A method, apparatus, device and medium for adjusting the image quality of a display device

Abstract

The application belongs to the technical field of display, and relates to a display device quality adjustment method and device, equipment and medium, comprising: continuously collecting three types of original data of device environment, watching behavior and content data, inputting a preset time sequence risk model to calculate a visual fatigue risk index representing cumulative visual loss of human eyes, determining four types of fine quality regulation parameters corresponding to the current moment based on the index and the content data, judging whether there is a historical target display parameter generated at a previous moment of the current moment, if there is, adopting a frame-level smoothing function to perform smoothing transition processing on the four types of fine quality regulation parameters based on the historical target display parameter to obtain a target display parameter, and adjusting the quality of the display device based on the target display parameter. The application can effectively solve the problems of response lag of traditional static gear regulation and insufficient scene adaptability.

Description

Technical Field

[0001] This application relates to the field of display technology, and in particular to a method, apparatus, device and medium for adjusting the image quality of a display device. Background Technology

[0002] Currently, large-screen display devices are widely used in various scenarios such as home entertainment, desktop office, and online education. In high-frequency usage scenarios such as watching movies in low light at night, working at close range, and studying online for extended periods, the human eye continuously receives optical stimuli that are not compatible with the current viewing environment. This can easily lead to symptoms of visual fatigue such as eye strain and blurred vision. Long-term use can also exacerbate visual loss in the human eye. The resulting visual loss problem restricts the improvement of viewing comfort on large-screen display terminals.

[0003] Currently, most mainstream display devices employ pre-configured fixed-level modes for image quality control, including static control schemes such as standard mode, movie mode, and basic eye protection mode. These schemes are ill-suited to the complex and ever-changing real-world viewing scenarios, exhibiting significant technical shortcomings. Specifically, existing static image quality control strategies rely solely on the device's built-in ambient light sensor to collect single-environment illuminance data as the basis for adjustment. This single-environment parameter results in low accuracy in assessing user visual fatigue. Furthermore, this fixed-mode control logic lacks dynamic response capabilities. When ambient light intensity fluctuates in real time, the user's viewing position changes, or the brightness of the image dynamically switches, the corresponding image quality parameters cannot be updated synchronously. This results in a significant lag in the control method, making it difficult to adapt to dynamically changing viewing environments and usage patterns.

[0004] In summary, existing static level-based image quality control solutions for display devices have drawbacks such as fixed control logic, inability to dynamically adapt to changes in scenarios, and limited dimensions and accuracy in assessing visual fatigue. Summary of the Invention

[0005] The purpose of this application is to provide a method, apparatus, computer device and storage medium for adjusting the image quality of a display device, so as to solve the problems of the existing image quality control mode being fixed, the visual fatigue assessment dimension being single, and the difficulty in adapting to dynamic viewing scenarios.

[0006] Firstly, a method for adjusting the image quality of a display device is provided, which adopts the following technical solution: The system continuously collects environmental parameter data, viewing behavior data, and content data from the display device. Based on these data, a pre-defined temporal risk model is used to determine the visual fatigue risk index for the current moment. Based on the visual fatigue risk index and content data, the system determines the total set of multi-dimensional image quality control parameters for the current moment. It then checks whether historical target display parameters generated in the previous moment exist. If so, a pre-defined frame-level smoothing function is used to smooth the total set of multi-dimensional image quality control parameters based on the historical target display parameters, resulting in the target display parameters. Finally, the system adjusts the image quality of the display device based on these target display parameters.

[0007] Secondly, a display device image quality adjustment device is provided, which adopts the following technical solution: The data acquisition module is used to continuously collect environmental parameter data, viewing behavior data, and content data of the display device. Based on the environmental parameter data, viewing behavior data, and content data, the visual fatigue risk index corresponding to the current moment is determined through a preset time-series risk model. The determination module is used to determine the total set of multi-dimensional image quality control parameters corresponding to the current moment based on the visual fatigue risk index and content data; The judgment module is used to determine whether the historical target display parameters generated in the previous time step exist. The smooth transition module is used to perform a smooth transition on the total set of multi-dimensional image quality control parameters based on historical target display parameters, using a preset frame-level smoothing function if the parameters exist, to obtain the target display parameters. The adjustment module is used to adjust the image quality of the display device based on the target display parameters.

[0008] Thirdly, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the image quality adjustment method of the above-described display device.

[0009] Fourthly, a computer-readable storage medium is provided, which stores a computer program that, when executed by a processor, implements the steps of the image quality adjustment method for the above-described display device.

[0010] Compared with existing technologies, the embodiments of this application have the following main advantages: By simultaneously collecting three types of data—environment, viewing behavior, and screen content—and combining them with a time-series risk model to calculate the fatigue index, visual fatigue is assessed from multiple dimensions, significantly improving the accuracy of the assessment. Based on the fatigue index and screen content, four types of subdivided image quality parameters are generated synchronously, providing more comprehensive control dimensions. A frame-level smoothing function is called in conjunction with historical parameters for transition processing, avoiding flickering caused by sudden changes in screen parameters. Finally, the image quality adjustment is uniformly driven based on the smoothed complete parameter set, achieving adaptive dynamic control for viewing scenarios, effectively solving the problems of lag in response and insufficient scene adaptability in traditional static level control. Attached Figure Description

[0011] To more clearly illustrate the solutions in this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is an exemplary system architecture diagram to which this application can be applied; Figure 2 A flowchart of an embodiment of the image quality adjustment method for a display device according to this application; Figure 3 This is a schematic diagram of one embodiment of the image quality adjustment device for a display device according to this application; Figure 4 This is a schematic diagram of the structure of one embodiment of the computer device according to this application. Detailed Implementation

[0013] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein in the specification of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having," and any variations thereof, in the specification, claims, and foregoing drawings of this application, are intended to cover non-exclusive inclusion. The terms "first," "second," etc., in the specification, claims, or foregoing drawings of this application are used to distinguish different objects, not to describe a particular order.

[0014] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0015] like Figure 1As shown, the system architecture 100 may include a terminal device 101, a network 102, and a server 103. The terminal device 101 may be a laptop computer 1011, a tablet computer 1012, or a mobile phone 1013. The network 102 is used as a medium to provide a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links, or fiber optic cables. Users can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications may be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social media platform software, etc. Terminal device 101 can be various electronic devices with a display screen and support web browsing. Besides laptops 1011, tablets 1012, or mobile phones 1013, terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 player (Moving Picture Experts Group Audio Layer IV), a laptop computer, and a desktop computer. Server 103 can be a server providing various services, such as a backend server supporting the pages displayed on terminal device 101.

[0016] It should be noted that the image quality adjustment method for the display device provided in this application embodiment is generally executed by a server / terminal device, and correspondingly, the image quality adjustment device for the display device is generally located in the server / terminal device. It should be understood that... Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0017] Continue to refer to Figure 2 A flowchart illustrating an embodiment of a display device image quality adjustment method according to this application is shown. The image quality adjustment method of the display device includes the following steps: Step S201: Continuously collect environmental parameter data, viewing behavior data, and content data of the display device. Based on the environmental parameter data, viewing behavior data, and content data, determine the visual fatigue risk index corresponding to the current moment through a preset time-series risk model.

[0018] In this embodiment, the display device is a large-screen display terminal equipped with a Mini-LED local dimming module, which can be adapted to various usage scenarios such as home audio-visual playback, desktop office, and online teaching. The device can continuously collect three types of raw data: external environment, user viewing behavior, and screen output image, and carry out the entire process of time-series risk model calculation, visual fatigue index solution, multi-dimensional image quality parameter adaptive calculation, and real-time image dimming.

[0019] In this embodiment, the environmental parameter data is the raw environmental perception data stream that the display device collects and outputs in real time through its built-in ambient light sensor. It includes unstandardized raw sampling information such as the sensor's original photosensitized values ​​and the time-series sampling signals of ambient brightness fluctuations. This data has temporal continuity, updates synchronously with the collection time, and can completely record the characteristics of external illumination changes throughout the entire time period within the sliding time window.

[0020] In this embodiment, the viewing behavior data is the raw sampling data of the user's viewing position collected by the display device. It may include the raw measurement values ​​of the distance between the user and the screen at different times, representing the degree of eye muscle tension corresponding to the user's viewing angle. The content data is the raw matrix data of pixel brightness extracted frame by frame by the display device, which can be used to statistically analyze the discrete characteristics of pixel brightness distribution in a single frame.

[0021] In this embodiment, the time-series risk model is a weighted nonlinear superposition integral operation model preset and embedded in the display device's storage unit. The complete mathematical operation formula for solving the visual fatigue risk index is shown below:

[0022] Wherein, R(t) represents the visual fatigue risk index corresponding to the current time t, which is the final output quantification value of the time series risk model, used to characterize the overall visual fatigue loss caused by the user's cumulative reception of optical stimuli within the sliding window duration.

[0023] Where t represents the current time, which is the base timestamp for this visual fatigue index calculation and also the upper limit of the integration calculation interval. All the latest collected environmental, viewing behavior, and screen content time series data are taken as the time series endpoint at this point in time.

[0024] Where T represents the total duration of the fixed sliding time window, which is a fixed constant built into the model. An example value can be 30 minutes. The integration interval is defined from tT to t, and only historical sampling data within this period participates in the integration calculation.

