Adaptive brightness adjustment eye protection screen

Abstract

This invention belongs to the field of screens, specifically an adaptive brightness adjustment eye-protection screen. It includes the screen itself, and further comprises: an environment sensing module, a user behavior analysis module, a machine learning engine module, an integrated eye-protection algorithm module, a central processing module, and a display screen module. The environment sensing module integrates multiple environmental sensors to collect and fuse environmental data in real time, identifying user scenarios and achieving comprehensive and accurate perception of the usage environment, providing reliable environmental and scenario data support for system brightness adjustment. The user behavior analysis module connects to the environment sensing module and collects user behavior data. This invention is rationally designed, employing a progressive brightness adjustment algorithm to achieve smooth brightness transitions, avoiding abrupt brightness changes, conforming to the human visual adaptation pattern, and improving user comfort. Through intelligent predictive adjustment, it pre-adapts to user needs without manual intervention, while also supporting user-defined adjustments, balancing convenience and personalization.

Description

Technical Field

[0001] This invention relates to the field of screen technology, and more particularly to an adaptive brightness adjustment eye-protection screen. Background Technology

[0002] Currently, the main brightness adjustment methods on the market are manual adjustment, traditional automatic adjustment, and basic eye protection mode. Among them, manual adjustment is cumbersome and cannot adapt to changes in ambient light in real time.

[0003] Existing display screens have many defects in brightness adjustment, which seriously affect users' eye health and user experience. The specific problems are as follows: manual adjustment is not precise enough and cannot adapt to the dynamic changes in ambient light in real time, causing users to need to make frequent manual adjustments in different scenarios, which is cumbersome.

[0004] Setting the brightness to a fixed level in different lighting conditions, such as strong light or weak light, can easily irritate the eyes or cause blurred vision, and long-term use can lead to eye fatigue.

[0005] When used at night, the screen emits strong blue light, which can interfere with the body's biological rhythm. Long-term exposure can damage vision and affect sleep quality.

[0006] Sudden brightness changes are common and can easily cause visual fatigue and discomfort, which does not conform to the human visual adaptation pattern. Therefore, we proposed an adaptive brightness adjustment eye-protection screen to solve the above problems. Summary of the Invention

[0007] The purpose of this invention is to address the shortcomings of existing technologies by proposing an adaptive brightness adjustment eye-protection screen.

[0008] To achieve the above objectives, the present invention adopts the following technical solution:

[0009] The adaptive brightness adjustment eye-protection screen includes the screen itself, as well as: an environment sensing module, a user behavior analysis module, a machine learning engine module, an integrated eye-protection algorithm module, a central processing module, and a display screen module. The environment sensing module integrates multiple environmental sensors to collect and process environmental data in real time, identify user scenarios, and achieve comprehensive and accurate perception of the usage environment, providing reliable environmental and scenario data support for system brightness adjustment. The user behavior analysis module connects to the environment sensing module and collects user behavior data, providing user-dimensional data support for personalized brightness adjustment and algorithm optimization, enabling the adjustment scheme to adapt to user habits. The machine learning engine module receives environmental and user behavior data, analyzes user scenarios, eye health status, and usage habits, optimizes relevant algorithm parameters, and achieves continuous iterative improvement in system adjustment accuracy. The integrated eye-protection algorithm module… Based on optimized algorithm parameters, multiple eye protection and adjustment algorithms are integrated to generate precise brightness and blue light ratio adjustment instructions, achieving a balance between eye protection, color fidelity, and visual comfort. The central processing module, as the core control hub of the system, coordinates the collaborative work of various modules, receives and verifies various data and adjustment instructions, ensuring the orderly and efficient operation of the adjustment process. The brightness adjustment module receives control instructions and precisely adjusts the screen brightness and blue light filter ratio to achieve a smooth brightness transition and avoid visual discomfort caused by sudden brightness changes. The display screen module presents the adjusted display effect, provides real-time feedback on screen status data, provides feedback support for algorithm optimization, and ensures a balance between display effect and eye protection needs.

