A display screen brightness self-adaptive adjusting method and system

Abstract

This invention relates to the field of intelligent control technology and discloses a method and system for adaptive brightness adjustment of a display screen. The method includes: acquiring ambient light intensity data and analyzing its changing trends to determine the directional characteristics of light intensity as the basis for adaptive speed adjustment; inputting the adaptive speed adjustment basis into a visual adaptation model to generate smooth curve parameters adapted to human eye characteristics, generating a brightness transition sequence through discretization sampling, and converting the brightness transition sequence into an adjustment instruction set; obtaining a target reference value from the adjustment instruction set, calculating the deviation between the actual brightness and the target reference value through a feedback mechanism to obtain a corrected brightness value; fusing real-time light intensity and historical data to construct a time series set and predicting the expected light sequence to generate a primary and backup adjustment path, adaptively switching based on the light intensity deviation; extracting the current adjustment instruction and transmitting it to the display driver module to achieve gradual brightness adjustment and a visually comfortable state. This method can achieve precise adaptation between human eye characteristics and display device hardware.

Description

Technical Field

[0001] This invention relates to the field of intelligent control technology, and in particular to a method and system for adaptive adjustment of display screen brightness. Background Technology

[0002] Currently, with the widespread use of portable display devices such as smartphones, tablets, and laptops, users' demand for switching between indoor, outdoor, and nighttime scenarios is increasing. Adaptive adjustment of display brightness has become a core technology for improving visual experience and reducing visual fatigue, while also being of great significance for optimizing device energy consumption and ensuring display stability.

[0003] In existing technologies, display brightness adjustment often employs a linear adjustment strategy based on the instantaneous value of ambient light intensity. This involves collecting real-time ambient light intensity data using a light sensor and directly mapping it to the display brightness value according to a preset fixed ratio. Some solutions simply set upper and lower thresholds for brightness adjustment, while a few optimized solutions perform simple filtering and noise reduction on the light intensity data before brightness matching adjustment. These solutions are directly adapted for use after the display device is manufactured, without considering the actual output characteristics of the display device and its compatibility with human visual perception. Existing technologies suffer from a lack of adaptation to human visual adaptation in brightness adjustment, resulting in abrupt adjustments that can easily cause visual discomfort. Furthermore, they lack predictability for changes in light intensity, exhibiting poor adjustment accuracy and stability in scenarios with gradual or sudden changes in light intensity. Additionally, they have low integration with the hardware characteristics of the display device, failing to achieve precise brightness correction based on the electro-optical conversion characteristics of the display device.

[0004] Existing technologies suffer from low accuracy in brightness correction. Summary of the Invention

[0005] This invention provides a method and system for adaptive brightness adjustment of a display screen to solve the problem of low accuracy in display brightness correction.

[0006] In a first aspect, to solve the above-mentioned technical problems, the present invention provides a display screen brightness adaptive adjustment method and system, comprising: Ambient light intensity data is acquired and the trend of light intensity change is analyzed. The directional characteristics of light brightness change are determined based on the light intensity change trend, and the directional characteristics are used as the basis for adjusting the adaptation speed. The adaptation speed is adjusted based on the input preset visual adaptation model to generate smooth curve parameters that adapt to the visual adaptation characteristics of the human eye. Discretize the smooth curve parameters to generate ordered time coordinates, calculate the target brightness value for each ordered time coordinate to form a brightness transition sequence, and convert the brightness transition sequence into an adjustment instruction set. The actual brightness value of the display is obtained, the target brightness value at the initial moment is extracted from the adjustment instruction set as the target reference value, the deviation between the actual brightness value and the target reference value is calculated, and the corrected brightness value is determined based on the deviation. Real-time light intensity data and historical light intensity data are acquired. A light intensity time series set is constructed by combining the historical light intensity data and the corrected brightness value. The light trend is predicted based on the light intensity time series set to obtain the expected light sequence. A primary adjustment path and a backup adjustment path are generated based on the expected light sequence. If the deviation between the real-time light intensity data and the expected value of the primary adjustment path exceeds a preset tolerance range, the system switches to the backup adjustment path to obtain the final brightness output scheme. The brightness adjustment command for the current time period is obtained from the brightness output scheme, and the brightness adjustment command is transmitted to the display driver module. The display driver module controls the display to perform a gradual brightness adjustment to obtain a visually comfortable state.

[0007] In a second aspect, the present invention provides a display screen brightness adaptive adjustment system, comprising: The light intensity trend analysis module is used to acquire ambient light intensity data and analyze the light intensity change trend. Based on the light intensity change trend, the directional characteristics of light brightness change are determined, and the directional characteristics are used as the basis for adjusting the adaptation speed. The curve parameter generation module is used to generate smooth curve parameters that adapt to the visual adaptation characteristics of the human eye based on the input preset visual adaptation model. The instruction set generation module is used to discretize the smooth curve parameters, generate ordered time coordinates, calculate the target brightness value for each ordered time coordinate, form a brightness transition sequence, and convert the brightness transition sequence into an adjustment instruction set. The brightness correction module is used to obtain the actual brightness value of the display, extract the target brightness value at the initial moment from the adjustment instruction set as the target reference value, calculate the deviation between the actual brightness value and the target reference value, and determine the corrected brightness value based on the deviation. The light prediction module is used to acquire real-time light intensity data and historical light intensity data, combine the historical light intensity data and the corrected brightness value to construct a light intensity time series set, and perform light trend prediction based on the light intensity time series set to obtain the expected light sequence. The path planning module is used to generate a main adjustment path and a backup adjustment path based on the expected light sequence. If the deviation between the real-time light intensity data and the expected value of the main adjustment path exceeds a preset tolerance range, the module switches to the backup adjustment path to obtain the final brightness output scheme. The brightness adjustment execution module is used to obtain the brightness adjustment command for the current time period from the brightness output scheme, transmit the brightness adjustment command to the display driver module, and the display driver module controls the display to perform a gradual brightness adjustment to obtain a visually comfortable state.

[0008] Compared with the prior art, the present invention has the following beneficial effects: (1) This invention determines the directional characteristics of light intensity by analyzing the trend of ambient light intensity changes and uses it as the basis for adjusting the adaptation speed. Combined with the visual adaptation model, it generates smooth curve parameters that are adapted to the physiological characteristics of the human eye. It changes the adjustment time for light adaptation scenarios to adapt to the slow adaptation characteristics of the human eye. This effectively solves the problems of existing technologies that ignore the asymmetry of human visual adaptation and cause visual discomfort due to abrupt adjustment process. It makes the brightness adjustment rhythm highly matched with the light and dark adaptation law of the human eye, greatly improves visual comfort, and reduces visual fatigue caused by long-term viewing.

[0009] (2) This invention calculates the deviation between the actual brightness of the display and the target reference value by constructing a feedback control mechanism, calculates the voltage compensation increment and corrects the driving voltage and duty cycle to obtain a precise corrected brightness value. At the same time, it incorporates gamma correction and electro-optic conversion law in the adjustment instruction set generation process, adapts to the hardware output characteristics of the display device manufacturing, effectively solves the problems of low brightness correction accuracy and poor integration with the hardware characteristics of the display device in the prior art, compensates for the output deviation caused by individual device differences and temperature drift, and realizes closed-loop precise control of brightness.

