Display color calibration method and system

Abstract

The present invention discloses a method and system for color calibration of a display. The method includes: using a multispectral sensor to collect spectral data of ambient light in real time according to the environment in which the display is located; using a visual response model to extract the user's visual features according to the user's visual preferences; using a dynamic optimization algorithm to adjust the color parameters of the display according to a dynamic data set of the ambient light field and a data set of the user's visual preferences to generate optimized color parameters; using a color management engine to perform real-time color calibration of the display based on the optimized color parameters, wherein the color management engine ensures low latency and high precision of color calibration through streaming computing technology and a distributed architecture to generate the final display effect. Using embodiments of the present invention, it is possible to adapt to changes in ambient light in real time while taking into account the user's visual preferences, thereby achieving efficient and accurate color calibration.

Description

Technical Field

[0001] The present invention belongs to the technical field of displays, and in particular to a display color adjustment method and system. Background Art

[0002] With the increasing popularity of electronic devices and the continuous development of display technology, displays are playing an increasingly important role in our daily lives and work. Displays are widely used not only in consumer electronics such as personal computers, televisions, and mobile phones, but also in professional fields such as graphic design, medical imaging, and film and television post-production. These scenarios place high demands on color performance, as accurate color reproduction directly affects the user's visual experience and work performance.

[0003] However, traditional display color calibration methods generally rely on static color standards and manual adjustments, often failing to adapt to rapidly changing ambient light conditions and user needs. Ambient light variations, such as the type, intensity, and color temperature of indoor light sources, can significantly affect the color displayed on a display. For example, under strong sunlight, a display's color rendering may be distorted, while in low-light conditions, the display may appear too dim. This situation forces users to regularly manually adjust the display's color settings, which is cumbersome and may not always result in optimal visual results. Summary of the Invention

[0004] The purpose of the present invention is to provide a display color adjustment method and system to address the deficiencies in the prior art, which can adapt to changes in ambient light in real time while taking into account the user's visual preferences to achieve efficient and accurate color adjustment.

[0005] An embodiment of the present application provides a display color calibration method, the method comprising:

[0006] Based on the environment in which the display is located, a multispectral sensor is used to collect spectral data of ambient light in real time. The multispectral sensor uses spectral analysis technology and an adaptive sampling mechanism to capture the wavelength distribution and intensity changes of the ambient light to generate ambient spectral data. Based on the ambient spectral data, a dynamic light field modeling algorithm is used to construct a real-time light field model of the ambient light. The light field model uses spatiotemporal interpolation technology and a light intensity distribution prediction mechanism to predict the dynamic change trend of the ambient light and generate a dynamic data set of the ambient light field.

[0007] Extracting the user's visual features based on the user's visual preferences using a visual response model, wherein the visual response model uses eye tracking technology and a deep learning algorithm to analyze the user's sensitivity and preference for different color parameters to generate a user visual feature vector. Based on the user's visual feature vector, a user visual preference model is constructed using a preference learning algorithm. The preference learning algorithm dynamically updates the user's preferences through incremental learning to generate a user visual preference dataset.

[0008] Adjusting the color parameters of the display using a dynamic optimization algorithm based on a dynamic dataset of ambient light fields and a dataset of user visual preferences, wherein the dynamic optimization algorithm adjusts color saturation, contrast, and color temperature in real time through a multi-objective optimization and adaptive feedback mechanism to generate optimized color parameters;

[0009] Based on the optimized color parameters, the color presentation of the display is adjusted in real time using a color management engine. The color management engine uses streaming computing technology and a distributed architecture to ensure low latency and high precision in color adjustment, thereby generating the final display effect.

[0010] Optionally, based on the environment in which the display is located, a multispectral sensor is used to collect spectral data of ambient light in real time, wherein the multispectral sensor captures the wavelength distribution and intensity changes of the ambient light through spectral analysis technology and an adaptive sampling mechanism to generate ambient spectral data. Based on the ambient spectral data, a real-time light field model of the ambient light is constructed using a dynamic light field modeling algorithm. The light field model predicts the dynamic change trend of the ambient light through spatiotemporal interpolation technology and a light intensity distribution prediction mechanism to generate a dynamic data set of the ambient light field, including:

[0011] A multispectral sensor collects spectral data of ambient light in real time, based on the display's environment. The sensor uses spectral analysis technology to capture the wavelength distribution and intensity changes of ambient light. Based on the dynamic changes in ambient light, the sensor uses an adaptive sampling mechanism to adjust the sampling frequency and resolution, ensuring that high-precision spectral data can be captured even when light levels change rapidly, generating a real-time ambient spectral dataset.

[0012] Preprocessing the real-time environmental spectral data set, wherein the preprocessing removes high-frequency noise and outliers in the spectral data using wavelet transform technology and noise filtering algorithm, and smoothing the spectral data using digital signal processing technology to generate a denoised environmental spectral data set;

[0013] Based on the denoised ambient spectral dataset, a real-time light field model of ambient light is constructed using a dynamic light field modeling algorithm. The light field modeling algorithm uses spatiotemporal interpolation technology to interpolate the ambient spectral data in both spatial and temporal dimensions to generate continuous light field distribution data. Furthermore, the light intensity distribution prediction mechanism is used to combine historical spectral data and ambient light change trends to predict the dynamic changes of the light field in the future and generate a dynamic dataset of the ambient light field.

[0014] Optionally, the method extracts the user's visual features based on the user's visual preferences using a visual response model, wherein the visual response model analyzes the user's sensitivity and preference for different color parameters through eye tracking technology and a deep learning algorithm to generate a user visual feature vector. Based on the user visual feature vector, a user visual preference model is constructed using a preference learning algorithm. The preference learning algorithm dynamically updates the user preferences through incremental learning to generate a user visual preference dataset, including:

[0015] Based on the user's visual preferences, real-time eye movement data is collected while the user is viewing the display. Using high-precision infrared imaging technology and pupil localization algorithms, the user's gaze distribution, gaze duration, and scan path are captured to generate a raw eye movement dataset.

[0016] Preprocessing the original eye movement dataset, removing noise and invalid data points from the eye movement data using filtering algorithms and outlier detection techniques, and extracting key visual features from the preprocessed eye movement dataset using a feature extraction algorithm to generate a user visual feature dataset. The key visual features include gaze point density, saccade speed, and area of ​​interest distribution.

[0017] Based on a user visual feature dataset, a visual response model is used to analyze users' sensitivity and preferences for different color parameters. The visual response model uses a deep learning algorithm to construct a multi-layer neural network to model the relationship between users' gaze behavior and color parameters. The multi-layer neural network is then trained to generate a user visual feature vector that quantifies the user's preference for color saturation, contrast, and color temperature.

[0018] Based on the user's visual feature vector, a user visual preference model is constructed using a preference learning algorithm. The preference learning algorithm dynamically updates the user preference model through incremental learning technology to ensure that it can adapt to changes in user preferences and generate a user visual preference dataset.

[0019] Optionally, the color parameters of the display are adjusted using a dynamic optimization algorithm based on the ambient light field dynamic dataset and the user visual preference dataset, wherein the dynamic optimization algorithm adjusts color saturation, contrast, and color temperature in real time through a multi-objective optimization and adaptive feedback mechanism to generate optimized color parameters, including:

[0020] Determining an optimization target for color parameters based on an ambient light field dynamic dataset and a user visual preference dataset, wherein the color parameters include color saturation, contrast, and color temperature;

[0021] A color parameter optimization model is constructed using a multi-objective optimization algorithm, wherein the optimization model generates a multi-objective optimization problem based on the optimization goal through the Pareto optimality theory, and uses constraints to limit the boundaries of the multi-objective optimization problem to generate an initial optimization solution space;

[0022] A dynamic optimization algorithm is used to solve the multi-objective optimization problem. The dynamic optimization algorithm searches for the optimal color parameter combination in the initial optimization solution space through genetic algorithms and / or particle swarm optimization techniques, and combines an adaptive feedback mechanism to adjust the search strategy of the dynamic optimization algorithm in real time to ensure that it can still converge quickly when the ambient light field and user preferences change dynamically, and generate an optimized color parameter set.

[0023] Optionally, the color presentation of the display is adjusted in real time using a color management engine based on the optimized color parameters, wherein the color management engine uses streaming computing technology and a distributed architecture to ensure low latency and high precision of color adjustment and generate the final display effect, including:

[0024] Loading the optimized color parameters into a color management engine, so that the color management engine receives and analyzes the color parameters in real time, and converts the optimized color parameters into color instructions executable by the display using a color mapping algorithm. The color mapping algorithm uses color space conversion technology to ensure that the color parameters match the hardware characteristics of the display and generate a color calibration instruction set.

