold; C max is the maximum allowable temperature rise; δ is the thermal diffusion suppression parameter.

[0204] If the predicted temperature rise does not exceed the preset safety threshold, the heat diffusion suppression parameter is assigned to 1;

[0205] The thermal diffusion suppression parameters of all pixel units are integrated into a gradient mask matrix according to coordinates, and each element in the matrix corresponds to the thermal diffusion suppression parameter of a pixel;

[0206] The thermal diffusion suppression parameters of all pixels are integrated and a thermal diffusion suppression parameter gradient mask matrix is ​​generated according to the physical coordinates of the screen.

[0207] Example 5

[0208] The first convolutional neural network inputs a touch pressure average of 0.5N and an acceleration of 2m / s², and after three layers of convolution, outputs a central area compensation coefficient of 0.8.

[0209] When the user's gaze area overlaps with the movie subtitle area by 70%, a color temperature correction factor of 1.2 is applied to the area.

[0210] ΔC of one pixel pred 8℃, C threshold 5℃, C max is 10℃, γ is 0.2, N touch 15 times / minute;

[0211] Calculated ΔC pred_adj 8×[1+0.2×15]= 32°C, exceeding the preset safety threshold;

[0212] δ=1-(32-5) / (10-5)=-4.4, forcing δ=0, complete suppression.

[0213] Specifically, S500 includes the following steps:

[0214] S510: Weight superposition processing of backlight partitions, specifically including:

[0215] Extracting a backlight intensity dynamic allocation table from the initial optimization parameter set, and obtaining a spatial distribution map of brightness attenuation compensation coefficients from the dynamic correction coefficient set;

[0216] Perform a region-by-region product operation on the local contrast gain value of the backlight partition and the brightness attenuation compensation coefficient of the corresponding partition to generate a fused backlight weight matrix;

[0217] The fused backlight weight matrix is ​​converted into a backlight control signal waveform through the physical addressing mapping relationship of the backlight driver chip;

[0218] S520: Iteratively adjust the gamma value of the pixel matrix, specifically including:

[0219] Constructing a gamma correction parameter mapping table based on the independent compensation coefficients of the RGB channels in the three-dimensional color compensation coefficient matrix;

[0220] Extract the color temperature offset correction factor matrix from the dynamic correction coefficient set and align it with the gamma correction parameter mapping table;

[0221] The original gamma value is iteratively adjusted through a pixel-by-pixel weighted average algorithm to generate a dynamic gamma correction curve;

[0222] The adjustment formula of the dynamic gamma correction curve is:

[0223] γ'=γ0·[1+ω·(K_c+K_t)]

[0224] Among them, γ' is the adjusted dynamic gamma value; γ0 is the original gamma value; ω is the set weight factor; K_c is the independent compensation coefficient of the RGB channel in the three-dimensional color compensation coefficient matrix; K_t is the color temperature offset correction factor in the color temperature offset correction factor matrix.

[0225] S530: Execute color space remapping processing, specifically including:

[0226] The dynamic gamma correction curve is input into the color management engine and combined with the thermal diffusion suppression parameter gradient mask matrix to establish the color gamut constraint condition;

[0227] Based on the color gamut constraint, the RGB color space is nonlinearly transformed to generate a three-dimensional lookup table of the CIE XYZ intermediate color space;

[0228] A bilinear interpolation algorithm is used to map the 3D lookup table to the native color gamut of the display, completing the color space recalibration.

[0229] S540: Generate a target optimization instruction set, specifically including:

[0230] The fused backlight weight matrix, dynamic gamma correction curve and recalibrated color space parameters are encoded synchronously in time sequence;

[0231] Based on the instruction set architecture of the display driver chip, the encoded parameters are converted into executable binary optimized instruction sequences;

[0232] The binary optimization instruction sequence is sent to the backlight controller, gamma correction module and color processing unit in real time through a high-speed serial interface to achieve coordinated optimization of display parameters.

[0233] Specifically, S600 includes the following steps:

[0234] S610, collecting screen performance indicators after display parameter execution in real time; wherein the screen performance indicators include actual brightness uniformity error, color temperature deviation value, and temperature rise suppression efficiency;

[0235] S620: Compare the screen performance index with the preset target threshold value to generate an optimization effect evaluation table; the optimization effect evaluation table records the brightness error ratio, color temperature deviation level and heat diffusion suppression success rate of each backlight partition.

[0236] Example 6

[0237] The screen performance indicators are as follows:

[0238] Brightness uniformity: The measured brightness deviation in the central area is less than 5%, and the target threshold is 8%.

