Display color temperature dynamic optimization method and system based on ambient light and content recognition

Abstract

The invention discloses a display color temperature dynamic optimization method and system based on ambient light and content recognition, and relates to the technical field of display regulation and control, and the method comprises the steps: obtaining an ambient light parameter of an environment where a display screen is located in real time; determining the type of the display content and content feature distribution; determining a preset reference color temperature parameter; in combination with a visual comfort model corresponding to the display content type, performing content adaptability correction on the reference color temperature parameter to generate a dynamic optimized color temperature parameter; carrying out regionalized weight distribution on the dynamic optimization color temperature parameters; and generating a color temperature regulation and control instruction of each pixel region of the display screen based on a regionalized weight distribution result, and driving a backlight module to execute regional color temperature adjustment. Through a multi-dimensional cooperation mechanism of ambient light adaptive compensation, content feature driven optimization, regionalized weight distribution and physiological feedback closed-loop regulation and control, dynamic and accurate adaptation of the color temperature of the display screen is realized, the visual comfort and the color expressive force are remarkably improved, and the visual fatigue occurrence rate is reduced.

Description

Technical Field

[0001] This invention relates to the field of display control technology, specifically to a method and system for dynamic optimization of display color temperature based on ambient light and content recognition. Background Technology

[0002] With the rapid development of display technology, users' demands for visual comfort are increasing. Traditional display devices often rely on ambient light sensors or manual user settings for color temperature adjustment, lacking the ability to dynamically perceive the characteristics of the displayed content. Existing ambient light adaptive solutions typically adjust globally based on a single color temperature parameter, failing to effectively differentiate the visual needs of different content types such as text and images. This can easily lead to localized glare or color temperature conflicts, especially in mixed content scenarios. Furthermore, mainstream algorithms do not fully consider the correlation between ambient light distribution and the spatial characteristics of the displayed content, making it difficult to achieve zoned optimization that conforms to the physiological adaptation patterns of the human eye, potentially causing visual fatigue with prolonged use.

[0003] Existing methods often produce a visual jarring effect due to lag in color temperature compensation when ambient light changes abruptly or content switches rapidly. Furthermore, the lack of quantitative constraints on color temperature gradients between adjacent control units leads to color temperature banding in the image. In addition, content recognition mechanisms based on fixed thresholds struggle to adapt to complex and ever-changing display scenarios. Especially when processing high dynamic range images, existing color temperature smoothing algorithms are prone to detail loss, failing to balance the dual requirements of color accuracy and visual comfort. Summary of the Invention

[0004] To address the aforementioned technical issues, this paper provides a method and system for dynamic optimization of display color temperature based on ambient light and content recognition. This technical solution solves the problems of existing methods, which often produce a visual jump due to color temperature compensation lag when ambient light changes abruptly or content switches rapidly, and lack quantitative constraints on the color temperature gradient between adjacent control units, resulting in color temperature banding in the image.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows: A dynamic color temperature optimization method for displays based on ambient light and content recognition includes: The ambient light parameters of the environment in which the display screen is located are acquired in real time, and the ambient light parameters include at least the ambient light color temperature and the ambient light intensity. Perform image recognition on the currently displayed content to determine the type and distribution of content features; Based on a pre-trained personalized color temperature adaptation model, preset baseline color temperature parameters are determined. By combining the visual comfort model corresponding to the type of displayed content, the baseline color temperature parameters are adjusted to adapt to the content, and dynamically optimized color temperature parameters are generated. Based on the spatial correlation between ambient light intensity and the distribution of display content characteristics, the dynamic optimization color temperature parameters are assigned regional weights. Based on the regional weight allocation results, color temperature control instructions for each pixel area of ​​the display screen are generated, and the backlight module is driven to perform regional color temperature adjustment.

[0006] Preferably, the preset reference color temperature parameters are determined by the pre-trained personalized color temperature adaptation model as follows: Collect historical user operation data, which includes color temperature parameters manually adjusted by users under different ambient light conditions; Outliers were removed from the historical user operation data, and the optimal color temperature for each ambient light zone was calculated using the sliding window mean method. A mapping model between ambient light parameters and the optimal color temperature is established using a support vector machine, and the model output value is used as the reference color temperature parameter.