[0025] Using streaming computing technology to adjust the display's color output in real time based on a color calibration instruction set, the streaming computing technology distributes color calibration instructions to multiple computing nodes through a distributed architecture, processing color parameter adjustments in parallel to ensure low-latency and high-precision color calibration, and generating real-time calibration results.

[0026] Based on the real-time adjustment results, the color output of the display is rendered using a color rendering engine, wherein the color rendering engine uses hardware acceleration technology to ensure the real-time and smoothness of color rendering to generate the final display effect.

[0027] Another embodiment of the present application provides a display color calibration system, the system comprising:

[0028] An acquisition module is configured to utilize a multispectral sensor to collect spectral data of ambient light in real time based on the environment in which the display is located. The multispectral sensor uses spectral analysis technology and an adaptive sampling mechanism to capture the wavelength distribution and intensity changes of the ambient light to generate ambient spectral data. Based on the ambient spectral data, a dynamic light field modeling algorithm is used to construct a real-time light field model of the ambient light. The light field model uses spatiotemporal interpolation technology and a light intensity distribution prediction mechanism to predict the dynamic change trend of the ambient light and generate a dynamic data set of the ambient light field.

[0029] An extraction module is configured to extract the user's visual features based on the user's visual preferences using a visual response model, wherein the visual response model analyzes the user's sensitivity and preference for different color parameters through eye tracking technology and a deep learning algorithm to generate a user visual feature vector. Based on the user visual feature vector, a user visual preference model is constructed using a preference learning algorithm. The preference learning algorithm dynamically updates the user's preferences through incremental learning to generate a user visual preference dataset.

[0030] an adjustment module for adjusting the color parameters of the display using a dynamic optimization algorithm based on the ambient light field dynamic dataset and the user visual preference dataset, wherein the dynamic optimization algorithm adjusts color saturation, contrast, and color temperature in real time through a multi-objective optimization and adaptive feedback mechanism to generate optimized color parameters;

[0031] The adjustment module is used to use the color management engine to adjust the color presentation of the display in real time according to the optimized color parameters. The color management engine uses streaming computing technology and distributed architecture to ensure low latency and high precision of color adjustment to generate the final display effect.

[0032] Yet another embodiment of the present application provides a storage medium, wherein the storage medium stores a computer program, wherein the computer program is configured to execute any of the above methods when run.

[0033] Yet another embodiment of the present application provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute any of the above methods.

[0034] Compared with the existing technology, the present invention provides a display color adjustment method, which uses a multispectral sensor to collect spectral data of ambient light in real time according to the environment in which the display is located; uses a visual response model to extract the user's visual features according to the user's visual preferences; uses a dynamic optimization algorithm to adjust the color parameters of the display according to the ambient light field dynamic data set and the user's visual preference data set to generate optimized color parameters; uses a color management engine to perform real-time adjustment of the color presentation of the display based on the optimized color parameters, wherein the color management engine uses streaming computing technology and distributed architecture to ensure low latency and high precision of color adjustment, and generates the final display effect, so that it can adapt to changes in ambient light in real time, while taking into account the user's visual preferences, to achieve efficient and accurate color adjustment. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 A hardware structure block diagram of a computer terminal for a display color calibration method provided by an embodiment of the present invention;

[0036] Figure 2 A schematic diagram of a flow chart of a display color calibration method provided by an embodiment of the present invention;

[0037] Figure 3 A schematic structural diagram of a display color calibration system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0038] The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and are not to be construed as limiting the present invention.

[0039] The embodiment of the present invention first provides a display color calibration method, which can be applied to electronic devices such as computer terminals, specifically ordinary computers.

[0040] The following describes it in detail by taking running on a computer terminal as an example. Figure 1 The hardware structure block diagram of a computer terminal for a display color calibration method provided by an embodiment of the present invention. Figure 1 As shown, the computer device includes a processor, a memory, and a network interface connected via a system bus, wherein the memory may include a non-volatile storage medium and an internal memory.

[0041] The non-volatile storage medium can store an operating system and a computer program. The computer program includes program instructions, which, when executed, can enable the processor to perform any display color calibration method.

[0042] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.

[0043] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can execute any display color calibration method.

[0044] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that Figure 1 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0045] It should be understood that 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), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0046] See also Figure 2 , an embodiment of the present invention provides a display color calibration method, which may include the following steps:

[0047] S201, using a multispectral sensor to collect spectral data of ambient light in real time according to the environment in which the display is located, wherein the multispectral sensor uses spectral analysis technology and an adaptive sampling mechanism to capture the wavelength distribution and intensity changes of the ambient light to generate ambient spectral data; based on the ambient spectral data, a real-time light field model of the ambient light is constructed using a dynamic light field modeling algorithm; the light field model uses spatiotemporal interpolation technology and a light intensity distribution prediction mechanism to predict the dynamic change trend of the ambient light to generate a dynamic data set of the ambient light field;

[0048] The key to this step is to accurately capture the lighting conditions surrounding the display, ensuring that the display can adjust its color output in real time based on environmental changes. The use of multispectral sensors enables the system to capture light intensity information at different wavelengths, generating more comprehensive and accurate environmental spectral data. This spectral data not only covers variations in light intensity but also reflects the color temperature and spectral composition of the light source, providing the necessary foundational data support for subsequent light field modeling.

[0049] The significance of this process is to achieve intelligent adjustment of the display's color to enhance the user's visual experience. By collecting detailed environmental spectral data in real time, the system can accurately identify the impact of light changes on the display. When lighting conditions change, for example, switching from indoor lighting to sunlight, the display can instantly adjust its output color parameters to offset the interference of ambient light and ensure accurate color presentation. In addition, building a light field model based on environmental spectral data can predict the changing trends of lighting conditions, making the display adjustment process more predictable, thereby maintaining optimal visual effects in dynamic environments.

[0050] Specifically, a multispectral sensor can be used to collect spectral data of ambient light in real time based on the environment in which the display is located. The sensor uses spectral analysis technology to capture the wavelength distribution and intensity changes of ambient light. Based on the dynamic changes of ambient light, the sampling frequency and resolution are adjusted through an adaptive sampling mechanism to ensure that high-precision spectral data can still be captured when the light changes rapidly, generating a real-time environmental spectral data set.

[0051] The primary purpose of this step is to ensure accurate, real-time spectral data collection under a variety of ambient lighting conditions. The advanced technology of multispectral sensors enables the device to flexibly adapt to various lighting conditions in rapidly changing environments. This adaptive mechanism safeguards data collection, preventing data loss or inaccuracies caused by varying lighting conditions.

[0052] This process ensures that subsequent display calibration is based on the latest and most accurate ambient light data. By acquiring real-time, highly accurate spectral data, the display can dynamically adapt to changing lighting conditions, providing users with a consistent, high-quality color experience. This mechanism also ensures that the display maintains color accuracy and visual comfort under varying lighting conditions, significantly improving user satisfaction and overall experience.

[0053] In the specific implementation, we first select a highly sensitive multispectral sensor with multi-channel spectral acquisition capability, which can accurately obtain ambient light information within the wavelength range of 410nm to 700nm.

[0054] The sensor will be mounted directly in front of or to the side of the display to maximize real-time data on ambient light. The sensor will operate continuously, automatically adjusting its sampling rate as light levels change. For example, under drastic lighting conditions, the sensor may collect data 20 times per second, while under relatively stable lighting conditions, the sampling rate will be reduced to 2 times per second. This allows the sensor to flexibly respond to light fluctuations in diverse environmental conditions.

[0055] During data acquisition, the sensor stores real-time spectral data in an internal cache and periodically uploads it to the central processing unit. The system then formats the acquired spectral data for subsequent analysis and processing. Ultimately, this spectral data is converted into a structured, real-time ambient spectral dataset containing information such as timestamps, wavelength distribution, and light intensity, ensuring accurate and comprehensive ambient light data for subsequent steps.