[0010] (3) This invention constructs a time series set by integrating real-time light intensity and historical light intensity data and performs light trend prediction, generates a main adjustment path and multiple scene backup adjustment paths, realizes path adaptive switching based on real-time light intensity deviation, and generates gradual step size data to control brightness gradual adjustment in combination with pixel response time. This effectively solves the problems of insufficient predictability of light intensity changes and poor adjustment stability when facing gradual or sudden changes in light intensity in the existing technology, realizes adaptive response to various light intensity change scenarios, ensures the continuity and stability of brightness adjustment, and makes the brightness gradual process more in line with the hardware driving law of display devices. Attached Figure Description

[0011] Figure 1 This is a schematic flowchart of the adaptive brightness adjustment method for a display screen provided in the first embodiment of the present invention; Figure 2 This is a schematic diagram of the display screen brightness adaptive adjustment system provided in the second embodiment of the present invention. Detailed Implementation

[0012] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0013] Reference Figure 1 The first embodiment of the present invention provides a method for adaptive adjustment of display screen brightness, including the following steps: S11, acquire ambient light intensity data and analyze the light intensity change trend, determine the directional characteristics of light brightness change based on the light intensity change trend, and use the directional characteristics as the basis for adjusting the adaptation speed. S12, The adaptation speed is adjusted according to the preset visual adaptation model to generate smooth curve parameters that adapt to the visual adaptation characteristics of the human eye. S13, Discretize the smooth curve parameters to generate ordered time coordinates, calculate the target brightness value for each ordered time coordinate to form a brightness transition sequence, and convert the brightness transition sequence into an adjustment instruction set; S14, obtain the actual brightness value of the display, extract the target brightness value at the initial moment from the adjustment instruction set as the target reference value, calculate the deviation between the actual brightness value and the target reference value, and determine the corrected brightness value based on the deviation; S15, acquire real-time light intensity data and historical light intensity data, combine the historical light intensity data and the corrected brightness value to construct a light intensity time series set, and perform light trend prediction based on the light intensity time series set to obtain the expected light sequence; S16, generate a main adjustment path and a backup adjustment path according to the expected light sequence. If the deviation between the real-time light intensity data and the expected value of the main adjustment path exceeds a preset tolerance range, switch to the backup adjustment path to obtain the final brightness output scheme. S17. Obtain the brightness adjustment command for the current time period from the brightness output scheme, transmit the brightness adjustment command to the display driver module, and have the display driver module control the display to perform a gradual brightness adjustment to obtain a visually comfortable state.

[0014] In step S11, ambient light intensity data is acquired and the trend of light intensity change is analyzed. Based on the trend of light intensity change, the directional characteristics of light brightness change are determined, and the directional characteristics are used as the basis for adjusting the adaptation speed, including: The raw signals of ambient light intensity data are acquired according to the preset sampling frequency to construct an ambient light history sequence; The light intensity gradient feature is obtained by performing a difference operation on the ambient light history sequence, and the light intensity change slope is obtained by performing a linear fitting on the ambient light history sequence. If the slope of the light intensity change is greater than zero and the light intensity gradient feature is less than a preset fluctuation threshold, a trend vector with a positive polarity is generated. If the slope of the light intensity change is less than zero and the light intensity gradient feature exceeds the preset fluctuation threshold, a trend vector with a negative polarity is generated. In other cases, a trend vector with a stable polarity is generated to obtain the light intensity change trend. The response weight is obtained by searching a preset mapping table based on the light intensity change trend. The product of the response weight and the slope of the light intensity change is calculated to obtain the adaptation coefficient. The trend vector and the adaptation coefficient are used as the basis for adjusting the adaptation speed.

[0015] In one implementation, this embodiment first constructs an ambient light history sequence. Raw signals of ambient light intensity data are acquired according to a preset sampling frequency, and then the ambient light history sequence is constructed. The sampling frequency is preset to 10Hz, meaning that raw light intensity values ​​are collected every 100 milliseconds. This frequency is determined by comprehensively considering the human eye's perception threshold for light intensity changes and the brightness response speed of the display device. This ensures that the true trend of light intensity changes is captured without increasing the system's computational burden due to excessive sampling. The length of the ambient light history sequence is fixed at 30 sampling points, corresponding to a 3-second historical data window. This length setting is based on the temporal correlation of light intensity changes, balancing trend capture accuracy and real-time performance. Data acquisition is completed through an ambient light sensor integrated into the display device. The sensor output signal is converted into a digital quantity of 0-1023 after analog-to-digital conversion, corresponding to a light intensity range of 0-10000 lux, covering the full-scene usage needs from indoor low light to outdoor high light.

[0016] It should be noted that the light intensity gradient feature is directly obtained through differential operations, which employ a first-order backward differential method. By calculating the light intensity difference between two adjacent sampling points, the instantaneous increase or decrease trend of light intensity is directly reflected. Linear fitting uses the least squares method to fit the light intensity data from 30 sampling points, obtaining a straight line that characterizes the overall light intensity change trend. The slope of this line is the light intensity change slope; a positive slope indicates an overall increasing trend, while a negative slope indicates a decreasing trend. The absolute value of the slope directly reflects the rate of light intensity change. The preset fluctuation threshold is set to 5 lux. This value is determined based on extensive experimental statistics. By collecting 1000 sets of light intensity change data in different scenarios such as indoors, outdoors, and dawn / dusk, it was found that the differential results in normal gradual change scenarios are all less than 5 lux, while the differential results in sudden occlusion, light switching, and other abrupt change scenarios are all greater than 5 lux. Therefore, 5 lux is used as the critical value to distinguish between gradual and abrupt changes.

[0017] In another implementation, this embodiment generates a trend vector based on the slope of light intensity change and the light intensity gradient feature. When the slope of light intensity change is greater than zero and the light intensity gradient feature is less than a preset fluctuation threshold, a trend vector with a positive polarity is generated; when the slope of light intensity change is less than zero and the light intensity gradient feature exceeds the preset fluctuation threshold, a trend vector with a negative polarity is generated; in all other cases, a trend vector with a stable polarity is generated, thus obtaining the light intensity change trend. The trend vector is a two-dimensional vector containing two dimensions: polarity and change type. The polarity indicator "+1" corresponds to positive (increasing light intensity), "-1" corresponds to negative (decreasing light intensity), and "0" corresponds to stable. The change type "0" corresponds to gradual change (gradient feature less than or equal to the preset fluctuation threshold), and "1" corresponds to abrupt change (gradient feature greater than the preset fluctuation threshold).

[0018] It is worth further explaining that in this embodiment, the response weight is obtained by looking up a preset mapping table based on the obtained light intensity change trend. The product of the response weight and the absolute value of the light intensity change slope is calculated to obtain the adaptation coefficient. The trend vector and the adaptation coefficient are used together as the basis for adjusting the adaptation speed. The input items of the preset mapping table are the polarity and change type of the trend vector, and the output items are the response weights that match the light intensity change trend. Each set of inputs in the table corresponds to an optimal response weight that has been calibrated experimentally. The preset mapping table is constructed by combining multi-dimensional experimental statistics with user comfort feedback calibration. First, 50 subjects of different ages (18-60 years old) were selected, covering people with different visual sensitivities, and comfort tests were conducted in typical light environment scenarios such as indoor low light, indoor high light, outdoor sunny day, outdoor cloudy day, dawn-dusk transition, and sudden change in lighting. In each scenario, by adjusting the direction (increasing / decreasing), rate (0.1-1.0 lux / ms), and smoothness (gradual / abrupt) of light intensity changes, subjects rated the comfort level of the brightness adjustment speed from 1 to 10 (1 being the most uncomfortable and 10 the most comfortable). Subsequently, the average comfort score for each scenario combination (direction + rate + smoothness) was calculated, and the weight coefficients corresponding to the optimal adjustment speed with a score greater than or equal to 8 were selected. The trend vectors of all scenario combinations and the optimal response weights were then compiled to form a pre-defined mapping table.

[0019] In step S12, the adaptation speed is adjusted according to the preset visual adaptation model to generate smooth curve parameters that adapt to the visual adaptation characteristics of the human eye, including: The adaptation speed is adjusted based on the input preset visual adaptation model, and the neural response feature value is output. The excitation signal component and the inhibition signal component in the neural response feature value are analyzed, the ratio of the excitation signal component to the inhibition signal component is calculated to obtain the signal component ratio, the visual perception state is determined according to the signal component ratio, and the visual perception state is divided into light adaptation priming state and dark adaptation priming state. If the brightness adaptation is in the aforementioned state, the time compression factor is calculated based on the rhodopsin decomposition rate constant. The time compression factor is then used to perform a time-domain compression transformation on the preset reference brightness adjustment curve to construct a brightness adjustment target trajectory sequence. If the dark adaptation is activated, the preset reference brightness adjustment curve is directly used to generate a brightness adjustment target trajectory sequence adapted to dark adaptation. High-order interpolation calculations are performed on the brightness adjustment target trajectory sequence to obtain smooth curve parameters.

