Liquid crystal display panel control method and system based on artificial intelligence

Abstract

The present invention proposes a liquid crystal display panel control method and system based on artificial intelligence, the method comprising: using a high-resolution camera to capture a user's facial image, extracting and identifying facial features through a deep learning algorithm, and estimating the user's age; adjusting the blue light of the liquid crystal display panel based on the estimated user age, ambient light brightness, time, user's geographical location, and the type of application used by the user; after adjusting the blue light of the liquid crystal display panel, obtaining user feedback, training a deep learning model based on the user feedback, and adaptively adjusting the blue light of the liquid crystal display panel to suit the user's needs based on the trained deep learning model; after adaptive adjustment, collecting the user's new manual adjustment record, updating the data set, and retraining the deep learning model using the updated data set. Through this method and the corresponding system, the blue light output can be dynamically adjusted according to the usage time and the user's personal preferences.

Description

Technical Field

[0001] The invention proposes a liquid crystal display panel control method and system based on artificial intelligence, and relates to the field of display screen control. Background Art

[0002] With the advent of the digital age, liquid crystal display panels (LCDs) have become an integral part of our daily lives, appearing almost everywhere from smartphones and laptops to large flat-panel displays. However, the blue light emitted by screens during use is believed to be a major factor causing eye fatigue and digital vision syndrome.

[0003] However, traditional LCDs have limitations in blue light control, and cannot be intelligently adjusted according to the user's specific usage scenario and personal age. For example, when a user uses the device at home at night, the ideal blue light intensity should be softer than when used in the office during the day to reduce the potential impact on sleep quality. In addition, traditional technology also ignores the user's personalized blue light comfort needs, because different users have different sensitivities and acceptance of blue light. Therefore, a more intelligent blue light adjustment system that can dynamically adjust blue light output based on ambient light, usage time and user's personal preferences will greatly improve user experience and visual health. Summary of the invention

[0004] The present invention provides a liquid crystal display panel control method and system based on artificial intelligence to solve the above-mentioned problems:

[0005] The present invention proposes a liquid crystal display panel control method based on artificial intelligence, the method comprising:

[0006] Use a high-resolution camera to capture the user's facial image, extract and recognize facial features through a deep learning algorithm, and estimate the user's age;

[0007] Adjusting the blue light of the LCD panel based on the estimated age of the user, ambient light level, time of day, the user's geographic location, and the type of applications the user is using;

[0008] After adjusting the blue light of the liquid crystal display panel, obtaining user feedback, training a deep learning model according to the user feedback, and adaptively adjusting the blue light of the liquid crystal display panel to suit the user's needs based on the trained deep learning model;

[0009] After adaptive adjustment, new manual adjustment records of users are collected, the data set is updated, and the deep learning model is retrained using the updated data set.

[0010] Furthermore, a high-resolution camera is used to capture the user's facial image, and facial features are extracted and recognized through a deep learning algorithm to estimate the user's age, including:

[0011] Using a high-resolution camera to capture a user's facial image, and preprocessing the captured user's facial image, wherein the preprocessing includes grayscale conversion, mean normalization, and denoising;

[0012] Using a face detection algorithm to detect the face area from the preprocessed face image;

[0013] The detected face area is cropped and scaled to a specified size, and the pre-trained deep convolutional neural network model VGG-Face is used to extract deep features from the cropped and scaled face area;

[0014] The extracted deep features are converted into feature vectors and input into the pre-trained face recognition neural network model to obtain the user age estimation result.

[0015] Further, adjusting the blue light of the liquid crystal display panel based on the estimated user age, time, user geographic location, and type of application used by the user includes:

[0016] The liquid crystal display panel obtains the user's geographical location and time through the GPS device of the connected host device;

[0017] The liquid crystal display panel monitors the type of application used by the user of the current active window through a monitoring program in the operating system of the connected host;

[0018] The blue light of the liquid crystal display panel is adjusted based on the estimated user age, time, user geographic location, and user application type. The adjustment range of the blue light of the liquid crystal display panel is calculated by a blue light adjustment model. Specifically, the blue light adjustment model is:

[0019] ;

[0020] in, represents the blue light regulation factor, Indicates the basic blue light output value, represents the application type factor, represents the geographical location factor, Indicates the user's age. Indicates the base age, represents the age coefficient, represents the age constant, represents the age weight, represents the usage time weight, Indicates the maximum time of a day, Indicates the time the user uses the device;

[0021] Based on the calculated blue light adjustment factor, the blue light is adjusted to an adjustment ratio relative to the original blue light intensity.