[0007] Preferably, the step of combining the visual comfort model corresponding to the display content type to perform content-adaptive correction on the baseline color temperature parameters and generate dynamically optimized color temperature parameters specifically includes: When the displayed content is identified as text, the cool color temperature compensation weight coefficient K1 is increased, where K1∈[1.2,1.5]; When the displayed content is identified as an image, a color temperature gradient algorithm is applied to apply a smooth color temperature transition constraint in the high dynamic range area of ​​the image. When a user's gaze area is detected, a color temperature compensation enhancement factor is applied to that area, and the enhancement factor is positively correlated with the gaze duration.

[0008] Preferably, the step of allocating regional weights to the dynamically optimized color temperature parameters based on the spatial correlation between ambient light intensity and the distribution of display content features specifically includes: The display screen is divided into N×M control units, and each control unit corresponds to an independent color temperature control circuit. Based on the convolution operation results of the ambient light intensity distribution map and the edge feature map of the displayed content, a color temperature influence factor matrix for each control unit is generated. An adaptive particle swarm optimization algorithm is used to iteratively solve for the optimal weight allocation ratio of each control unit with the visual comfort function as the objective.

[0009] Preferably, when generating color temperature control instructions for each pixel region of the display screen based on the regional weight allocation results, and driving the backlight module to perform regional color temperature adjustment, a gradient constraint is satisfied, wherein the gradient constraint is: A gradual constraint condition is applied to the color temperature difference between adjacent control units. Specifically, the color temperature difference between adjacent control units satisfies the following relationship: Where ΔT is the color temperature difference, d is the distance between adjacent control units, and α is the material-related attenuation coefficient; A color temperature transition algorithm based on the time dimension is used to ensure that the rate of color temperature change during a single adjustment does not exceed the threshold of human eye perception.

[0010] Preferably, the method further includes a user physiological monitoring feedback control mechanism, which specifically comprises: During the color temperature adjustment process, the user's physiological feedback parameters are monitored in real time, including the pupil diameter change rate and blink frequency. When the pupil contraction rate is detected to exceed the threshold, the current color temperature compensation intensity is automatically reduced. A feedback learning mechanism is established to store the correlation between user physiological response data and color temperature adjustment parameters in a historical database, which is used to optimize the visual comfort model.

[0011] Furthermore, a dynamic color temperature optimization system based on ambient light and content recognition is proposed to implement the aforementioned dynamic color temperature optimization method based on ambient light and content recognition, specifically including: The ambient light sensing module is configured to acquire ambient light parameters, including ambient light color temperature and intensity, in real time. The content analysis module is configured to determine the type and feature distribution of the displayed content through image recognition. The reference color temperature calculation module includes a support vector machine model, configured to generate a mapping relationship between ambient light parameters and reference color temperature based on historical user data; The dynamic compensation engine is configured to calculate an initial compensation value based on the difference between the reference color temperature and the ambient light color temperature, and then adjust it according to the content type in combination with the visual comfort model. Text content is given a 1.2-1.5 times cool color temperature compensation weight, while image content is subject to color temperature smooth transition constraints. The region optimization module is configured to generate a color temperature influence factor matrix of ambient light and content features through convolution operations, and iteratively solve the optimal weight allocation of the display area based on the adaptive particle swarm algorithm. The zone control module includes an N×M independent color temperature control circuit array, configured to drive the backlight module to perform zoned color temperature adjustment, while satisfying the color temperature difference between adjacent units. Spatial constraints and temporal constraints where the rate of change of color temperature in a single adjustment is lower than the human eye's perception threshold.

[0012] Optionally, the system further includes a physiological monitoring feedback module for implementing the user physiological monitoring feedback control mechanism as described in claim 6, wherein the physiological monitoring feedback module specifically includes: A physiological monitoring unit is used to monitor user physiological feedback parameters in real time during color temperature adjustment, including pupil diameter change rate and blink frequency; A feedback adjustment unit is used to automatically reduce the current color temperature compensation intensity when the pupil contraction rate is detected to exceed a threshold. An adaptive learning unit is used to establish a feedback learning mechanism, which stores the correlation between user physiological response data and color temperature adjustment parameters in a historical database to optimize the visual comfort model.