[0020] In one implementation, this embodiment first adjusts the adaptation speed according to a preset visual adaptation model and outputs neural response feature values. The visual adaptation model used in this invention is a biomimetic fully connected neural network based on the response mechanism of human retinal photoreceptor cells, which corely simulates the activation-inhibition process of cone cells and rod cells. The model input layer is a 2-dimensional vector (trend vector + adaptation coefficient), and the hidden layer contains two fully connected network layers: the first layer has 64 neurons and uses the ReLU activation function; the second layer has 32 neurons and uses the LeakyReLU activation function to alleviate the gradient vanishing problem; the output layer uses the Sigmoid activation function and outputs 8-dimensional neural response feature values ​​(including 4-dimensional excitation signal components and 4-dimensional inhibition signal components), which quantifies the intensity of the visual system's neural response to changes in light intensity.

[0021] In one implementation, the neural response feature values ​​are obtained by using the pupil diameter change rate acquired by eye tracker and the amplitude of visual cortical evoked potentials acquired by electroencephalography as the raw signals, denoising them by 0.5~30Hz bandpass filtering, extracting the peak value and mean value in a 100ms time window, then reducing the dimension to 4-dimensional excitation components and 4-dimensional inhibition components by principal component analysis, and finally normalizing to the [0,1] interval to obtain 8-dimensional neural response feature values.

[0022] The training dataset for the visual adaptation model contains physiological data on visual responses from 50 subjects of different ages (18-60 years old), covering typical scenarios such as indoor low light, outdoor high light, dawn-dusk transition, and sudden changes in lighting. 1000 samples were collected for each scenario, totaling 6000 training samples, 1000 validation samples, and 500 test samples. The input features are the adaptation speed adjustment criteria (trend vector + adaptation coefficient), and the target output is the normalized physiological signal collected by eye-tracking and electroencephalography (EEG) equipment. The model is trained using supervised learning, with the cross-entropy loss function and the Adam optimizer. The initial learning rate is set to 0.001, decaying to 90% of the original learning rate every 10 training epochs. An early stopping mechanism is used during training: when the prediction error on the validation set does not decrease and falls below 5% for 20 consecutive epochs, training is stopped and the optimal model weights are saved.

[0023] In one implementation, this embodiment analyzes the output neural response feature values, extracts the excitation signal component and the inhibition signal component, determines the visual perception state based on the ratio of the two types of signals, and divides the visual perception state into a light adaptation initiation state and a dark adaptation initiation state. Specifically, when the ratio of the excitation signal component to the inhibition signal component is greater than a preset ratio threshold (which is experimentally and statistically set to 1.5), it is determined to be a light adaptation initiation state, representing that the visual system is adapting from a dark environment to a bright environment; when the ratio is less than a preset ratio threshold (set to 0.8), it is determined to be a dark adaptation initiation state, representing that the visual system is adapting from a bright environment to a dark environment.

[0024] It is worth further explaining that the ratio threshold is set based on experimental data of human visual physiological characteristics. By statistically analyzing the proportion of neural signal components of subjects under different adaptation scenarios, it was found that the excitatory signal component is significantly dominant in the light adaptation process, while the inhibitory signal component is relatively prominent in the dark adaptation process. Therefore, 1.5 and 0.8 were selected as the critical values ​​to distinguish between the two adaptation states.

[0025] In one implementation, if the light adaptation is initiated, a time compression factor is calculated based on the rhodopsin decomposition rate constant. This time compression factor is then used to perform a time-domain compression transformation on a preset reference brightness adjustment curve to construct a target brightness adjustment trajectory sequence. The rhodopsin decomposition rate constant is set to 0.05 per second, a value referenced to the physiologically accepted range of rhodopsin photochemical decomposition rate (0.04-0.06 per second), taking the middle value to balance adaptation differences among different populations. The calculation of the time compression factor is combined with the light intensity change rate in the light adaptation initiated state; the faster the light intensity changes, the greater the compression factor, ensuring that the brightness adjustment duration is synchronized with the physiological process of rhodopsin decomposition. The preset reference brightness adjustment curve is an S-shaped curve fitted based on a large amount of light adaptation experimental data, which can reflect the nonlinear characteristics of brightness perception during the human eye's light adaptation process.

[0026] In one implementation, the time compression ratio is calculated using a preset compression ratio mapping table. This mapping table is calibrated based on a combination of the rhodopsin decomposition rate constant and the light intensity change rate. Multiple light intensity change rates within the range of 0.1 to 1.0 lux / ms are selected, and the actual accommodation time at which the subject's light adaptation is most comfortable is recorded. This time is compared with the duration of the baseline curve to obtain the compression ratio, which is then compiled into a mapping table with the light intensity change rate as input and the compression ratio as output. In actual use, the compression ratio is obtained by looking up the table based on the current light intensity change rate. The preset baseline brightness adjustment curve is an S-shaped curve optimized based on the comfort scores of a large number of subjects in typical scenarios. Specifically, in scenarios such as indoor low light and outdoor high light, multiple candidate curves are generated with different steepness coefficients. Subjects rate the comfort of brightness changes, and the curve parameter with the highest average score is selected as the steepness coefficient of the baseline curve, thereby determining the standard accommodation curve that adapts to the visual characteristics of the human eye.

[0027] In another implementation, if dark adaptation is detected as initiated, a target trajectory sequence for dark adaptation brightness adjustment is directly generated using the preset reference brightness adjustment curve. This reference brightness adjustment curve is a curve specifically designed for dark adaptation scenarios. Its slope is designed to match the photosensitive activation rate of rod cells, allowing it to match the physiological rhythm of dark adaptation without additional temporal stretching, thus avoiding visual discomfort caused by over-adjustment.

[0028] In one implementation, this embodiment performs high-order interpolation calculations on the brightness adjustment target trajectory sequence to obtain smooth curve parameters. The high-order interpolation employs a third-order spline interpolation algorithm, which constructs a smooth cubic polynomial curve between adjacent data points in the trajectory sequence. This ensures the continuity of the first and second derivatives of the curve at connection points, thereby eliminating abrupt changes during the brightness adjustment process. The interpolated smooth curve parameters include the target brightness value, rate of change, and acceleration information at each time point.

[0029] In step S13, the smooth curve parameters are discretized and sampled to generate ordered time coordinates. The target brightness value for each ordered time coordinate is calculated to form a brightness transition sequence. The brightness transition sequence is then converted into an adjustment instruction set, including: Discretization sampling is performed on the smooth curve parameters at fixed time intervals to generate a set of time point indices containing ordered time coordinates; For each time coordinate in the time point index set, the corresponding target brightness value is calculated by interpolation, and a brightness transition sequence with time domain information is constructed. Obtain the gamma correction data pre-stored on the display screen, use the gamma correction data to convert the target brightness value in the brightness transition sequence into a gray level value, and determine the corresponding driving voltage amplitude based on the gray level value; The duty cycle of the pulse width modulation signal is calculated based on the amplitude of the driving voltage, and the duty cycle of the pulse width modulation signal is encapsulated in time coordinate order to generate a continuous set of adjustment instructions.

[0030] In one implementation, this embodiment first performs discretization sampling on the smooth curve parameters at fixed time intervals to generate a set of time point indices containing ordered time coordinates. The fixed time interval is set to 50 milliseconds. This value is determined by comprehensively considering the refresh rate of the display device and the smoothness requirements of brightness adjustment. The refresh rate of the display device is typically 60Hz (approximately 16.7 milliseconds / frame). The 50-millisecond sampling interval ensures that the brightness change between adjacent sampling points is within a range imperceptible to the human eye, while also avoiding excessively large adjustment instruction set data due to an excessively short sampling interval, thus balancing adjustment accuracy and system transmission efficiency. The time point index set is arranged in chronological order, with each index corresponding to a specific sampling time.