[0010] In this embodiment, the environmental perception module includes an integrated ambient light sensor, a color temperature sensor, and a distance sensor. The environmental data collected includes ambient light intensity, ambient color temperature, and the viewing distance between the user and the screen. The collection frequency is 100ms / time. A weighted fusion mechanism is used to allocate dynamic weights based on the real-time confidence of each sensor data source to generate a brightness adjustment feature set.

[0011] The formula for the weighted fusion algorithm is:

[0012] in: This is the combined value of the fused brightness adjustment feature set. , , These are the dynamic weights for ambient light intensity, color temperature, and viewing distance, respectively. , The ambient light intensity is the measured value (unit: lux). Color temperature (unit: K) is the measured value. Viewing distance data (unit: cm).

[0013] In this embodiment, the user behavior analysis module can analyze user behavior data, including user viewing time, blinking frequency, and manual adjustment preferences. The collected data is synchronously transmitted to the machine learning engine module to provide precise support for personalized adjustment and algorithm optimization.

[0014] In this embodiment, a dynamic brightness adjustment index table is built within the machine learning engine module. Based on the environmental change triggering mechanism, the node attributes and edge association strength are updated in real time. Scene recognition is achieved through machine learning algorithms, and the recognized scenes include, but are not limited to, reading, video, and games.

[0015] In this embodiment, the integrated algorithm includes an intelligent eye protection algorithm, a content adaptive algorithm, and a progressive brightness adjustment algorithm; wherein, the intelligent eye protection algorithm includes a brightness adjustment curve based on biological rhythms, dynamic blue light filtering technology, and an eye fatigue detection algorithm;

[0016] Dynamic blue light filtering technology uses zoned blue light suppression coefficients Calculate the adjustment parameters. ,in This is the physiological weighting coefficient, and 0.5 ≤ ≤0.8, where apupil is the real-time pupil area, amax is the maximum pupil area, and tview is the continuous viewing duration. Let be the time decay constant, and 1h ≤ With a duration of ≤3 hours, the peak wavelength of the blue light chip can be controlled at 460–470nm. The eye fatigue detection algorithm assesses the user's eye fatigue level by collecting data such as blink frequency and viewing time.

[0017] In this embodiment, the content adaptive algorithm includes image content analysis, scene optimization algorithm, and color fidelity technology. Image content analysis can identify the type of content displayed on the screen (including text, images, and videos), extract features such as grayscale level and brightness distribution of the content, and determine the gamma value corresponding to the grayscale level of each image. The scene optimization algorithm provides the optimal brightness configuration for different content types. The color fidelity technology uses a perovskite quantum dot stabilization layer to control the emission wavelength shift within ±2nm, while correcting color deviation through a color compensation algorithm.

[0018] The color compensation algorithm formula is:

[0019]

[0020]

[0021] ;

[0022] in, , , The red, green, and blue channel pixel values ​​after compensation. , , The original pixel values ​​before compensation. , , Standard color pixel values, , , This is the color compensation coefficient.

[0023] In this embodiment, the progressive adjustment algorithm adopts a linear transition algorithm with a brightness transition speed of 0.3-1 cd / m² / s. It supports user-defined adjustment speed and amplitude, and at the same time constructs a time-domain flicker hysteresis bandwidth to suppress brightness jitter.

[0024] The formula for the linear transition algorithm is:

[0025] in: for Screen brightness value at any given time (unit: cd / m²). To adjust the initial time brightness value, Lightness transition speed (unit: cd / m² / s). For real-time timing during the adjustment process;

[0026] The formula for calculating the time-domain scintillation bandwidth is:

[0027] Among them, For hysteresis bandwidth, This is an adjustment coefficient (with a value of 0.05-0.1). The standard deviation of historical brightness values;

[0028] The algorithm also features timed adjustment and intelligent predictive adjustment functions.

[0029] In this embodiment, the screen display module is equipped with a feedback unit, and the feedback status data includes the current brightness and blue light filtering ratio, and the user can manually fine-tune the feedback data.