[0013] Compared with the prior art, the beneficial effects of the present invention are as follows: By constructing an ambient light-reference color temperature mapping model using support vector machines and combining it with user historical adjustment data for machine learning, the reference color temperature calculation is made to have both environmental adaptability and personalized features, effectively solving the visual discomfort problem caused by traditional fixed color temperature parameters. An innovative content-driven compensation mechanism is used to enhance the reading comfort of text content by implementing cool color temperature enhancement, and to maintain the continuity of image colors by using a color temperature gradient algorithm for image content. At the same time, eye-tracking technology is combined to dynamically enhance and compensate the gaze area, making the color temperature optimization more in line with the visual attention characteristics of the human eye. The partitioned control strategy based on convolution operation and adaptive particle swarm optimization constructs a spatially related influencing factor matrix and a gradient constraint model to achieve pixel-level precise control while ensuring a smooth transition of color temperature in the image. This successfully eliminates the color temperature banding phenomenon caused by traditional global adjustment and reduces the incidence of visual fatigue. A physiological feedback closed-loop control mechanism is introduced, which dynamically adjusts the compensation intensity by monitoring pupil response in real time and continuously optimizes the visual comfort model by combining feedback learning, so that the system has the ability to adapt to dynamic environments and can maintain the best color temperature balance under complex lighting conditions. Attached Figure Description

[0014] Figure 1 The flowchart shows the display color temperature dynamic optimization method based on ambient light and content recognition proposed in Example 1. Figure 2 This is a flowchart of the method for determining preset reference color temperature parameters proposed in Example 1; Figure 3 This is a flowchart of the method for generating dynamically optimized color temperature parameters proposed in Example 1; Figure 4 This is a flowchart of the method for regional weight allocation of dynamically optimized color temperature parameters proposed in Example 1; Figure 5 This is a flowchart of the method for generating color temperature control instructions for each pixel area of ​​the display screen as proposed in Embodiment 1; Figure 6 This is a flowchart of the user physiological monitoring feedback regulation mechanism proposed in Example 2; Figure 7This is an architecture diagram of the electronic devices in this solution; Figure 8 This is a schematic diagram of the computer-readable storage medium structure in this scheme.

[0015] The numbers on the map are: 500 - Electronic device; 501 - Bus; 502 - CPU; 503 - ROM; 504 - RAM; 505 - Communication port; 506 - Input / output component; 507 - Hard disk; 508 - User interface; 600 - Computer-readable storage medium. Detailed Implementation

[0016] The following description is intended to disclose the invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious variations will occur to those skilled in the art.

[0017] Example 1: Reference Figure 1 As shown, this embodiment proposes a dynamic color temperature optimization method for displays based on ambient light and content recognition, including: Real-time acquisition of ambient light parameters of the environment in which the display screen is located, including at least ambient light color temperature and ambient light intensity; Ambient light color temperature and ambient light intensity are collected synchronously by a multispectral ambient light sensor array and a light intensity distribution detector. A Kalman filter algorithm is used to eliminate instantaneous interference. At the same time, an RGB-IR camera captures the distribution characteristics of ambient light sources to achieve accurate analysis of mixed multi-light source scenes. Perform image recognition on the currently displayed content to determine the type and distribution of content features; The improved YOLOv7 network is applied for real-time semantic segmentation, and frequency domain feature analysis technology is combined to identify content types such as text, images, and videos; Based on a pre-trained personalized color temperature adaptation model, preset baseline color temperature parameters are determined. By quantifying the difference between the reference color temperature and ambient light, a scientific compensation benchmark is generated, providing a reasonable adjustment range for subsequent content adaptation and correction, and preventing problems of over-compensation or under-compensation. By combining the visual comfort model corresponding to the type of displayed content, the baseline color temperature parameters are adjusted to adapt to the content, and dynamically optimized color temperature parameters are generated. Specifically, the cool color temperature is enhanced for text content to improve readability, and a smooth color temperature transition is implemented for image content to maintain color continuity. At the same time, the compensation intensity in the user's gaze area is strengthened, significantly improving visual comfort and content expressiveness. Based on the spatial correlation between ambient light intensity and the distribution of display content characteristics, the dynamic optimization color temperature parameters are assigned regional weights. Spatial correlation analysis is used to achieve regional differential compensation, optimize local color temperature matching accuracy and eliminate color temperature discontinuity in scenarios with uneven ambient light distribution or complex content features. Based on the regional weight allocation results, color temperature control instructions for each pixel area of ​​the display screen are generated, and the backlight module is driven to perform regional color temperature adjustment.