[0022] Further, after adjusting the blue light of the liquid crystal display panel, obtaining user feedback, training a deep learning model according to the user feedback, and adaptively adjusting the blue light of the liquid crystal display panel to suit the user's needs based on the trained deep learning model, including:

[0023] Adjusting the blue light output intensity of the liquid crystal display panel according to the blue light adjustment model, monitoring and recording when and under what circumstances the user manually adjusts the blue light intensity, and recording the blue light intensity values ​​before and after the adjustment and context information, wherein the context information includes: time, ambient light, application type, and user's geographic location;

[0024] Cleaning historical manual adjustment records, removing invalid and erroneous adjustment records, and extracting features from the manual adjustment records from which erroneous records have been removed, wherein the features include adjustment time, adjustment amplitude, ambient light intensity, and currently used application;

[0025] Build a deep learning model LSTM model, where the input layer receives the extracted features and the output layer predicts the blue light intensity adjustment value that the user wants;

[0026] Use historical manual adjustment data to preliminarily train the model and learn the user's blue light adjustment preferences.

[0027] Collect context information in real time during user use, including time, ambient light, application type, and user's geographic location;

[0028] The data collected in real time is input into the trained deep learning model LSTM model to predict the blue light intensity desired by the user, and the blue light intensity of the LCD display panel is automatically adjusted based on the model's prediction results.

[0029] Furthermore, after the adaptive adjustment, new manual adjustment records of the user are collected, the data set is updated, and the deep learning model is retrained using the updated data set, including:

[0030] When the user is still not satisfied with the automatically adjusted blue light intensity and adjusts it manually again, the new adjustment data is recorded and added to the training data set for incremental update of the model;

[0031] Retrain the deep learning model using the updated dataset.

[0032] The present invention proposes an artificial intelligence-based liquid crystal display panel control system, the system comprising:

[0033] The user age estimation module is used to capture the user's facial image using a high-resolution camera, extract and recognize facial features through a deep learning algorithm, and estimate the user's age;

[0034] a preliminary adjustment module for adjusting the blue light of the liquid crystal display panel based on an estimated user age, time, user geographic location, and type of application used by the user;

[0035] An adaptive adjustment module, used to obtain user feedback after adjusting the blue light of the liquid crystal display panel, train a deep learning model according to the user feedback, and adaptively adjust the blue light of the liquid crystal display panel based on the trained deep learning model to suit the user's needs;

[0036] The update training module is used to collect new manual adjustment records of users after adaptive adjustment, update the data set, and use the updated data set to retrain the deep learning model.

[0037] Furthermore, the module for estimating user age includes:

[0038] A user facial image capturing module is used to capture a user facial image using a high-resolution camera and perform preprocessing on the captured user facial image, wherein the preprocessing includes grayscale conversion, mean normalization and denoising;

[0039] A face detection module, used to detect a face area from a preprocessed facial image using a face detection algorithm;

[0040] The feature extraction module is used to crop the detected face area and scale it to a specified size, and use the pre-trained deep convolutional neural network model VGG-Face to extract deep features from the cropped and scaled face area;

[0041] The estimation module is used to convert the extracted deep-level features into feature vectors and input them into the pre-trained face recognition neural network model to obtain the user age estimation result.

[0042] Furthermore, the preliminary adjustment module includes:

[0043] A module for obtaining geographic location and time, used for the liquid crystal display panel to obtain the user's geographic location and time through a GPS device of a connected host device;

[0044] An application monitoring module, used for the liquid crystal display panel to monitor the type of application used by the user of the current active window through a monitoring program in the operating system of the connected host;

[0045] The module for calculating the blue light adjustment ratio is used to adjust the blue light of the liquid crystal display panel based on the estimated user age, time, user geographical location and user application type. The adjustment range of the blue light of the liquid crystal display panel is calculated by a blue light adjustment model. Specifically, the blue light adjustment model is:

[0046] ;

[0047] in, represents the blue light regulation factor, Indicates the basic blue light output value, represents the application type factor, represents the geographical location factor, Indicates the user's age. Indicates the base age, represents the age coefficient, represents the age constant, represents the age weight, represents the usage time weight, Indicates the maximum time of a day, Indicates the time the user uses the device;

[0048] The adjustment module is used to adjust the blue light to an adjustment ratio relative to the original blue light intensity based on the calculated blue light adjustment factor.