[0025] Where τ represents the integral variable, which represents any historical acquisition time within the sliding window range [tT,t]. The display device synchronously completes the acquisition of three types of raw data—environment, viewing behavior, and screen content—at each τ time, and is a general time identifier for discrete time-series sampling.

[0026] The set of multi-dimensional weight coefficients w1, w2, and w3 are built-in normalized fixed parameters that satisfy the constraint w1+w2+w3=1. w1 is the weight of the ambient illumination dimension, w2 is the weight of the viewing distance dimension, and w3 is the weight of the image content dimension, which respectively allocate the contribution ratio of the three types of factors to visual fatigue.

[0027] Among them, L env (τ) represents the standardized ambient illuminance at the historical acquisition time τ, in units of lux. It is obtained by mapping and calibrating the environmental parameter data collected by the display device and represents the ambient light intensity at that time.

[0028] Among them, L ref The reference standard illuminance is a fixed benchmark value built into the model. It is the comfortable ambient brightness threshold that makes it easy for the human eye to view for a long time without causing fatigue. It is used to normalize the ambient illuminance dimension data.

[0029] Among them, D user (τ) represents the standardized user viewing distance at the historical acquisition time τ, which is obtained by correcting the original measurement data of the distance sensing module and represents the straight-line distance between the user's eyes and the display panel at that time.

[0030] Among them, D ref This indicates the recommended viewing distance, which is a fixed reference value built into the model. For example, it can be set to 3 times the height of the display screen, which is the standard distance for comfortable viewing by the human eye.

[0031] Where, σ content (τ) represents the standard deviation of brightness of the frame corresponding to the historical acquisition time τ. It is obtained by statistical analysis of the pixel brightness matrix frame by frame, quantifies the discrete fluctuation range of pixel brightness in a single frame, and reflects the intensity of stimulation to the human eye caused by the switching between light and dark and high-frequency flicker.

[0032] Here, λ represents the forgetting factor, a fixed constant greater than 0 built into the model, and is the core parameter for constructing the temporal decay weight function. The larger the value of λ, the faster the weight decays for older historical sampling data, which is used to fit the physiological characteristic that the human eye is more sensitive to recent optical stimuli.

[0033] Among them, e λ(t τ) This represents the exponential decay time-weighted function, which is calculated using the forgetting factor λ and the time difference between the current time t and the historical sampling time τ. The further back in time the historical sampling point is from the current time, the smaller the output value of this function, thus achieving differentiated weighting of fatigue contributions at different time periods.

[0034] In this embodiment, the visual fatigue risk index is a quantified value R(t) output by the time-series risk model after summing all weighted instantaneous fatigue risk integrals within the sliding window, with the current time t as the integration endpoint. This value integrates the instantaneous fatigue contributions from three dimensions: ambient illuminance, viewing distance, and screen brightness fluctuations, and is further expressed through the exponential term e corresponding to the forgetting factor λ. λ(t τ) More recent sampled data is given higher weight to fully characterize the overall visual fatigue loss caused by the cumulative optical stimuli received by the user over a fixed period of time. The magnitude of the value directly corresponds to the degree of eye fatigue.

[0035] Step S202: Based on the visual fatigue risk index and content data, determine the total set of multi-dimensional image quality control parameters corresponding to the current moment.

[0036] In this embodiment, the set of multi-dimensional image quality control parameters includes a brightness upper limit parameter, a target color temperature parameter, a complete set of local contrast compression coefficients, and a set of backlight zone limiting coefficients. The brightness upper limit parameter is the maximum output brightness constraint value of the display device at the current moment, adapted to the user's visual fatigue state. It is a frame-level control parameter dynamically generated based on the device's hardware limits and the real-time visual fatigue risk index. This parameter differs from the device's fixed hardware maximum brightness and can adaptively and dynamically limit the brightness according to the level of fatigue risk. The higher the fatigue risk, the stricter the corresponding brightness upper limit constraint, which can actively suppress strong light flicker and excessive brightness stimulation.

[0037] In this embodiment, the target color temperature parameter is a precise screen color temperature adjustment value adapted to the current level of visual fatigue and the characteristics of the image content. It is used to define the white light color cast reference and color reproduction tone of the current frame. This parameter is based on the factory-fixed reference color temperature of the device, combined with a preset maximum color temperature offset constraint adjustment range, and dynamically corrected in conjunction with the visual fatigue risk index and real-time image content characteristics. It can fine-tune the warm or cool color temperature tendency according to different viewing and office scenarios. Compared with the fixed yellow color adjustment strategy of traditional eye protection mode, this parameter has dynamic adjustable characteristics. While alleviating the stimulation of short-wavelength blue light to the human eye and reducing visual fatigue, it avoids the image color distortion and color cast problems caused by a fixed color temperature offset across the entire range.

[0038] In this embodiment, the complete local contrast compression coefficient set is a fine-grained contrast control parameter group covering all pixel areas of the current image frame. It includes independent compression adjustment coefficients corresponding to different bright and dark areas of the image, used to specifically correct overexposure in bright areas and underexposure in dark areas, achieving local dynamic contrast adaptive optimization. The backlight zone limiting coefficient set is a grid-style brightness constraint parameter group adapted to the Mini-LED zone backlight architecture of the display device, corresponding to the independent brightness limiting ratio of each backlight zone.

[0039] Step S203: Determine whether there are historical target display parameters generated in the previous time step.

[0040] In this embodiment, the historical target display parameters are a complete set of image quality control parameters that the display device, after smoothing processing, finally takes effect and is cached and stored during the previous frame image rendering cycle. These parameters fully include four categories of control parameters: historical brightness, color temperature, local contrast, and backlight zone limiting. These parameters serve as the temporal benchmark for the smooth iteration of image quality parameters in the current image frame. Unlike the instantaneous calculation parameters of the current image frame, they record the actual image quality state of the display device at the previous moment, providing stable historical data support for the weighted fusion of parameters from adjacent frames.

[0041] Step S204: If it exists, a preset frame-level smoothing function is used to perform smooth transition processing on the total set of multi-dimensional image quality control parameters based on historical target display parameters to obtain target display parameters.

[0042] In this embodiment, the frame-level smoothing function is a time-weighted fusion operation function pre-installed in the display device's algorithm program, and it is the core operation model for achieving flexible transition of image quality parameters. This function can match exclusive smoothing weights according to different parameter types, and perform weighted iterative operations on the instantaneous parameters of the current frame and the effective parameters of historical frames. It can suppress drastic fluctuations in single-frame parameters, so that the image quality parameters of each frame are gradually updated based on the state of the previous frame. This can solve the technical problems of sudden changes in image quality, screen flicker, and color jumps during dynamic adaptive adjustment.

[0043] In this embodiment, the smooth transition processing abandons the abrupt adjustment logic that makes instantaneous parameters take effect directly. Instead, it constrains the change range of current parameters by using historical parameters to achieve a frame-by-frame gradual transition of brightness, color temperature, contrast, and backlight zone brightness. This significantly improves the smoothness of viewing in dynamic scenes and avoids the visual disjointedness caused by adaptive eye protection adjustment.

[0044] In this embodiment, the target display parameters are the complete set of image quality control parameters that are finally determined after frame-level smooth transition processing and are officially effective for the current image frame. They are the direct execution basis for the display device to perform the final image quality adjustment.

[0045] Step S205: If not, the total set of multi-dimensional image quality control parameters determined at the current moment is determined as the target display parameters.

[0046] In one embodiment, if none of these parameters exist, the current brightness upper limit parameter, target color temperature parameter, complete local contrast compression coefficient set, and backlight zone limiting coefficient set are directly used as the target display parameters.

[0047] Step S206: Adjust the image quality of the display device based on the target display parameters.

[0048] In this embodiment, image quality adjustment is a hardware execution process in which the display device synchronously drives the backlight driving circuit, color temperature adjustment module, contrast rendering module, and local dimming module to perform corresponding adjustment actions based on the final generated target display parameters. This process dynamically corrects the screen peak brightness, image color temperature tone, local image contrast, and backlight brightness of each zone based on smoothed multi-dimensional adaptation parameters. This achieves adaptive eye protection adjustment that adapts to the user's real-time visual fatigue state and the characteristics of the image content, effectively improving the shortcomings of traditional static level adjustment, such as poor adaptability and abrupt adjustment.

[0049] This application's embodiments simultaneously collect three types of data—environment, viewing behavior, and screen content—and combine them with a time-series risk model to calculate a fatigue index, thus assessing visual fatigue from multiple dimensions and significantly improving assessment accuracy. Based on the fatigue index and screen content, four types of detailed image quality parameters are generated synchronously, providing more comprehensive control dimensions. A frame-level smoothing function is invoked, combined with historical parameters, for transition processing to avoid flickering caused by sudden changes in screen parameters. Finally, the smoothed complete parameter set uniformly drives image quality adjustment, achieving adaptive dynamic control for viewing scenarios, effectively solving the problems of lag and insufficient scene adaptability in traditional static level control.