[0018] It achieves precise color temperature control in pixel areas, ensuring a smooth transition of the overall color temperature of the image, while dynamically responding to changes in environment and content, taking into account both visual comfort and display quality consistency.

[0019] Specifically, refer to Figure 2 As shown, in this embodiment, the preset reference color temperature parameters are determined based on the pre-trained personalized color temperature adaptation model as follows: Collect historical user operation data, which includes color temperature parameters manually adjusted by users under different ambient light conditions; Outliers were removed from historical user operation data, and the optimal color temperature for each ambient light zone was calculated using the sliding window mean method. A mapping model between ambient light parameters and the optimal color temperature is established using a support vector machine, and the model output value is used as the reference color temperature parameter.

[0020] The objective function of the support vector machine is: The constraints for support vector machines are: in, This is a weight vector, representing the weight distribution of the influence of different ambient light parameters on color temperature. This is a bias term used as the baseline offset in a linear model. This is a penalty factor, ranging from 0 to 100, which controls the balance between model complexity and data fit. These are slack variables used to handle the tolerance for classification error. For Gaussian kernel function, Ambient light parameter vector, To optimize the color temperature value; Through regularization terms and loss items By constructing an objective function and solving it under constraints, the globally optimal w and b parameters are obtained. A deterministic mapping relationship between ambient light parameters and color temperature preference is established. A Gaussian kernel function is introduced into the constraints, which can effectively handle the heterogeneity of ambient light data collected at different times and locations. The final w vector can accurately reveal the contribution of each ambient light parameter to the color temperature decision.

[0021] A baseline color temperature model is constructed by combining data cleaning and machine learning to effectively balance environmental adaptability and personalized needs. A data preprocessing mechanism based on the sliding window mean method eliminates outliers, ensuring that the baseline color temperature parameters accurately reflect the common preferences of the user group. A Gaussian kernel function of a support vector machine is introduced to handle multi-source heterogeneous data distributions, overcoming the limitations of traditional linear models and establishing a nonlinear mapping relationship between environmental parameters and color temperature decisions in complex lighting scenarios. Through the synergistic optimization of regularization terms and relaxation variables, the model accurately captures individual adjustment characteristics while maintaining generalization ability, ensuring both group universality and preserving personalized adjustment space. The physical interpretability of the weight vector clearly quantifies the contribution of ambient light parameters to color temperature decisions, providing a scientific basis for system parameter optimization and significantly improving the robustness of the color temperature adjustment strategy and the user's subjective comfort experience.

[0022] Reference Figure 3 As shown, in this embodiment, the reference color temperature parameters are adjusted for content adaptation based on the visual comfort model corresponding to the displayed content type, and the dynamically optimized color temperature parameters are generated specifically including: When the displayed content is identified as text, the cool color temperature compensation weight coefficient K1 is increased, where K1∈[1.3,1.5]; When the displayed content is identified as an image, a color temperature gradient algorithm is applied to apply a smooth color temperature transition constraint in the high dynamic range area of ​​the image. When a user's gaze area is detected, a color temperature compensation enhancement factor is applied to that area, and the enhancement factor is positively correlated with the gaze duration.

[0023] An enhancement factor is introduced to enhance local color temperature compensation during color temperature optimization. After locking the gaze area using eye-tracking technology, the factor dynamically increases the color temperature adjustment intensity of that area based on the gaze duration. This ensures that the color temperature of important visual areas is accurately adapted to ambient light and content characteristics, rather than being uniformly adjusted across the entire screen. When it is detected that the user has been continuously gazing at a certain area for more than 200ms, the enhancement factor mechanism initiates progressive color temperature compensation. If the user moves their gaze away, the area compensation intensity gradually returns to the baseline level, avoiding residual color temperature deviation.

[0024] A content-driven color temperature compensation mechanism significantly enhances the visual comfort and adaptability of the display system. A cool color temperature enhancement strategy is applied to text-based content, effectively improving text edge sharpness and black-and-white contrast, reducing visual fatigue caused by prolonged reading. For image-based content, a color temperature gradient constraint algorithm is employed to maintain the color tension of high dynamic range images while eliminating color banding through smooth color temperature transitions, maintaining the natural consistency of the image's color temperature. A specially designed gaze area enhancement factor, combined with eye-tracking technology, achieves dynamic compensation focusing. Gradual color temperature optimization is initiated in the user's gaze area (>200ms), ensuring a precise match between the color temperature of key areas and ambient light and content features. After the gaze shifts, an exponential decay algorithm restores the baseline color temperature, enhancing the detail in the visually focused area while avoiding the accumulation of color temperature deviations caused by full-screen adjustments. This composite correction strategy enables the display system to intelligently distinguish between content features and user intent, achieving a unified approach of precise local optimization and global color temperature coordination in complex scenarios.