[0056] Preprocessing the real-time environmental spectral data set, wherein the preprocessing removes high-frequency noise and outliers in the spectral data using wavelet transform technology and noise filtering algorithm, and smoothing the spectral data using digital signal processing technology to generate a denoised environmental spectral data set;

[0057] This step is crucial to ensuring that the collected ambient light data accurately reflects real-world lighting conditions. By applying techniques like wavelet transforms, the system effectively removes high-frequency noise caused by external interference, thereby improving data quality. This processing results in a cleaner and smoother dataset, facilitating subsequent analysis and model building.

[0058] This preprocessing step is crucial for improving the accuracy of subsequent analysis and dynamic light field modeling algorithms. Denoised data reduces the impact of erroneous data on algorithm calculations, enabling the light field model to more accurately reflect actual changes in ambient light. Furthermore, this cleaning process significantly enhances the algorithm's adaptability and stability under dynamic lighting conditions, providing reliable data support for overall color calibration.

[0059] Specifically, the system first imports the real-time environmental spectral dataset into the preprocessing module, which is equipped with a wavelet transform algorithm and a noise filtering algorithm that can effectively identify and remove noise in the spectral data.

[0060] During the initial processing phase, the system uses wavelet transforms to perform a multi-level decomposition of the raw spectral data, extracting individual frequency components and identifying high-frequency noise in the signal. Using an appropriate wavelet basis function (e.g., Daubechies wavelet) is crucial in this step, as it adapts to the characteristics of the spectral data. After completing the wavelet transform, the system sets a threshold to remove high-frequency noise, ensuring that the actual spectral signal is preserved.

[0061] The denoised spectral data then undergoes further smoothing to eliminate minor fluctuations and outliers. The system applies digital signal processing techniques, such as moving averages or Savitzky-Golay filters, to smooth the spectral data. This process results in a more reliable and accurate denoised environmental spectral dataset, providing a solid foundation for the subsequent construction of a dynamic light field model.

[0062] Based on the denoised ambient spectral dataset, a real-time light field model of ambient light is constructed using a dynamic light field modeling algorithm. The light field modeling algorithm uses spatiotemporal interpolation technology to interpolate the ambient spectral data in both spatial and temporal dimensions to generate continuous light field distribution data. Furthermore, the light intensity distribution prediction mechanism is used to combine historical spectral data and ambient light change trends to predict the dynamic changes of the light field in the future and generate a dynamic dataset of the ambient light field.

[0063] This step emphasizes converting ambient spectral data into a real-time light field model through mapping and modeling techniques, thereby providing the necessary foundation for dynamic adjustment of the display.

[0064] This step enables dynamic prediction of ambient light changes, providing forward-looking data support for display color calibration. An effective light field model not only reflects current lighting conditions in real time but also predicts upcoming changes, enabling the preparation of appropriate color adjustment strategies. This predictive capability significantly enhances the display's adaptive adjustment capabilities in complex environments and improves the user experience.

[0065] In the specific implementation, the denoised environmental spectral data first needs to be imported into the dynamic light field modeling module. This module will use the spatiotemporal interpolation algorithm to generate the spatial and temporal continuity of the light field based on the relationship between the spectral data.

[0066] The spatiotemporal interpolation process considers the spectral data at each time point and the data from adjacent time points. Through methods such as bilinear interpolation or kriging interpolation, a light field data grid is formed that describes the distribution characteristics of the light field. This not only improves the accuracy of the model but also ensures that the generated light field model can smoothly transition and avoid sudden changes caused by missing data. During this process, the system also regularly updates historical spectral data to incorporate the influence of the latest lighting environment, making the model more adaptable to dynamic changes.

[0067] Then, combined with a light intensity distribution prediction mechanism, the system analyzes trends in historical spectral data, such as periodic variations in sunlight intensity, to predict potential dynamic changes in the light field over the next few minutes or hours. By incorporating machine learning algorithms such as time series analysis or regression analysis, the system identifies patterns and generates a dynamic dataset of the ambient light field. This series of data processing and analysis not only enhances the model's predictive capabilities but also provides a precise basis for color adjustments on the display, helping to maintain optimal display quality.

[0068] S202: extracting visual features of the user based on the user's visual preferences using a visual response model, wherein the visual response model analyzes the user's sensitivity and preference for different color parameters using eye tracking technology and a deep learning algorithm to generate a user visual feature vector. Based on the user visual feature vector, a user visual preference model is constructed using a preference learning algorithm. The preference learning algorithm dynamically updates the user's preferences through incremental learning to generate a user visual preference dataset.

[0069] The core of this step is to capture the user's true reactions through high-tech means to achieve personalized color optimization. Eye tracking technology can provide detailed data on the user's gaze point, focus area, and visual fatigue level, while deep learning algorithms can extract the user's implicit preferences from complex data and form a sensitivity analysis of color parameters such as saturation, contrast, and color temperature.

[0070] This process aims to eliminate one-size-fits-all color adjustments and ensure every user has the best visual experience. By analyzing the user's visual preferences in real time, the display automatically adjusts its color output to suit the unique color needs of each user. This method also dynamically updates the user's visual preferences through incremental learning, achieving continuous optimization to address visual fatigue or changes in color aesthetics that may occur after prolonged use of the display. This personalized adjustment not only improves user comfort, but also enhances work efficiency and entertainment experience.

[0071] Specifically, the user's eye movement data when viewing the display can be collected in real time based on the user's visual preferences. High-precision infrared imaging technology and pupil positioning algorithms are used to capture the user's gaze point distribution, gaze duration, and scanning path to generate an original eye movement dataset.

[0072] At this stage, the system uses advanced infrared cameras to accurately capture the user's eye movements. By leveraging pupil location algorithms, the system can capture the user's gaze point, gaze duration, and eye movement path, generating a detailed raw eye movement dataset. This data provides deep insights into the distribution of user attention and aids in subsequent analysis of color preferences.

[0073] This process aims to obtain real-world visual feedback from users, providing a basis for color calibration. Eye-tracking data not only reflects where users focus when viewing an interface, but also reveals their sensitivity and preferences for specific colors or image content. By analyzing this data, the system can more accurately understand user needs and optimize the display's color settings to better align with their visual habits and aesthetic standards, significantly improving the user experience.

[0074] To achieve this, a high-precision infrared camera is typically installed above or to the side of the display to ensure comprehensive eye movement capture. This camera illuminates the user's eyes with an infrared light source, allowing even subtle changes in eye movement to be accurately recorded by the sensor.

[0075] During data collection, the system monitors the user's eye movements in real time and analyzes the captured video stream using an advanced pupil localization algorithm. This algorithm accurately detects the user's eye movements, the specific location of gaze, and the angle of eye rotation. The system also identifies the different areas of gaze and records the duration of gaze in each area, generating a comprehensive eye movement dataset. This dataset provides an important foundation for subsequent analysis, containing rich information on gaze distribution.

[0076] Finally, the collected data is formatted and stored in a database for subsequent analysis and feature extraction. The system regularly archives this data to ensure that user trends can be tracked, particularly visual responses to varying lighting conditions or content types. Through these steps, the system fully ensures the accuracy and comprehensiveness of user eye movement data, laying a solid foundation for subsequent visual feature analysis and preference modeling.

[0077] Preprocessing the original eye movement dataset, removing noise and invalid data points from the eye movement data using filtering algorithms and outlier detection techniques, and extracting key visual features from the preprocessed eye movement dataset using a feature extraction algorithm to generate a user visual feature dataset. The key visual features include gaze point density, saccade speed, and area of ​​interest distribution.

[0078] At this stage, the system passes the raw eye movement data to the preprocessing module, which applies filtering algorithms (such as high-pass filters) to remove noise caused by device jitter or external interference. At the same time, it uses outlier detection technology to eliminate data points that significantly deviate from normal values ​​to ensure the accuracy of the final data.

[0079] This process aims to improve the validity and reliability of eye movement data. By removing noise and invalid data, the resulting dataset is clearer and more accurately reflects the user's visual behavior. Key visual features, such as fixation density and saccade speed, provide an accurate basis for subsequent visual preference analysis, effectively supporting color calibration.

[0080] At this stage, the system first needs to perform noise reduction on the raw eye movement data. Typically, high-pass or low-pass filters are used to remove noise caused by device jitter or unexpected interference. After filtering, the system will obtain a relatively clean eye movement dataset.

[0081] Next, the system applies outlier detection technology to identify and remove eye movement data points that significantly deviate from the normal range. For example, when a user's eye movement velocity exceeds a certain threshold (such as 300 degrees per second), this may indicate rapid head movements or adjustments in visual focus, rather than normal eye movement behavior. By setting appropriate thresholds, the system can effectively exclude these abnormal data points, ensuring the accuracy of subsequent analysis.