[0050] In some optional implementations, step S201, based on environmental parameter data, viewing behavior data, and content data, determines the visual fatigue risk index corresponding to the current moment through a preset time-series risk model, specifically including the following steps: Using a pre-defined time-series risk model, environmental parameter data, viewing behavior data, and content data are mapped and processed to obtain the ambient illuminance, user viewing distance, and standard deviation of screen brightness at each collection time. Based on the reference standard values, recommended viewing distance, and weight coefficient set built into the time-series risk model, the instantaneous visual fatigue risk components corresponding to each historical collection time are calculated and weighted by using ambient illuminance, user viewing distance, and standard deviation of screen brightness, to obtain the instantaneous fatigue risk at each historical collection time. Based on the forgetting factor built into the time-series risk model, an exponential decay weight is applied to the instantaneous fatigue risk at each historical collection time to obtain the weighted instantaneous fatigue risk at each historical collection time. Through the time-series risk model, within a fixed-duration sliding time window, the weighted instantaneous fatigue risks at all times are integrated and accumulated to obtain the visual fatigue risk index corresponding to the current time.

[0051] Among them, the instantaneous fatigue risk at a single moment is a quantified value obtained by weighting and summing the instantaneous fatigue sub-items of environment, viewing distance, and image content at any historical acquisition moment τ in the integral formula according to the weight coefficients. It corresponds to the part in square brackets in the above formula:

[0052] This value only represents the degree of immediate visual fatigue stimulation caused by three factors—environment, viewing distance, and image content—at a single sampling moment. It does not incorporate historical time-series attenuation weights and only reflects the instantaneous fatigue contribution at the sampling moment. It serves as the basis for subsequent intermediate calculations for applying exponential attenuation weights and integral accumulation operations.

[0053] Wherein, the exponential decay weight is the time-domain decay function e λ(t τ) The output value is obtained by solving for the forgetting factor λ and the time difference between the current time t and the historical acquisition time τ, and is a time weight term multiplied separately in the integral formula. This weight value decreases exponentially with the increase of the time interval between the historical acquisition time and the current time; the further back the historical sampling data is from the current time, the smaller the corresponding decay weight value. This weight is multiplied by the instantaneous fatigue risk at a single moment to complete the differentiated weighting of fatigue contribution in different historical periods, accurately simulating the human eye's differentiated perception ability of new and old visual stimuli.

[0054] The weighted instantaneous fatigue risk at a single moment is a quantified value obtained by multiplying the instantaneous fatigue risk at a specific historical data collection moment by the exponentially decaying weight matched for that moment, corresponding to the overall integrand in the above formula:

[0055] This value integrates the three-dimensional comprehensive fatigue stimulus at the instant, as well as the time decay effect of the period from the current time, to fully characterize the effective contribution of the historical sampling period to the current overall cumulative visual fatigue.

[0056] The fixed-duration sliding time window is a pre-configured continuous historical observation period intercepted from the current time t, with the time series risk model as the endpoint. The total window duration T is a fixed constant, corresponding to the lower limit tT of the integral in the above formula. The window defines the boundary of all historical acquisition times participating in the visual fatigue integral calculation. Only the weighted instantaneous fatigue risk within the interval [tT, t] inside the window participates in the cumulative calculation, while historical sampling data exceeding the fixed duration outside the window is discarded. The window continuously slides forward with the current time, updating the historical time series data included in the calculation in real time, realizing rolling cumulative fatigue quantification, and adapting to user scenarios of uninterrupted long-term viewing.

[0057] The integral accumulation is a continuous time-domain integral operation performed by the time-series risk model on the instantaneous fatigue risk at a single moment after weighting all values ​​within the sliding window [tT,t]. The operation continuously superimposes all effective instantaneous fatigue contributions with time decay weights within the window, ultimately outputting a visual fatigue risk index R(t) that integrates the cumulative effects of the entire time series. Unlike simple discrete numerical addition, integral accumulation can smoothly process high-frequency continuously sampled time-series data, accurately fit the fatigue accumulation process of the human eye continuously receiving optical stimuli, and improve the continuity and accuracy of fatigue quantification results.

[0058] This application's embodiments overcome the limitations of existing technologies that rely solely on single-environmental illumination assessments by simultaneously collecting three types of raw data and standardizing three-dimensional evaluation indicators through model mapping, thus broadening the dimensions of fatigue assessment. It solves for instantaneous fatigue components by combining human eye physiological laws across dimensions and weights them, accurately quantifying the independent fatigue contribution of each factor based on the formula's component structure, thereby improving the rationality of instantaneous stimulus assessment. It constructs an exponential decay weight term based on the forgetting factor, aligning with the physiological characteristic that the human eye is more sensitive to recent visual stimuli, and differentiates the fatigue impact of stimuli at different times. It achieves temporal cumulative quantification through fixed-duration sliding window definite integral accumulation, fully restoring the fatigue accumulation effect of prolonged viewing, significantly improving the accuracy of visual fatigue risk index assessment, and providing precise quantitative basis for refined adaptive image quality control.

[0059] In some optional implementations, the step "based on the reference standard values, recommended viewing distances, and weight coefficient sets built into the time-series risk model, using ambient illuminance, user viewing distance, and standard deviation of screen brightness, calculates the instantaneous visual fatigue risk components corresponding to each historical acquisition moment in different dimensions and then sums them by weight to obtain the single-moment instantaneous fatigue risk corresponding to each historical acquisition moment" specifically includes the following steps: The time-series risk model is equipped with a set of built-in reference standard values, recommended viewing distances, and weight coefficients. The weight coefficient set includes environmental illuminance weight coefficients, viewing distance weight coefficients, and image fluctuation weight coefficients. For each historical acquisition moment, considering the environmental illuminance, user viewing distance, and image brightness standard deviation, a first ratio of the environmental illuminance to the reference standard value is calculated. This first ratio is then fused with the environmental illuminance weight coefficient to obtain the instantaneous fatigue risk component for the environmental dimension. A non-linear mapping is performed between the recommended viewing distance and the user viewing distance to obtain a distance matching quantization value. This distance matching quantization value is then fused with the viewing distance weight coefficient to obtain the instantaneous fatigue risk component for the viewing distance dimension. Similarly, the image brightness standard deviation is fused with the image fluctuation weight coefficient to obtain the instantaneous fatigue risk component for the image fluctuation dimension. Finally, the instantaneous fatigue risk components for the environmental dimension, viewing distance dimension, and image fluctuation dimension are summed to obtain the single-moment instantaneous fatigue risk for the corresponding historical acquisition moment. This process is repeated for all historical acquisition moments to obtain the single-moment instantaneous fatigue risk for each historical acquisition moment.

[0060] Among them, the reference standard value is the standardized comfortable ambient illuminance L built into the time-series risk model. ref , is a fixed constant pre-stored in the device's storage unit, and is the baseline ambient light threshold that prevents the human eye from experiencing soreness, dryness, and fatigue when viewing a screen for a long time.

[0061] The first ratio is the standardized ambient illuminance L at a single historical data acquisition time. env (τ) and the reference standard value L ref The dimensionless value obtained by division corresponds to the terms of the above formula. It is used to quantify the degree to which the actual ambient light deviates from the comfort reference illuminance at the current moment.

[0062] Among them, the instantaneous fatigue risk component of the environmental dimension corresponds to w1 in the formula. The value is obtained by combining the first ratio with the environmental illuminance weighting coefficient w1. It represents the fatigue quantification caused solely by environmental lighting conditions at a single historical data collection moment. This component independently characterizes the magnitude of visual stimulation caused by environmental illuminance deviating from the comfort standard. It reflects only the contribution of the lighting dimension to human eye fatigue and is independent of and does not interfere with the viewing distance and image fluctuation dimensions.

[0063] Among them, the distance matching quantization value is the recommended viewing distance D. ref Viewing distance D from the user user (τ) after inverse square nonlinear mapping operation ( ) 2The output dimensionless numerical value corresponds to the basic term of the distance dimension in the formula. This quantified value is based on a non-linear mapping logic constructed according to the physiological characteristics of the human eye: the closer the user's viewing distance, the larger the value, simulating the fatigue exacerbated by the excessive screen viewing angle and continuous tension of the ciliary muscle when viewing at close range.

[0064] Among them, the instantaneous fatigue risk component of the viewing distance dimension corresponds to w2 in the formula. ( ) 2 This value is generated by fusing the distance matching quantization value with the viewing distance weighting coefficient w2, representing the quantification value of visual fatigue caused solely by abnormal user viewing distance at a single historical data collection moment. This sub-item independently isolates the fatigue contribution of the viewing behavior dimension, relying on an inverse square nonlinear mapping to conform to the physiological laws of human eye muscle tension, thus overcoming the shortcoming of existing technologies that completely ignore the impact of viewing distance on visual fatigue.

[0065] Among them, the instantaneous fatigue risk component of the image fluctuation dimension corresponds to w3 in the formula. σ content (τ), derived from the standard deviation of screen brightness σ content (τ) is obtained by fusing it with the image fluctuation weighting coefficient w3, and is an independent fatigue quantification value caused only by image brightness fluctuations and high-frequency flicker at a single historical acquisition moment. The image brightness standard deviation represents the degree of pixel brightness dispersion in a single frame. The higher the value, the more intense the image switching and flickering, and the stronger the stimulation to the photoreceptor cells of the human eye.