[0049] Furthermore, the adaptive adjustment module includes:

[0050] Obtain a manual adjustment recording module, which is used to adjust the blue light output intensity of the liquid crystal display panel according to the blue light adjustment model, monitor and record when and under what circumstances the user manually adjusts the blue light intensity, and record the blue light intensity value before and after the adjustment and context information, wherein the context information includes: time, ambient light, application type, and user's geographical location;

[0051] A cleaning module, used to clean the historical manual adjustment records, remove invalid and erroneous adjustment records, and extract features from the manual adjustment records without erroneous records, wherein the features include adjustment time, adjustment amplitude, ambient light intensity, and currently used application;

[0052] Build a deep learning model module, which is used to build a deep learning model LSTM model. The input layer receives the extracted features, and the output layer predicts the blue light intensity adjustment value desired by the user;

[0053] A preliminary training module, used to perform preliminary training on the model using historical manual adjustment data, and to preliminarily learn the user's blue light adjustment preference;

[0054] A context information collection module is used to collect context information in real time during the user's use process, and the context information includes: time, ambient light, application type and user's geographical location;

[0055] The prediction module is used to input the real-time collected data into the trained deep learning model LSTM model to predict the blue light intensity desired by the user, and automatically adjust the blue light intensity of the LCD display panel according to the prediction results of the model.

[0056] Furthermore, the updating training module includes:

[0057] The update data set module is used to record the new adjustment data when the user is still not satisfied with the blue light intensity after automatic adjustment and adjusts it manually again, and add the new manual adjustment data to the training data set for incremental update of the model;

[0058] Retraining module, used to retrain the deep learning model using the updated dataset.

[0059] The beneficial effects of the present invention are as follows: improving user experience, adjusting screen blue light based on user's personalized needs, helping to improve visual comfort and reduce visual fatigue; blue light management for different age groups can reduce the potential health risks of blue light, such as eye damage and biorhythm interference; through machine learning and intelligent feedback mechanism, the system can continuously learn and adapt to individual needs, so that it can provide the best display effect in different situations; through intelligent management of blue light, unnecessary energy consumption is reduced, and at the same time, excessive color temperature is avoided. Interference with the user's biorhythm; with the continuous improvement and optimization of the model, user satisfaction will increase with the improvement of visual experience, encouraging longer-term use. The artificial intelligence-based LCD display panel control method is not only a blue light optimization tool, but also a comprehensive personalized display solution, combined with AI technology, to provide users with a healthy, safe and comfortable visual experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 A schematic diagram of an artificial intelligence-based liquid crystal display panel control method according to the present invention. DETAILED DESCRIPTION

[0061] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0062] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. The embodiments described are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0063] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0064] One embodiment of the present invention provides a liquid crystal display panel control method based on artificial intelligence, the method comprising:

[0065] Use a high-resolution camera to capture the user's facial image, extract and recognize facial features through a deep learning algorithm, and estimate the user's age;

[0066] Adjusting the blue light of the LCD panel based on the estimated age of the user, ambient light level, time of day, the user's geographic location, and the type of applications the user is using;

[0067] After adjusting the blue light of the liquid crystal display panel, obtaining user feedback, training a deep learning model according to the user feedback, and adaptively adjusting the blue light of the liquid crystal display panel to suit the user's needs based on the trained deep learning model;

[0068] After adaptive adjustment, new manual adjustment records of users are collected, the data set is updated, and the deep learning model is retrained using the updated data set.

[0069] The working principle and effect of the above technical solution are as follows: using a high-resolution camera to capture the user's facial image, applying a deep learning algorithm to extract facial features to estimate the user's age. Age estimation helps to personalize the adjustment of blue light output, because people of different ages have different sensitivity and needs for blue light; using an ambient light sensor to obtain the light brightness around the LCD panel in real time, and collect other information such as time, geographic location and application type. These data are combined to establish a comprehensive input vector for automatic adjustment of blue light output; dynamically adjust the blue light intensity and color temperature of the LCD panel through a deep learning model, taking into account factors such as the user's age, usage environment, time period, etc., so that the display effect is more suitable for personal biorhythms and preferences; collect user feedback, visual comfort scores, and manual adjustment history, and use these feedbacks to retrain the deep learning model to continuously optimize its prediction accuracy and adjustment effect; use the user's new manual adjustment records to update the data set to improve the universality and personalized response capabilities of the model; through a periodic retraining process, the model can adapt to changes in user habits and preferences. Improve user experience and adjust screen blue light based on user's personalized needs, which helps to improve visual comfort and reduce visual fatigue; blue light management for different age groups can reduce the potential health risks of blue light, such as eye damage and biorhythm interference; through machine learning and intelligent feedback mechanism, the system can continuously learn and adapt to individual needs, so that it can provide the best display effect in different situations; through intelligent management of blue light, reduce unnecessary energy consumption, and avoid excessive color temperature from interfering with user's biorhythm; with the continuous improvement and optimization of the model, user satisfaction will increase with the improvement of visual experience, encouraging longer-term use. The artificial intelligence-based LCD display panel control method is not only a blue light optimization tool, but also a comprehensive personalized display solution, combined with AI technology, to provide users with a healthy, safe and comfortable visual experience.