[0031] It should be noted that in this embodiment, for each time coordinate in the time point index set, the corresponding target brightness value is calculated by interpolation to construct a brightness transition sequence with time domain information. The interpolation calculation adopts a linear interpolation algorithm, which obtains the brightness values ​​of two key nodes before and after the current time coordinate in the smooth curve parameters, and calculates the target brightness value of the current coordinate based on the time proportion, ensuring that the brightness value at each sampling moment can accurately fit the changing trend of the smooth curve. The brightness transition sequence is stored in the form of key-value pairs of "time coordinate - target brightness value".

[0032] It is worth further explaining that the choice of linear interpolation algorithm is based on the real-time and accuracy requirements of brightness adjustment. Compared with higher-order interpolation algorithms, linear interpolation has lower computational complexity and can quickly calculate the target brightness value, meeting the requirements of real-time system adjustment. At the same time, since the smooth curve parameters have been guaranteed to have overall smoothness through third-order spline interpolation, linear interpolation will not introduce obvious brightness jumps under the premise of reasonable sampling intervals, thus balancing efficiency and effectiveness.

[0033] In one implementation, this embodiment utilizes gamma correction data to convert the target brightness value in the brightness transition sequence into a grayscale value, and determines the corresponding driving voltage amplitude based on the grayscale value. The gamma correction data is proprietary data calibrated during the display device manufacturing stage. Different display devices have different gamma characteristics. By inputting different grayscale values, the corresponding actual brightness output is measured, and a non-linear mapping relationship between grayscale and brightness is fitted, i.e., the gamma correction curve. During the conversion process, the corresponding grayscale value (range 0-255) is found on the gamma correction curve based on the target brightness value, and then the driving voltage amplitude is determined using a preset grayscale-driving voltage mapping table. The pulse width modulation signal duty cycle is calculated based on the driving voltage amplitude, and the pulse width modulation signal duty cycle is encapsulated in time coordinate order to generate a continuous adjustment instruction set. The calculation of the pulse width modulation signal duty cycle is based on the driving principle of the display device, and the driving voltage amplitude and duty cycle have a linear mapping relationship.

[0034] In step S14, the actual brightness value of the display is obtained, the target brightness value at the initial moment is extracted from the adjustment instruction set as the target reference value, the deviation between the actual brightness value and the target reference value is calculated, and the corrected brightness value is determined based on the deviation, including: The duty cycle of the pulse width modulation signal at the initial moment is extracted from the adjustment instruction set, and the duty cycle of the pulse width modulation signal is mapped to the initial estimated brightness value using a preset electro-optic conversion model, which is then used as the target reference value. Obtain the actual brightness value and the original driving voltage amplitude of the display, and calculate the brightness deviation between the actual brightness value and the target reference value; The voltage compensation increment is calculated based on the brightness deviation, and the voltage compensation increment is added to the original driving voltage amplitude to obtain the correction voltage value. The duty cycle of the fine-tuned pulse width modulation signal is generated based on the corrected voltage value, and the corrected brightness value is obtained by mapping based on the fine-tuned duty cycle of the pulse width modulation signal.

[0035] In one implementation, this embodiment first extracts the duty cycle of the pulse width modulation (PWM) signal at the initial moment from the adjustment instruction set, inputs the duty cycle of the PWM signal into a preset electro-optic conversion model to complete the mapping from electrical signal parameters to brightness values, obtains the initial estimated brightness value, and uses it as the target reference value.

[0036] It is worth noting that the electro-optic conversion model is a nonlinear numerical mapping model constructed based on the electro-optic conversion characteristics of display device hardware. Its core is used to realize the accurate mapping and conversion between electrical signal parameters such as pulse width modulation signal duty cycle and driving voltage and the actual brightness value of the display screen. It provides a numerical basis for hardware adaptation for setting brightness reference value and correcting brightness deviation, and is compatible with the hardware characteristics of mainstream display panels such as LCD and OLED.

[0037] The model is a single-input, single-output numerical mapping structure. The input is the duty cycle of the pulse width modulation (PWM) signal (LCD panel) / driving current (OLED panel), and the output is the actual brightness value of the display screen (unit: nit). The core of the model is the fitted polynomial function, which directly converts the electrical signal parameters into brightness values. There are no additional hidden layers or computational units, ensuring the real-time performance and lightweight nature of the model. The model is constructed using hardware calibration and fitting, without the training process of a deep learning model. The calibration experiment is completed before the display device leaves the factory, in a standard working environment of 25℃±2℃ and 50%±5% humidity. Within the range of 0-100% duty cycle (LCD) / 0-500mA driving current (OLED), the actual brightness output value of the panel corresponding to the electrical signal parameters is collected point by point with a step size of 1% duty cycle / 1mA current to form a calibration dataset. The least squares method is used to perform polynomial fitting on the calibration dataset. For both LCD and OLED panels, a cubic polynomial is used as the fitting function. The polynomial coefficients obtained after fitting are the core parameters of the model.

[0038] It should be noted that this embodiment obtains the actual brightness value of the display through a brightness sensor integrated into the backlight module of the display panel. The sensor sampling frequency is synchronized with the time base of the adjustment command set, set to 20Hz, with a sampling accuracy of ±1 nit, which can capture subtle changes in the actual brightness output of the panel in real time. At the same time, the original driving voltage amplitude of the current driving panel is read from the register of the display driving module. This voltage amplitude is the actual operating voltage driving the backlight source, which, together with the duty cycle of the pulse width modulation signal, determines the panel brightness output. After obtaining the actual brightness value and the target reference value, the brightness deviation between the two is calculated by subtraction. The brightness deviation is the difference between the actual brightness value and the target reference value. A positive deviation indicates that the actual brightness is too high, a negative deviation indicates that the actual brightness is too low, and zero indicates that the actual brightness is perfectly matched with the target reference value.

[0039] It is worth further explaining that in this embodiment, the voltage compensation increment is calculated based on the brightness deviation. The calculation process is completed based on a preset brightness-voltage compensation mapping table, which is obtained through experimental calibration. Under different reference voltages and different brightness ranges, the voltage adjustment required to compensate for a unit brightness deviation is tested point by point, and the voltage compensation coefficient for the entire working range is statistically obtained. The voltage compensation increment is the brightness deviation multiplied by the voltage compensation coefficient of the corresponding brightness range. The unit of the voltage compensation coefficient is V / nit, ensuring that the voltage compensation increment can accurately offset the brightness deviation. After obtaining the voltage compensation increment, it is superimposed with the original driving voltage amplitude to obtain the corrected voltage value. The corrected voltage value is equal to the original driving voltage amplitude plus the voltage compensation increment. During the superposition operation, upper and lower voltage thresholds are set. The upper limit is the rated maximum driving voltage of the display device, and the lower limit is the backlight source start-up voltage, to avoid the corrected voltage value exceeding the hardware operating range, which could lead to device damage or brightness adjustment failure.

[0040] In one implementation, this embodiment generates a fine-tuned pulse width modulation (PWM) signal duty cycle based on the corrected voltage value. The conversion process is based on the voltage-duty cycle linear mapping relationship of the display device. This relationship is determined by the hardware characteristics of the driver chip; that is, under the same brightness output, the driving voltage amplitude is linearly inversely proportional to the PWM signal duty cycle. The corrected voltage value is accurately converted into the corresponding PWM duty cycle, with the conversion accuracy retained to 0.1%, ensuring the fineness of the electrical signal adjustment. The fine-tuned duty cycle is input into the electro-optical conversion model, and the corresponding brightness value is obtained through mapping, which is the corrected brightness value.