[0066] This application's embodiments achieve controllable and adjustable contribution ratios of the three types of fatigue-influencing factors by retrieving the model's built-in complete set of benchmark parameters and independent dimension weights. It unifies the illumination assessment scale through the ratio of ambient illuminance to standard illuminance, accurately separating the independent fatigue contribution of ambient light. It employs an inverse-square nonlinear mapping to quantify the physiological fatigue effect of viewing distance, supplementing the viewing behavior assessment dimension missing in existing technologies. It quantifies image fluctuation stimulation based on the standard deviation of image brightness, improving the multi-dimensional assessment system. By independently solving the three categories and then summing them to obtain instantaneous risk, it can accurately distinguish the individual fatigue contribution of each factor, significantly improving the precision of single-moment visual stimulus assessment.

[0067] In some optional implementations, step 202, based on the visual fatigue risk index and content data, determines the total set of multi-dimensional image quality control parameters corresponding to the current moment, specifically including the following steps: Based on the display device's built-in maximum hardware brightness and visual fatigue risk index, the upper limit parameter of brightness at the current moment is determined; based on the display device's built-in reference color temperature, preset maximum color temperature offset, visual fatigue risk index, and content data, the target color temperature parameter at the current moment is determined; the current image frame corresponding to the current acquisition moment is extracted from the content data, and based on the current image frame and visual fatigue risk index, the complete local contrast compression coefficient set corresponding to the current moment is determined; based on the maximum hardware brightness of each backlight zone built-in in the display device and the current image frame, the backlight zone limiting coefficient set corresponding to the current moment is determined; the upper limit parameter of brightness, target color temperature parameter, complete local contrast compression coefficient set, and backlight zone limiting coefficient set are determined as the total set of multi-dimensional image quality control parameters corresponding to the current moment.

[0068] Among them, the maximum hardware brightness is the absolute peak output brightness that the display device is fixed at the factory and that the hardware driving circuit and backlight module can support. It is an inherent static hardware parameter of the device and does not change with software algorithms, screen content and usage scenarios.

[0069] Among them, the reference color temperature is a standard neutral color temperature fixed value that is preset by the display device at the factory and adapted to standard movie viewing scenarios. It is the reference tone for the true reproduction of the picture color and serves as the initial reference for the dynamic adjustment of the target color temperature parameter.

[0070] Among them, the maximum color temperature offset is the upper limit threshold of the color temperature adjustment range preset by the algorithm. It is used to constrain the maximum offset range of the target color temperature relative to the reference color temperature and belongs to the fixed algorithm constraint parameters.

[0071] The current image frame is the original image data to be rendered on the screen at the current moment, which is extracted frame by frame from the real-time content data. It contains original image information such as complete pixel brightness matrix, color distribution, and brightness and darkness details.

[0072] Among them, the maximum brightness of the hardware of each zone is the inherent peak brightness parameter corresponding to each independent backlight zone of the display device, which is determined by the hardware specifications of the Mini-LED backlight module. It is the physical upper limit of independent dimming of each zone, and each zone can have the same or different hardware brightness thresholds.

[0073] In one example, first, the maximum hardware brightness B of the display device is obtained. dev The preset brightness attenuation function f is used. bright (R), the visual fatigue risk index R is processed by nonlinear mapping, and the scalar result output by function operation is the brightness attenuation coefficient k. bright (R), satisfying f bright (R)=k bright (R). The brightness decay function is composed of a preset steepness coefficient β1 and a brightness adjustment threshold R. th1The brightness decay function expression is constructed as follows:

[0074] Set the hardware maximum brightness B dev With brightness attenuation coefficient k bright (R) is multiplied and fused to obtain the upper limit parameter B of the brightness at the current time. max .

[0075] Next, obtain the reference color temperature T built into the display device. base The preset maximum color temperature offset ΔT, adjustment coefficient β2, and color temperature adjustment threshold R th2 The preset color temperature weighting function f is used. temp (R), the visual fatigue risk index R is processed by nonlinear mapping, and the scalar result output by function operation is the color temperature weighting coefficient k. temp (R), satisfying f temp (R)=k temp (R). Color temperature weighting function f temp (R) is constructed from the adjustment coefficient β2 and the color temperature adjustment threshold. th2 The expression for the color temperature weighting coefficient is:

[0076] The maximum color temperature offset ΔT and the color temperature weighting coefficient k temp (R) is then fused to obtain the color temperature shift correction amount ΔT×k. temp (R), for reference color temperature T base The base target color temperature T is obtained by fusing it with the color temperature offset correction amount (i.e., T=T). base +ΔT×k temp (R)), based on content data, the basic target color temperature is adjusted by range constraints: preset lower limit T for color temperature adjustment. min =T base -ΔT, upper limit of color temperature adjustment T max =T base +ΔT, lock the base target color temperature at [T min T max [Range; if the base target color temperature is below the lower limit, then a value of T is forcibly assigned.] min If it exceeds the upper limit, it will be forcibly assigned the value T. max With the remaining values ​​unchanged, the target color temperature parameters corresponding to the current moment are obtained after the constraints are completed.

[0077] Next, the current image frame corresponding to the current acquisition time is extracted from the content data. Based on the current image frame and the visual fatigue risk index, the complete local contrast compression coefficient set corresponding to the current time is calculated. At the same time, based on the maximum hardware brightness of each backlight zone built into the display device and the current image frame, the backlight zone limiting coefficient set corresponding to the current time is calculated. Finally, the brightness upper limit parameter, target color temperature parameter, complete local contrast compression coefficient set, and backlight zone limiting coefficient set are determined as the total set of multi-dimensional image quality control parameters corresponding to the current time.

[0078] This application's embodiments dynamically generate upper limit parameters for brightness based on the device's maximum hardware brightness and fatigue risk index, achieving flexible brightness constraints based on hardware boundaries and avoiding the drawbacks of a one-size-fits-all approach to brightness reduction. By linking the reference color temperature and controllable maximum offset with the fatigue index for color adjustment, low-distortion blue light suppression is achieved, balancing eye protection and color reproduction. A set of local contrast coefficients is generated by combining real-time image frames and fatigue risk, and contrast is compressed differently according to different areas of the image, effectively balancing eye protection and image detail preservation. By matching the hardware brightness of each zone with the image content to solve for the zone limiting coefficient, fine-grained dimming by zone is achieved, improving the poor adaptability and severe image quality degradation problems of traditional static control.

[0079] In some optional implementations, the step "determine the complete set of local contrast compression coefficients corresponding to the current moment based on the current image frame and the visual fatigue risk index" specifically includes the following steps: The current image frame is divided into blocks to obtain multiple non-overlapping image sub-blocks. The global maximum brightness and global minimum brightness of the current image frame are extracted, and the average brightness of each sub-block is calculated. A preset adjustment intensity function is used to perform non-linear mapping processing on the visual fatigue risk index to obtain a fatigue matching adjustment intensity value. For each sub-block, the corresponding sub-block average brightness, global maximum brightness, and global minimum brightness are quantized into ratios to obtain a quantized value of the sub-block brightness proportion. The fatigue matching adjustment intensity value and the quantized value of the sub-block brightness proportion are fused to obtain a sub-block contrast correction amount for each sub-block. Based on a preset benchmark value, the sub-block contrast correction amount is canceled to obtain a local contrast compression coefficient for each sub-block. All image sub-blocks are traversed to obtain a complete set of local contrast compression coefficients corresponding to the current time.

[0080] Among them, multiple image sub-blocks are non-overlapping rectangular image units generated by equally dividing the current single-frame complete image frame according to a fixed M-row N-column grid rule. After all sub-blocks are stitched together, the complete image frame can be restored without omission. Each image sub-block has coordinates (x, y).

[0081] The global maximum brightness is denoted as L. bright, is the peak constant among all pixel brightness values ​​in the current image frame, and is the upper limit boundary of the dynamic range of brightness of the entire frame.

[0082] The global minimum brightness is denoted as L. dark , is the valley value constant among all pixel brightness values ​​in the current image frame, representing the brightness benchmark of the darkest pixel in the entire frame. This parameter, together with the global maximum brightness, defines the complete dynamic brightness range of a single frame. bright ,L dark ].

[0083] The average brightness of the sub-block is denoted as L. local (x,y) represents the arithmetic mean of the brightness of all pixels within a single image sub-block at coordinates (x,y), characterizing the overall brightness level of that sub-block. This value is the core input variable for the block quantization ratio calculation, enabling precise differentiation between bright sub-blocks, neutral brightness sub-blocks, and dark sub-blocks.

[0084] The intensity adjustment function is denoted as α(R), which is a preset, fixed nonlinear mapping function stored in the display device's memory unit. The input variable is the visual fatigue risk index R, and the output value range is fixed within [0, 0.5]. The function expression is:

[0085] In the function expression, β α β is the steepness parameter for the contrast adjustment curve. thα The contrast compression trigger risk threshold is a preset constant. The intensity adjustment function α(R) is used to establish the relationship between the user's cumulative fatigue level and the contrast compression intensity. The higher the fatigue risk index R value, the larger the function output value, which represents the stronger the contrast compression intensity.

