Color adjusting method and system of display screen based on environmental information

Abstract

The invention relates to the technical field of display screen color adjustment, and discloses a display screen color adjustment method and system based on environment information, and the method comprises the steps: obtaining display content data, environment color data, environment light data and a display screen type of a display screen; calculating color perception data according to the environment color data and the display screen type, and performing data processing on the color perception data to obtain chromaticity feedback data; establishing a relationship between the ambient light data and user preferences through a support vector machine method to obtain user evaluation data; inputting the chromaticity feedback data and the user evaluation data into a color correction model to obtain color adjustment data; classifying the display content data and calculating a type weight index through a squirrel optimization algorithm to obtain a weight index; and generating a color adjustment instruction according to the color adjustment data and the weight index, and performing adaptive adjustment on the display content. The method solves the problems that the color adjustment of the display screen has high requirements on a light source environment and is strong in subjectivity.

Description

Technical Field

[0001] The present invention relates to the technical field of display screen color adjustment, and in particular to a display screen color adjustment method and system based on environmental information. Background Art

[0002] With the continuous advancement of technology and the improvement of living standards, consumers' requirements for electronic devices such as mobile phones, tablets, TVs and monitors are gradually increasing. The screens of these devices are evolving towards larger sizes, slimmer designs, higher brightness, finer resolutions and more vivid colors to meet users' growing demand for visual experience. However, the development of display technology faces many challenges. When the ambient light conditions change, the screen color will be distorted to varying degrees, resulting in unstable display effects and affecting user experience. This color difference phenomenon is not only affected by changes in external lighting conditions, but also limited by the material properties and light-emitting principles of the display itself. The color performance of the screen will be different in different environments, which directly affects the quality of the viewing experience. Therefore, in order to ensure consistent and high-quality visual enjoyment under various lighting conditions, it is particularly important to research and develop advanced color calibration algorithms and technologies.

[0003] The traditional method of adjusting the color of the display screen first uses a light sensor to obtain the brightness and color temperature data of the current environment. The ambient reflectivity is calculated based on the data. Next, an environmental correction matrix is ​​generated based on the calculated ambient reflectivity to determine the adjustment parameters that each color should have in the current environment. The generated environmental correction matrix is ​​then applied to the color management system of the display screen to compensate for the effects of ambient light by adjusting the gain values ​​corresponding to each color coordinate, ensuring accurate color reproduction under different lighting conditions. Finally, the final color output parameters are adjusted according to the viewing distance to ensure that the display screen can correctly display colors under specific ambient light conditions.

[0004] However, because traditional color adjustment methods rely on accurate ambient light measurement and human judgment, and are mainly applicable to standard RGB light source environments, it is necessary to reconstruct the ambient reflectance model under non-standard light sources, which increases complexity and errors. Therefore, the existing technology has the problem that display color adjustment has high requirements for the light source environment and is highly subjective. Summary of the invention

[0005] The present invention provides a method and system for adjusting the color of a display screen based on environmental information, so as to solve the problem that the color adjustment of the display screen has high requirements on the light source environment and strong subjectivity.

[0006] In a first aspect, in order to solve the above technical problems, the present invention provides a color adjustment method of a display screen based on environmental information, comprising:

[0007] Acquire display content data, display environment data and display type of the display screen, wherein the display environment data includes ambient color data and ambient light data;

[0008] Calculating color perception data based on the ambient color data and the display screen type;

[0009] Performing quantization processing, smoothing adjustment, cluster analysis and polynomial regression analysis on the color perception data to obtain chromaticity feedback data;

[0010] Establishing the relationship between the ambient light data and the user preference by using a support vector machine method to obtain user evaluation data;

[0011] Inputting the chromaticity feedback data and the user evaluation data into a pre-trained color correction model to obtain color adjustment data;

[0012] Classifying the display content data by using the Kingfisher optimization algorithm, and calculating a type weight index according to the classification result and the user evaluation data to obtain a weight index;

[0013] A color adjustment instruction is generated according to the color adjustment data and the weight index, and the display content is adaptively adjusted according to the color adjustment instruction.

[0014] In an optional implementation, the calculating the color perception data according to the environmental color data and the display screen type includes:

[0015] Performing gamma correction on the environmental color data to obtain corrected color data;

[0016] Selecting an element in a corresponding independent space conversion matrix according to the display screen type;

[0017] Performing independent space conversion on the corrected color data to obtain independent color data;

[0018] Performing perceptual uniform color space conversion on the independent color data to obtain color perception data;

[0019] Gamma correction is performed by the following formula:

[0020] C′=C γ

[0021] Independent space conversion is performed using the following formula:

[0022]

[0023] The perceptually uniform color space conversion is performed by the following formula:

[0024] L *=116f(Y / Y n )-16

[0025] a * =500[f(X / X n )-f(Y / Y n )]

[0026] b * =200[f(Y / Y n )-f(Z / Z n )]

[0027]

[0028] Wherein, C represents the environmental color data, γ represents the preset gamma value, C′ represents the correction color data, R represents the red data in the correction color data, G represents the green data in the correction color data, B represents the blue data in the correction color data, and m 11 , m 12 , m 13 , m 21 , m 22 , m 23 , m 31 , m 32 , m 33 Represents the elements in the preset independent space conversion matrix, X, Y, Z represent independent color data, X n , Y n , Z n Indicates the tristimulus values ​​of the preset reference white point, L * , a * , b * represents color perception data, and t represents the result of dividing the value of the substituted independent color data by its corresponding reference white point.

[0029] In an optional implementation, the step of performing quantization processing, smoothing adjustment, cluster analysis and polynomial regression analysis on the color perception data to obtain chromaticity feedback data includes:

[0030] Quantizing the color perception data by a uniform quantization method to obtain quantized data;

[0031] Smoothing the quantized data using a Gaussian filter to obtain smoothed data;

[0032] Performing cluster analysis on the smoothed data by using a K-means clustering algorithm to obtain cluster analysis data;

[0033] Analyzing the cluster analysis data by polynomial regression analysis to obtain chromaticity feedback data;

[0034] The quantification is done by the following formula:

[0035]

[0036] The Gaussian filter looks like this:

[0037]

[0038] Where F represents L in color perception data * or a * or b * One of the data, F min Represents the minimum value in color perception data, F max represents the maximum value in the color perception data, N represents the total number of color perception data, p represents the quantized data, and p i+j represents the i+jth quantized data, σ and w represent the preset filter parameters, and p′ i Represents smoothed data.