[0041] In step S15, real-time light intensity data and historical light intensity data are acquired. A light intensity time series set is constructed by combining the historical light intensity data and the corrected brightness value. Light trend prediction is performed based on the light intensity time series set to obtain the expected light sequence, including: Acquire real-time light intensity data, historical light intensity data, and the corrected brightness value; perform luminous interference compensation on the real-time light intensity data based on the corrected brightness value; integrate the compensated real-time light intensity data with the historical light intensity data to obtain a corrected light intensity time series set. The light intensity time series set is input into a preset time series prediction model, and a preliminary future light ray prediction value is output. The preliminary future light ray prediction value is smoothed to obtain the light state estimate value. Trend fitting is performed on the estimated light state values ​​to obtain the expected light sequence.

[0042] In one implementation, this embodiment first acquires real-time light intensity data using an ambient light sensor at a sampling frequency of 10Hz. Simultaneously, it retrieves historical light intensity data from a local database for the past 5 minutes. The historical data and real-time light intensity data maintain the same time base and dimensions, both being digital quantities ranging from 0 to 10000 lux. The system synchronously reads the corrected brightness value output in step S14. This brightness value is the actual output brightness of the panel after closed-loop correction, serving as a reference benchmark for light intensity data correction. Based on the corrected brightness value, a luminous interference compensation operation is performed on the real-time light intensity data. According to a preset brightness-light intensity correlation coefficient, the compensation value for the real-time light intensity data under the current panel brightness is calculated. This compensation value is then superimposed onto the corresponding sampling point of the real-time light intensity data. The compensated real-time light intensity data and historical light intensity data are arranged in ascending order by sampling timestamp, constructing a two-dimensional light intensity time series set containing both time and light intensity dimensions. The set data is stored in key-value pairs of timestamp and corrected light intensity value.

[0043] It should be noted that the brightness-light intensity correlation coefficient was obtained through experimental calibration. The influence of panel brightness reflection on the ambient light sensor was collected in different panel brightness ranges (0-200nit, 200-500nit, 500-1000nit), and the correlation coefficient corresponding to each range was statistically obtained. The value range is 0.001-0.005 lux / nit, which ensures that the calibration operation can accurately offset the interference of panel brightness on light intensity acquisition and restore the true ambient light intensity data.

[0044] In one implementation, this embodiment inputs the corrected light intensity time series set into a preset time series prediction model and outputs preliminary future light intensity prediction values. The time series prediction model used in this invention is a three-layer stacked structure for trend prediction of light intensity time series data. The input layer receives a 60-dimensional feature vector (corrected light intensity values ​​from 60 consecutive sampling points). The first layer has 128 hidden units, the second layer has 64 hidden units, and the third layer has 32 hidden units. Each layer adds a dropout layer (dropout rate of 0.2) to prevent overfitting. The output layer is a fully connected layer with 30 neurons, outputting preliminary light intensity prediction values ​​for the next 30 time steps.

[0045] The model's training dataset consists of two parts: first, real-world ambient light intensity data collected over the past three years (sampling frequency 10Hz), covering all scenarios including indoor, outdoor, and nighttime environments; second, augmented data generated using lighting simulation software (including light intensity gradients, abrupt changes, and stationary states). The input is a time-series sequence of light intensity from 60 consecutive sampling points, and the target output is the true light intensity values ​​from the subsequent 30 sampling points. The model is trained using supervised learning, employing the mean squared error (MSE) loss function and the Adam optimizer. The batch size is set to 64, and the training iterations are set to 100 epochs. A dynamic learning rate decay mechanism is introduced during training, with an initial learning rate of 0.001. When the validation set loss shows no decrease for 10 consecutive epochs, the learning rate is multiplied by 0.9. The model convergence criterion is a validation set prediction error below 3%.

[0046] It is worth further explaining that this embodiment smooths the preliminary future light prediction value to obtain a light state estimate. The smoothing process uses an adaptive Kalman filter algorithm, which can dynamically adjust the filter gain according to the fluctuation of the prediction value: when the fluctuation of the preliminary prediction value is small, the filter gain is increased to retain more trend information; when the fluctuation of the preliminary prediction value is large, the filter gain is decreased to suppress high-frequency noise interference. By iteratively filtering the preliminary future light prediction value using the adaptive Kalman filter algorithm, the jitter of the prediction value caused by factors such as sensor noise and sudden environmental interference is eliminated, resulting in a smooth and continuous light state estimate. This estimate more closely matches the actual change law of ambient light intensity and avoids frequent fluctuations in brightness adjustment caused by sudden changes in the prediction value.

[0047] It should be noted that this invention employs an adaptive Kalman filter algorithm to smooth the initial light intensity prediction values ​​output by the preset time series prediction model. The state equation dimension is set to 1 (light intensity value only), the observation equation dimension is set to 1, the initial state estimate is set to the real-time light intensity value at the current moment, the initial error covariance matrix is ​​set to a diagonal matrix (diagonal elements are 1), the process noise covariance is set to 0.01, and the initial observation noise covariance is set to 0.1. The residual standard deviation of the prediction values ​​is calculated in real time. When the residual standard deviation is less than 5 lux (stable light intensity scenario), the observation noise covariance is reduced to 0.05, the filter gain is increased, and more trend information is retained. When the residual standard deviation is greater than or equal to 5 lux (light intensity abrupt change scenario), the observation noise covariance is increased to 0.2, the filter gain is reduced, and high-frequency noise is suppressed. Each time new real-time light intensity data is received, the state estimate and error covariance matrix are updated. The smoothed light state estimate is obtained through iterative calculation, ensuring the continuity and stability of the output data.

[0048] In one implementation, this embodiment performs trend fitting on the estimated light state values ​​to obtain a light prediction sequence. The trend fitting employs a nonlinear least squares method. Based on the distribution characteristics of the estimated light state values, a suitable fitting function is selected. If the light intensity exhibits a linear trend, a first-order polynomial fitting is used; if the light intensity exhibits a nonlinear gradual trend, an exponential function or S-curve fitting is used. During the fitting process, the sum of squared residuals at each sampling point is calculated, and iterative optimization minimizes the sum of squared residuals to ensure a close fit between the fitted curve and the estimated light state values. The fitted curve is discretized and sampled at 100-millisecond intervals to obtain light intensity prediction values ​​for the next 30 time steps. These prediction values ​​are arranged in timestamp order to construct a light prediction sequence. Each light intensity prediction value in the sequence corresponds to a specific time node, providing an accurate light intensity trend reference for subsequent brightness adjustment path planning.

[0049] It should be noted that the construction of the light intensity time series set and the prediction of light trends are real-time iterative processes. Every time the system collects new real-time light intensity data, it updates the light intensity time series set, removes the earliest historical data, adds new corrected light intensity data, and re-executes the prediction, filtering, and fitting operations to update the light expected sequence. This ensures that the light expected sequence can track the changing trend of ambient light intensity in real time and achieve dynamic prediction of changes in ambient light intensity.

[0050] In step S16, a primary adjustment path and a backup adjustment path are generated based on the expected light sequence. If the deviation between the real-time light intensity data and the expected value of the primary adjustment path exceeds a preset tolerance range, the system switches to the backup adjustment path to obtain the final brightness output scheme, including: Based on the expected light sequence, a main adjustment path is generated according to the preset illumination change gradient, and a backup adjustment path is generated for scenarios with sudden changes in light intensity. For the main adjustment path, a light intensity deviation tolerance range is set, and a mapping relationship is established between the backup adjustment path and different deviation ranges exceeding the tolerance range, and a path switching index table is constructed. Calculate the deviation of the real-time light intensity data from the expected light intensity value at the corresponding time of the main adjustment path; If the light intensity deviation exceeds the light intensity deviation tolerance range, the path switching index table is searched to match the corresponding backup adjustment path; if it does not exceed the range, the main adjustment path is used. The alternative or main adjustment path obtained by parsing and matching is used to generate the corresponding drive current sequence, and the drive current sequence is used as the final brightness output scheme.