[0086] Among them, the fatigue matching adjustment intensity value is a dimensionless scalar output after substituting the adjustment intensity function α(R) into the current visual fatigue risk index R. The value range is limited to [0, 0.5]. This value quantifies the maximum allowable amplitude of contrast compression corresponding to the current user's visual fatigue level. The higher the fatigue level, the larger the value, and the stronger the reduction of the contrast of the bright sub-blocks.

[0087] The quantization ratio processing involves a standardized computational process that takes the average brightness of a single image sub-block, the global maximum brightness, and the global minimum brightness as input, and performs normalized fractional operations. This process converts the original average brightness of the sub-block, which has no fixed range, into a dimensionless percentage value between 0 and 1, eliminating computational biases caused by differences in brightness baselines across different images, unifying the brightness quantization scale of all sub-blocks, and intuitively representing the relative brightness level of a single sub-block within the overall image's brightness range.

[0088] The sub-block brightness ratio quantization value is a dimensionless value output after quantization ratio processing, and its value range can be [0,1]. Its calculation formula is as follows:

[0089] The closer the brightness ratio quantization value of this sub-block is to 1, the closer the overall brightness of the sub-block is to the peak brightness of the image, indicating a bright area; a value close to 0 indicates that the sub-block is a dark area. This quantization value accurately distinguishes the brightness attributes of different sub-blocks, allowing bright sub-blocks to receive a greater amount of contrast correction, while dark sub-blocks undergo almost no contrast compression, balancing eye protection needs with the preservation of dark details.

[0090] The sub-block contrast correction amount is a value obtained by multiplying and fusing the fatigue matching adjustment intensity value and the sub-block brightness ratio quantization value. This value represents the magnitude of contrast reduction required for the corresponding image sub-block. The higher the sub-block brightness and the higher the user fatigue level, the larger the correction amount, indicating a stronger magnitude of contrast compression required.

[0091] The preset reference value is a fixed constant that can be set to 1. This reference value represents the reference scaling factor when there is no contrast compression. When the fatigue matching adjustment intensity value is 0 (no visual fatigue), the local contrast compression factor is equal to 1, and the image contrast is completely preserved without reduction. Using 1 as a unified reference can ensure that the compression factor value range is stable in [0.5,1], avoiding excessive contrast compression that causes the image to appear grayish and lose layers.

[0092] The cancellation operation involves subtracting the sub-block contrast correction amount from a preset baseline value of 1. By using the subtraction cancellation method, the compression magnitude corresponding to the contrast correction amount is subtracted from the complete baseline contrast, thereby automatically reducing the contrast in bright areas. The output value is the local contrast compression coefficient. The closer the value is to 1, the more complete the contrast is preserved; the smaller the value, the stronger the contrast compression.

[0093] Wherein, the local contrast compression coefficient is denoted as C(x,y), which is the contrast scaling control parameter specific to a single image sub-block at coordinate (x,y). It is the final output result after the cancellation operation, and the complete solution formula is:

[0094] The local contrast compression coefficient ranges from [0.5, 1]. The higher the fatigue level and the brighter the sub-block, the smaller the coefficient value, and the more obvious the contrast compression, thus suppressing the stimulation of the human eye by bright light.

[0095] This application's embodiments break through the limitations of globally uniform adjustment by dividing image frames into non-overlapping grid blocks, achieving refined contrast control for different zones. It extracts global extreme values ​​of brightness and darkness and calculates the average brightness of sub-blocks, accurately quantifying the relative brightness characteristics of each zone. Relying on a fatigue-driven adjustment intensity function to map compression levels, the adjustment range aligns with the user's real-time fatigue state. Sub-block brightness levels are quantified through normalized ratios, unifying the calculation scale across different images. The fatigue intensity is fused with the sub-block brightness ratio to generate a correction amount, automatically matching a larger compression range to bright areas. The correction amount is offset by a baseline value to obtain the zone compression coefficient, balancing eye protection and dark detail. A complete coefficient set is generated by traversing all sub-blocks, significantly improving the defects of static uniform compression that cause glare in bright areas and loss of image detail.

[0096] In some optional implementations, the step "determine the set of backlight zone limiting coefficients corresponding to the current moment based on the maximum hardware brightness of each backlight zone built into the display device and the current image frame" specifically includes the following steps: The system reads the maximum hardware brightness of each backlight zone built into the display device. Based on the image content data of the current image frame, it establishes a mapping relationship between the backlight zone index and the corresponding panel screen area of ​​each backlight zone. Using a preset attenuation mapping function, it performs non-linear mapping processing on the visual fatigue risk index to obtain the brightness attenuation correction amount. It iterates through each backlight zone and performs quantization ratio processing on the maximum hardware brightness of the zone and the brightness attenuation correction amount to obtain the single-zone backlight limiting coefficient corresponding to each backlight zone. It integrates the single-zone backlight limiting coefficients corresponding to all backlight zones to obtain the zone basic limiting parameter array. It binds and matches the zone basic limiting parameter array and the mapping relationship to obtain the set of backlight zone limiting coefficients corresponding to the current moment.

[0097] The maximum brightness of the partition hardware can be expressed as L. max_hw , is the factory-fixed peak luminous brightness of a single backlight zone module in the Mini-LED backlight architecture. It is a static constant representing the physical upper limit of the backlight output of the zone. Different backlight zones can be configured with the same or different hardware brightness thresholds.

[0098] The mapping relationship between the backlight partition index and the corresponding panel screen area of ​​each backlight partition is a one-to-one correspondence index lookup table stored in the display device cache. Each digital backlight partition index k is uniquely bound to a fixed rectangular screen display area on the screen panel, precisely defining the pixel screen range that the k-th backlight partition is responsible for rendering. This mapping achieves coordinate alignment between the backlight hardware partition and the image frame screen area, ensuring that the partition limiting coefficient can accurately match the corresponding position of the screen and avoiding misalignment between backlight dimming and screen content.

[0099] The attenuation mapping function is a pre-defined S-shaped nonlinear transfer function, which is the core computational model for solving the single-zone backlight limiting coefficient. The complete expression is:

[0100] The attenuation mapping function takes the visual fatigue risk index R as its input variable and includes a built-in fixed constant steepness parameter β and a risk threshold R that triggers the amplitude limit. th k represents the k-th backlight zone. This function is used to establish a non-linear relationship between the cumulative visual fatigue level and the peak compression amplitude of the backlight zone. When the fatigue index is higher than the threshold R... th When the output value increases, it decreases smoothly as R increases, realizing a flexible limiting logic that allows for lower peak brightness in the partitioned backlight as fatigue increases, thus avoiding the brightness flickering problem caused by linear dimming.

[0101] Among them, the brightness attenuation correction is a dimensionless scaling factor generated by the attenuation mapping function after completing the nonlinear mapping based on the visual fatigue risk index R, corresponding to the above. The attenuation weight is calculated using an internal exponential method. This correction quantifies the compression ratio of the peak brightness of the local area backlight due to the current user's accumulated fatigue. The larger the fatigue risk index R, the larger the correction value, and the stronger the compression of the maximum brightness of the local area hardware.

[0102] The single-zone backlight limiting coefficient is denoted as L. dim (k) represents the peak brightness constraint parameter specific to the k-th backlight zone. This coefficient is the upper limit threshold for the real-time output brightness of the zone's backlight, and its value is less than or equal to the corresponding zone's maximum hardware brightness L. max_hw When visual fatigue is low, R <R th When the coefficient approaches the hardware limit brightness of the partition, the bright details of the image are fully preserved; when the fatigue level exceeds the standard and R>R th When the coefficient decreases smoothly, the peak backlight brightness of the zone is actively reduced, suppressing local strong light stimulation and achieving independent eye protection light control for each zone.

[0103] Among them, the partition basic limiting parameter array is formed by combining all backlight partition indices k with the corresponding solved single-partition backlight limiting coefficients L. dim (k) A two-dimensional parameter array is generated by integrating the data according to an ordered grid structure. The array dimensions correspond one-to-one with the row and column arrangement of the Mini-LED backlight physical partitions. The array completely stores the independent brightness upper limit constraint values ​​of all backlight partitions of the screen.

[0104] The binding matching process involves matching the single-partition backlight limiting coefficient L corresponding to each backlight partition index k in the partition basic limiting parameter array. dim(k) is a structured processing flow that associates and binds each set of limiting coefficients with a pre-established mapping relationship between the backlight partition and the image area. After processing, each set of limiting coefficients synchronously carries the coordinate information of the panel image area it controls, so that the limiting parameters correspond precisely to the pixel area of ​​the image frame. Finally, a set of backlight partition limiting coefficients that can be directly used for image rendering and dimming is generated, ensuring that different bright and dark areas of the image match the differentiated peak constraints of the corresponding backlight partition, and realizing content-following partitioned eye-protection dimming.

[0105] This application embodiment achieves precise alignment between backlight hardware and screen pixels by reading the inherent hardware brightness of each zone and establishing a mapping between the zone and the screen area, thus avoiding dimming misalignment. It utilizes an S-shaped attenuation mapping function to nonlinearly calculate the fatigue index, obtaining an attenuation correction amount to smoothly transition backlight brightness and eliminate flicker during level switching. Independent limiting coefficients are calculated for each zone based on the hardware brightness and attenuation correction amount, achieving differentiated peak constraints for each zone. All zone coefficients are systematically integrated to generate a regular parameter array for easy batch reading and retrieval. Binding and matching the parameter array with the screen mapping ensures precise backlight limiting to the bright and dark areas of the screen, effectively solving the shortcomings of traditional global backlight control—a one-size-fits-all approach, strong light in high-brightness areas irritating the eyes, and an inability to balance eye protection with image detail.