[0239] Color temperature consistency: White screen ΔE is less than 1.5, and the target value ΔE is less than 2.

[0240] Temperature rise control: The heating rate in the high temperature area is reduced from 0.8℃ / s to 0.3℃ / s.

[0241] An example of an evaluation form is shown in the table below;

[0242] Table 1 Evaluation table example

[0243]

[0244] This specific embodiment is merely an explanation of the present invention and is not intended to limit the present invention. After reading this specification, those skilled in the art may make non-creative modifications to this embodiment as needed. However, as long as such modifications are within the scope of the claims of the present invention, they are protected by patent law.

Claims

1. A global dynamic optimization system for ultra-high-definition glass-based display screens, characterized in that: The system operation process specifically includes the following steps: S100, obtaining a real-time status data set of a display screen; wherein the real-time status data set includes brightness distribution data, color temperature gradient data, ambient light intensity data, and screen surface temperature data; S200, generating an initial set of optimization parameters based on a preset optimization strategy and a user behavior model; wherein the preset optimization strategy includes a dynamic contrast enhancement rule, a color gamut adaptive matching rule, and a thermal balance constraint rule; the user behavior model is trained using historical operation data; and the initial set of optimization parameters includes a partition backlight intensity parameter, a pixel drive voltage parameter, and a color compensation coefficient matrix; S300, capturing user interaction signals and environmental change signals in real time; wherein the user interaction signals include touch trajectory data, gaze area coordinates, and operation response duration, and the environmental change signals are synchronously collected by an ambient light sensor and an infrared thermal array; S400, generating a dynamic correction coefficient set according to the user interaction signal and the environment change signal; wherein the dynamic correction coefficient set includes a brightness attenuation compensation coefficient, a color temperature offset correction factor, and a heat diffusion suppression parameter; S500, performing global parameter fusion based on the initial optimization parameter set and the dynamic correction coefficient set to generate a target optimization instruction set; wherein the global parameter fusion includes weight superposition of backlight partitions, iterative adjustment of the gamma value of the pixel matrix, and color space remapping processing; S600, feedback optimization effect evaluation form based on optimization effect; The step S200 specifically includes the following steps: S210, performing regional segmentation on the brightness distribution data according to the dynamic contrast enhancement rule, calculating a local contrast gain value of each partition, and generating a backlight intensity dynamic allocation table; S220, performing difference analysis on the color temperature gradient data based on the color gamut adaptive matching rule to generate a three-dimensional color compensation coefficient matrix; S230 , establishing a heat diffusion suppression model and generating a pixel voltage attenuation curve by using the thermal balance constraint rule in combination with the screen surface temperature data and the user interaction signal.

2. The global dynamic optimization system for an ultra-high-definition glass-based display screen according to claim 1, characterized in that: The S210 specifically includes: The brightness distribution data in the real-time status dataset is divided into multiple backlight partitions according to a preset grid. The division of each partition is dynamically adjusted based on the gaze area coordinate distribution in the user behavior model. For each backlight partition, extract the mean and standard deviation of its brightness distribution data, and calculate the local contrast gain value by combining the multi-directional incident light intensity in the ambient light intensity data: According to the heat accumulation value of the corresponding partition in the screen surface temperature data, the local contrast gain value is dynamically attenuated and compensated to generate a backlight intensity dynamic allocation table; The S220 specifically includes: Extract the red, green, and blue sub-pixel color coordinate offsets of the color temperature gradient data from the color temperature gradient data in the real-time status data set, and construct a three-dimensional color difference mapping matrix in the color space; The three-dimensional color difference mapping matrix is ​​compared pixel by pixel with the color temperature range of the preset standard color gamut, the color difference value is calculated, and a difference quantization table including a color difference weight factor is generated; wherein the step of generating the difference quantization table is: According to the color preference data in the user behavior model, a color difference weight factor is assigned to the color difference value to generate a difference quantization table, where the color difference weight factor is positively correlated with the color adjustment frequency in the user's historical operations; According to the temperature gradient of each pixel area in the screen surface temperature data, the color difference value of the high temperature area is nonlinearly scaled and corrected; Multiply the color difference weight factor in the difference quantization table by the corrected color difference value to generate independent compensation coefficients for the RGB channels, specifically including: For each pixel coordinate position, calculate the compensation coefficients of the red, green and blue channels respectively; Integrate the red, green and blue channel compensation coefficients of each pixel position into a three-dimensional color compensation coefficient matrix according to spatial coordinates; The S230 specifically includes: Based on the screen surface temperature data in the real-time status dataset, a temperature field distribution map with pixel coordinates as variables is constructed. Furthermore, a heat source intensity distribution model is established based on the historical touch pressure distribution data stored in the user behavior model. Based on the principles of thermodynamics, a heat conduction equation is established, and then the finite volume method is used to discretize and solve it, outputting the predicted value of the temperature change rate of each pixel unit; According to the historical operation response time and touch trajectory data in the user behavior model, combined with the temperature change rate prediction value, a piecewise continuous pixel voltage attenuation curve is generated.