[0082] Finally, the pre-processed eye movement data is fed into a feature extraction algorithm, which extracts key visual features such as gaze density (the number of times the user fixates on different areas), saccade speed (the speed at which the user switches between areas), and the distribution of regions of interest (the areas the user most frequently gazes at). This information is organized into a user visual feature dataset to facilitate subsequent deep learning model training and analysis of user preferences.

[0083] Based on a user visual feature dataset, a visual response model is used to analyze users' sensitivity and preferences for different color parameters. The visual response model uses a deep learning algorithm to construct a multi-layer neural network to model the relationship between users' gaze behavior and color parameters. The multi-layer neural network is then trained to generate a user visual feature vector that quantifies the user's preference for color saturation, contrast, and color temperature.

[0084] During this process, the system inputs the processed visual feature data into a designed visual response model, using deep learning techniques to train a multi-layer neural network based on user gaze behavior. This network learns the user's underlying preferences from a large amount of sample data, thereby establishing a complex relationship between color parameters and user responses. This process quantifies the user's visual preferences, enabling more precise and personalized display adjustments. By analyzing the user's responses to different color parameters, the system not only identifies the user's specific preferences but also provides clear guidance for color adjustment, helping to achieve the best visual effects and user experience.

[0085] During this process, the system first inputs a previously extracted dataset of user visual features into a designed deep learning model. This model utilizes a multi-layer neural network architecture, capable of processing large amounts of complex data and continuously training to improve its alignment with user preferences.

[0086] Using a backpropagation algorithm, the system optimizes based on user gaze behavior (such as gaze duration and scanning speed) and corresponding color parameters (such as saturation, contrast, and color temperature). The model adjusts weights during each training cycle to find the optimal parameter combination that maximizes the user's color preference. To ensure the effectiveness of the model, the system also requires regular validation to improve prediction accuracy.

[0087] Ultimately, after sufficient training, the model generates a user visual feature vector that quantifies the user's preferences for different color parameters. For example, the vector might show an 80% preference for highly saturated colors, while a 30% preference for low-contrast colors. These quantitative results enable the system to more accurately understand and predict the user's visual needs.

[0088] Based on the user's visual feature vector, a user visual preference model is constructed using a preference learning algorithm. The preference learning algorithm dynamically updates the user preference model through incremental learning technology to ensure that it can adapt to changes in user preferences and generate a user visual preference dataset.

[0089] In this step, the system uses the previously generated user visual feature vector as a foundation and applies a preference learning algorithm to build a more comprehensive user visual preference model. Incremental learning technology enables the model to continuously absorb new visual feature data and gradually refine its understanding of user preferences, ensuring the model's long-term effectiveness and adaptability. This process provides the display with the ability to continuously optimize. As user visual preferences may change over time and with changing usage habits, the dynamically updated user visual preference model ensures that the display can always adjust color based on current user needs. This flexibility not only enhances the user experience but also reduces visual fatigue during extended use, effectively protecting the user's vision.

[0090] In this step, the system feeds the previously generated user visual feature vector into a preference learning algorithm, which uses incremental learning to continuously adapt the model to changes in user preferences. Incremental learning allows the model to optimize and adjust as it receives new data without requiring a complete retraining, saving time and computing resources.

[0091] In practice, the system monitors eye movement data from users as they use the display at different times. Over time, new data is continuously added to the existing dataset. Applying an online learning strategy, the model analyzes this new eye movement data and, combined with past preference data, automatically updates the visual preference model. For example, if the system detects a user's increased preference for darker tones over time, the model automatically adjusts its parameters to reflect this change, ensuring that color calibration always meets the user's new needs.

[0092] The system will also regularly conduct model evaluation and performance monitoring to ensure its accuracy and effectiveness. During this evaluation process, the system can present optimized color settings to different users through A / B testing and collect their feedback. This real-time feedback mechanism will further enhance the model's adaptability, enabling it to quickly adjust based on user feedback, thereby generating a more comprehensive and accurate dataset on user visual preferences.

[0093] S203, adjusting color parameters of the display using a dynamic optimization algorithm based on the ambient light field dynamic dataset and the user visual preference dataset, wherein the dynamic optimization algorithm adjusts color saturation, contrast, and color temperature in real time through a multi-objective optimization and adaptive feedback mechanism to generate optimized color parameters;

[0094] The core of the dynamic optimization algorithm lies in multi-objective optimization and adaptive feedback mechanisms. By analyzing real-time data, the system intelligently assesses the current ambient light conditions and the user's visual preferences, optimizing key parameters such as color saturation, contrast, and color temperature. For example, if the ambient light changes significantly (such as from bright to dim), the system automatically increases color saturation and contrast to ensure that the image remains clear and the colors remain vivid in the new lighting environment. During this process, the dynamic optimization algorithm considers multiple objectives to maintain optimal visual effects under different conditions.

[0095] The significance of this optimization step lies in enabling a personalized visual experience. A user's visual perception is influenced by ambient light and personal preferences, and continuous dynamic optimization ensures that displayed content is always in its optimal visual state. By adjusting the display's color parameters, not only can viewing comfort be improved, but visual fatigue can also be reduced. For example, prolonged viewing of content with inappropriate color settings can cause eye fatigue or discomfort. Refined dynamic adjustment ensures consistent and comfortable visuals regardless of ambient lighting conditions.

[0096] Specifically, the optimization target of the color parameters can be determined according to the ambient light field dynamic data set and the user visual preference data set, wherein the color parameters include color saturation, contrast and color temperature;

[0097] In this step, the system first analyzes the real-time dynamic dataset of the ambient light field and the user's visual preference dataset. Through deep learning and data mining techniques, the system can identify the user's color preferences under different lighting conditions. For example, in bright environments, users may prefer low-saturation and high-contrast color settings, while in dim environments, users may prefer to increase color saturation to improve visual effects. The system then sets corresponding optimization targets based on this information.

[0098] The significance of this process lies in providing clear guidance for subsequent optimization efforts. Once specific optimization targets are identified, color calibration of the entire system becomes more targeted, ensuring that the final color rendering meets the user's actual needs. Through repeated testing under different lighting conditions, detailed user preference data can be obtained, effectively defining appropriate color parameter targets.

[0099] In this step, the system first needs to integrate the dynamic data from the ambient light field with the user's visual preference dataset. The ambient light field dynamic dataset is the ambient light information captured in real time by a multispectral sensor, such as spectral distribution, intensity changes, etc., while the user visual preference dataset is the user's color preferences under different lighting conditions obtained through means such as eye tracking. By analyzing this data, the system can define the user's optimal color performance under specific ambient light conditions. For example, in bright natural light, the user may prefer lower color saturation and higher contrast to enhance the clarity and visual impact of the picture; in dim environments, the user may tend to choose higher color saturation to prevent the image from appearing too dark.

[0100] During implementation, the system leverages machine learning algorithms and historical data for training and analysis. By analyzing user behavior in different environments (such as gaze duration and scanning paths), the system can gradually build a model of user preferences. During this process, the system also continuously adjusts parameters based on real-time feedback to ensure that optimization goals are highly consistent with user needs. For example, if a user is detected frequently adjusting brightness under specific lighting conditions, the system will infer the user's sensitivity to brightness in that environment and make corresponding optimization settings.

[0101] Ultimately, the core purpose of this step is to provide a clear target for subsequent color optimization. Once the system determines the optimization target for color parameters, the next step involves fine-tuning the color parameters based on this target. This is crucial for improving the user's visual experience in various lighting conditions. Setting optimization targets not only improves the readability of displayed content but also enhances user viewing comfort, ultimately improving overall user satisfaction.

[0102] A color parameter optimization model is constructed using a multi-objective optimization algorithm, wherein the optimization model generates a multi-objective optimization problem based on the optimization goal through the Pareto optimality theory, and uses constraints to limit the boundaries of the multi-objective optimization problem to generate an initial optimization solution space;

[0103] In this step, the system utilizes a multi-objective optimization algorithm to construct a color parameter optimization model, employing Pareto optimality theory to address the trade-offs between multiple objectives. The application of Pareto optimality theory allows the system to move beyond the singular pursuit of optimality for a single color parameter and instead comprehensively consider color saturation, contrast, and color temperature. For example, in some cases, increasing color saturation may compromise contrast. The optimization algorithm ensures a balance between these various objectives while maintaining high satisfaction.