[0106] In some optional implementations, step S204 involves using a preset frame-level smoothing function to perform a smooth transition process on the total set of multi-dimensional image quality control parameters based on historical target display parameters, thereby obtaining the target display parameters. This specifically includes the following steps: Obtain preset global scalar smoothing weights, image sub-block smoothing weights, and backlight zone smoothing weights; decompose historical target display parameters to obtain a total set of historical multi-dimensional image quality control parameters, including historical brightness upper limit parameters, historical target color temperature parameters, a set of historical complete local contrast compression coefficients, and a set of historical backlight zone limiting coefficients; use a preset frame-level smoothing function to perform weighted fusion processing on the brightness upper limit parameters and historical brightness upper limit parameters, and the target color temperature parameters and historical target color temperature parameters, respectively, to obtain smoothed brightness upper limit parameters and smoothed target color temperature parameters; traverse all image sub-blocks, call the frame-level smoothing function, and compare the local contrast compression coefficients at the same coordinate with the historical complete local contrast... The historical local contrast compression coefficients corresponding to the compression coefficient set are weighted and processed. The weighted processing results of all image sub-blocks are integrated to generate a smoothed complete local contrast compression coefficient set. All backlight partitions are traversed, and the frame-level smoothing function is called to weight the single-partition backlight limiting coefficient under the same backlight partition index with the corresponding historical single-partition backlight limiting coefficient in the historical backlight partition limiting coefficient set. The calculation results of all backlight partitions are integrated to generate a smoothed backlight partition limiting coefficient set. The smoothed brightness upper limit parameter, the smoothed target color temperature parameter, the smoothed complete local contrast compression coefficient set, and the smoothed backlight partition limiting coefficient set are integrated to obtain the target display parameters corresponding to the current time.

[0107] Among them, the global scalar smoothing weight is a fixed weighting coefficient preset for single-value scalar parameters such as the upper limit of brightness and the target color temperature. It is a dedicated control parameter of the frame-level smoothing function.

[0108] The image sub-block smoothing weight is a pre-defined weighting coefficient for the local contrast compression coefficient array, adapted to the smoothing iterative calculation of the two-dimensional parameters of the segmented image. This weight is used to control the fusion ratio of the historical contrast parameters and the current instantaneous contrast parameters of a single image sub-block.

[0109] Among them, the backlight partition smoothing weight is a preset differential weighting coefficient for the backlight partition limiting coefficient array, which is adapted to the timing smoothing calculation of the Mini-LED partition backlight grid parameters.

[0110] The historical brightness upper limit parameter is the screen global brightness upper limit constraint parameter that was finally effective and cached in the previous image frame period. This parameter records the peak brightness upper limit of the device at the previous stable operation moment, and serves as the benchmark for smooth correction of the brightness upper limit parameter of the current image frame.

[0111] Among them, the historical target color temperature parameter is the screen reference color temperature adjustment parameter that was finally effective in the previous rendering cycle. It is the core quantum parameter that controls the color tone of the screen in the historical target display parameters.

[0112] The historical complete set of local contrast compression coefficients is an array of contrast control parameters that took effect in the previous image frame period and covers all image sub-blocks. This set preserves the stable contrast compression state of each image sub-block in the previous frame.

[0113] Among them, the historical backlight zone limiting coefficient set is an array of brightness limiting parameters that took effect in the previous rendering cycle and covers all Mini-LED backlight zones.

[0114] Among them, the smoothed upper limit brightness parameter takes into account both the historical stable brightness state and the current fatigue state adaptation needs. It retains the accuracy of adaptive eye protection dimming while avoiding large instantaneous fluctuations in global brightness. It is the stable execution parameter for the current image frame screen peak brightness control.

[0115] Among them, the smoothed target color temperature parameter weakens the instantaneous color temperature shift amplitude, so that the warm and cool tones of the picture gradually adjust according to the user's visual fatigue state. While achieving blue light suppression and eye-protecting color adjustment, it ensures that the color tone of the picture is continuous without jumps, and improves dynamic viewing comfort.

[0116] Among them, the smoothed complete local contrast compression coefficient set realizes the smooth transition of contrast in every local area of ​​the picture, accurately adapts to the changes in dynamic picture content, retains the local eye protection compression effect, and avoids the problems of harsh contrast transition and flickering details in local picture.

[0117] Among them, the set of backlight zone limiting coefficients after smoothing enables frame-by-frame gradual adjustment of the backlight brightness of each zone, adapting to dynamic screen brightness switching and fatigue state changes, effectively solving the flickering and brightness fluctuation problems that are prone to occur in Mini-LED zone light control, and taking into account both eye protection effect and screen display stability.

[0118] This application embodiment configures three types of differentiated smoothing weights to specifically adapt to the transition requirements of different image quality parameters, improving the precision of smoothing control. It splits historical target display parameters to achieve precise matching of various temporal parameters, avoiding parameter cross-interference that affects smoothing accuracy. Weighted fusion of scalar parameters effectively eliminates instantaneous jumps and flickering in global brightness and color temperature. Sub-block smoothing comparison parameters ensure natural transitions in local image details without abrupt flickering. Zone-by-zone correction of backlight limiting parameters solves the problem of brightness and darkness fluctuations in Mini-LED zone control. Integrating multi-dimensional smoothing parameters to generate final control parameters significantly improves the continuity of image display and viewing comfort in dynamic scenes while maintaining adaptive eye protection accuracy.

[0119] In some optional implementations, after adjusting the image quality of the display device based on the target display parameters in step S205, the following steps are further included: After completing the real-time adaptive image quality adjustment of a single device, continuously collecting the user's individual preference adjustment parameter set under the display device, the individual preference adjustment parameter set consists of the image quality adjustment weights and various nonlinear mapping function parameters that are continuously iteratively optimized during the device's adaptive control process; uniformly encapsulating and packaging the user ID, source device type, parameter synchronization timestamp, and individual preference adjustment parameter set corresponding to the current user; encrypting and uploading the encapsulated individual preference adjustment parameter set, user ID, source device type, and synchronization timestamp to the cloud server for storage; and recognizing the user's login with the same user account on the target device. The system retrieves the target device's device type, peak brightness, and corresponding inverse photoelectric conversion function. It then accesses the source device's adjustment parameter set, photoelectric conversion function, and peak brightness from cloud storage. Based on a preset parameter normalization mapping formula, the source device's adjustment parameters are converted: the original adjustment parameters are mapped to the standard visual brightness space using the display device's photoelectric conversion function, multiplied by the ratio of the source device's peak brightness to the target device's peak brightness, and the target device's corresponding device type correction coefficient. Finally, the system performs a reverse conversion using the target device's inverse photoelectric conversion function to obtain the normalized adjustment parameters adapted to the target device. These normalized adjustment parameters are then loaded onto the target device to complete the image quality parameter adaptation. Cross-device parameter synchronization adaptation is triggered when the user switches display devices or logs in.

[0120] This application embodiment continuously collects and iteratively generates a set of user preference parameters after single-device adaptive image quality adjustment, fully preserving the adjustment weights and mapping functions adapted to individual visual habits. It binds accounts, devices, and timestamps to encapsulate data packets, ensuring the traceability of user parameter ownership and version. Encrypted uploads to the cloud enable persistent storage of preference parameters across devices. When a user logs into other devices, the hardware photoelectric parameters are automatically identified, accurately matching the cloud-based source device's baseline data. Based on standard brightness space normalization, parameter adaptation deviations caused by differences in screen hardware specifications are eliminated. Reverse conversion generates adjustment parameters adapted to the device and loads them, eliminating the need for manual adjustments by the user; switching devices seamlessly continues the exclusive eye-protection image quality control logic.

[0121] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing related hardware through computer-readable instructions. These computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. The aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, optical disk, or read-only memory (ROM), or random access memory (RAM).

[0122] Further reference Figure 3 As a response to the above Figure 2 The implementation of the method shown in this application provides an embodiment of a display device image quality adjustment apparatus, which is similar to... Figure 2 Corresponding to the illustrated method embodiments, this device can be specifically applied to various electronic devices. For example... Figure 3 As shown, the image quality adjustment device 400 of the display device in this embodiment includes: a collection module 401, a determination module 402, a judgment module 403, a smooth transition module 404, and an adjustment module 405. Wherein: The acquisition module 401 is used to continuously acquire environmental parameter data, viewing behavior data, and content data of the display device. Based on the environmental parameter data, viewing behavior data, and content data, the visual fatigue risk index corresponding to the current moment is determined through a preset time-series risk model. The determination module 402 is used to determine the total set of multi-dimensional image quality control parameters corresponding to the current moment based on the visual fatigue risk index and content data; The judgment module 403 is used to determine whether the historical target display parameters generated in the previous time are present. The smooth transition module 404 is used to, if present, employ a preset frame-level smoothing function to perform smooth transition processing on the total set of multi-dimensional image quality control parameters based on historical target display parameters, thereby obtaining the target display parameters; The adjustment module 405 is used to adjust the image quality of the display device based on the target display parameters.