[0025] Reference Figure 4 As shown, this embodiment also proposes to allocate regional weights to the dynamically optimized color temperature parameters based on the spatial correlation between ambient light intensity and the distribution of display content characteristics. Specifically, this includes: The display screen is divided into N×M control units, and each control unit corresponds to an independent color temperature control circuit. Based on the convolution operation results of the ambient light intensity distribution map and the edge feature map of the displayed content, a color temperature influence factor matrix for each control unit is generated. An adaptive particle swarm optimization algorithm is used to iteratively solve for the optimal weight allocation ratio of each control unit with the visual comfort function as the objective.

[0026] Global color temperature compensation is performed using a regional weight allocation method. Compared with a global uniform compensation method, it can achieve specific enhancement based on the displayed content. Combined with the enhancement factor mechanism, it can achieve dual enhancement optimization extreme values ​​based on user gaze and displayed content, thus realizing personalized enhancement of the displayed content.

[0027] By combining content spatial correlation analysis with intelligent optimization algorithms, the system achieves refined control of color temperature compensation for the display screen. By dividing the screen into independent control units and constructing a color temperature influence factor matrix, the system can accurately quantify the interaction between ambient light distribution and content edge features, overcoming the uniformity limitations of traditional global compensation. An adaptive particle swarm optimization algorithm is used to optimize the visual comfort function across multiple objectives. While ensuring overall color temperature coordination, it implements gradient control of compensation intensity for highly dynamic content edge areas, effectively eliminating the visual discontinuity caused by sudden color temperature changes. The dual optimization architecture, combined with an enhancement factor mechanism, retains the ability to enhance key areas of user attention while simultaneously adapting the color temperature of the main screen structure through content feature-driven optimization. This achieves a dynamic balance between local compensation accuracy and global visual comfort in complex lighting scenarios, significantly improving the detail and visual persistence of high-contrast display content.

[0028] Reference Figure 5 As shown, this embodiment further points out that when color temperature control instructions for each pixel region of the display screen are generated based on the regional weight allocation results, and the backlight module is driven to perform regional color temperature adjustment, the gradient constraint is satisfied. The gradient constraint is as follows: A gradual constraint is applied to the color temperature difference between adjacent control units. Specifically, the color temperature difference between adjacent control units must satisfy the following relationship: Where ΔT is the color temperature difference, d is the distance between adjacent control units, and α is the material-related attenuation coefficient; A time-based color temperature transition algorithm is employed to ensure that the rate of color temperature change during a single adjustment does not exceed the human eye's perception threshold. Specifically, the expression for the time-based color temperature transition algorithm is as follows: ,in, The maximum permissible rate of change is set to 300 k / s. This is a smoothing coefficient, ranging from 2 to 10, used to control the steepness of the rate of change curve. To adjust the start time, Let t be the rate of color temperature change at time t.

[0029] A natural and smooth transition in color temperature control is achieved through a dual spatiotemporal constraint mechanism, significantly improving the continuity and comfort of the visual experience. Spatially, a color temperature difference constraint formula based on material properties strictly limits the color temperature difference between adjacent control units. Through adaptive adjustment of the physical attenuation coefficient α, color temperature discontinuity is eliminated while retaining a reasonable local compensation gradient, ensuring that the color temperature transition in the boundary between light and dark areas in high-dynamic scenes conforms to the human eye's perception of color gradation. Temporally, a nonlinear transition algorithm dynamically controls the color temperature adjustment rate, ensuring that each adjustment process meets both the highest perceptual threshold of color temperature change for the human eye and intelligently adjusts the response speed according to the complexity of the image content. This composite constraint mechanism, combined with a regional weight allocation strategy, forms a closed-loop synergy, enabling the regional color temperature compensation to exhibit a natural and coherent gradient change in spatial distribution, maintaining a smooth and imperceptible adjustment process over time, ultimately achieving a deep coupling optimization of high-precision color temperature control and visual comfort.