[0039] In an optional implementation, the establishing the relationship between the ambient light data and the user preference by a support vector machine method to obtain the user evaluation data includes:

[0040] Performing standardization processing on the ambient light data to obtain standardized data;

[0041] Inputting the standardized data into a pre-trained support vector machine model to calculate a decision function, and using the output result of the decision function as decision data;

[0042] Mapping the decision data to a pre-stored evaluation interval to obtain user evaluation data;

[0043] The decision function is as follows:

[0044]

[0045] Among them, f(e new ) represents the decision function, SV represents the number of samples of the pre-stored historical ambient light data, represents the optimal solution of the trained Lagrange multiplier, b * Indicates the bias term after training, y i Indicates the weight coefficient of training completion, K(e i , e new ) represents the preset kernel function, e i represents the i-th data of historical ambient light data, e new Represents ambient light data.

[0046] In an optional implementation, the training process of the color correction model includes:

[0047] Inputting the pre-stored historical chromaticity feedback data and the pre-stored historical user evaluation data into the input layer of the initial color correction model for training, and obtaining the predicted value data output by the output layer of the initial color correction model;

[0048] Substituting the predicted value data and the pre-stored actual target value into the loss function to calculate the loss value to obtain the loss value data;

[0049] Calculating the gradient of the output layer output of the initial color correction model according to the loss value data, and passing the gradient forward layer by layer through the chain rule, calculating the gradient of the parameters of each layer, and obtaining gradient data;

[0050] Update the parameters of each layer of the initial color correction model according to the gradient data and the preset learning rate;

[0051] The parameters of each layer are updated repeatedly and iteratively until the training times of the initial color correction model are greater than the preset times, or when the loss value data of the initial color correction model is less than the preset loss threshold, the training is determined to be completed and the color correction model is obtained.

[0052] In an optional implementation, the display content data is classified by using the Kingfisher optimization algorithm, and a type weight index is calculated according to the classification result and the user evaluation data to obtain the weight index, including:

[0053] The display content data is classified by using the Kingfisher optimization algorithm to obtain the display content type.

[0054] The displayed content type and the user evaluation data are input into a pre-trained content type weight adjustment model to obtain a weight index.

[0055] In an optional implementation, the generating a color adjustment instruction according to the color perception data, the color adjustment data and the weight index, and adaptively adjusting the display content according to the color adjustment instruction includes:

[0056] Calculating the color difference between the color adjustment data to obtain color difference data;

[0057] Calculate a weight coefficient of the display content type according to the color difference data;

[0058] generating a color adjustment instruction according to the weight coefficient and the weight index;

[0059] According to the color adjustment instruction and the color adjustment data, gamma value adjustment, white balance adjustment, RGB gain adjustment, and color adjustment are performed on the display screen;

[0060] Among them, the color difference data is calculated by the following formula:

[0061]

[0062] The weight coefficient is calculated by the following formula:

[0063]

[0064] The color adjustment instructions are generated by the following formula:

[0065]

[0066] Where, ΔL * ik , Δa * ij , Δb * ik Represents the difference between the i-th color perception data and the j-th color perception data, ΔE ij represents the color difference between the i-th color perception data and the j-th color perception data, w ij Represents the weight coefficient, W i represents the weight index, k represents the preset slope, θ represents the preset threshold parameter, A i Indicates color adjustment instructions.

[0067] In a second aspect, the present invention provides a color adjustment system for a display screen based on environmental information, comprising:

[0068] A data acquisition module, used to acquire display content data, display environment data and display type of the display screen, wherein the display environment data includes ambient color data and ambient light data;

[0069] A color perception calculation module, used for calculating color perception data according to the environmental color data and the display screen type;

[0070] A chromaticity feedback analysis module, used for performing quantization processing, smoothing adjustment, cluster analysis and polynomial regression analysis on the color perception data to obtain chromaticity feedback data;

[0071] A user evaluation analysis module, used to establish a relationship between the ambient light data and user preferences through a support vector machine method to obtain user evaluation data;

[0072] A color correction module, used for inputting the chromaticity feedback data and the user evaluation data into a pre-trained color correction model to obtain color adjustment data;

[0073] A weight index calculation module, used to classify the display content data by using a Ban Kingfisher optimization algorithm, and calculate a type weight index according to the classification result and the user evaluation data to obtain a weight index;

[0074] The color adjustment module is used to generate a color adjustment instruction according to the color adjustment data and the weight index, and to adaptively adjust the display content according to the color adjustment instruction.

[0075] In a third aspect, the present invention further provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the color adjustment method of a display screen based on environmental information as described above is implemented.

[0076] In a fourth aspect, the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned methods for adjusting the color of a display screen based on environmental information.

[0077] Compared with the prior art, the present invention has the following beneficial effects:

[0078] The present invention discloses a color adjustment method for a display screen based on environmental information, comprising obtaining display content data, display environment data and display screen type of the display screen, wherein the display environment data includes environmental color data and environmental light data; calculating color perception data according to the environmental color data and the display screen type; performing quantization processing, smoothing adjustment, cluster analysis and polynomial regression analysis on the color perception data to obtain chromaticity feedback data; establishing the relationship between the ambient light data and user preferences by a support vector machine method to obtain user evaluation data; inputting the chromaticity feedback data and the user evaluation data into a pre-trained color correction model to obtain color adjustment data; classifying the display content data by a kingfisher optimization algorithm, and calculating the type weight index according to the classification result and the user evaluation data to obtain the weight index; generating a color adjustment instruction according to the color adjustment data and the weight index, and adaptively adjusting the display content according to the color adjustment instruction. The method obtains the display content data, display environment data and display screen type of the display screen, calculates the color perception data, and obtains the chromaticity feedback data through analysis and processing. At the same time, the support vector machine is used to associate the ambient light with the user preference to obtain the user evaluation data. After these data are input into the color correction model, color adjustment data is generated. Then the Ban Kingfisher optimization algorithm is used to classify the display content and calculate the weight index. Finally, instructions are generated according to the adjustment scheme and weight to achieve adaptive adjustment of the display content. This method reduces the requirements for specific light sources, reduces subjectivity, and improves the consistency and accuracy of color adjustment. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] Figure 1 is a schematic flow chart of a method for adjusting the color of a display screen based on environmental information provided by a first embodiment of the present invention;

[0080] Figure 2 1 is a schematic diagram of the structure of a color adjustment system for a display screen based on environmental information provided by a second embodiment of the present invention. DETAILED DESCRIPTION

[0081] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0082] Reference Figure 1 A first embodiment of the present invention provides a method for adjusting the color of a display screen based on environmental information, comprising the following steps:

[0083] S11, acquiring display content data, display environment data and display type of the display screen, wherein the display environment data includes ambient color data and ambient light data;

[0084] S12, calculating color perception data according to the environmental color data and the display screen type;

[0085] S13, performing quantization processing, smoothing adjustment, cluster analysis and polynomial regression analysis on the color perception data to obtain chromaticity feedback data;

[0086] S14, establishing a relationship between the ambient light data and the user preference by using a support vector machine method to obtain user evaluation data;

[0087] S15, inputting the chromaticity feedback data and the user evaluation data into a pre-trained color correction model to obtain color adjustment data;

[0088] S16, classifying the display content data by using a Bancroftian optimization algorithm, and calculating a type weight index according to the classification result and the user evaluation data to obtain a weight index;

[0089] S17, generating a color adjustment instruction according to the color adjustment data and the weight index, and adaptively adjusting the display content according to the color adjustment instruction.