3. The global dynamic optimization system for an ultra-high-definition glass-based display screen according to claim 2, characterized in that: In S210, the local contrast gain value is dynamically attenuated and compensated according to the heat accumulation value of the corresponding partition in the screen surface temperature data to generate a backlight intensity dynamic allocation table, including: Extract the average temperature value of each backlight zone and calculate the temperature difference between it and the preset temperature threshold. If the temperature difference is greater than zero, modify the local contrast gain value based on the following logic: The gain attenuation ratio is calculated by calculating the ratio of the temperature difference to the safe operating temperature range of the display screen, and multiplying the ratio by the thermal attenuation coefficient. The safe operating temperature range of the display screen is the difference between the maximum allowable operating temperature and a preset temperature threshold. The thermal attenuation coefficient is obtained by training with historical temperature rise data from the user behavior model and is used to adaptively adjust the thermal attenuation intensity under different usage scenarios. Dynamically reducing the original local contrast gain value according to the gain attenuation ratio to ensure that the backlight intensity in the high temperature area does not exceed the thermal stability threshold; The corrected local contrast gain value is written into the backlight intensity dynamic allocation table according to the partition number and associated with the corresponding backlight driver chip control address.

4. The global dynamic optimization system for an ultra-high-definition glass-based display screen according to claim 3, characterized in that: The S200 specifically further includes the following steps: The backlight intensity dynamic allocation table, the three-dimensional color compensation coefficient matrix and the pixel voltage attenuation curve are integrated into an initial optimization parameter set, specifically including: Spatially aligning the local contrast gain values ​​of the partitions in the backlight intensity dynamic allocation table with the three-dimensional color compensation coefficient matrix to generate a multi-channel parameter mapping table; Synchronize the pixel voltage decay curve with the multi-channel parameter mapping table to ensure that backlight intensity adjustment, color compensation and voltage decay are coordinated within the refresh cycle; Based on the dynamic reflection suppression coefficient in the ambient light intensity data, the initial optimization parameter set is globally normalized to generate a binary control instruction sequence that can be directly input into the display driver chip.

5. The global dynamic optimization system for an ultra-high-definition glass-based display screen according to claim 2, characterized in that: The S300 specifically includes the following steps: Recording the acceleration and pressure distribution of the touch track through the capacitive touch layer to generate a touch behavior feature vector; the touch behavior feature vector includes the normalization of the touch pressure mean, acceleration amplitude, and track curvature radius; The eye tracking module is used to obtain the coordinate sequence of the user's gaze area, and the time decay model of the gaze heat map is constructed based on the timestamp. Collect spectral intensity data of the ambient light sensor in the visible light and infrared bands, and eliminate instantaneous interference noise through the Kalman filter algorithm; The multi-frame temperature distribution map of the synchronous infrared thermal array is used to calculate the movement trajectory and intensity change gradient of the ambient heat source using the optical flow method.