[0104] This step is crucial because it allows the system to find the best solution for complex user needs. By establishing a multi-objective optimization model, the system can effectively handle the changing needs of users in different scenarios, generating the optimal color parameter combination to ensure users receive the best visual experience when viewing content.

[0105] In this step, the system will establish a multi-objective optimization model to simultaneously meet the needs of different color parameters. In its specific implementation, the system will apply the Pareto optimality theory, which allows the system to find a balance when dealing with multiple objectives. For example, if the user wants higher color saturation to enhance the visual effect, but does not want too high contrast to cause visual fatigue, the system needs to find a balance between the two that can enhance the visual experience without causing burden. This is achieved through multi-objective optimization.

[0106] The first step in building this optimization model is to define the optimization goal and form a series of specific optimization parameters based on the user preferences and environmental data collected in the first step. The system will use historical data and user feedback to set the target ranges for color saturation, contrast, and color temperature. Next, the system will generate a multi-objective optimization problem and define the upper and lower limits of each color parameter by setting constraints. For example, color saturation may be limited to between 0-100, contrast between 50-200, and color temperature between 3000K-6500K to ensure that the generated parameter combination is optimal between physical feasibility and user preferences.

[0107] Once the solution space for this multi-objective optimization problem is generated, the system uses computer optimization algorithms, such as genetic algorithms or particle swarm optimization, to solve it. Taking the genetic algorithm as an example, the system first randomly generates an initial population, each representing a possible color parameter combination. Then, through operations such as gene crossover and mutation, the system evolves generation by generation, gradually approaching the optimal solution. Throughout this process, real-time user feedback is integrated into the optimization process to ensure that the final output color parameters meet the user's visual requirements. This process not only provides a scientific basis for optimization but also makes the entire adjustment process flexible and adaptable.

[0108] A dynamic optimization algorithm is used to solve the multi-objective optimization problem. The dynamic optimization algorithm searches for the optimal color parameter combination in the initial optimization solution space through genetic algorithms and / or particle swarm optimization techniques, and combines an adaptive feedback mechanism to adjust the search strategy of the dynamic optimization algorithm in real time to ensure that it can still converge quickly when the ambient light field and user preferences change dynamically, and generate an optimized color parameter set.

[0109] In this final step, the system applies dynamic optimization algorithms, specifically genetic algorithms and particle swarm optimization techniques, to solve the previously established multi-objective optimization model. Genetic algorithms simulate the process of natural selection, searching the initial solution space through operations such as crossover and mutation to find the optimal color parameter combination. Particle swarm optimization, on the other hand, simulates the foraging behavior of flocks of birds to efficiently search for the optimal solution. The system continuously monitors user responses and environmental changes, providing rapid feedback to the algorithm to refine its search strategy.

[0110] This step ensures efficient and real-time optimization, enabling the system to make timely adjustments to ensure optimal visual quality, especially when user preferences or ambient light levels change dramatically. This flexible dynamic optimization algorithm maintains accurate optimization direction in ever-changing environments, ensuring users always experience the most appropriate display quality.

[0111] In this step, the system applies dynamic optimization algorithms, primarily using genetic algorithms and particle swarm optimization techniques, to solve the aforementioned multi-objective optimization problem. To achieve optimal results, the system first evaluates each color parameter combination in the initial solution space, comparing its performance across all optimization objectives. For example, the system might detect that a combination has high saturation but low contrast, resulting in a poor overall visual effect. Therefore, through these evaluations, user satisfaction with different parameter combinations becomes a key optimization metric.

[0112] The use of a genetic algorithm enables the system to quickly identify high-quality color parameter combinations within the initial solution space by simulating the process of natural selection. Specifically, the system randomly generates a set of parameters, which are then evaluated based on a fitness function (i.e., user satisfaction). The best-performing parameters are then selected for crossover and mutation, generating new candidate parameters. This process is repeated until the preset convergence criteria are met. When the parameters no longer change significantly or the user's desired satisfaction level is reached, the algorithm stops calculating and outputs the final optimized parameters.

[0113] Furthermore, the integration of an adaptive feedback mechanism is a key innovation in this step. During operation, the system collects real-time user feedback and ambient light change data, incorporating this information into the optimization algorithm's operational strategy. For example, if the user still experiences discomfort under the adjusted parameters, the system can instantly adjust its search strategy to quickly find a more suitable parameter combination. This adaptive adjustment capability ensures that the system not only operates under ideal conditions but also responds promptly to user needs in real-world applications, ensuring that the resulting color parameter set is more closely aligned with the user's visual experience requirements. This flexibility and responsiveness are crucial for improving user satisfaction and optimizing overall visual quality.

[0114] S204, using a color management engine to perform real-time adjustments to the color presentation of the display based on the optimized color parameters, wherein the color management engine ensures low latency and high precision of color adjustment through streaming computing technology and distributed architecture to generate the final display effect.

[0115] When using the color management engine to adjust the display's color presentation in real time based on optimized color parameters, the system inputs the color parameters optimized in the previous steps (such as color saturation, contrast, and color temperature) into the color management engine. The engine is responsible for parsing these parameters and converting them into color instructions that the display can directly execute. The color mapping algorithm here uses color space conversion technology to ensure that the optimized color parameters match the hardware characteristics of the display to achieve more accurate color presentation. For example, if the optimized color parameters show that the saturation needs to be increased, the color management engine will perform the necessary calculations and conversions internally to generate instructions suitable for the display, ensuring that the colors of the final image are realistic and meet user expectations.

[0116] The significance of this step is to ensure that users can enjoy the best visual experience under various ambient light conditions through efficient color calibration. Real-time calibration can adapt to the user's immediate feedback on color, thereby effectively reducing visual discomfort caused by changes in light. Using streaming computing technology and distributed architecture, the system can quickly respond to user needs, help reduce delays and discomfort during the calibration process, and thus improve overall user satisfaction. Such calibration not only improves the display effect, but also enhances the interactive experience between the user and the display, allowing users to feel the convenience of technology and personalized services during operation.

[0117] Specifically, the optimized color parameters can be loaded into a color management engine, so that the color management engine receives and analyzes the color parameters in real time, and uses a color mapping algorithm to convert the optimized color parameters into color instructions executable by the display. The color mapping algorithm uses color space conversion technology to ensure that the color parameters match the hardware characteristics of the display and generate a color calibration instruction set.

[0118] In this step, the system first needs to accurately load the optimized color parameters (such as color saturation, contrast, and color temperature) into the color management engine. To achieve this goal, the system converts these parameters into a universal format that the color management engine can quickly understand and process. Specifically, the color management engine converts this input data into a color calibration instruction set, which clearly defines the specific values ​​and variation ranges corresponding to each color parameter. During this process, the color mapping algorithm utilizes color space conversion technology to ensure that the generated color instructions can well match the hardware characteristics of the display. For example, if the color display characteristics of the display deviate from the standard sRGB color space, the color management engine will make necessary adjustments to ensure the authenticity of the display effect.

[0119] The significance of this process lies in the fact that only when the color parameters are perfectly matched to the display's hardware characteristics can the final image or video be guaranteed to achieve the desired effect. By analyzing color parameters in real time, the system can promptly respond to user needs and feedback, ensuring the optimal visual experience every time content is displayed. This process eliminates color deviation and discomfort during viewing, improving overall user satisfaction.

[0120] In this step, the system first needs to load the optimized color parameters (such as saturation, contrast, and color temperature) into the color management engine. The key to this process is ensuring that the color parameters can be input into the engine in an efficient format for subsequent processing. To achieve this goal, the system will design a data interface to ensure that the optimized color parameters can be quickly and accurately transmitted to the color management engine. The system typically uses JSON or XML formats to transmit these parameters because these formats are well-structured and readable.

[0121] The loaded color parameters will be deeply analyzed through the color mapping algorithm. The algorithm will take into account the specific hardware characteristics of the display, such as color gamut, contrast, brightness and other factors. For example, if the optimized color parameter display requires a higher saturation, and the color gamut of the display itself is limited, the color management engine will adjust the saturation to a more suitable range according to the mapping algorithm to avoid picture distortion. At the same time, during the color mapping process, color space conversion technology can be used to achieve conversion between different color spaces (such as sRGB, Adobe RGB, etc.) to ensure that the final generated color instructions can accurately reflect the user's visual preferences.