[0090] In step S11, the display content data, display environment data and display type of the display screen are acquired, wherein the display environment data includes environment color data and environment light data.

[0091] Display content data consists of the information currently presented by the display, including but not limited to the characteristic information of color, brightness, and contrast of images, videos, and text elements. Display environment data is collected through integrated or external sensors that can sense the color and light intensity in the surrounding environment and convert these physical quantities into digital signals. Ambient color data reflects the color distribution in the environment, while ambient light data records the intensity and color temperature characteristics of the ambient light. Display type information can be obtained directly from product data, including the technical parameters and physical properties of the display, such as screen size, resolution, panel type (such as LCD, OLED), and light-emitting principle.

[0092] In step S12, color perception data is calculated according to the environmental color data and the display screen type.

[0093] In a specific implementation, the calculating the color perception data according to the environmental color data and the display screen type includes:

[0094] Performing gamma correction on the environmental color data to obtain corrected color data;

[0095] Selecting an element in a corresponding independent space conversion matrix according to the display screen type;

[0096] Performing independent space conversion on the corrected color data to obtain independent color data;

[0097] Performing perceptual uniform color space conversion on the independent color data to obtain color perception data;

[0098] Gamma correction is performed by the following formula:

[0099] C′=C γ

[0100] Independent space conversion is performed using the following formula:

[0101]

[0102] The perceptually uniform color space conversion is performed by the following formula:

[0103] L * =116f(Y / Y n )-16

[0104] a * =500[f(X / X n )-f(Y / Y n )]

[0105] b * =200[f(Y / Y n )-f(Z / Z n )]

[0106]

[0107] Wherein, C represents the environmental color data, γ represents the preset gamma value, C′ represents the correction color data, R represents the red data in the correction color data, G represents the green data in the correction color data, B represents the blue data in the correction color data, and m 11 , m 12 , m 13 , m 21 , m 22 , m 23 , m 31 , m 32 , m 33 Represents the elements in the preset independent space conversion matrix, X, Y, Z represent independent color data, X n , Y n , Z nIndicates the tristimulus values ​​of the preset reference white point, L * , a * , b * represents color perception data, t represents the value of the substituted independent color data (X, Y, Z) divided by its corresponding reference white point (X n , Y n , Z n ) after.

[0108] Specifically, first, gamma correction is performed on the ambient color data to resolve the nonlinear relationship between the display output and the human eye's perception, ensuring the consistency and accuracy of colors on different display devices. Gamma correction adjusts the brightness distribution of the image by applying a power function, making the mid-tones brighter and closer to the actual perception of the human eye. Specifically, for a given ambient color data C, its gamma-corrected value C′ can be obtained by the formula C′=C γ It is calculated that γ is the preset gamma value, which is a parameter of nonlinear transformation and is related to the display type.

[0109] Next, based on the information about the display type obtained, select an element in an independent space conversion matrix that matches it. Each display requires a specific space conversion matrix for color conversion due to its unique physical properties and technical parameters (such as LCD or OLED panels). The matrix consists of multiple preset coefficients that are used to convert the red R, green G, and blue B data in the RGB color model into corresponding values ​​in the XYZ color space. The specific conversion formula is:

[0110]

[0111] Among them, X, Y, Z represent independent color data, m 11 , m 12 , m 13 , m 21 , m 22 , m 23 , m 31 , m 32 , m 33 Represents an element selected from a predefined space transformation matrix.

[0112] Then, in order to further process the obtained independent color data, it is converted to a perceptually uniform color space, namely the CIELAB color space. This conversion is intended to create a color representation method that is more consistent with the human visual system, in which color points with similar distances appear closer. The conversion formula is as follows:

[0113] L * =116f(Y / Y1)-16

[0114] a * =500[f(X / X n )-f(Y / Y n )]

[0115] b * =200[f(Y / Y n )-f(Z / Z n )]

[0116] Among them, X n , Y n , Z n Indicates the tristimulus values ​​of the preset reference white point, L * , a * , b * represents color perception data; the function f(t) is defined as:

[0117]

[0118] Where t represents the value of the independent color data (X, Y, Z) divided by its corresponding reference white point (X n , Y n , Z n ) after the above series of transformations are performed on the color data. The color perception data (L * , a * , b * ) can better reflect the true perception of color by the human visual system, thereby achieving accurate calculation of color perception data.

[0119] The function f(t) is to perform nonlinear mapping on independent color data in order to more accurately reflect the brightness and chromaticity changes in human visual perception. The linear part is used to avoid large errors in low-brightness areas, and when the t value is greater than the threshold When , a cube root operation is used to approximate the human eye's response to brightness changes.

[0120] Substituting the function f(t) into the perceptual uniform color space conversion formula, we get the specific formula shown below:

[0121]

[0122] In step S13, the color perception data is subjected to quantization processing, smoothing adjustment, cluster analysis and polynomial regression analysis to obtain chromaticity feedback data.

[0123] In a specific implementation, the color perception data is subjected to quantization processing, smoothing adjustment, cluster analysis and polynomial regression analysis to obtain chromaticity feedback data, including:

[0124] Quantizing the color perception data by a uniform quantization method to obtain quantized data;

[0125] Smoothing the quantized data using a Gaussian filter to obtain smoothed data;

[0126] Performing cluster analysis on the smoothed data by using a K-means clustering algorithm to obtain cluster analysis data;

[0127] Analyzing the cluster analysis data by polynomial regression analysis to obtain chromaticity feedback data;

[0128] The quantification is done by the following formula:

[0129]

[0130] The Gaussian filter looks like this:

[0131]

[0132] Where F represents L in color perception data * or a * or b * One of the data, F min Represents the minimum value in color perception data, F max represents the maximum value in the color perception data, N represents the total number of color perception data, p represents the quantized data, and p i+j represents the i+jth quantized data, σ and w represent the preset filter parameters, and p′ i Represents smoothed data.