[0030] Example 2: Reference Figure 6 As shown, based on Embodiment 1, this embodiment also proposes a user physiological monitoring feedback control mechanism, which is specifically as follows: During the color temperature adjustment process, the user's physiological feedback parameters are monitored in real time. These parameters include the pupil diameter change rate and blink frequency. The collection and use of the user's physiological feedback parameters must be known and agreed to by the user, and the use of the user's physiological feedback parameters must meet the privacy information protection guidelines. When the pupil contraction rate is detected to exceed the threshold, the current color temperature compensation intensity is automatically reduced. Establish a feedback learning mechanism to store the correlation between user physiological response data and color temperature adjustment parameters in a historical database for optimizing the visual comfort model.

[0031] Specifically, the formula for calculating the rate of change of pupil diameter is: In the formula, The rate of change of pupil diameter. Based on the pupil diameter, The time interval for sampling pupil diameter. for Pupil diameter at any given moment for The pupil diameter at any given moment; When the pupil diameter change rate is greater than 0.15, the color temperature compensation intensity attenuation is triggered. The specific attenuation formula is as follows: In the formula, This is the color temperature value after attenuation correction. The color temperature value before attenuation correction. This is the response time coefficient, which is related to the display screen's response speed.

[0032] This embodiment achieves dynamic and personalized color temperature optimization through a closed-loop control mechanism that integrates physiological feedback and machine learning. By non-invasive physiological monitoring to capture the pupil diameter change rate and blink frequency in real time, a quantitative assessment system for user visual fatigue is established. When the pupil contraction rate exceeds a threshold, a color temperature compensation intensity attenuation algorithm is triggered, smoothly reducing the color temperature value to the physiologically comfortable range, effectively alleviating ciliary muscle tension caused by excessive color temperature adjustments. Combined with a feedback learning mechanism, the visual comfort model is continuously optimized, enabling the system to adaptively adjust compensation strategies based on individual differences. For example, for light-sensitive users, the adjustment range of the cool color temperature weight coefficient K1 is automatically reduced. Privacy protection design ensures that physiological data is only used for model training with user authorization, and information security is guaranteed through data anonymization and encrypted storage technologies. This mechanism, in conjunction with the color temperature regionalization strategy, maintains the color performance of the image while reducing the visual fatigue index of users during prolonged use, significantly improving the human-computer interaction friendliness and physiological adaptation accuracy of the display system.

[0033] Example 3: This example proposes a dynamic color temperature optimization system based on ambient light and content recognition to implement the dynamic color temperature optimization method based on ambient light and content recognition proposed in Examples 1 and 2, including: The ambient light sensing module is configured to acquire ambient light parameters, including ambient light color temperature and intensity, in real time. The content analysis module is configured to determine the type and feature distribution of the displayed content through image recognition. The reference color temperature calculation module includes a support vector machine model, configured to generate a mapping relationship between ambient light parameters and reference color temperature based on historical user data; The dynamic compensation engine is configured to calculate an initial compensation value based on the difference between the reference color temperature and the ambient light color temperature, and then adjust it according to the content type in combination with the visual comfort model. Text content is given a 1.2-1.5 times cool color temperature compensation weight, while image content is subject to color temperature smooth transition constraints. The region optimization module is configured to generate a color temperature influence factor matrix of ambient light and content features through convolution operations, and iteratively solve the optimal weight allocation of the display area based on the adaptive particle swarm algorithm. The zone control module includes an N×M independent color temperature control circuit array, configured to drive the backlight module to perform zoned color temperature adjustment, while satisfying the color temperature difference between adjacent units. Spatial constraints and temporal constraints where the rate of color temperature change in a single adjustment is lower than the human eye's perception threshold. The physiological monitoring feedback module includes: The physiological monitoring unit is used to monitor the user's physiological feedback parameters in real time during the color temperature adjustment process. The parameters include the rate of change of pupil diameter and blink frequency. The feedback adjustment unit is used to automatically reduce the current color temperature compensation intensity when the pupil contraction rate is detected to exceed the threshold. The adaptive learning unit is used to establish a feedback learning mechanism, storing the correlation between user physiological response data and color temperature adjustment parameters in a historical database to optimize the visual comfort model.