[0123] In one embodiment, the acquisition module 401 includes: The mapping submodule is used to map environmental parameter data, viewing behavior data, and content data respectively through a preset time-series risk model to obtain the ambient illuminance, user viewing distance, and standard deviation of screen brightness at each collection time. The calculation submodule is used to calculate the instantaneous visual fatigue risk sub-items corresponding to each historical collection moment based on the reference standard value, recommended viewing distance and weight coefficient set built into the time series risk model, using ambient illuminance, user viewing distance and screen brightness standard deviation, and then weighted summation to obtain the instantaneous fatigue risk at each historical collection moment. The application submodule is used to apply an exponentially decaying weight to the instantaneous fatigue risk at each historical acquisition time based on the forgetting factor built into the time series risk model, so as to obtain the weighted instantaneous fatigue risk at each historical acquisition time. The integral accumulation submodule is used to accumulate the weighted instantaneous fatigue risk at a single moment within a fixed sliding time window using a time-series risk model, and obtain the visual fatigue risk index corresponding to the current moment.

[0124] In one embodiment, the calculation submodule is further configured to obtain the reference standard value, recommended viewing distance, and weight coefficient set built into the time-series risk model. The weight coefficient set includes the ambient illuminance weight coefficient, the viewing distance weight coefficient, and the image fluctuation weight coefficient. For each historical acquisition moment, the ambient illuminance, user viewing distance, and image brightness standard deviation are used to calculate a first ratio of the ambient illuminance to the reference standard value. The first ratio is then fused with the ambient illuminance weight coefficient to obtain the instantaneous fatigue risk component in the environmental dimension. The recommended viewing distance and the user viewing distance are then subjected to nonlinear mapping to obtain a distance matching quantization value. This distance matching quantization value is then fused with the viewing distance weight coefficient to obtain the instantaneous fatigue risk component in the viewing distance dimension. The image brightness standard deviation and the image fluctuation weight coefficient are then fused to obtain the instantaneous fatigue risk component in the image fluctuation dimension. The instantaneous fatigue risk components in the environmental dimension, the viewing distance dimension, and the image fluctuation dimension are then summed to obtain the single-moment instantaneous fatigue risk for the corresponding historical acquisition moment. All historical acquisition moments are then traversed to obtain the single-moment instantaneous fatigue risk for each historical acquisition moment.

[0125] In one embodiment, the determining module 402 includes: The first determining submodule is used to determine the upper limit parameter of brightness at the current moment based on the maximum hardware brightness and visual fatigue risk index built into the display device. The second determination submodule is used to determine the target color temperature parameters at the current moment based on the reference color temperature built into the display device, the preset maximum color temperature offset, the visual fatigue risk index, and the content data. The third determination submodule is used to extract the current image frame corresponding to the current acquisition time from the content data, and determine the complete set of local contrast compression coefficients corresponding to the current time based on the current image frame and the visual fatigue risk index. The fourth determination submodule is used to determine the set of backlight zone limiting coefficients corresponding to the current moment based on the maximum brightness of each backlight zone built into the display device and the current image frame. The determination submodule is used to determine the brightness upper limit parameter, target color temperature parameter, complete local contrast compression coefficient set, and backlight zone limiting coefficient set as the total set of multi-dimensional image quality control parameters corresponding to the current moment.

[0126] In one embodiment, the third determining submodule is further configured to perform block processing on the current image frame to obtain multiple non-overlapping image sub-blocks; extract the global maximum brightness and global minimum brightness of the current image frame, and calculate the average brightness of each sub-block; use a preset adjustment intensity function to perform nonlinear mapping processing on the visual fatigue risk index to obtain a fatigue matching adjustment intensity value; for each image sub-block, perform quantization ratio processing on the corresponding sub-block average brightness, global maximum brightness, and global minimum brightness to obtain a quantized value of the sub-block brightness proportion corresponding to each image sub-block; perform fusion processing on the fatigue matching adjustment intensity value and the sub-block brightness proportion quantized value to obtain a sub-block contrast correction amount corresponding to each image sub-block; perform a cancellation operation on the sub-block contrast correction amount based on a preset benchmark value to obtain a local contrast compression coefficient corresponding to each image sub-block, and traverse all image sub-blocks to obtain a complete set of local contrast compression coefficients corresponding to the current time.

[0127] In one embodiment, the fourth determining submodule is further configured to read the maximum hardware brightness of each backlight zone built into the display device, establish a mapping relationship between the backlight zone index and the panel screen area corresponding to each backlight zone based on the image content data of the current image frame; use a preset attenuation mapping function to perform nonlinear mapping processing on the visual fatigue risk index to obtain the brightness attenuation correction amount; traverse each backlight zone, perform quantization ratio processing on the maximum hardware brightness of the zone and the brightness attenuation correction amount to obtain the single-zone backlight limiting coefficient corresponding to each backlight zone; integrate the single-zone backlight limiting coefficients corresponding to all backlight zones to obtain the zone basic limiting parameter array; bind and match the zone basic limiting parameter array and the mapping relationship to obtain the backlight zone limiting coefficient set corresponding to the current moment.

[0128] In one embodiment, the smooth transition module 404 includes: The acquisition submodule is used to acquire preset global scalar smoothing weights, image sub-block smoothing weights, and backlight partition smoothing weights. The splitting submodule is used to split the historical target display parameters to obtain a total set of historical multi-dimensional image quality control parameters. The total set of historical multi-dimensional image quality control parameters includes historical brightness upper limit parameters, historical target color temperature parameters, historical complete local contrast compression coefficient set, and historical backlight zone limiting coefficient set. The weighted submodule is used to perform weighted fusion processing on the upper limit brightness parameter and the historical upper limit brightness parameter, and the target color temperature parameter and the historical target color temperature parameter, respectively, using a preset frame-level smoothing function, to obtain the smoothed upper limit brightness parameter and the smoothed target color temperature parameter. The first traversal submodule is used to traverse all image sub-blocks, call the frame-level smoothing function, perform weighted processing on the local contrast compression coefficients under the same coordinates and the corresponding historical local contrast compression coefficients in the historical complete local contrast compression coefficient set, integrate the weighted processing results of all image sub-blocks, and generate a smoothed complete local contrast compression coefficient set. The second traversal submodule is used to traverse all backlight partitions, call the frame-level smoothing function, perform weighted processing on the single-partition backlight limiting coefficient under the same backlight partition index and the corresponding historical single-partition backlight limiting coefficient in the historical backlight partition limiting coefficient set, integrate the calculation results of all backlight partitions, and generate a smoothed backlight partition limiting coefficient set. The integration submodule is used to integrate the smoothed brightness upper limit parameter, the smoothed target color temperature parameter, the smoothed complete local contrast compression coefficient set, and the smoothed backlight zone limiting coefficient set to obtain the target display parameters corresponding to the current moment.

[0129] To address the aforementioned technical problems, embodiments of this application also provide a computer device. Please refer to [link / reference needed]. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0130] Computer device 6 includes a memory 61, a processor 62, and a network interface 63 that are interconnected via a system bus. It should be noted that only computer device 6 with memory 61, processor 62, and network interface 63 is shown in the figure; however, it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented alternatively. Those skilled in the art will understand that the computer device described herein is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0131] The memory 61 includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 61 may be an internal storage unit of the computer device 6, such as the hard disk or memory of the computer device 6. In other embodiments, the memory 61 may also be an external storage device of the computer device 6, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the computer device 6. Of course, the memory 61 may include both the internal storage unit and the external storage device of the computer device 6. In this embodiment, the memory 61 is typically used to store the operating system and various application software installed on the computer device 6, such as computer-readable instructions for adjusting the image quality of a display device. In addition, the memory 61 may also be used to temporarily store various types of data that have been output or will be output.

[0132] In some embodiments, processor 62 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip. Processor 62 is typically used to control the overall operation of computer device 6. In this embodiment, processor 62 is used to execute computer-readable instructions stored in memory 61 or to process data, such as computer-readable instructions for executing image quality adjustment methods for a display device.

[0133] The network interface 63 may include a wireless network interface or a wired network interface, which is typically used to establish a communication connection between the computer device 6 and other electronic devices.

[0134] This application also provides another embodiment, namely, providing a computer-readable storage medium storing computer-readable instructions that can be executed by at least one processor to cause the at least one processor to perform the steps of the image quality adjustment method of the display device as described above.

[0135] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods of the various embodiments of this application.

[0136] Obviously, the embodiments described above are only some embodiments of this application, not all embodiments. The accompanying drawings show preferred embodiments of this application, but do not limit the patent scope of this application. This application can be implemented in many different forms; rather, the purpose of providing these embodiments is to provide a more thorough and comprehensive understanding of the disclosure of this application. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing specific embodiments, or make equivalent substitutions for some of the technical features. Any equivalent structures made using the content of this application's specification and drawings, directly or indirectly applied to other related technical fields, are similarly within the scope of patent protection of this application.