[0133] First, the color perception data is quantized by uniform quantization, a process that aims to reduce the complexity of color representation while maintaining sufficient accuracy to capture the key characteristics of color. Specifically, for a given color perception data, its quantized value can be obtained by the formula This formula maps the original color perception data to a discrete value range, thereby achieving effective compression of color information.

[0134] Next, in order to further improve the quality of the quantized data and reduce the impact of noise, a Gaussian filter is used to smooth the quantized data. Gaussian filtering is a linear low-pass filter that can effectively suppress noise that follows a normal distribution while keeping the main features of the image unchanged. For each quantized data point, its smoothed value can be calculated according to the following formula:

[0135]

[0136] Among them, σ and w are the preset filter parameters, which determine the size and shape of the filter window; p i+j Represents the i+jth quantized data point. This formula achieves a smoothing effect by applying a weighted average to each data point and the points in its neighborhood. The weight is determined by a Gaussian function, with the center point having the largest weight and gradually decreasing with increasing distance.

[0137] Next, in the process of clustering the smoothed data using the K-means clustering algorithm, we first need to determine the number of clusters to be formed, K. The choice of this parameter can be determined according to the needs of the specific application scenario or through techniques such as the Elbow method. Once K is determined, the algorithm will randomly select K data points as the initial cluster centers.

[0138] Next, the algorithm enters the iterative optimization phase, and its core steps include:

[0139] Assign samples: Calculate p for each data point i The distance to each cluster center is calculated and assigned to the cluster to which the nearest cluster center belongs. The distance metric here usually uses Euclidean distance, but other metrics can also be selected according to specific circumstances.

[0140] Update cluster center: For each cluster, recalculate the mean of all data points in the cluster and use it as the new cluster center position. This means that the cluster center will gradually "move" toward the data points in the cluster to better represent the data distribution characteristics of the cluster.

[0141] Check convergence conditions: Repeat the above two steps until a specific termination condition is met. Common termination conditions include no significant change in cluster centers, reaching a preset maximum number of iterations, or the change in cluster members is less than a preset threshold.

[0142] After clustering is completed, the clustering results provide structured input for subsequent analysis. In order to further understand the relationship between different clusters and the trend of color changes within the clusters, polynomial regression analysis can be applied based on the results of cluster analysis. Polynomial regression models allow capturing more complex nonlinear relationships between independent variables and dependent variables, and are particularly suitable for describing data patterns that show curved rather than straight-line trends.

[0143] The specific formation process of the polynomial model:

[0144] Assume that x is one or more independent variables (such as brightness, hue, etc.), and y is the corresponding dependent variable. In order to build a polynomial regression model, you first need to determine the order n of the polynomial, which depends on the observed data trend and the fitting accuracy you want the model to achieve. Although a higher order can provide a better fit, it may also lead to overfitting problems, that is, the model follows the noise or outliers in the training data too closely.

[0145] Once the order n of the polynomial is determined, the general form of the polynomial regression model can be defined as follows:

[0146] y=β0+β1x+β2x 2 +...+β n x n +∈

[0147] Among them, β k (k=0,1,...,n) are the coefficients to be estimated, ∈ represents the error term, which reflects the variability of the data that the model cannot explain. In order to solve these unknown coefficients, the commonly used method is the least squares method, which attempts to minimize the predicted value The sum of the squared differences between y and the actual observed value y. Specifically, the residual sum of squares (RSS) can be calculated by the following formula:

[0148]

[0149] Where m is the number of samples. By adjusting the coefficient β to be estimated k The value of makes the RSS minimum and a set of optimal polynomial coefficients can be obtained.

[0150] In this way, the polynomial regression model can not only reveal the color variation patterns within the clusters, but also provide a scientific basis for dynamically adjusting the display content, thereby ensuring a consistent and realistic visual experience in various environments.

[0151] In step S14, a relationship between the ambient light data and user preferences is established by using a support vector machine method to obtain user evaluation data.

[0152] In a specific implementation, the relationship between the ambient light data and the user preference is established by a support vector machine method to obtain the user evaluation data, including:

[0153] Performing standardization processing on the ambient light data to obtain standardized data;

[0154] Inputting the standardized data into a pre-trained support vector machine model to calculate a decision function, and using the output result of the decision function as decision data;

[0155] Mapping the decision data to a pre-stored evaluation interval to obtain user evaluation data;

[0156] The decision function is as follows:

[0157]

[0158] Among them, f(enew ) represents the decision function, SV represents the number of samples of the pre-stored historical ambient light data, represents the optimal solution of the trained Lagrange multiplier, b * Indicates the bias term after training, y i Indicates the weight coefficient of training completion, K(e i , e new ) represents the preset kernel function, e i represents the i-th data of historical ambient light data, e new represents the ambient light data. The output result of the decision function is the decision data.

[0159] Specifically, the raw ambient light data is first preprocessed to ensure that the data is suitable for input into the pre-trained support vector machine model for calculation. Specifically, the task of this stage is to perform standardization on the ambient light data to obtain standardized data. Standardization is the conversion of data of different dimensions into dimensionless pure values ​​for easy comparison and weighting. The z-score standardization method is usually used, which makes the processed data conform to the standard normal distribution, that is, the mean is 0 and the standard deviation is 1.

[0160] After completing data normalization, the next step is to input the normalized ambient light data as a new sample into the pre-trained support vector machine model to calculate the decision function. The core of the support vector machine is to solve the maximum margin hyperplane. For nonlinearly separable data, the kernel function is used to map the data to a higher dimensional space to make it linearly separable. In this process, the model constructs the optimal classification boundary based on the support vectors in the training set and determines the Lagrange multiplier. and the bias term b * , and the category label y corresponding to each support vector i For new ambient light data new , the decision function f(e new ) is as follows:

[0161]

[0162] Once the decision function f(e new), i.e., the decision data, the next step is to map the decision data to the pre-stored evaluation interval to obtain the final user evaluation data. This step involves converting the continuous decision value into a discrete evaluation level or score to ensure that the output result has intuitive meaning and can directly reflect the user's preference. To achieve this, a mapping rule can be defined, such as linear mapping or piecewise linear mapping, to set the corresponding conversion formula according to the output range of the decision function and the expected evaluation interval. If the evaluation interval is set to [0,1] or [-1,1], the decision value can be adapted to this interval by adjusting the mapping parameters. In addition, the threshold segmentation method can be considered to divide the decision value into several intervals, each interval corresponding to a different evaluation level, thereby realizing the transition from continuous value to discrete evaluation.