[0122] Ultimately, after processing through the color mapping algorithm, the system generates a set of color calibration instructions that detail how to adjust the display's color output. For example, an instruction set might include "increase color saturation to 75%" or "adjust color temperature to 6500K," each of which is optimized and guaranteed to match the display hardware. This set of instructions serves as the foundation for subsequent real-time adjustments and rendering processes, ensuring a consistently optimal user experience.

[0123] Using streaming computing technology to adjust the display's color output in real time based on a color calibration instruction set, the streaming computing technology distributes color calibration instructions to multiple computing nodes through a distributed architecture, processing color parameter adjustments in parallel to ensure low-latency and high-precision color calibration, and generating real-time calibration results.

[0124] During this step, the system utilizes streaming computing technology to process the color calibration instruction set and adjust the display's color output in real time. Streaming computing technology allows the system to break down calibration tasks into smaller units, improving the efficiency of the entire calibration process through parallel processing. In a distributed computing architecture, the instruction set is distributed to multiple computing nodes, allowing each node to independently adjust specific color parameters. This architecture ensures that even under high load, the system maintains low latency and high accuracy when processing complex color adjustments.

[0125] The significance of this process is that, through streaming computing, the system can not only quickly respond to new input color instructions, but also maintain high-quality output during the processing. When the color parameters are adjusted, the user hardly notices any delay, so the display can provide a smooth and consistent visual experience. For example, when watching dynamic video content, real-time color adjustment can ensure that each frame can display the best color effect based on the current lighting conditions and user preferences, greatly enhancing the user's immersion.

[0126] During this step, the system uses streaming computing technology to make real-time adjustments to the display's color output based on the previously generated color calibration instruction set. Streaming computing technology allows the system to split computing tasks into multiple independent subtasks, each of which is processed in parallel by different computing nodes, improving overall processing power. For example, if ten different pixel areas on a display need to be adjusted, streaming computing technology can assign the calibration instructions for each area to separate computing nodes, allowing them to process them almost simultaneously, significantly reducing the time required for color adjustments.

[0127] Each compute node adjusts color parameters accordingly based on the instructions it receives. For example, one node might adjust the contrast of a specific area, while another adjusts the color temperature. This allows the system to quickly adapt to user input and present the color calibration results in real time. During implementation, the system ensures smooth information flow between nodes, enabling rapid sharing and updating of data when needed. For example, when a user adjusts their color preferences, all relevant nodes receive immediate feedback.

[0128] Finally, after stream computing, each node aggregates the processing results to generate an overall real-time calibration result. This result is then passed back to the color management engine for subsequent rendering. This process ensures that the display's color output remains optimal at all times, allowing users to experience virtually no lag when viewing content, and the smooth color rendering significantly enhances the viewing experience.

[0129] Based on the real-time adjustment results, the color output of the display is rendered using a color rendering engine, wherein the color rendering engine uses hardware acceleration technology to ensure the real-time and smoothness of color rendering to generate the final display effect.

[0130] In the final step, the system uses the color rendering engine to perform the final rendering of the display's color output based on the previous real-time calibration results. The color rendering engine is a component specifically designed to process and optimize color performance. Through hardware acceleration technology, it can quickly and efficiently process each pixel, ensuring the rendering process achieves the best results in terms of real-time and smoothness. For example, when the user adjusts the brightness or color preference of the content being viewed, the rendering engine can immediately optimize the output based on the real-time calibration results without waiting for long calculations and processing.

[0131] The significance of this step lies in the fact that, through efficient color rendering, the system ultimately generates a display that better meets the user's aesthetic needs and visual preferences. For example, when watching animated content with vibrant colors, the rendering engine can quickly adapt to changes in ambient light and adjust the color output in real time, ensuring that the viewing effect always appears vivid and eye-catching. This responsiveness can significantly enhance the user's immersion and comfort when watching visual content such as movies, TV shows, and games.

[0132] In this step, the system uses the color rendering engine to render the real-time calibration results, generating the final color display. The color rendering engine is a component specifically designed to process and optimize color. Its core is to leverage hardware acceleration technologies, such as GPU acceleration, to ensure high efficiency and low latency in color rendering. Through hardware acceleration, the rendering engine can process the color of each pixel in a short period of time, ensuring smooth real-time display.

[0133] Specifically, the system configures the rendering engine parameters based on the real-time calibration results. The rendering engine maps the adjusted color data to the pixels of the display. During this process, the system takes into account the resolution and refresh rate of the display to ensure that the rendering effect matches the hardware. For example, when processing high-resolution 4K video, the rendering engine can quickly process a large number of pixels, achieving color-accurate rendering while avoiding frame rate drops or screen freezes.

[0134] Ultimately, the rendered color output is the desired effect, with vibrant colors and distinct layers, faithfully reproducing the aesthetic of the content. This process not only enhances the visual experience but also increases the user's immersion and satisfaction when watching various content, such as movies and games. For example, when watching an action movie, the color rendering engine can quickly adapt to the rapidly changing scene, ensuring that every frame of the image accurately displays color, allowing viewers to better appreciate the plot's intensity and tension. Through this series of processing, the system provides users with a smooth and high-quality visual experience.

[0135] It can be seen that according to the environment in which the display is located, the spectral data of the ambient light is collected in real time using a multispectral sensor; according to the user's visual preferences, the visual characteristics of the user are extracted using a visual response model; according to the dynamic data set of the ambient light field and the user's visual preference data set, the color parameters of the display are adjusted using a dynamic optimization algorithm to generate optimized color parameters; according to the optimized color parameters, the color presentation of the display is adjusted in real time using a color management engine, wherein the color management engine uses streaming computing technology and a distributed architecture to ensure low latency and high precision of color adjustment, and generates the final display effect, so that it can adapt to changes in ambient light in real time, while taking into account the user's visual preferences, to achieve efficient and accurate color adjustment.

[0136] Another embodiment of the present invention provides a display color calibration system, see Figure 3 , the system may include:

[0137] An acquisition module 301 is configured to collect spectral data of ambient light in real time using a multispectral sensor based on the environment in which the display is located. The multispectral sensor uses spectral analysis technology and an adaptive sampling mechanism to capture the wavelength distribution and intensity changes of the ambient light to generate ambient spectral data. Based on the ambient spectral data, a dynamic light field modeling algorithm is used to construct a real-time light field model of the ambient light. The light field model uses spatiotemporal interpolation technology and a light intensity distribution prediction mechanism to predict the dynamic change trend of the ambient light and generate a dynamic data set of the ambient light field.

[0138] Extraction module 302 is configured to extract the user's visual features based on the user's visual preferences using a visual response model, wherein the visual response model uses eye tracking technology and a deep learning algorithm to analyze the user's sensitivity and preference for different color parameters to generate a user visual feature vector. Based on the user visual feature vector, a user visual preference model is constructed using a preference learning algorithm. The preference learning algorithm dynamically updates the user's preferences through incremental learning to generate a user visual preference dataset.

[0139] An adjustment module 303 is configured to adjust the color parameters of the display using a dynamic optimization algorithm based on the ambient light field dynamic dataset and the user visual preference dataset. The dynamic optimization algorithm adjusts color saturation, contrast, and color temperature in real time through a multi-objective optimization and adaptive feedback mechanism to generate optimized color parameters.

[0140] The adjustment module 304 is used to use the color management engine to adjust the color presentation of the display in real time according to the optimized color parameters. The color management engine uses streaming computing technology and distributed architecture to ensure low latency and high precision of color adjustment to generate the final display effect.

[0141] It can be seen that according to the environment in which the display is located, the spectral data of the ambient light is collected in real time using a multispectral sensor; according to the user's visual preferences, the visual characteristics of the user are extracted using a visual response model; according to the dynamic data set of the ambient light field and the user's visual preference data set, the color parameters of the display are adjusted using a dynamic optimization algorithm to generate optimized color parameters; according to the optimized color parameters, the color presentation of the display is adjusted in real time using a color management engine, wherein the color management engine uses streaming computing technology and a distributed architecture to ensure low latency and high precision of color adjustment, and generates the final display effect, so that it can adapt to changes in ambient light in real time, while taking into account the user's visual preferences, to achieve efficient and accurate color adjustment.

[0142] An embodiment of the present invention further provides a storage medium storing a computer program, wherein the computer program is configured to execute the steps of any one of the above method embodiments when running.