[0030] In this embodiment, the status data fed back by the screen display module and the user's manual fine-tuning feedback data continuously optimize the algorithm parameters of the integrated eye protection algorithm module to achieve intelligent predictive adjustment.

[0031] In this embodiment, the brightness prediction algorithm uses an LSTM model based on a temporal attention mechanism, and its core prediction formula is as follows:

[0032]

[0033] in, for Predicted brightness value at time. To predict lead time, for Historical brightness values ​​at any given time for Comprehensive environmental parameters at any given time;

[0034] for The comprehensive environmental parameters at any given time are obtained by weighted calculation of ambient light intensity and color temperature:

[0035]

[0036] in, , These are the weighting coefficients, and , For ambient light intensity, For ambient color temperature; The user behavior feature parameters at time t are obtained by normalizing viewing duration, blink frequency, and manual adjustment preference. , , is the weight coefficient obtained from model training, and b is the bias term; the model updates the weight coefficient in real time through brightness fine-tuning data fed back by users, iteratively optimizes the prediction accuracy, and ensures that the deviation between the predicted brightness and the user's actual needs does not exceed 5cd / m².

[0037] The beneficial effects of this invention are:

[0038] 1. Significant eye protection effect: Through dynamic blue light filtering, eye fatigue detection and biorhythm adaptation, it effectively reduces harmful blue light radiation, relieves eye fatigue, reduces the risk of vision damage, and avoids interference with the body's biorhythm.

[0039] 2. High adjustment accuracy: Combining environmental perception, user behavior analysis and machine learning optimization, it achieves adaptive adjustment of three dimensions: environment, content and user. The adjustment parameters can be iteratively optimized in real time to adapt to the personalized needs of different scenarios and different users.

[0040] 3. High visual comfort: It adopts a progressive brightness adjustment algorithm to achieve a smooth brightness transition, avoid sudden brightness changes, conform to the human visual adaptation law, and improve the user comfort.

[0041] 4. High level of intelligence: Through intelligent prediction and adjustment function, it adapts to user needs in advance without the need for manual intervention by the user. At the same time, it supports user-customized adjustment, taking into account both convenience and personalization. Attached Figure Description

[0042] Figure 1 This is a three-dimensional structural diagram of the adaptive brightness adjustment eye-protection screen proposed in this invention;

[0043] Figure 2 This is a block diagram of the adaptive brightness adjustment eye-protection screen proposed in this invention;

[0044] Figure 3 This is a block diagram of the environmental perception module for the adaptive brightness adjustment eye-protection screen proposed in this invention;

[0045] Figure 4 This is a flowchart illustrating the workflow of the adaptive brightness adjustment eye-protection screen proposed in this invention.

[0046] In the image: 1. The screen itself. Detailed Implementation

[0047] The following is in conjunction with the appendix Figure 1-4 This application will be described in further detail.

[0048] This application discloses an adaptive brightness adjustment eye-protection screen.

[0049] Reference Figure 1-4The adaptive brightness adjustment eye-protection screen includes the screen body 1, and also includes: an environment sensing module, a user behavior analysis module, a machine learning engine module, an integrated eye-protection algorithm module, a central processing module, and a display screen module. The environment sensing module is connected to the central processing module and the user behavior analysis module, while the brightness adjustment module is connected to the central processing module, the integrated algorithm module, and the screen display module. The machine learning engine module is also connected to the user behavior analysis and integrated algorithm modules. The environment sensing module integrates multiple environmental sensors to collect and fuse environmental data in real time, identify user scenarios, and achieve comprehensive and accurate perception of the usage environment, providing reliable environmental and scenario data support for system brightness adjustment. The user behavior analysis module connects to the environment sensing module and collects user behavior data, providing user-dimensional data support for personalized brightness adjustment and algorithm optimization, enabling the adjustment scheme to adapt to user habits. The machine learning engine module receives environmental data and user behavior data, analyzes user scenarios, eye health status, and usage habits, optimizes relevant algorithm parameters, and achieves continuous iterative improvement in system adjustment accuracy. The integrated eye-protection algorithm... The system comprises several modules: a central processing module and a central processing module. The central processing module, based on optimized algorithm parameters, integrates multiple eye protection and adjustment algorithms to generate precise brightness and blue light ratio adjustment commands, achieving a balance between eye protection, color fidelity, and visual comfort. The central processing module, acting as the core control hub, coordinates the collaborative work of all modules, receives various data and adjustment commands, verifies and issues them, ensuring the orderly and efficient operation of the adjustment process. The brightness adjustment module receives control commands and precisely adjusts the screen brightness and blue light filter ratio, achieving a smooth brightness transition and avoiding visual discomfort caused by sudden brightness changes. The display screen module presents the adjusted display effect, provides real-time feedback on screen status data, and provides feedback support for algorithm optimization, ensuring a balance between display effect and eye protection needs.