[0051] In one implementation, this embodiment generates a main adjustment path based on the expected light sequence and a preset illumination change gradient, while simultaneously constructing a backup adjustment path for scenarios with sudden changes in light intensity. The preset illumination change gradient is set according to the human visual comfort threshold and has a value of 0.5 lux / ms. The brightness change rate of the main adjustment path strictly matches this gradient. Using the light intensity value of the expected light intensity sequence as a benchmark, and combining the electro-optical conversion law and the visual adaptation model, a brightness adjustment trajectory that changes smoothly over time is generated. Each time step in the trajectory corresponds to a unique target brightness value, ensuring that the brightness adjustment is highly consistent with the gradual change trend of light intensity and adapts to the natural visual perception rhythm of the human eye. For scenarios involving sudden changes in light intensity, this embodiment pre-generates three types of backup adjustment paths, which are adapted to scenarios of sudden increase in light intensity (positive deviation value and exceeding the tolerance range), sudden decrease in light intensity (negative deviation value and exceeding the tolerance range), and drastic fluctuation in light intensity (alternating positive and negative deviation values ​​and exceeding the tolerance range). The brightness adjustment rate of each backup adjustment path is adapted according to the degree of change. The adjustment rate for sudden increase / decrease in light intensity is 1.0-1.5 lux / ms, while for drastic fluctuations in light intensity, a step-wise adjustment rate of slow first and then fast is adopted, which ensures a rapid response to sudden changes in light intensity while avoiding excessively abrupt brightness adjustment that may cause visual discomfort.

[0052] In one implementation, the backup adjustment path is generated based on a preset path template library. In practical applications, the corresponding template is matched according to the detected light intensity deviation range, and a future brightness target value sequence is generated according to the template rate, starting from the current brightness. Specifically, the path template library collects raw data from typical light intensity change scenarios such as indoor and outdoor environments, tunnels, and light switches, and divides the samples into three levels: mild, moderate, and severe, based on the magnitude of the change. The sample curves within each level are dynamically time-normalized and aligned, and the mean is calculated. After smoothing, the baseline adjustment curve for that level is obtained. Finally, it is discretized into a drive current sequence according to the display refresh rate, and the change type and level are labeled to form a backup adjustment path template library containing three categories and six templates. In practical applications, the corresponding level template is matched according to the detected light intensity deviation, and the template sequence is scaled up and down from the current brightness to generate a backup adjustment path adapted to the current scenario.

[0053] It should be noted that this embodiment sets a light intensity deviation tolerance range for the main adjustment path. This range is determined through statistical analysis of numerous scenario experiments. Based on the expected light intensity value at the corresponding moment of the main adjustment path, the upper and lower fluctuation thresholds are both set to 20 lux. That is, the tolerance range is the difference between the expected light intensity value and 20 lux to the sum of the expected light intensity value and 20 lux. The threshold comprehensively considers the normal fluctuation range of ambient light intensity and sensor acquisition error, ensuring that there is no need to switch paths when the light intensity fluctuates slightly, thus maintaining the stability of brightness adjustment. In one implementation, the determination of the light intensity deviation tolerance range of ±20 lux is based on a subjective evaluation experiment of 100 users. The expected light intensity value of the main adjustment path is set, and different sizes of light intensity deviation values ​​are introduced. Users are asked to evaluate whether brightness adjustment is necessary. The maximum deviation value that users believe does not need adjustment is statistically analyzed, and the average value is taken to obtain 20 lux. Based on this tolerance range, this embodiment divides the deviation range beyond the range into six levels. Among them, the sudden increase in light intensity is divided into three levels: +20~+50 lux, +50~+100 lux, and greater than 100 lux. The sudden decrease in light intensity is divided into three levels: -20~-50 lux, -50~-100 lux, and less than -100 lux. Each deviation range uniquely matches a backup adjustment path. The correspondence between the deviation range and the backup adjustment path, the path call priority, and the brightness adjustment parameters are organized into structured data to construct a path switching index table. The data in the table is stored in the form of key-value pairs. The key is the deviation range, and the value is the identifier and core parameters of the corresponding backup adjustment path, which supports fast retrieval and matching.

[0054] In one implementation, the path switching index table is constructed by dividing the deviation range beyond the tolerance range into six levels, with each level corresponding to a backup adjustment path, and storing this correspondence in key-value pairs. The six levels include three levels of sudden increase in light intensity and three levels of sudden decrease in light intensity, and the range of each level is determined by experimental statistics. The structure of the index table includes the deviation range, the corresponding backup path identifier, the path call priority, and the core adjustment parameters, supporting fast retrieval of matching paths based on the actual deviation.

[0055] It is worth further explaining that this embodiment calculates the light intensity deviation between the real-time light intensity data and the expected value at the corresponding moment of the main adjustment path. The light intensity deviation is calculated using a combination of relative and absolute deviation. If the expected light intensity value is 0, the absolute value of the real-time light intensity value is directly taken as the deviation. After calculating the deviation, it is first determined whether the absolute deviation of the real-time light intensity value exceeds the preset 20 lux tolerance range. Then, the deviation level is determined by combining the deviation value. This dual determination standard avoids misjudgment caused by small absolute deviations under low light intensity and can accurately identify relative deviations under high light intensity, thus improving the accuracy of path switching determination.

[0056] In one implementation, this embodiment executes path selection logic based on the determination result of light intensity deviation. If the absolute deviation value does not exceed the 20 lux tolerance range, the main adjustment path is directly used to maintain the continuity of brightness adjustment. If the absolute deviation value exceeds the tolerance range, the path switching index table is retrieved according to the actual deviation value range to match the corresponding backup adjustment path, ensuring that the response time of path matching is controlled within 10ms to meet the requirements of real-time adjustment. After the path matching is completed, the selected main adjustment path or backup adjustment path is parsed, and the target brightness value of each time step in the path is extracted. Combining the electro-optical conversion model of the display device, the gamma correction curve, and the current-brightness mapping relationship of the driver chip, the target brightness value is sequentially converted into the corresponding driving current value. The driving current values ​​of each time step are arranged in timestamp order to generate a continuous driving current sequence. This sequence contains core parameters such as current amplitude, rate of change, and duration, which are directly used as the final brightness output scheme, providing a precise electrical signal control basis for subsequent brightness adjustment execution.

[0057] In step S17, the brightness adjustment command for the current time period is obtained from the brightness output scheme, and the brightness adjustment command is transmitted to the display driver module. The display driver module then controls the display to perform a gradual brightness adjustment to obtain a visually comfortable state, including: The timestamp index of the brightness output scheme is parsed, and the drive current sequence that matches the current system clock is extracted as the brightness adjustment command for the current time period. Based on the driving current sequence, a preset gamma correction curve is retrieved, and the corresponding grayscale voltage control value is obtained by mapping. By combining the real-time pixel response time of the display, the difference between the grayscale voltage control value and the voltage state of the previous frame is calculated to generate gradient step size data. Based on the gradually changing step size data, the duty cycle of the pulse width modulation signal is modulated to generate a timing control signal, which is then transmitted to the display driver module. The display driving module controls the pixel brightness to be gradually adjusted according to the timing control signal and the gradual step size data to achieve a visually comfortable state.

[0058] In one implementation, this embodiment first performs timestamp indexing and parsing on the driving current sequence in the brightness output scheme to ensure that the adjustment command is precisely synchronized with the current system clock. The driving current sequence in the brightness output scheme contains current parameters for the next 30 time steps, each parameter being associated with a unique timestamp. The system compares the timestamp with the current system clock (with an accuracy of 1 millisecond) to extract the current data corresponding to the current moment and the next two adjacent time steps, forming the brightness adjustment command for the current time period.

[0059] It should be noted that this embodiment retrieves a preset gamma correction curve based on the extracted drive current sequence to complete the nonlinear mapping from current to grayscale voltage. The gamma correction curve is a dedicated curve calibrated for the panel characteristics before the display device leaves the factory. The calibration process involves collecting the actual brightness output of the panel point by point within a 0-500mA drive current range in 1mA steps, and then fitting this data with the nonlinear characteristics of human vision. The curve gamma value is set to 2.2, a value determined based on industry standards and visual characteristics to ensure linearity in brightness perception. During mapping, the corresponding grayscale voltage control value is found on the curve based on the drive current value. The voltage range is 0-5V, and the mapping accuracy is maintained to 0.001V.