6. The global dynamic optimization system for an ultra-high-definition glass-based display screen according to claim 5, characterized in that: The S400 specifically includes the following steps: S410: Inputting the touch behavior feature vector into a first convolutional neural network and outputting a spatial distribution map of brightness attenuation compensation coefficients, specifically including: Normalize the touch behavior feature vector; The three-dimensional convolution layer extracts the spatiotemporal correlation features of the touch behavior. After the feature dimensions are compressed by the pooling layer, the fully connected layer outputs the brightness attenuation compensation coefficient corresponding to the backlight partition. The first convolutional neural network is trained based on historical touch data, with the optimization goal of minimizing the error between the predicted brightness attenuation value and the actual backlight adjustment value; Mapping the brightness attenuation compensation coefficient output by the first convolutional neural network into a spatial distribution map according to the backlight partition number; S420: Matching the time decay model of the gaze heat map with the key areas of the currently displayed content, and generating a color temperature offset correction factor through an attention weight allocation algorithm, specifically including: Extract high-contrast areas in the displayed content and the user's historical attention areas as key areas, and calculate the spatial matching score by combining the time decay weight of the gaze heat map with the key area mask; Normalize the matching scores to generate attention weight distribution, and weight the current color temperature gradient data to obtain the color temperature offset correction factor matrix; S430: Based on the movement trajectory of the ambient heat source, a thermodynamic simulation model is used to predict the local temperature rise trend of the screen and generate heat diffusion suppression parameters, specifically including: According to the movement trajectory and intensity change gradient of the ambient heat source, a heat flux density distribution model of the screen surface is constructed to obtain the heat flux input density of each pixel unit; For each pixel unit, the predicted temperature rise in the future time window is fitted based on its heat flux input density and historical temperature rise response curve. At the same time, the temperature rise compensation coefficient is added based on the touch operation frequency in the user behavior model. If the corrected predicted temperature rise of the pixel unit exceeds the preset safety threshold, the thermal diffusion suppression parameter is calculated; specifically, the following steps are performed: Calculate the difference between the corrected predicted temperature rise and the preset safety threshold to obtain the excess temperature rise; Divide the excess temperature rise by the difference between the maximum allowable temperature rise and the preset safety threshold to obtain the normalized temperature rise risk ratio; Finally, the heat diffusion suppression parameter is obtained by subtracting the temperature rise risk ratio from 1; If the predicted temperature rise does not exceed the preset safety threshold, the heat diffusion suppression parameter is assigned to 1; The thermal diffusion suppression parameters of all pixel units are integrated into a gradient mask matrix according to coordinates, and each element in the matrix corresponds to the thermal diffusion suppression parameter of a pixel; The thermal diffusion suppression parameters of all pixels are integrated and a thermal diffusion suppression parameter gradient mask matrix is ​​generated according to the physical coordinates of the screen.

7. The global dynamic optimization system for an ultra-high-definition glass-based display screen according to claim 6, characterized in that: The S500 specifically includes the following steps: S510: Weight superposition processing of backlight partitions, specifically including: Extracting a backlight intensity dynamic allocation table from the initial optimization parameter set, and simultaneously obtaining a spatial distribution map of brightness attenuation compensation coefficients from the dynamic correction coefficient set; Perform a region-by-region product operation on the local contrast gain value of the backlight partition and the brightness attenuation compensation coefficient of the corresponding partition to generate a fused backlight weight matrix; Converting the fused backlight weight matrix into a backlight control signal waveform through the physical addressing mapping relationship of the backlight driver chip; S520: Iteratively adjust the gamma value of the pixel matrix, specifically including: Constructing a gamma correction parameter mapping table based on the independent compensation coefficients of the RGB channels in the three-dimensional color compensation coefficient matrix; Extracting a color temperature offset correction factor matrix from the dynamic correction coefficient set, and performing channel alignment on the matrix with the gamma correction parameter mapping table; The original gamma value is iteratively adjusted through a pixel-by-pixel weighted average algorithm to generate a dynamic gamma correction curve; S530: Execute color space remapping processing, specifically including: Inputting the dynamic gamma correction curve into a color management engine and combining it with a thermal diffusion suppression parameter gradient mask matrix to establish a color gamut constraint condition; Perform nonlinear transformation on the RGB color space based on the color gamut constraint to generate a three-dimensional lookup table of the color space; A bilinear interpolation algorithm is used to map the three-dimensional lookup table to the native color gamut space of the display screen to complete the recalibration of the color space; S540: Generate a target optimization instruction set, specifically including: The fused backlight weight matrix, dynamic gamma correction curve and recalibrated color space parameters are encoded synchronously in time sequence; Based on the instruction set architecture of the display driver chip, the encoded parameters are converted into executable binary optimized instruction sequences; The binary optimization instruction sequence is sent to the backlight controller, gamma correction module and color processing unit in real time through a high-speed serial interface to achieve coordinated optimization of display parameters.

8. The global dynamic optimization system for an ultra-high-definition glass-based display screen according to claim 7, characterized in that: The S600 specifically includes the following steps: S610, collecting screen performance indicators after display parameter execution in real time; wherein the screen performance indicators include actual brightness uniformity error, color temperature deviation value and temperature rise suppression efficiency; S620: Compare the screen performance index with a preset target threshold to generate an optimization effect evaluation table; the optimization effect evaluation table records the brightness error ratio, color temperature deviation level, and heat diffusion suppression success rate of each backlight partition.

Images