[0143] Specifically, in this embodiment, the above-mentioned storage medium may be configured to store a computer program for performing the following steps:

[0144] S201, using a multispectral sensor to collect spectral data of ambient light in real time according to the environment in which the display is located, wherein the multispectral sensor uses spectral analysis technology and an adaptive sampling mechanism to capture the wavelength distribution and intensity changes of the ambient light to generate ambient spectral data; based on the ambient spectral data, a real-time light field model of the ambient light is constructed using a dynamic light field modeling algorithm; the light field model uses spatiotemporal interpolation technology and a light intensity distribution prediction mechanism to predict the dynamic change trend of the ambient light to generate a dynamic data set of the ambient light field;

[0145] S202: extracting visual features of the user based on the user's visual preferences using a visual response model, wherein the visual response model analyzes the user's sensitivity and preference for different color parameters using eye tracking technology and a deep learning algorithm to generate a user visual feature vector. Based on the user visual feature vector, a user visual preference model is constructed using a preference learning algorithm. The preference learning algorithm dynamically updates the user's preferences through incremental learning to generate a user visual preference dataset.

[0146] S203, adjusting color parameters of the display using a dynamic optimization algorithm based on the ambient light field dynamic dataset and the user visual preference dataset, wherein the dynamic optimization algorithm adjusts color saturation, contrast, and color temperature in real time through a multi-objective optimization and adaptive feedback mechanism to generate optimized color parameters;

[0147] S204, using a color management engine to perform real-time adjustments to the color presentation of the display based on the optimized color parameters, wherein the color management engine ensures low latency and high precision of color adjustment through streaming computing technology and distributed architecture to generate the final display effect.

[0148] It can be seen that according to the environment in which the display is located, the spectral data of the ambient light is collected in real time using a multispectral sensor; according to the user's visual preferences, the visual characteristics of the user are extracted using a visual response model; according to the dynamic data set of the ambient light field and the user's visual preference data set, the color parameters of the display are adjusted using a dynamic optimization algorithm to generate optimized color parameters; according to the optimized color parameters, the color presentation of the display is adjusted in real time using a color management engine, wherein the color management engine uses streaming computing technology and a distributed architecture to ensure low latency and high precision of color adjustment, and generates the final display effect, so that it can adapt to changes in ambient light in real time, while taking into account the user's visual preferences, to achieve efficient and accurate color adjustment.

[0149] An embodiment of the present invention further provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to perform the steps in any one of the above method embodiments.

[0150] Specifically, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0151] Specifically, in this embodiment, the processor may be configured to execute the following steps through a computer program:

[0152] S201, using a multispectral sensor to collect spectral data of ambient light in real time according to the environment in which the display is located, wherein the multispectral sensor uses spectral analysis technology and an adaptive sampling mechanism to capture the wavelength distribution and intensity changes of the ambient light to generate ambient spectral data; based on the ambient spectral data, a real-time light field model of the ambient light is constructed using a dynamic light field modeling algorithm; the light field model uses spatiotemporal interpolation technology and a light intensity distribution prediction mechanism to predict the dynamic change trend of the ambient light to generate a dynamic data set of the ambient light field;

[0153] S202: extracting visual features of the user based on the user's visual preferences using a visual response model, wherein the visual response model analyzes the user's sensitivity and preference for different color parameters using eye tracking technology and a deep learning algorithm to generate a user visual feature vector. Based on the user visual feature vector, a user visual preference model is constructed using a preference learning algorithm. The preference learning algorithm dynamically updates the user's preferences through incremental learning to generate a user visual preference dataset.

[0154] S203, adjusting color parameters of the display using a dynamic optimization algorithm based on the ambient light field dynamic dataset and the user visual preference dataset, wherein the dynamic optimization algorithm adjusts color saturation, contrast, and color temperature in real time through a multi-objective optimization and adaptive feedback mechanism to generate optimized color parameters;

[0155] S204, using a color management engine to perform real-time adjustments to the color presentation of the display based on the optimized color parameters, wherein the color management engine ensures low latency and high precision of color adjustment through streaming computing technology and distributed architecture to generate the final display effect.

[0156] It can be seen that according to the environment in which the display is located, the spectral data of the ambient light is collected in real time using a multispectral sensor; according to the user's visual preferences, the visual characteristics of the user are extracted using a visual response model; according to the dynamic data set of the ambient light field and the user's visual preference data set, the color parameters of the display are adjusted using a dynamic optimization algorithm to generate optimized color parameters; according to the optimized color parameters, the color presentation of the display is adjusted in real time using a color management engine, wherein the color management engine uses streaming computing technology and a distributed architecture to ensure low latency and high precision of color adjustment, and generates the final display effect, so that it can adapt to changes in ambient light in real time, while taking into account the user's visual preferences, to achieve efficient and accurate color adjustment.

[0157] The above describes in detail the structure, features and effects of the present invention based on the embodiments shown in the drawings. The above is only a preferred embodiment of the present invention, but the scope of implementation of the present invention is not limited to what is shown in the drawings. Any changes made in accordance with the concept of the present invention, or modifications to equivalent embodiments with equivalent changes, which do not exceed the spirit covered by the description and drawings, should be within the scope of protection of the present invention.

Claims

1. A display color calibration method, characterized in that: The method comprises: Based on the environment in which the display is located, a multispectral sensor is used to collect spectral data of ambient light in real time. The multispectral sensor uses spectral analysis technology and an adaptive sampling mechanism to capture the wavelength distribution and intensity changes of the ambient light to generate ambient spectral data. Based on the ambient spectral data, a dynamic light field modeling algorithm is used to construct a real-time light field model of the ambient light. The light field model uses spatiotemporal interpolation technology and a light intensity distribution prediction mechanism to predict the dynamic change trend of the ambient light and generate a dynamic data set of the ambient light field. Extracting the user's visual features based on the user's visual preferences using a visual response model, wherein the visual response model uses eye tracking technology and a deep learning algorithm to analyze the user's sensitivity and preference for different color parameters to generate a user visual feature vector. Based on the user's visual feature vector, a user visual preference model is constructed using a preference learning algorithm. The preference learning algorithm dynamically updates the user's preferences through incremental learning to generate a user visual preference dataset. Adjusting the color parameters of the display using a dynamic optimization algorithm based on a dynamic dataset of ambient light fields and a dataset of user visual preferences, wherein the dynamic optimization algorithm adjusts color saturation, contrast, and color temperature in real time through a multi-objective optimization and adaptive feedback mechanism to generate optimized color parameters; Based on the optimized color parameters, a color management engine is used to perform real-time adjustment on the color presentation of the display, wherein the color management engine ensures low latency and high precision of color adjustment through streaming computing technology and distributed architecture to generate a final display effect; wherein, based on the optimized color parameters, the color parameters are loaded into the color management engine so that the color management engine receives and parses the color parameters in real time, and a color mapping algorithm is used to convert the optimized color parameters into color instructions executable by the display, wherein the color mapping algorithm ensures matching of the color parameters with the hardware characteristics of the display through color space conversion technology to generate a color adjustment instruction set; According to the color calibration instruction set, the color output of the display is adjusted in real time using streaming computing technology, wherein the streaming computing technology distributes the color calibration instructions to multiple computing nodes through a distributed architecture, processes color parameter adjustments in parallel, ensures low latency and high-precision color calibration, and generates real-time calibration results; based on the real-time calibration results, the color output of the display is rendered using a color rendering engine, wherein the color rendering engine uses hardware acceleration technology to ensure the real-time and smoothness of color rendering, and generates the final display effect.

2. The method according to claim 1, characterized in that The method comprises: collecting spectral data of ambient light in real time using a multispectral sensor according to the environment in which the display is located; capturing the wavelength distribution and intensity changes of the ambient light through spectral analysis technology and an adaptive sampling mechanism to generate ambient spectral data; constructing a real-time light field model of the ambient light using a dynamic light field modeling algorithm based on the ambient spectral data; and predicting the dynamic change trend of the ambient light through spatiotemporal interpolation technology and a light intensity distribution prediction mechanism to generate a dynamic data set of the ambient light field. The method comprises: A multispectral sensor collects spectral data of ambient light in real time, based on the display's environment. The sensor uses spectral analysis technology to capture the wavelength distribution and intensity changes of ambient light. Based on the dynamic changes in ambient light, the sensor uses an adaptive sampling mechanism to adjust the sampling frequency and resolution, ensuring that high-precision spectral data can be captured even when light levels change rapidly, generating a real-time ambient spectral dataset. Preprocessing the real-time environmental spectral data set, wherein the preprocessing removes high-frequency noise and outliers in the spectral data using wavelet transform technology and noise filtering algorithm, and smoothing the spectral data using digital signal processing technology to generate a denoised environmental spectral data set; Based on the denoised ambient spectral dataset, a real-time light field model of ambient light is constructed using a dynamic light field modeling algorithm. The light field modeling algorithm uses spatiotemporal interpolation technology to interpolate the ambient spectral data in both spatial and temporal dimensions to generate continuous light field distribution data. Furthermore, the light intensity distribution prediction mechanism is used to combine historical spectral data and ambient light change trends to predict the dynamic changes of the light field in the future and generate a dynamic dataset of the ambient light field.