[0050] In this embodiment, the environmental perception module includes an integrated ambient light sensor, a color temperature sensor, and a distance sensor. The environmental data collected includes ambient light intensity, ambient color temperature, and the viewing distance between the user and the screen. The collection frequency is 100ms / time. A weighted fusion mechanism is used to assign dynamic weights based on the real-time confidence of each sensor data source to generate a brightness adjustment feature set.

[0051] The formula for the weighted fusion algorithm is:

[0052] in: This is the combined value of the fused brightness adjustment feature set. , , These are the dynamic weights for ambient light intensity, color temperature, and viewing distance, respectively. , The ambient light intensity is the measured value (unit: lux). Color temperature (unit: K) is the measured value. Viewing distance data (unit: cm).

[0053] In this embodiment, the user behavior analysis module can analyze user behavior data, including user viewing time, blinking frequency, and manual adjustment preferences. The collected data is synchronously transmitted to the machine learning engine module to provide precise support for personalized adjustment and algorithm optimization.

[0054] In this embodiment, a dynamic brightness adjustment index table is built within the machine learning engine module. Based on the environmental change trigger mechanism, the node attributes and edge association strength are updated in real time. Scene recognition is achieved through machine learning algorithms, and the recognized scenes include, but are not limited to, reading, video, and games.

[0055] In this embodiment, the integrated algorithms include an intelligent eye protection algorithm, a content adaptive algorithm, and a progressive brightness adjustment algorithm; wherein, the intelligent eye protection algorithm includes a brightness adjustment curve based on biological rhythms, dynamic blue light filtering technology, and an eye fatigue detection algorithm;

[0056] Dynamic blue light filtering technology uses zoned blue light suppression coefficients Calculate the adjustment parameters. ,in This is the physiological weighting coefficient, and 0.5 ≤ ≤0.8, where apupil is the real-time pupil area, amax is the maximum pupil area, and tview is the continuous viewing duration. Let be the time decay constant, and 1h ≤ For viewing times ≤3 hours, the peak wavelength of the blue light chip can be controlled at 460–470nm. An eye fatigue detection algorithm assesses the user's eye fatigue level by collecting data such as blink frequency and viewing duration. A preset circadian rhythm curve is used, with the blue light filtering ratio gradually increasing from 30% to 60% and the brightness gradually decreasing from 500cd / m² to 50cd / m² between 22:00 and 7:00 the next day. In dynamic blue light filtering technology… The value is 0.6. The peak wavelength of the blue light chip is controlled at 460–470nm by setting a value of 2h. The eye fatigue detection algorithm assesses the user's fatigue state by blinking frequency and viewing time, and continuous viewing for more than 1 hour is judged as fatigue.

[0057] In this embodiment, the content adaptive algorithm includes image content analysis, scene optimization algorithm, and color fidelity technology. Image content analysis can identify the type of content displayed on the screen (including text, images, and videos), extract features such as grayscale level and brightness distribution of the content, and determine the gamma value corresponding to the grayscale level of each image. The scene optimization algorithm provides the optimal brightness configuration for different content types. The color fidelity technology uses a perovskite quantum dot stabilization layer to control the emission wavelength shift within ±2nm, while correcting color deviation through a color compensation algorithm.