[0034] Furthermore, the method according to the embodiments of this application can also be achieved by means of... Figure 7 The architecture of the electronic device shown is used to implement this. For example... Figure 7 As shown, the electronic device 500 may include a bus 501, one or more CPUs 502, ROM 503, RAM 504, a communication port 505 connected to a network, an input / output component 506, a hard disk 507, etc. The storage device in the electronic device 500, such as ROM 503 or hard disk 507, may store the display color temperature dynamic optimization method based on ambient light and content recognition provided in this application. The electronic device 500 may also include a user interface 508. Of course, Figure 7 The architecture shown is merely exemplary and can be omitted as needed when implementing different devices. Figure 7 One or more components in the illustrated electronic device.

[0035] Figure 8 This is a schematic diagram of a computer-readable storage medium structure provided in one embodiment of this application. Figure 8 The diagram illustrates a computer-readable storage medium 600 according to one embodiment of this application. The computer-readable storage medium 600 stores computer-readable instructions. When executed by a processor, the computer-readable instructions can perform the display color temperature dynamic optimization method based on ambient light and content recognition according to an embodiment of this application, as described with reference to the above figures. The storage medium 600 includes, but is not limited to, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0036] In summary, the advantages of this invention are as follows: By constructing an ambient light-reference color temperature mapping model using support vector machines and combining it with user historical adjustment data for machine learning, the reference color temperature calculation possesses both environmental adaptability and personalized characteristics, effectively solving the visual discomfort problem caused by traditional fixed color temperature parameters; An innovative content-feature-driven compensation mechanism enhances reading comfort by implementing cool color temperature enhancement for text-based content and maintains color continuity for image-based content using a color temperature gradient algorithm, while simultaneously combining eye-tracking technology to dynamically strengthen and compensate the gaze area, making color temperature optimization more in line with the characteristics of human visual attention; A partitioned control strategy based on convolution operations and adaptive particle swarm optimization, through the construction of a spatially relevant influencing factor matrix and a gradient constraint model, achieves pixel-level precise control while ensuring a smooth transition of image color temperature, successfully eliminating the color temperature discontinuity phenomenon caused by traditional global adjustments and reducing the incidence of visual fatigue; The introduction of a physiological feedback closed-loop control mechanism dynamically adjusts the compensation intensity by real-time monitoring of pupil response, and continuously optimizes the visual comfort model through feedback learning, enabling the system to have dynamic environmental adaptability and maintain optimal color temperature balance even under complex lighting conditions.

[0037] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the claimed invention. The scope of protection claimed by the appended claims and their equivalents is defined.

Claims

1. A dynamic color temperature optimization method for displays based on ambient light and content recognition, characterized in that, include: The ambient light parameters of the environment in which the display screen is located are acquired in real time, and the ambient light parameters include at least the ambient light color temperature and the ambient light intensity. Perform image recognition on the currently displayed content to determine the type and distribution of content features; Based on a pre-trained personalized color temperature adaptation model, preset baseline color temperature parameters are determined. By combining the visual comfort model corresponding to the type of displayed content, the baseline color temperature parameters are adjusted to adapt to the content, and dynamically optimized color temperature parameters are generated. Based on the spatial correlation between ambient light intensity and the distribution of display content characteristics, the dynamic optimization color temperature parameters are assigned regional weights. Based on the regional weight allocation results, color temperature control instructions for each pixel area of ​​the display screen are generated, and the backlight module is driven to perform regional color temperature adjustment.

2. The display color temperature dynamic optimization method based on ambient light and content recognition according to claim 1, characterized in that, The pre-trained personalized color temperature adaptation model determines the preset baseline color temperature parameters as follows: Collect historical user operation data, which includes color temperature parameters manually adjusted by users under different ambient light conditions; Outliers were removed from the historical user operation data, and the optimal color temperature for each ambient light zone was calculated using the sliding window mean method. A mapping model between ambient light parameters and the optimal color temperature is established using a support vector machine, and the model output value is used as the reference color temperature parameter.

3. The display color temperature dynamic optimization method based on ambient light and content recognition according to claim 2, characterized in that, The process of combining the visual comfort model corresponding to the displayed content type to perform content-adaptive correction on the baseline color temperature parameters and generate dynamically optimized color temperature parameters specifically includes: When the displayed content is identified as text, the cool color temperature compensation weight coefficient K1 is increased, where K1∈[1.2,1.5]; When the displayed content is identified as an image, a color temperature gradient algorithm is applied to apply a smooth color temperature transition constraint in the high dynamic range area of ​​the image. When a user's gaze area is detected, a color temperature compensation enhancement factor is applied to that area, and the enhancement factor is positively correlated with the gaze duration.