3. The method according to claim 2, characterized in that The method extracts the user's visual features based on the user's visual preferences using a visual response model, wherein the visual response model analyzes the user's sensitivity and preference for different color parameters through eye tracking technology and a deep learning algorithm to generate a user visual feature vector. Based on the user visual feature vector, a user visual preference model is constructed using a preference learning algorithm. The preference learning algorithm dynamically updates the user preferences through incremental learning to generate a user visual preference dataset, including: Based on the user's visual preferences, real-time eye movement data is collected while the user is viewing the display. Using high-precision infrared imaging technology and pupil localization algorithms, the user's gaze distribution, gaze duration, and scan path are captured to generate a raw eye movement dataset. Preprocessing the original eye movement dataset, removing noise and invalid data points from the eye movement data using filtering algorithms and outlier detection techniques, and extracting key visual features from the preprocessed eye movement dataset using a feature extraction algorithm to generate a user visual feature dataset. The key visual features include gaze point density, saccade speed, and area of ​​interest distribution. Based on a user visual feature dataset, a visual response model is used to analyze users' sensitivity and preferences for different color parameters. The visual response model uses a deep learning algorithm to construct a multi-layer neural network to model the relationship between users' gaze behavior and color parameters. The multi-layer neural network is then trained to generate a user visual feature vector that quantifies the user's preference for color saturation, contrast, and color temperature. Based on the user's visual feature vector, a user visual preference model is constructed using a preference learning algorithm. The preference learning algorithm dynamically updates the user preference model through incremental learning technology to ensure that it can adapt to changes in user preferences and generate a user visual preference dataset.

4. The method according to claim 3, characterized in that The method comprises: adjusting the color parameters of the display using a dynamic optimization algorithm based on the ambient light field dynamic data set and the user visual preference data set, wherein the dynamic optimization algorithm adjusts the color saturation, contrast, and color temperature in real time through a multi-objective optimization and adaptive feedback mechanism to generate optimized color parameters, including: Determining an optimization target for color parameters based on an ambient light field dynamic dataset and a user visual preference dataset, wherein the color parameters include color saturation, contrast, and color temperature; A color parameter optimization model is constructed using a multi-objective optimization algorithm, wherein the optimization model generates a multi-objective optimization problem based on the optimization goal through the Pareto optimality theory, and uses constraints to limit the boundaries of the multi-objective optimization problem to generate an initial optimization solution space; A dynamic optimization algorithm is used to solve the multi-objective optimization problem. The dynamic optimization algorithm searches for the optimal color parameter combination in the initial optimization solution space through genetic algorithms and / or particle swarm optimization techniques, and combines an adaptive feedback mechanism to adjust the search strategy of the dynamic optimization algorithm in real time to ensure that it can still converge quickly when the ambient light field and user preferences change dynamically, and generate an optimized color parameter set.

5. A display color calibration system, characterized in that: The system comprises: An acquisition module is configured to utilize a multispectral sensor to collect spectral data of ambient light in real time based on the environment in which the display is located. The multispectral sensor uses spectral analysis technology and an adaptive sampling mechanism to capture the wavelength distribution and intensity changes of the ambient light to generate ambient spectral data. Based on the ambient spectral data, a dynamic light field modeling algorithm is used to construct a real-time light field model of the ambient light. The light field model uses spatiotemporal interpolation technology and a light intensity distribution prediction mechanism to predict the dynamic change trend of the ambient light and generate a dynamic data set of the ambient light field. An extraction module is configured to extract the user's visual features based on the user's visual preferences using a visual response model, wherein the visual response model analyzes the user's sensitivity and preference for different color parameters through eye tracking technology and a deep learning algorithm to generate a user visual feature vector. Based on the user visual feature vector, a user visual preference model is constructed using a preference learning algorithm. The preference learning algorithm dynamically updates the user's preferences through incremental learning to generate a user visual preference dataset. an adjustment module for adjusting the color parameters of the display using a dynamic optimization algorithm based on the ambient light field dynamic dataset and the user visual preference dataset, wherein the dynamic optimization algorithm adjusts color saturation, contrast, and color temperature in real time through a multi-objective optimization and adaptive feedback mechanism to generate optimized color parameters; a calibration module for calibrating the color presentation of the display in real time using a color management engine based on the optimized color parameters, wherein the color management engine ensures low latency and high precision of color calibration through streaming computing technology and a distributed architecture, thereby generating a final display effect; wherein, based on the optimized color parameters, the color parameters are loaded into the color management engine so that the color management engine receives and parses the color parameters in real time, and the optimized color parameters are converted into color instructions executable by the display using a color mapping algorithm, wherein the color mapping algorithm ensures that the color parameters match the hardware characteristics of the display through color space conversion technology, thereby generating a color calibration instruction set; According to the color calibration instruction set, the color output of the display is adjusted in real time using streaming computing technology, wherein the streaming computing technology distributes the color calibration instructions to multiple computing nodes through a distributed architecture, processes color parameter adjustments in parallel, ensures low latency and high-precision color calibration, and generates real-time calibration results; based on the real-time calibration results, the color output of the display is rendered using a color rendering engine, wherein the color rendering engine uses hardware acceleration technology to ensure the real-time and smoothness of color rendering, and generates the final display effect.

6. The system according to claim 5, characterized in that The acquisition module is specifically used to: A multispectral sensor collects spectral data of ambient light in real time, based on the display's environment. The sensor uses spectral analysis technology to capture the wavelength distribution and intensity changes of ambient light. Based on the dynamic changes in ambient light, the sensor uses an adaptive sampling mechanism to adjust the sampling frequency and resolution, ensuring that high-precision spectral data can be captured even when light levels change rapidly, generating a real-time ambient spectral dataset. Preprocessing the real-time environmental spectral data set, wherein the preprocessing removes high-frequency noise and outliers in the spectral data using wavelet transform technology and noise filtering algorithm, and smoothing the spectral data using digital signal processing technology to generate a denoised environmental spectral data set; Based on the denoised ambient spectral dataset, a real-time light field model of ambient light is constructed using a dynamic light field modeling algorithm. The light field modeling algorithm uses spatiotemporal interpolation technology to interpolate the ambient spectral data in both spatial and temporal dimensions to generate continuous light field distribution data. Furthermore, the light intensity distribution prediction mechanism is used to combine historical spectral data and ambient light change trends to predict the dynamic changes of the light field in the future and generate a dynamic dataset of the ambient light field.

7. The system according to claim 6, characterized in that The extraction module is specifically used to: Based on the user's visual preferences, real-time eye movement data is collected while the user is viewing the display. Using high-precision infrared imaging technology and pupil localization algorithms, the user's gaze distribution, gaze duration, and scan path are captured to generate a raw eye movement dataset. Preprocessing the original eye movement dataset, removing noise and invalid data points from the eye movement data using filtering algorithms and outlier detection techniques, and extracting key visual features from the preprocessed eye movement dataset using a feature extraction algorithm to generate a user visual feature dataset. The key visual features include gaze point density, saccade speed, and area of ​​interest distribution. Based on a user visual feature dataset, a visual response model is used to analyze users' sensitivity and preferences for different color parameters. The visual response model uses a deep learning algorithm to construct a multi-layer neural network to model the relationship between users' gaze behavior and color parameters. The multi-layer neural network is then trained to generate a user visual feature vector that quantifies the user's preference for color saturation, contrast, and color temperature. Based on the user's visual feature vector, a user visual preference model is constructed using a preference learning algorithm. The preference learning algorithm dynamically updates the user preference model through incremental learning technology to ensure that it can adapt to changes in user preferences and generate a user visual preference dataset.

8. A storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program is configured to execute the method according to any one of claims 1 to 4 when run.

9. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to perform the method according to any one of claims 1 to 4.

Images