[0060] It is worth further explaining that this embodiment reads the real-time pixel response time of the display through the registers of the display driver module. This time is the actual response time for a pixel to switch from the current grayscale to the target grayscale, with a value ranging from 2 to 10 milliseconds, and it changes dynamically with the panel temperature and the current brightness range. Based on this response time, the difference between the grayscale voltage control value and the voltage state of the previous frame is calculated to generate gradient step size data. When the pixel response time is short (2-4 milliseconds), the step size is set to 0.02V / frame to avoid visual discomfort caused by excessively rapid brightness changes; when the response time is long (6-10 milliseconds), the step size is adjusted to 0.03V / frame to ensure that the brightness transition is completed within the human eye's perception threshold; when the response time is medium (4-6 milliseconds), the step size is set to 0.025V / frame to balance adjustment speed and smoothness. The gradient step size data is allocated according to the refresh rate of the display device (60Hz), that is, one step voltage is output every 16.67 milliseconds to ensure that the brightness gradient is synchronized with the panel refresh rate.

[0061] In one implementation, the gradient step size data is obtained through the mapping relationship between pixel response time and step size factor; the ratio of step voltage to total voltage difference (step size factor) that makes brightness changes smooth and without overshoot within the response time range of 2~10ms is experimentally calibrated, and a response time-step size factor lookup table is established; in actual calculation, the step size factor is first obtained by looking up the table according to the current response time, and then multiplied by the difference between the target grayscale voltage and the voltage of the previous frame to obtain the gradient step size of the current frame.

[0062] It is important to note that after receiving the timing control signal, the display driver module converts the digital control signal into an analog driving voltage through its internal digital-to-analog converter. This voltage drives the panel backlight module or pixel units to adjust brightness according to a gradual step size. During the adjustment process, the driver module monitors the actual brightness feedback value of the panel in real time (collected by an integrated brightness sensor at a sampling frequency of 60Hz). If the deviation between the feedback value and the target step brightness exceeds ±1 nit, the duty cycle parameter of the next frame is dynamically fine-tuned, forming a closed-loop control. Ultimately, through multiple frames of continuous gradual adjustment, the panel brightness smoothly transitions to the target value, with the brightness change rate controlled within the range of 0.5-1.5 lux / ms, conforming to the visual adaptation characteristics of the human eye and achieving a visually comfortable state without jumps or flickering.

[0063] In summary, this invention discloses a method for adaptive brightness adjustment of a display screen, comprising: acquiring ambient light intensity data and analyzing its changing trend to determine the directional characteristics of light brightness changes as the basis for adaptive speed adjustment; inputting the adjustment basis into a visual adaptation model to generate smooth curve parameters adapted to the physiological characteristics of the human eye; discretizing and sampling the curve parameters to form a brightness transition sequence and converting it into an adjustment instruction set; calculating the deviation between the actual brightness of the display and the target reference value through a feedback control mechanism to determine the corrected brightness value; fusing real-time light intensity and historical light intensity data to construct a time series set, and obtaining a light expectation sequence through trend prediction; generating a main adjustment path and multiple scene backup adjustment paths based on the expectation sequence, and achieving path adaptive switching according to the real-time light intensity deviation to obtain the final brightness output scheme; finally extracting the adjustment instruction for the current time period and transmitting it to the display driver module to control the gradual adjustment of brightness to achieve a visually comfortable state.

[0064] Reference Figure 2 The second embodiment of the present invention provides a display screen brightness adaptive adjustment system, comprising: The light intensity trend analysis module is used to acquire ambient light intensity data and analyze the light intensity change trend. Based on the light intensity change trend, the directional characteristics of light brightness change are determined, and the directional characteristics are used as the basis for adjusting the adaptation speed. The curve parameter generation module is used to generate smooth curve parameters that adapt to the visual adaptation characteristics of the human eye based on the input preset visual adaptation model. The instruction set generation module is used to discretize the smooth curve parameters, generate ordered time coordinates, calculate the target brightness value for each ordered time coordinate, form a brightness transition sequence, and convert the brightness transition sequence into an adjustment instruction set. The brightness correction module is used to obtain the actual brightness value of the display, extract the target brightness value at the initial moment from the adjustment instruction set as the target reference value, calculate the deviation between the actual brightness value and the target reference value, and determine the corrected brightness value based on the deviation. The light prediction module is used to acquire real-time light intensity data and historical light intensity data, combine the historical light intensity data and the corrected brightness value to construct a light intensity time series set, and perform light trend prediction based on the light intensity time series set to obtain the expected light sequence. The path planning module is used to generate a main adjustment path and a backup adjustment path based on the expected light sequence. If the deviation between the real-time light intensity data and the expected value of the main adjustment path exceeds a preset tolerance range, the module switches to the backup adjustment path to obtain the final brightness output scheme. The brightness adjustment execution module is used to obtain the brightness adjustment command for the current time period from the brightness output scheme, transmit the brightness adjustment command to the display driver module, and the display driver module controls the display to perform a gradual brightness adjustment to obtain a visually comfortable state.

[0065] It should be noted that the display screen brightness adaptive adjustment system provided in this embodiment of the invention is used to execute all the process steps of the display screen brightness adaptive adjustment method in the above embodiment. The working principle and beneficial effects of the two are one-to-one, so they will not be described again.

[0066] It should be noted that the system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the system embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0067] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention for those skilled in the art.

Claims

1. A method for adaptive brightness adjustment of a display screen, characterized in that, include: Ambient light intensity data is acquired and the trend of light intensity change is analyzed. The directional characteristics of light brightness change are determined based on the light intensity change trend, and the directional characteristics are used as the basis for adjusting the adaptation speed. The adaptation speed is adjusted based on the input preset visual adaptation model to generate smooth curve parameters that adapt to the visual adaptation characteristics of the human eye. Discretize the smooth curve parameters to generate ordered time coordinates, calculate the target brightness value for each ordered time coordinate to form a brightness transition sequence, and convert the brightness transition sequence into an adjustment instruction set. The actual brightness value of the display is obtained, the target brightness value at the initial moment is extracted from the adjustment instruction set as the target reference value, the deviation between the actual brightness value and the target reference value is calculated, and the corrected brightness value is determined based on the deviation. Real-time light intensity data and historical light intensity data are acquired. A light intensity time series set is constructed by combining the historical light intensity data and the corrected brightness value. The light trend is predicted based on the light intensity time series set to obtain the expected light sequence. A primary adjustment path and a backup adjustment path are generated based on the expected light sequence. If the deviation between the real-time light intensity data and the expected value of the primary adjustment path exceeds a preset tolerance range, the system switches to the backup adjustment path to obtain the final brightness output scheme. The brightness adjustment command for the current time period is obtained from the brightness output scheme, and the brightness adjustment command is transmitted to the display driver module. The display driver module controls the display to perform a gradual brightness adjustment to obtain a visually comfortable state.

2. The adaptive brightness adjustment method for a display screen according to claim 1, characterized in that, The process of acquiring ambient light intensity data and analyzing the trend of light intensity changes, determining the directional characteristics of light brightness changes based on the light intensity change trend, and using the directional characteristics as the basis for adjusting the adaptation speed includes: The raw signals of ambient light intensity data are acquired according to the preset sampling frequency to construct an ambient light history sequence; The light intensity gradient feature is obtained by performing a difference operation on the ambient light history sequence, and the light intensity change slope is obtained by performing a linear fitting on the ambient light history sequence. If the slope of the light intensity change is greater than zero and the light intensity gradient feature is less than a preset fluctuation threshold, a trend vector with a positive polarity is generated. If the slope of the light intensity change is less than zero and the light intensity gradient feature exceeds the preset fluctuation threshold, a trend vector with a negative polarity is generated. In other cases, a trend vector with a stable polarity is generated to obtain the light intensity change trend. The response weight is obtained by searching a preset mapping table based on the light intensity change trend. The product of the response weight and the slope of the light intensity change is calculated to obtain the adaptation coefficient. The trend vector and the adaptation coefficient are used as the basis for adjusting the adaptation speed.