[0058] The color compensation algorithm formula is:

[0059]

[0060]

[0061] ;

[0062] in, , , The red, green, and blue channel pixel values ​​after compensation. , , The original pixel values ​​before compensation. , , Standard color pixel values, , , For color compensation coefficients, the image recognition algorithm identifies content type in real time. Text content brightness is controlled at 100-200 cd / m², video content brightness is dynamically adjusted based on screen brightness (adjustment range 50-500 cd / m²), and image content brightness is controlled at 200-300 cd / m². , , The value ranges from 0.1 to 0.3, and is dynamically adjusted according to the blue light filtering ratio to ensure color fidelity.

[0063] In this embodiment, the progressive adjustment algorithm adopts a linear transition algorithm with a brightness transition speed of 0.3-1 cd / m² / s. It supports user-defined adjustment speed and amplitude, and at the same time constructs a time-domain flicker hysteresis bandwidth to suppress brightness jitter.

[0064] The formula for the linear transition algorithm is:

[0065] in: for Screen brightness value at any given time (unit: cd / m²). To adjust the initial time brightness value, Lightness transition speed (unit: cd / m² / s). For real-time timing during the adjustment process;

[0066] The formula for calculating the time-domain scintillation bandwidth is:

[0067] Among them, For hysteresis bandwidth, This is an adjustment coefficient (with a value of 0.05-0.1). The standard deviation of historical brightness values;

[0068] The algorithm also features timed adjustment and intelligent predictive adjustment. It employs a linear transition algorithm to construct a time-domain flicker hysteresis bandwidth with k set to 0.08, thus suppressing brightness jitter. It supports user-defined adjustment speed and amplitude, and also features timed adjustment, allowing users to set the time for brightness adjustment.

[0069] In this embodiment, a feedback unit is provided in the screen display module. The feedback status data includes the current brightness and blue light filtering ratio, and the user can manually fine-tune the feedback data.

[0070] In this embodiment, the status data fed back by the screen display module and the user's manual fine-tuning feedback data continuously optimize the algorithm parameters of the integrated eye protection algorithm module to achieve intelligent predictive adjustment. The brightness prediction algorithm adopts an LSTM model based on a temporal attention mechanism, and its core prediction formula is as follows:

[0071]

[0072] in, for Predicted brightness value at time. To predict lead time, for Historical brightness values ​​at any given time for Comprehensive environmental parameters at any given time;

[0073] for The comprehensive environmental parameters at any given time are obtained by weighted calculation of ambient light intensity and color temperature:

[0074]

[0075] in, , These are the weighting coefficients, and , For ambient light intensity, For ambient color temperature; The user behavior feature parameters at time t are obtained by normalizing viewing duration, blink frequency, and manual adjustment preference. , , is the weight coefficient obtained from model training, and b is the bias term; the model updates the weight coefficient in real time through brightness fine-tuning data fed back by users, iteratively optimizes the prediction accuracy, and ensures that the deviation between the predicted brightness and the user's actual needs does not exceed 5cd / m².

[0076] The workflow of this invention is as follows: The environmental perception module collects data on ambient light intensity, color temperature, and viewing distance between the user and the screen in real time. After weighted fusion processing, it generates a brightness adjustment feature set. At the same time, it identifies the user's usage scenario (such as WeChat text chat, which is determined to be a reading scenario). The feature set and scenario analysis results are then transmitted to the central processing module.

[0077] The user behavior analysis module collects the user's blink frequency (18 times / minute, which is considered normal) and viewing duration, and transmits them synchronously to the machine learning engine module.

[0078] The machine learning engine module combines environmental data and user behavior data to analyze the user's current usage scenario as reading and with normal eye condition, optimizes the parameters of the integrated eye protection algorithm module, and transmits them to the integrated eye protection algorithm module.

[0079] The integrated eye protection algorithm module generates adjustment instructions based on optimized parameters: brightness is adjusted to 150 cd / m², blue light filtering ratio is 20%, and the adjustment is gradually made through a linear transition algorithm and transmitted to the central processing module.