[0163] The training process of the Support Vector Machine (SVM) model is an iterative optimization process, the goal of which is to find the hyperplane that can best distinguish different categories of data. To achieve this, the SVM algorithm needs to solve a convex quadratic programming problem that aims to maximize the classification interval while minimizing the classification error. The following are the specific steps involved in training the support vector machine model involved in establishing the relationship between ambient light data and user preferences.

[0164] First, before starting training, the dataset must be prepared and preprocessed. This includes collecting ambient light data and standardizing or normalizing it to ensure that all features have a similar numerical range, thereby avoiding some features having an undue impact on the model due to their large magnitude. In addition, the dataset needs to be divided into training and test sets so that the model performance can be evaluated after training.

[0165] Next, choosing an appropriate kernel function is a crucial step. For linearly separable data sets, a simple linear kernel can be selected; for nonlinearly separable data sets, a polynomial kernel, radial basis function (RBF) kernel or other types of kernel functions can be used to elevate the data to a higher dimensional space to make it linearly separable. The choice of kernel function directly affects the model's capabilities and generalization performance.

[0166] Then, we enter the core training phase. In this phase, SVM tries to find the optimal hyperplane by solving the objective function of the following form:

[0167]

[0168] Among them, w is the weight vector, b is the bias term, C is the regularization parameter, which controls the degree of punishment for misclassified samples, and ξ iis a slack variable that allows a certain degree of misclassification, and v is the number of training samples. This objective function not only considers maximizing the classification interval (given by ∥w∥ 2 ), and also consider reducing the classification error (denoted by ξ i In order to ensure the existence and uniqueness of the solution, the constraints under the KKT condition must also be met.

[0169] In order to solve the above optimization problem, a common method is to use the Lagrange multiplier method, introduce the Lagrange multiplier α, and transform the original problem into a dual problem. The dual problem is a maximization problem about α, and its expression is as follows:

[0170]

[0171] Here, K(x i ,x j ) is the selected kernel function used to measure the similarity between two samples. By taking the derivative of W(α) and setting it equal to zero, the optimal Then we get the optimal w * and b * .

[0172] Once the optimal solution w is found * and b * , we can determine the final support vectors. These support vectors are the data points closest to the decision boundary, and they determine the position of the hyperplane. It is worth noting that the SVM model only relies on these support vectors for prediction, not all training samples, which means that even if the non-support vectors are removed, the results of the model will not change.

[0173] After training, the next step is to validate and tune the model. This usually involves testing the model's performance on an independent validation set and adjusting the model parameters based on the results. The goal is to ensure that the model is neither overfitting nor underfitting, and has good generalization capabilities on unknown data.

[0174] In summary, by standardizing the ambient light data, using the pre-trained support vector machine model to calculate the decision function, and mapping the decision data to the pre-stored evaluation interval, we can effectively establish the connection between the ambient light data and the user's preferences, and finally generate evaluation data that accurately reflects the user's preferences. This approach not only improves the reliability and accuracy of the analysis results, but also provides a solid foundation for personalized services.

[0175] In step S15, the chromaticity feedback data and the user evaluation data are input into a pre-trained color correction model to obtain color adjustment data.

[0176] In a specific implementation, the training process of the color correction model includes:

[0177] Inputting the pre-stored historical chromaticity feedback data and the pre-stored historical user evaluation data into the input layer of the initial color correction model for training, and obtaining the predicted value data output by the output layer of the initial color correction model;

[0178] Substituting the predicted value data and the pre-stored actual target value into the loss function to calculate the loss value to obtain the loss value data;

[0179] Calculating the gradient of the output layer output of the initial color correction model according to the loss value data, and passing the gradient forward layer by layer through the chain rule, calculating the gradient of the parameters of each layer, and obtaining gradient data;

[0180] Update the parameters of each layer of the initial color correction model according to the gradient data and the preset learning rate;

[0181] The parameters of each layer are updated repeatedly and iteratively until the training times of the initial color correction model are greater than the preset times, or when the loss value data of the initial color correction model is less than the preset loss threshold, the training is determined to be completed and the color correction model is obtained.

[0182] Specifically, the training of the color correction model begins with the preparation stage, which is to collect and preprocess historical color feedback data and user evaluation data. After preprocessing operations such as cleaning, normalization or standardization, these data are organized into a form suitable for neural network input. Subsequently, these data sets are divided into training sets and validation sets, where the training set is used to guide the learning of model parameters, while the validation set is used to evaluate the model's generalization ability and avoid overfitting.

[0183] Entering the training phase, the initial color correction model receives input from the training set - namely historical chromaticity feedback data and user evaluation data - and passes it to the hidden layer through the input layer for feature extraction and conversion, and finally generates predicted value data by the output layer.

[0184] In order to measure the difference between the predicted value and the actual target value, a loss function is introduced, which calculates the distance between the two. The loss value data reflects the quality of the current model's prediction performance. The smaller the loss value, the closer the prediction result is to the real one.

[0185] Next, the gradient of the output layer is calculated based on the loss value data, that is, the derivative of the loss function with respect to the model parameters is calculated. This step is to determine how to adjust the parameters to reduce the loss value. For a multi-layer neural network, this process requires the use of the chain rule to pass the gradient of the output layer forward layer by layer until the input layer, thereby calculating the gradient of each layer parameter. In this way, the gradient information of each layer parameter relative to the loss function can be obtained.

[0186] After obtaining the gradient information, the next step is to update the parameters of each layer of the model according to the preset learning rate. The update rule follows the gradient descent algorithm. It is crucial to choose the learning rate appropriately, because too large a learning rate may lead to excessive parameter updates, while too small a learning rate will make the convergence speed too slow. In addition, strategies such as momentum and adaptive learning rate can be combined to further improve the optimization efficiency.

[0187] The entire training process is an iterative process, and each iteration includes four main steps: forward propagation, loss calculation, back propagation, and parameter update. As the number of iterations increases, the model gradually learns to extract useful features from the input data and make more accurate predictions. Training terminates when any of the following conditions is met: first, the number of model training times exceeds the preset maximum number of iterations; second, the model's loss value has dropped below the preset loss threshold, indicating that the model has achieved a satisfactory level of accuracy.

[0188] After obtaining the trained color correction model, the chromaticity feedback data and user evaluation data need to be formatted into a form suitable for the color correction model input to ensure data consistency and compatibility.