Claims

1. A method for adjusting the image quality of a display device, characterized in that, Includes the following steps: Continuously collect environmental parameter data, viewing behavior data, and content data of the display device. Based on the environmental parameter data, the viewing behavior data, and the content data, determine the visual fatigue risk index corresponding to the current moment through a preset time-series risk model. Based on the visual fatigue risk index and the content data, determine the total set of multi-dimensional image quality control parameters corresponding to the current moment; Determine whether historical target display parameters generated in the previous time step exist; If present, a preset frame-level smoothing function is used to perform a smooth transition on the total set of multi-dimensional image quality control parameters based on the historical target display parameters, thereby obtaining the target display parameters; If not, the total set of multi-dimensional image quality control parameters determined at the current moment shall be determined as the target display parameter; Based on the target display parameters, the display device is adjusted for image quality.

2. The method according to claim 1, characterized in that, The step of determining the visual fatigue risk index corresponding to the current moment based on the environmental parameter data, the viewing behavior data, and the content data using a preset time-series risk model includes: By using a preset time-series risk model, the environmental parameter data, the viewing behavior data, and the content data are mapped and processed to obtain the ambient illuminance, user viewing distance, and standard deviation of screen brightness at each collection time. Based on the reference standard value, recommended viewing distance and weight coefficient set built into the time series risk model, the instantaneous visual fatigue risk sub-item value corresponding to each historical collection moment is calculated in different dimensions using the ambient illuminance, user viewing distance and screen brightness standard deviation, and then weighted and summed to obtain the single-moment instantaneous fatigue risk corresponding to each historical collection moment. Based on the forgetting factor built into the time series risk model, an exponentially decaying weight is applied to the instantaneous fatigue risk at each historical acquisition time to obtain the weighted instantaneous fatigue risk at each historical acquisition time. Using the time-series risk model, within a fixed-duration sliding time window, the weighted instantaneous fatigue risk at a single moment is integrated and accumulated to obtain the visual fatigue risk index corresponding to the current moment.

3. The method according to claim 2, characterized in that, The steps of calculating the instantaneous visual fatigue risk at each historical acquisition moment based on the reference standard value, recommended viewing distance, and weight coefficient set built into the time-series risk model, using the ambient illuminance, user viewing distance, and standard deviation of screen brightness, and then weighting and summing the values, to obtain the instantaneous fatigue risk at each historical acquisition moment, include: Obtain the reference standard value, recommended viewing distance, and weight coefficient set built into the time series risk model. The weight coefficient set includes the environmental illumination weight coefficient, the viewing distance weight coefficient, and the image fluctuation weight coefficient. For each historical data collection moment, the ambient illuminance, user viewing distance, and standard deviation of screen brightness are considered. A first ratio between the ambient illuminance and the reference standard value is calculated. The first ratio is then fused with the ambient illuminance weighting coefficient to obtain the instantaneous fatigue risk component of the environmental dimension. The recommended viewing distance and the user viewing distance are subjected to nonlinear mapping processing to obtain a distance matching quantization value. The distance matching quantization value and the viewing distance weight coefficient are fused to obtain the instantaneous fatigue risk component of the viewing distance dimension. The standard deviation of image brightness and the weighting coefficient of image fluctuation are fused to obtain the instantaneous fatigue risk component of image fluctuation dimension; The instantaneous fatigue risk components of the environmental dimension, the viewing distance dimension, and the image fluctuation dimension are summed to obtain the instantaneous fatigue risk of a single moment at the corresponding historical acquisition time. All historical acquisition times are traversed to obtain the instantaneous fatigue risk of a single moment at each historical acquisition time.

4. The method according to claim 1, characterized in that, The step of determining the total set of multi-dimensional image quality control parameters corresponding to the current moment based on the visual fatigue risk index and the content data includes: Based on the maximum hardware brightness of the display device and the visual fatigue risk index, determine the upper limit parameter of brightness at the current moment; Based on the reference color temperature built into the display device, the preset maximum color temperature offset, the visual fatigue risk index, and the content data, the target color temperature parameter corresponding to the current moment is determined. Extract the current image frame corresponding to the current acquisition time from the content data, and determine the complete set of local contrast compression coefficients corresponding to the current time based on the current image frame and the visual fatigue risk index. Based on the maximum hardware brightness of each backlight zone built into the display device and the current image frame, determine the set of backlight zone limiting coefficients corresponding to the current moment; The upper limit of brightness, the target color temperature, the complete set of local contrast compression coefficients, and the set of backlight zone limiting coefficients are determined as the total set of multi-dimensional image quality control parameters corresponding to the current moment.

5. The method according to claim 4, characterized in that, The step of determining the complete set of local contrast compression coefficients corresponding to the current moment based on the current image frame and the visual fatigue risk index includes: The current image frame is divided into blocks to obtain multiple non-overlapping image sub-blocks; Extract the global maximum brightness and global minimum brightness of the current image frame, and calculate the average brightness of each image sub-block respectively; A preset adjustment intensity function is used to perform nonlinear mapping processing on the visual fatigue risk index to obtain a fatigue matching adjustment intensity value; For each image sub-block, the average brightness of the corresponding sub-block, the global maximum brightness, and the global minimum brightness are quantized into a ratio to obtain the quantized value of the brightness proportion of the sub-block for each image sub-block. The fatigue matching adjustment intensity value and the sub-block brightness ratio quantization value are fused to obtain the sub-block contrast correction amount corresponding to each image sub-block; Based on a preset benchmark value, the contrast correction amount of the sub-block is offset to obtain the local contrast compression coefficient corresponding to each image sub-block. All image sub-blocks are traversed to obtain the complete set of local contrast compression coefficients corresponding to the current time.

6. The method according to claim 5, characterized in that, The step of determining the set of backlight zone limiting coefficients corresponding to the current moment based on the maximum hardware brightness of each backlight zone built into the display device and the current image frame includes: Read the maximum hardware brightness of each backlight zone built into the display device, and establish a mapping relationship between the backlight zone index and the panel screen area corresponding to each backlight zone based on the image content data of the current image frame; A preset attenuation mapping function is used to perform nonlinear mapping processing on the visual fatigue risk index to obtain the brightness attenuation correction amount; For each backlight zone, the maximum hardware brightness of the zone and the brightness attenuation correction amount are quantized to obtain the single-zone backlight limiting coefficient for each backlight zone. The single-zone backlight limiting coefficients corresponding to all backlight zones are integrated to obtain a zone basic limiting parameter array. The partition basic limiting parameter array and the mapping relationship are bound and matched to obtain the backlight partition limiting coefficient set corresponding to the current time.

7. The method according to claim 6, characterized in that, The step of using a preset frame-level smoothing function to perform smooth transition processing on the total set of multi-dimensional image quality control parameters based on the historical target display parameters to obtain the target display parameters specifically includes: Obtain the preset global scalar smoothing weights, image sub-block smoothing weights, and backlight partition smoothing weights; The historical target display parameters are broken down to obtain a total set of historical multi-dimensional image quality control parameters. The total set of historical multi-dimensional image quality control parameters includes historical brightness upper limit parameters, historical target color temperature parameters, historical complete local contrast compression coefficient set, and historical backlight zone limiting coefficient set. Using a preset frame-level smoothing function, the upper limit brightness parameter and the historical upper limit brightness parameter, as well as the target color temperature parameter and the historical target color temperature parameter, are weighted and fused to obtain the smoothed upper limit brightness parameter and the smoothed target color temperature parameter. Traverse all the image sub-blocks, call the frame-level smoothing function, perform weighted processing on the local contrast compression coefficients under the same coordinates and the corresponding historical local contrast compression coefficients in the historical complete local contrast compression coefficient set, integrate the weighted processing results of all the image sub-blocks, and generate a smoothed complete local contrast compression coefficient set. Traverse all backlight partitions, call the frame-level smoothing function, perform weighted processing on the single-partition backlight limiting coefficient under the same backlight partition index and the corresponding historical single-partition backlight limiting coefficient in the historical backlight partition limiting coefficient set, integrate the calculation results of all backlight partitions, and generate a smoothed backlight partition limiting coefficient set. The smoothed upper limit brightness parameter, the smoothed target color temperature parameter, the smoothed complete local contrast compression coefficient set, and the smoothed backlight zone limiting coefficient set are integrated to obtain the target display parameters corresponding to the current moment.

8. A picture quality adjustment device for a display device, characterized in that, include: The data acquisition module is used to continuously collect environmental parameter data, viewing behavior data, and content data of the display device. Based on the environmental parameter data, the viewing behavior data, and the content data, the visual fatigue risk index corresponding to the current moment is determined through a preset time-series risk model. The determination module is used to determine the total set of multi-dimensional image quality control parameters corresponding to the current moment based on the visual fatigue risk index and the content data; The judgment module is used to determine whether the historical target display parameters generated in the previous time step exist. The smooth transition module is used to, if present, employ a preset frame-level smoothing function to perform smooth transition processing on the total set of multi-dimensional image quality control parameters based on the historical target display parameters, thereby obtaining the target display parameters; The adjustment module is used to adjust the image quality of the display device based on the target display parameters.

9. A computer device, characterized in that, The device includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor executes the computer-readable instructions to implement the steps of the image quality adjustment method of the display device as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the image quality adjustment method of the display device as described in any one of claims 1 to 7.

Images