[0080] After verifying the adjustment command, the central processing module sends it to the brightness adjustment module;

[0081] The brightness adjustment module executes instructions to adjust the screen brightness and blue light filter ratio, smoothly transitioning at a speed of 0.5 cd / m² / s to avoid sudden brightness changes;

[0082] The display screen module presents the adjusted display effect, and the feedback unit collects the current brightness and blue light filtering ratio data in real time, transmits it to the central processing module, and then transmits it to the machine learning engine module.

[0083] The machine learning engine module continuously optimizes algorithm parameters based on feedback data. After a user watches continuously for 1 hour, the eye fatigue detection algorithm determines that the user is fatigued and generates a new adjustment instruction by integrating the eye protection algorithm module: adjust the brightness to 120cd / m², increase the blue light filtering ratio to 30%, and pop up a rest reminder.

[0084] If the user manually fine-tunes the brightness to 130 cd / m², the feedback unit collects the fine-tuning data and transmits it to the machine learning engine module. The model updates the weight coefficients, and the subsequent brightness prediction will be adapted to the user's manual adjustment preference to ensure that the adjustment is more in line with the user's needs.

[0085] The above are all preferred embodiments of this application, and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the structure, shape and principle of this application should be covered within the scope of protection of this application.

Claims

1. An adaptive brightness adjustment eye-protection screen, comprising a screen body (1), characterized in that, Also includes: The environmental perception module integrates multiple environmental sensors to collect and fuse environmental data in real time, identify user scenarios, and achieve comprehensive and accurate perception of the usage environment, providing reliable environmental and scenario data support for system brightness adjustment. The user behavior analysis module connects to the environmental perception module and collects user behavior data, providing user-dimensional data support for personalized brightness adjustment and algorithm optimization, and enabling the adjustment scheme to adapt to user habits. The machine learning engine module receives environmental data and user behavior data, analyzes user scenarios, eye health status and usage habits, optimizes relevant algorithm parameters, and achieves continuous iterative improvement of the system's adjustment accuracy. An integrated eye protection algorithm module, based on optimized algorithm parameters, integrates multiple eye protection and adjustment algorithms to generate precise brightness and blue light ratio adjustment instructions, achieving a balance between eye protection effect, color fidelity and visual comfort; The central processing module, as the core control hub of the system, coordinates the collaborative work of various modules, receives various data and adjustment instructions, verifies and issues them, and ensures the orderly and efficient operation of the adjustment process. The brightness adjustment module receives control commands and precisely adjusts the screen brightness and blue light filter ratio to achieve a smooth brightness transition and avoid visual discomfort caused by sudden brightness changes. The display screen module presents the adjusted display effect, provides real-time feedback on screen status data, provides feedback support for algorithm optimization, and ensures a balance between display effect and eye protection needs.

2. The adaptive brightness adjustment eye-protection screen according to claim 1, characterized in that, The environmental perception module includes an integrated ambient light sensor, a color temperature sensor, and a distance sensor. The environmental data collected includes ambient light intensity, ambient color temperature, and the viewing distance between the user and the screen. The collection frequency is 100ms / time. A weighted fusion mechanism is used to assign dynamic weights based on the real-time confidence of each sensor data source to generate a brightness adjustment feature set. The formula for the weighted fusion algorithm is: in: This is the combined value of the fused brightness adjustment feature set. , , These are the dynamic weights for ambient light intensity, color temperature, and viewing distance, respectively. , The ambient light intensity is the measured value (unit: lux). Color temperature (unit: K) is the measured value. Viewing distance data (unit: cm).

3. The adaptive brightness adjustment eye-protection screen according to claim 2, characterized in that, The user behavior analysis module can analyze user behavior data, including user viewing time, blinking frequency, and manual adjustment preferences. The collected data is synchronously transmitted to the machine learning engine module to provide precise support for personalized adjustment and algorithm optimization.

4. The adaptive brightness adjustment eye-protection screen according to claim 3, characterized in that, The machine learning engine module constructs a dynamic brightness adjustment index table, and updates node attributes and edge association strength in real time based on an environmental change trigger mechanism. Scene recognition is achieved through machine learning algorithms, and the recognized scenes include, but are not limited to, reading, video, and games.