[0189] Once the data is preprocessed, the next step is to prepare the model input. At this stage, the color feedback data and user evaluation data are combined to form a multi-dimensional feature vector as the model input. This multi-dimensional feature vector contains all the necessary information so that the color correction model can predict new color adjustment parameters based on historical learning experience.

[0190] When the input data enters the color correction model, the model will perform forward propagation based on the internal learned parameters. During this process, each layer of neurons will receive information from the previous layer and apply the activation function for nonlinear mapping, and finally the output layer will generate a set of values ​​representing the color adjustment suggestions. This series of values ​​constitutes the color adjustment data.

[0191] In summary, by inputting chromaticity feedback data and user evaluation data into the pre-trained color correction model, we can not only effectively obtain color adjustment data, but also ensure that the model can provide high-quality color correction services in complex real-world scenarios through a deep understanding of the color correction model training process. This process reflects the powerful ability and flexibility of machine learning technology in solving practical problems.

[0192] In step S16, the display content data is classified by using the Kingfisher optimization algorithm, and the type weight index is calculated according to the classification result and the user evaluation data to obtain the weight index.

[0193] In a specific implementation, the display content data is classified by using the Kingfisher optimization algorithm, and a type weight index is calculated according to the classification result and the user evaluation data to obtain the weight index, including:

[0194] The display content data is classified by using the Kingfisher optimization algorithm to obtain the display content type.

[0195] The displayed content type and the user evaluation data are input into a pre-trained content type weight adjustment model to obtain a weight index.

[0196] First, in order to achieve effective classification of display content data, the Kingfisher Optimization Algorithm needs to be applied. The Kingfisher Optimization Algorithm is a new meta-heuristic algorithm inspired by the unique hunting behavior and symbiotic relationship of the Kingfisher in nature. This algorithm is built around three different stages: perching / hovering prey (exploration / diversification), diving for prey (exploitation / intensification), and cultivating symbiotic relationships. For the classification task of display content data, the Kingfisher Optimization Algorithm starts the search process by initializing the population, that is, randomly generating a set of starting solutions from the search space as the first attempt. Each individual represents a possible classification scheme, and the quality of these schemes is evaluated by the fitness function. As the number of iterations increases, the Kingfisher Optimization Algorithm continuously updates the individual positions, simulating the foraging activities of the Kingfisher in the natural environment to find the optimal or near-optimal classification scheme.

[0197] Specifically, in the initialization phase, the Ban Kingfisher Optimization Algorithm randomly generates an initial population according to the formula Xi; j = LB + rand × (UB-LB), where Xi; j represents the position of the i-th individual in the j-th dimension, rand is a random value between 0 and 1, and UB and LB are the upper and lower bounds of the search range, respectively. Subsequently, in the exploration phase, the algorithm updates the position of the search population according to the perching and hovering behavior of the Ban Kingfisher, using the formula Xi(t+1) = Xi(t) + α × T, where α = 2 × randn(1, dim)-1, randn is used to generate a random number tensor, the dim parameter specifies the size of the tensor in the second dimension, and the T parameter is dynamically determined according to the current strategy. In the development phase, the Ban Kingfisher Optimization Algorithm imitates the fast and accurate diving ability of the Ban Kingfisher, using the formula Xi(t+1) = Best p osition+α×(Xi(t)-Best p osition), among which Best p osiion is the best location found so far.

[0198] After the classification is completed, the next task is to input the display content type together with the user evaluation data into the pre-trained content type weight adjustment model. This model aims to learn the relationship between different types of display content and user satisfaction, and calculate the corresponding weight index for each type. The pre-trained model has been fully learned on a large amount of historical data and can capture the potential connection between display content features and user feedback. When new display content types and user evaluation data are input, the model will make predictions based on internal parameters and output the corresponding weight index.

[0199] To ensure the accuracy of the weight index calculation, the content type weight adjustment model is trained using a supervised learning method. During the training process, the model receives the displayed content types and their corresponding user evaluation data from historical records as input, and uses the actual type weight index as the target output. By minimizing the difference between the predicted value and the true value, the model gradually adjusts its own parameters until a satisfactory performance level is achieved.

[0200] In summary, the process of classifying display content data through the Kingfisher optimization algorithm and calculating the type weight index in combination with user evaluation data is a comprehensive solution that integrates advanced optimization technology and machine learning models. This method not only improves the accuracy of classification, but also provides a scientific basis for subsequent decision-making by quantifying the importance of different types of display content.

[0201] In step S17, a color adjustment instruction is generated according to the color adjustment data and the weight index, and the display content is adaptively adjusted according to the color adjustment instruction.

[0202] In a specific implementation, generating a color adjustment instruction according to the color perception data, the color adjustment data, and the weight index, and adaptively adjusting the displayed content according to the color adjustment instruction includes:

[0203] Calculating the color difference between the color adjustment data to obtain color difference data;

[0204] Calculate a weight coefficient of the display content type according to the color difference data;

[0205] generating a color adjustment instruction according to the weight coefficient and the weight index;

[0206] According to the color adjustment instruction and the color adjustment data, gamma value adjustment, white balance adjustment, RGB gain adjustment, and color adjustment are performed on the display screen;

[0207] Among them, the color difference data is calculated by the following formula:

[0208]

[0209] The weight coefficient is calculated by the following formula:

[0210]

[0211] The color adjustment instructions are generated by the following formula:

[0212]

[0213] Where, ΔL * ij , Δa * ij , Δb * ij Represents the difference between the i-th color perception data and the j-th color perception data, ΔE ij represents the color difference between the i-th color perception data and the j-th color perception data, w ij Represents the weight coefficient, W i represents the weight index, k represents the preset slope, θ represents the preset threshold parameter, A i Indicates color adjustment instructions.

[0214] First, in order to quantify the difference between the color adjustment data, the color difference data needs to be calculated. Color difference is an important indicator to measure the perceived difference between two colors. The color difference formula in the CIE 1976Lab color space is used here. Specifically, for any pair of color perception data, the color difference between them is calculated using the following formula:

[0215]

[0216] This formula evaluates the difference between two sets of color perception data based on the Euclidean distance, and can provide an objective and quantitative color similarity metric.

[0217] Next, based on the color difference data calculated above, the weight coefficient of the display content type is further calculated. The weight coefficient reflects the degree of influence of the color difference between a pair of color perception data on the final color adjustment decision, and its calculation formula is as follows:

[0218]

[0219] Here, k is the preset slope parameter used to control the steepness of the function curve; and θ is the threshold parameter that determines the starting point of the change of the weight coefficient. ij When it is greater than θ, the weight coefficient w ij This mechanism ensures that only data with significant color difference will have a significant impact on subsequent color adjustment.