4. The display color temperature dynamic optimization method based on ambient light and content recognition according to claim 3, characterized in that, The process of allocating regional weights to dynamically optimized color temperature parameters based on the spatial correlation between ambient light intensity and the distribution of displayed content features specifically includes: The display screen is divided into N×M control units, and each control unit corresponds to an independent color temperature control circuit. Based on the convolution operation results of the ambient light intensity distribution map and the edge feature map of the displayed content, a color temperature influence factor matrix for each control unit is generated. An adaptive particle swarm optimization algorithm is used to iteratively solve for the optimal weight allocation ratio of each control unit with the visual comfort function as the objective.

5. The display color temperature dynamic optimization method based on ambient light and content recognition according to claim 4, characterized in that, When generating color temperature control instructions for each pixel region of the display screen based on the regional weight allocation results, and driving the backlight module to perform regional color temperature adjustment, the gradient constraint is satisfied. The gradient constraint is as follows: A gradual constraint condition is applied to the color temperature difference between adjacent control units. Specifically, the color temperature difference between adjacent control units satisfies the following relationship: Where ΔT is the color temperature difference, d is the distance between adjacent control units, and α is the material-related attenuation coefficient; A color temperature transition algorithm based on the time dimension is used to ensure that the rate of color temperature change during a single adjustment does not exceed the threshold of human eye perception.

6. The display color temperature dynamic optimization method based on ambient light and content recognition according to claims 1-5, characterized in that, It also includes a user physiological monitoring and feedback control mechanism, which specifically includes: During the color temperature adjustment process, the user's physiological feedback parameters are monitored in real time, including the pupil diameter change rate and blink frequency. When the pupil contraction rate is detected to exceed the threshold, the current color temperature compensation intensity is automatically reduced. A feedback learning mechanism is established to store the correlation between user physiological response data and color temperature adjustment parameters in a historical database, which is used to optimize the visual comfort model.

7. A display color temperature dynamic optimization system based on ambient light and content recognition, characterized in that, The method for dynamically optimizing display color temperature based on ambient light and content recognition as described in any one of claims 1-5 specifically includes: The ambient light sensing module is configured to acquire ambient light parameters, including ambient light color temperature and intensity, in real time. The content analysis module is configured to determine the type and feature distribution of the displayed content through image recognition. The reference color temperature calculation module includes a support vector machine model, configured to generate a mapping relationship between ambient light parameters and reference color temperature based on historical user data; The dynamic compensation engine is configured to calculate an initial compensation value based on the difference between the reference color temperature and the ambient light color temperature, and then adjust it according to the content type in combination with the visual comfort model. Text content is given a 1.2-1.5 times cool color temperature compensation weight, while image content is subject to color temperature smooth transition constraints. The region optimization module is configured to generate a color temperature influence factor matrix of ambient light and content features through convolution operations, and iteratively solve the optimal weight allocation of the display area based on the adaptive particle swarm algorithm. The zone control module includes an N×M independent color temperature control circuit array, configured to drive the backlight module to perform zoned color temperature adjustment, while satisfying the color temperature difference between adjacent units. Spatial constraints and temporal constraints where the rate of change of color temperature in a single adjustment is lower than the human eye's perception threshold.

8. The display color temperature dynamic optimization system based on ambient light and content recognition according to claim 7, characterized in that, The system further includes a physiological monitoring feedback module for implementing the user physiological monitoring feedback control mechanism as described in claim 6, wherein the physiological monitoring feedback module specifically includes: A physiological monitoring unit is used to monitor user physiological feedback parameters in real time during color temperature adjustment, including pupil diameter change rate and blink frequency; A feedback adjustment unit is used to automatically reduce the current color temperature compensation intensity when the pupil contraction rate is detected to exceed a threshold. An adaptive learning unit is used to establish a feedback learning mechanism, which stores the correlation between user physiological response data and color temperature adjustment parameters in a historical database to optimize the visual comfort model.

9. An electronic device, characterized in that, include: At least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the display color temperature dynamic optimization method based on ambient light and content recognition as described in any one of claims 1-6.

10. A computer-readable storage medium storing computer-readable instructions, characterized in that, When the computer-readable instructions are executed by the processor, they implement the display color temperature dynamic optimization method based on ambient light and content recognition as described in any one of claims 1-6.

Images