5. The adaptive brightness adjustment eye-protection screen according to claim 4, characterized in that, The integrated algorithms include an intelligent eye protection algorithm, a content adaptive algorithm, and a progressive brightness adjustment algorithm. The intelligent eye protection algorithm includes a brightness adjustment curve based on biological rhythms, dynamic blue light filtering technology, and an eye fatigue detection algorithm. The dynamic blue light filtering technology employs a zoned blue light suppression coefficient. Calculate the adjustment parameters. ,in This is the physiological weighting coefficient, and 0.5 ≤ ≤0.8, where apupil is the real-time pupil area, amax is the maximum pupil area, and tview is the continuous viewing duration. Let be the time decay constant, and 1h ≤ With a duration of ≤3 hours, the peak wavelength of the blue light chip can be controlled at 460–470nm. The eye fatigue detection algorithm assesses the user's eye fatigue level by collecting data such as blink frequency and viewing time.

6. The adaptive brightness adjustment eye-protection screen according to claim 5, characterized in that, The content adaptive algorithm includes image content analysis, scene optimization algorithm, and color fidelity technology. Image content analysis can identify the type of content displayed on the screen (including text, images, and videos), extract features such as grayscale level and brightness distribution of the content, and determine the gamma value corresponding to the grayscale level of each image. The scene optimization algorithm provides the optimal brightness configuration for different content types. The color fidelity technology uses a perovskite quantum dot stabilization layer to control the emission wavelength shift within ±2nm, while correcting color deviation through a color compensation algorithm. The color compensation algorithm formula is: ; in, , , The red, green, and blue channel pixel values ​​after compensation. , , The original pixel values ​​before compensation. , , Standard color pixel values, , , This is the color compensation coefficient.

7. The adaptive brightness adjustment eye-protection screen according to claim 6, characterized in that, The progressive adjustment algorithm adopts a linear transition algorithm with a brightness transition speed of 0.3-1 cd / m² / s. It supports user-defined adjustment speed and amplitude, and constructs a time-domain flicker hysteresis bandwidth to suppress brightness jitter. The formula for the linear transition algorithm is: in: for Screen brightness value at any given time (unit: cd / m²). To adjust the initial time brightness value, Lightness transition speed (unit: cd / m² / s). For real-time timing during the adjustment process; The formula for calculating the time-domain scintillation bandwidth is: Among them, For hysteresis bandwidth, This is an adjustment coefficient (with a value of 0.05-0.1). The standard deviation of historical brightness values; The algorithm also features timed adjustment and intelligent predictive adjustment functions.

8. The adaptive brightness adjustment eye-protection screen according to claim 7, characterized in that, The screen display module is equipped with a feedback unit, and the feedback status data includes the current brightness and blue light filtering ratio. The user can manually fine-tune the feedback data.

9. The adaptive brightness adjustment eye-protection screen according to claim 8, characterized in that, The status data fed back by the screen display module and the feedback data from the user's manual fine-tuning continuously optimize the algorithm parameters of the integrated eye protection algorithm module, thereby achieving intelligent predictive adjustment.

10. The adaptive brightness adjustment eye-protection screen according to claim 9, characterized in that, The brightness prediction algorithm uses an LSTM model based on a temporal attention mechanism, and its core prediction formula is as follows: in, for Predicted brightness value at time. To predict lead time, for Historical brightness values ​​at any given time for Comprehensive environmental parameters at any given time; for The comprehensive environmental parameters at any given time are obtained by weighted calculation of ambient light intensity and color temperature: in, , These are the weighting coefficients, and , For ambient light intensity, For ambient color temperature; The user behavior feature parameters at time t are obtained by normalizing viewing duration, blink frequency, and manual adjustment preference. , , is the weight coefficient obtained from model training, and b is the bias term; the model updates the weight coefficient in real time through brightness fine-tuning data fed back by users, iteratively optimizes the prediction accuracy, and ensures that the deviation between the predicted brightness and the user's actual needs does not exceed 5cd / m².

Images