[0220] Then, the previously calculated weight coefficient and weight index are combined to generate a color adjustment instruction for each display content type. The color adjustment instruction comprehensively considers the importance of different types of display content and the color difference relationship between them to guide the specific color adjustment operation. The specific formula is:

[0221]

[0222] In this way, color adjustment instructions not only take into account the characteristics of individual display content, but also take into account the consistency and harmony of the overall visual experience.

[0223] Finally, according to the generated color adjustment instructions and color adjustment data, a series of specific color adjustment measures are performed, including gamma value adjustment, white balance adjustment, RGB gain adjustment, etc. These adjustment measures directly act on the physical characteristics of the display, such as brightness response curve, color balance, etc., thereby changing the actual presentation effect of the displayed content. For example, gamma value adjustment can correct the image brightness distribution, making the dark details more clearly visible; white balance adjustment helps to eliminate the color temperature offset caused by light source changes and ensures faithful color reproduction; RGB gain adjustment allows independent control of the proportion of the three primary colors of red, green, and blue to optimize color saturation and contrast.

[0224] In summary, by conducting in-depth analysis of color adjustment data, using a series of methods such as color difference calculation, weight coefficient determination, and color adjustment parameter setting, accurate adaptive adjustment of display content is achieved. This process not only improves display quality, but also enhances the consistency and comfort of user experience.

[0225] The following describes the working process of the present invention using a relatively common scenario as an example. Figure 1 , a color adjustment method of a display screen based on environmental information, comprising the following steps:

[0226] Assume that the environment is a well-lit office with a display screen for displaying professional photography pictures. In order to ensure the accuracy of the picture colors and optimize the visual effects, the color adjustment system starts working. First, the system receives data from the ambient light sensor, which contains the current ambient light intensity and color temperature information. At the same time, the system also obtains the user's settings for color preferences.

[0227] Next, the color adjustment system analyzed the type of content being displayed and identified that it was a series of professional photographs that required high color fidelity. Based on this, the system evaluated the gap between the existing display settings and the ideal state and determined the necessary color adjustment parameters.

[0228] The color adjustment system then calculates the color difference between different color perception data and adjusts the weight coefficient of the display content type based on this. This process ensures that the color adjustment instructions can fully reflect the impact of ambient light conditions and user preferences on the final display effect.

[0229] Subsequently, the color adjustment system generates a color adjustment instruction based on the calculated weight coefficient and the pre-set weight index. The instruction takes various factors into consideration to achieve the best visual experience. According to the color adjustment instruction, the system adjusts the gamma value of the display screen to make the brightness distribution of the image more uniform and reasonable; adjusts the white balance to ensure the faithful reproduction of colors under different light sources; and adjusts the RGB gain to optimize the color saturation and contrast, ensuring that every photo can show the most realistic colors.

[0230] After completing the above adjustments, the professional photography works on the display screen showed excellent color expression, not only bright and natural colors, but also rich details and clear layers, which fully met the photographer's creative intentions and the audience's viewing needs. Throughout the process, the color adjustment system achieved the optimal presentation of display content in a specific environment through precise environmental information analysis and intelligent color adjustment, solving the problem that the color adjustment of the display screen has high requirements for the light source environment and strong subjectivity.

[0231] Reference Figure 2 A second embodiment of the present invention provides a color adjustment system for a display screen based on environmental information, comprising:

[0232] A data acquisition module, used to acquire display content data, display environment data and display type of the display screen, wherein the display environment data includes ambient color data and ambient light data;

[0233] A color perception calculation module, used for calculating color perception data according to the environmental color data and the display screen type;

[0234] A chromaticity feedback analysis module, used for performing quantization processing, smoothing adjustment, cluster analysis and polynomial regression analysis on the color perception data to obtain chromaticity feedback data;

[0235] A user evaluation analysis module, used to establish a relationship between the ambient light data and user preferences through a support vector machine method to obtain user evaluation data;

[0236] A color correction module, used for inputting the chromaticity feedback data and the user evaluation data into a pre-trained color correction model to obtain color adjustment data;

[0237] A weight index calculation module, used to classify the display content data by using a Ban Kingfisher optimization algorithm, and calculate a type weight index according to the classification result and the user evaluation data to obtain a weight index;

[0238] The color adjustment module is used to generate a color adjustment instruction according to the color adjustment data and the weight index, and to adaptively adjust the display content according to the color adjustment instruction.

[0239] It should be noted that a color adjustment device for a display screen based on environmental information provided in an embodiment of the present invention is used to execute all process steps of a color adjustment method for a display screen based on environmental information in the above embodiment. The working principles and beneficial effects of the two correspond one to one, and thus will not be described in detail.

[0240] An embodiment of the present invention further provides an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a color adjustment method program for a display screen based on environmental information. When the processor executes the computer program, the steps in the above-mentioned color adjustment method for a display screen based on environmental information are implemented, such as Figure 1 Alternatively, when the processor executes the computer program, the functions of the modules / units in the above-mentioned device embodiments are realized, such as the color adjustment method module of the display screen based on environmental information.

[0241] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the electronic device.

[0242] The electronic device may be a computing device such as a desktop computer, a notebook, a PDA, and a smart tablet. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the above components are merely examples of electronic devices and do not constitute a limitation on the electronic device. The electronic device may include more or fewer components than the above components, or may combine certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0243] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the electronic device, and uses various interfaces and lines to connect various parts of the entire electronic device.

[0244] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the electronic device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0245] Wherein, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0246] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0247] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A color adjustment method for a display screen based on environmental information, characterized in that: Executed by the controller, including: Acquire display content data, display environment data and display type of the display screen, wherein the display environment data includes ambient color data and ambient light data; Calculating color perception data based on the ambient color data and the display screen type; Performing quantization processing, smoothing adjustment, cluster analysis and polynomial regression analysis on the color perception data to obtain chromaticity feedback data; Establishing the relationship between the ambient light data and the user preference by using a support vector machine method to obtain user evaluation data; Inputting the chromaticity feedback data and the user evaluation data into a pre-trained color correction model to obtain color adjustment data; Classifying the display content data by using the Kingfisher optimization algorithm, and calculating a type weight index according to the classification result and the user evaluation data to obtain a weight index; A color adjustment instruction is generated according to the color adjustment data and the weight index, and display content is adaptively adjusted according to the color adjustment instruction.