3. The display screen brightness adaptive adjustment method according to claim 1, characterized in that, The step of adjusting the adaptation speed based on a preset visual adaptation model to generate smooth curve parameters that adapt to the visual adaptation characteristics of the human eye includes: The adaptation speed is adjusted based on the input preset visual adaptation model, and the neural response feature value is output. The excitation signal component and the inhibition signal component in the neural response feature value are analyzed, the ratio of the excitation signal component to the inhibition signal component is calculated to obtain the signal component ratio, the visual perception state is determined according to the signal component ratio, and the visual perception state is divided into light adaptation priming state and dark adaptation priming state. If the brightness adaptation is in the aforementioned state, the time compression factor is calculated based on the rhodopsin decomposition rate constant. The time compression factor is then used to perform a time-domain compression transformation on the preset reference brightness adjustment curve to construct a brightness adjustment target trajectory sequence. If the dark adaptation is activated, the preset reference brightness adjustment curve is directly used to generate a brightness adjustment target trajectory sequence adapted to dark adaptation. High-order interpolation calculations are performed on the brightness adjustment target trajectory sequence to obtain smooth curve parameters.

4. The display screen brightness adaptive adjustment method according to claim 1, characterized in that, The process of discretizing the smooth curve parameters to generate ordered time coordinates, calculating the target brightness value for each ordered time coordinate to form a brightness transition sequence, and converting the brightness transition sequence into an adjustment instruction set includes: Discretization sampling is performed on the smooth curve parameters at fixed time intervals to generate a set of time point indices containing ordered time coordinates; For each time coordinate in the time point index set, the corresponding target brightness value is calculated by interpolation, and a brightness transition sequence with time domain information is constructed. Obtain the gamma correction data pre-stored on the display screen, use the gamma correction data to convert the target brightness value in the brightness transition sequence into a gray level value, and determine the corresponding driving voltage amplitude based on the gray level value; The duty cycle of the pulse width modulation signal is calculated based on the amplitude of the driving voltage, and the duty cycle of the pulse width modulation signal is encapsulated in time coordinate order to generate a continuous set of adjustment instructions.

5. The display screen brightness adaptive adjustment method according to claim 1, characterized in that, The steps of obtaining the actual brightness value of the display, extracting the target brightness value at the initial moment from the adjustment instruction set as the target reference value, calculating the deviation between the actual brightness value and the target reference value, and determining the corrected brightness value based on the deviation include: The duty cycle of the pulse width modulation signal at the initial moment is extracted from the adjustment instruction set, and the duty cycle of the pulse width modulation signal is mapped to the initial estimated brightness value using a preset electro-optic conversion model, which is then used as the target reference value. Obtain the actual brightness value and the original driving voltage amplitude of the display, and calculate the brightness deviation between the actual brightness value and the target reference value; The voltage compensation increment is calculated based on the brightness deviation, and the voltage compensation increment is added to the original driving voltage amplitude to obtain the correction voltage value. The duty cycle of the fine-tuned pulse width modulation signal is generated based on the corrected voltage value, and the corrected brightness value is obtained by mapping based on the fine-tuned duty cycle of the pulse width modulation signal.

6. The display screen brightness adaptive adjustment method according to claim 1, characterized in that, The process involves acquiring real-time and historical light intensity data, constructing a light intensity time series set by combining the historical light intensity data and the corrected brightness value, and predicting light trends based on the light intensity time series set to obtain a predicted light sequence, including: Acquire real-time light intensity data, historical light intensity data, and the corrected brightness value; perform luminous interference compensation on the real-time light intensity data based on the corrected brightness value; integrate the compensated real-time light intensity data with the historical light intensity data to obtain a corrected light intensity time series set. The light intensity time series set is input into a preset time series prediction model, and a preliminary future light ray prediction value is output. The preliminary future light ray prediction value is smoothed to obtain the light state estimate value. Trend fitting is performed on the estimated light state values ​​to obtain the expected light sequence.

7. The display screen brightness adaptive adjustment method according to claim 1, characterized in that, The process of generating a primary adjustment path and a backup adjustment path based on the expected light sequence, wherein if the deviation between the real-time light intensity data and the expected value of the primary adjustment path exceeds a preset tolerance range, switches to the backup adjustment path to obtain the final brightness output scheme, includes: Based on the expected light sequence, a main adjustment path is generated according to the preset illumination change gradient, and a backup adjustment path is generated for scenarios with sudden changes in light intensity. For the main adjustment path, a light intensity deviation tolerance range is set, and a mapping relationship is established between the backup adjustment path and different deviation ranges exceeding the tolerance range, and a path switching index table is constructed. Calculate the deviation of the real-time light intensity data from the expected light intensity value at the corresponding time of the main adjustment path; If the light intensity deviation exceeds the light intensity deviation tolerance range, the path switching index table is searched to match the corresponding backup adjustment path; if it does not exceed the range, the main adjustment path is used. The alternative or main adjustment path obtained by parsing and matching is used to generate the corresponding drive current sequence, and the drive current sequence is used as the final brightness output scheme.

8. The display screen brightness adaptive adjustment method according to claim 1, characterized in that, The step of obtaining the brightness adjustment command for the current time period from the brightness output scheme, transmitting the brightness adjustment command to the display driver module, and having the display driver module control the display to perform a gradual brightness adjustment to obtain a visually comfortable state includes: The timestamp index of the brightness output scheme is parsed, and the drive current sequence that matches the current system clock is extracted as the brightness adjustment command for the current time period. Based on the driving current sequence, a preset gamma correction curve is retrieved, and the corresponding grayscale voltage control value is obtained by mapping. By combining the real-time pixel response time of the display, the difference between the grayscale voltage control value and the voltage state of the previous frame is calculated to generate gradient step size data. Based on the gradually changing step size data, the duty cycle of the pulse width modulation signal is modulated to generate a timing control signal, which is then transmitted to the display driver module. The display driving module controls the pixel brightness to be gradually adjusted according to the timing control signal and the gradual step size data to achieve a visually comfortable state.

9. A display screen brightness adaptive adjustment system, characterized in that, include: The light intensity trend analysis module is used to acquire ambient light intensity data and analyze the light intensity change trend. Based on the light intensity change trend, the directional characteristics of light brightness change are determined, and the directional characteristics are used as the basis for adjusting the adaptation speed. The curve parameter generation module is used to generate smooth curve parameters that adapt to the visual adaptation characteristics of the human eye based on the input preset visual adaptation model. The instruction set generation module is used to discretize the smooth curve parameters, generate ordered time coordinates, calculate the target brightness value for each ordered time coordinate, form a brightness transition sequence, and convert the brightness transition sequence into an adjustment instruction set. The brightness correction module is used to obtain the actual brightness value of the display, extract the target brightness value at the initial moment from the adjustment instruction set as the target reference value, calculate the deviation between the actual brightness value and the target reference value, and determine the corrected brightness value based on the deviation. The light prediction module is used to acquire real-time light intensity data and historical light intensity data, combine the historical light intensity data and the corrected brightness value to construct a light intensity time series set, and perform light trend prediction based on the light intensity time series set to obtain the expected light sequence. The path planning module is used to generate a main adjustment path and a backup adjustment path based on the expected light sequence. If the deviation between the real-time light intensity data and the expected value of the main adjustment path exceeds a preset tolerance range, the module switches to the backup adjustment path to obtain the final brightness output scheme. The brightness adjustment execution module is used to obtain the brightness adjustment command for the current time period from the brightness output scheme, transmit the brightness adjustment command to the display driver module, and the display driver module controls the display to perform a gradual brightness adjustment to obtain a visually comfortable state.

Images