2. The color adjustment method of a display screen based on environmental information according to claim 1, characterized in that: The calculating the color perception data according to the environmental color data and the display screen type includes: Performing gamma correction on the environmental color data to obtain corrected color data; Selecting an element in a corresponding independent space conversion matrix according to the display screen type; Performing independent space conversion on the corrected color data to obtain independent color data; Performing perceptual uniform color space conversion on the independent color data to obtain color perception data; Gamma correction is performed by the following formula: C ′ =C γ Independent space conversion is performed using the following formula: The perceptually uniform color space conversion is performed by the following formula: L * =116f(Y / Y n )-16 a * =500[f(X / X n )-f(Y / Y n )] b * =200[f(Y / Y n )-f(Z / Z m )] Where C represents the ambient color data, γ represents the preset gamma value, and C ′ represents the corrected color data, R represents the red data in the corrected color data, G represents the green data in the corrected color data, B represents the blue data in the corrected color data, and m 11 , m 12 , m 13 , m 21 , m 22 , m 23 , m 31 , m 32 , m 33 Represents the elements in the preset independent space conversion matrix, X, Y, Z represent independent color data, X n , Y n , Z n Indicates the tristimulus values ​​of the preset reference white point, L * , a * , b * represents color perception data, and t represents the result of dividing the value of the substituted independent color data by its corresponding reference white point.

3. The color adjustment method of a display screen based on environmental information according to claim 1, characterized in that: The color perception data is subjected to quantization processing, smoothing adjustment, cluster analysis and polynomial regression analysis to obtain chromaticity feedback data, including: Quantizing the color perception data by a uniform quantization method to obtain quantized data; Smoothing the quantized data using a Gaussian filter to obtain smoothed data; Performing cluster analysis on the smoothed data by using a K-means clustering algorithm to obtain cluster analysis data; Analyzing the cluster analysis data by polynomial regression analysis to obtain chromaticity feedback data; The quantification is done by the following formula: The Gaussian filter looks like this: Where F represents L in color perception data * or a * or b * One of the data, F min Represents the minimum value in color perception data, F max represents the maximum value in the color perception data, N represents the total number of color perception data, p represents the quantized data, and p i+j represents the i+jth quantized data, σ and w represent the preset filter parameters, and p ′ i Represents smoothed data.

4. The color adjustment method of a display screen based on environmental information according to claim 1, characterized in that: The method of establishing the relationship between the ambient light data and the user preference by using the support vector machine method to obtain the user evaluation data includes: Performing standardization processing on the ambient light data to obtain standardized data; Inputting the standardized data into a pre-trained support vector machine model to calculate a decision function, and using the output result of the decision function as decision data; Mapping the decision data to a pre-stored evaluation interval to obtain user evaluation data; The decision function is as follows: Among them, f(e new ) represents the decision function, SV represents the number of samples of the pre-stored historical ambient light data, represents the optimal solution of the trained Lagrange multiplier, b * Indicates the bias term after training, y i Indicates the weight coefficient of training completion, K(e i ,e new ) represents the preset kernel function, e i represents the i-th data of historical ambient light data, e new Represents ambient light data.

5. The color adjustment method of a display screen based on environmental information according to claim 1, characterized in that: The training process of the color correction model includes: Inputting the pre-stored historical chromaticity feedback data and the pre-stored historical user evaluation data into the input layer of the initial color correction model for training, and obtaining the predicted value data output by the output layer of the initial color correction model; Substituting the predicted value data and the pre-stored actual target value into the loss function to calculate the loss value to obtain the loss value data; Calculating the gradient of the output layer output of the initial color correction model according to the loss value data, and passing the gradient forward layer by layer through the chain rule, calculating the gradient of the parameters of each layer, and obtaining gradient data; Update the parameters of each layer of the initial color correction model according to the gradient data and the preset learning rate; The parameters of each layer are updated repeatedly and iteratively until the training times of the initial color correction model are greater than the preset times, or when the loss value data of the initial color correction model is less than the preset loss threshold, the training is determined to be completed and the color correction model is obtained.

6. The color adjustment method of a display screen based on environmental information according to claim 1, characterized in that: The display content data is classified by using the Kingfisher optimization algorithm, and a type weight index is calculated according to the classification result and the user evaluation data to obtain a weight index, including: The display content data is classified by using the Kingfisher optimization algorithm to obtain the display content type. The displayed content type and the user evaluation data are input into a pre-trained content type weight adjustment model to obtain a weight index.

7. The color adjustment method of a display screen based on environmental information according to claim 6, characterized in that: The step of generating a color adjustment instruction according to the color perception data, the color adjustment data and the weight index, and adaptively adjusting the display content according to the color adjustment instruction includes: Calculating the color difference between the color adjustment data to obtain color difference data; Calculate a weight coefficient of the display content type according to the color difference data; generating a color adjustment instruction according to the weight coefficient and the weight index; According to the color adjustment instruction and the color adjustment data, gamma value adjustment, white balance adjustment, RGB gain adjustment, and color adjustment are performed on the display screen; Among them, the color difference data is calculated by the following formula: The weight coefficient is calculated by the following formula: The color adjustment instructions are generated by the following formula: Where, ΔL * ij , Δα * ij , Δb * ij Represents the difference between the i-th color perception data and the j-th color perception data, ΔE ij represents the color difference between the i-th color perception data and the j-th color perception data, w ij Represents the weight coefficient, W i represents the weight index, k represents the preset slope, θ represents the preset threshold parameter, A i Indicates color adjustment instructions.

8. A color adjustment system for a display screen based on environmental information, characterized in that: include: A data acquisition module, used to acquire display content data, display environment data and display type of the display screen, wherein the display environment data includes ambient color data and ambient light data; A color perception calculation module, used for calculating color perception data according to the environmental color data and the display screen type; A chromaticity feedback analysis module, used for performing quantization processing, smoothing adjustment, cluster analysis and polynomial regression analysis on the color perception data to obtain chromaticity feedback data; A user evaluation analysis module, used to establish a relationship between the ambient light data and user preferences through a support vector machine method to obtain user evaluation data; A color correction module, used for inputting the chromaticity feedback data and the user evaluation data into a pre-trained color correction model to obtain color adjustment data; A weight index calculation module, used to classify the display content data by using a Ban Kingfisher optimization algorithm, and calculate a type weight index according to the classification result and the user evaluation data to obtain a weight index; The color adjustment module is used to generate a color adjustment instruction according to the color adjustment data and the weight index, and to adaptively adjust the display content according to the color adjustment instruction.

9. An electronic device, characterized in that: The invention comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the color adjustment method of a display screen based on environmental information as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the color adjustment method of a display screen based on environmental information as described in any one of claims 1 to 7.

Images