[0070] In one embodiment of the present invention, a high-resolution camera is used to capture a user's facial image, and facial feature extraction and recognition are performed through a deep learning algorithm to estimate the user's age, including:

[0071] Using a high-resolution camera to capture a user's facial image, and preprocessing the captured user's facial image, wherein the preprocessing includes grayscale conversion, mean normalization, and denoising;

[0072] Using a face detection algorithm to detect the face area from the preprocessed face image;

[0073] The detected face area is cropped and scaled to the specified size, and the pre-trained deep convolutional neural network model VGG-Face is used to extract deep features from the cropped and scaled face area;

[0074] The extracted deep features are converted into feature vectors and input into the pre-trained face recognition neural network model to obtain the user age estimation result.

[0075] The working principle and effect of the above technical solution are as follows: image preprocessing, grayscale conversion converts color facial images into grayscale images to reduce computational complexity while retaining important features of the image; mean normalization makes the image pixel values ​​within a uniform range by subtracting the mean and standardizing, so as to improve the stability and accuracy of the feature extraction model; uses filters (such as Gaussian filtering) to reduce image noise and enhance image quality, thereby improving the accuracy of facial feature extraction; uses face detection algorithms (such as Haar cascade classifiers or modern deep learning models MTCNN) to identify facial areas from preprocessed images;

[0076] Ensure reliable positioning and accurate detection even when the face is partially occluded or under different lighting conditions; crop the detected face area and scale it to a specified size (for example, 224x224 pixels) to adapt to the input requirements of the deep learning model; use the VGG-Face model to extract deep features from the processed face area. VGG-Face is a pre-trained deep convolutional neural network that is optimized for face recognition tasks and can effectively extract complex and recognizable features; convert the extracted deep features into feature vectors; input them into a pre-trained face recognition neural network model for analysis, and obtain the user's age estimation result through classification or regression mechanism. High accuracy. Deep learning models such as VGG-Face can efficiently distinguish different subtle facial features, thereby improving the accuracy of age estimation. The efficient algorithm and model structure enable the system to complete the entire age recognition process in a shorter time, which is suitable for real-time applications. Good robustness. Even under different shooting conditions (such as lighting changes, partial occlusion, etc.), the system can still effectively detect and recognize facial features. Personalized display adjustment. Based on the estimated age information, the system can better adjust the display device parameters for users, such as blue light intensity and color temperature optimization.

[0077] An embodiment of the present invention adjusts the blue light of a liquid crystal display panel based on an estimated user age, time, user geographic location, and type of application used by the user, including:

[0078] The liquid crystal display panel obtains the user's geographical location and time through the GPS device of the connected host device;

[0079] The liquid crystal display panel monitors the type of application used by the user of the current active window through a monitoring program in the operating system of the connected host;

[0080] The blue light of the liquid crystal display panel is adjusted based on the estimated user age, time, user geographic location, and user application type. The adjustment range of the blue light of the liquid crystal display panel is calculated by a blue light adjustment model. Specifically, the blue light adjustment model is:

[0081] ;

[0082] in, represents the blue light regulation factor, Indicates the basic blue light output value, represents the application type factor, represents the geographical location factor, Indicates the user's age. Indicates the base age, represents the age coefficient, represents the age constant, represents the age weight, represents the usage time weight, Indicates the maximum time of a day, Indicates the time the user uses the device;

[0083] Based on the calculated blue light adjustment factor, the blue light is adjusted to an adjustment ratio relative to the original blue light intensity.

[0084] The base age is set to 18 years old, and the location factor is set to different values ​​according to the user's current location.

[0085] At home: Generally, the lighting at home is relatively mild. To reduce eye irritation, offices usually have brighter artificial light sources and set Balanced blue light output, Outdoor: Light conditions vary, setting To adapt to stronger natural light.

[0086] Get the type of application used by the user. If the application type is entertainment, for comfort, lower blue light is usually required. Set If the application type is office reading or writing, moderate blue light is required to maintain high readability, set If the application type is design or color-sensitive work (such as image editing): high blue light is required to ensure color accuracy: set .

[0087] Scenario 1: A 12-year-old user uses the device at 12 o'clock in the evening and the blue light adjustment factor calculated is 58.32. Scenario 2: An 18-year-old user uses the device at 10 o'clock in the morning and the blue light adjustment factor calculated is 62.25.

[0088] The working principle and effect of the above technical solution are as follows: The ambient light sensor detects the ambient light brightness around the LCD panel. This helps to determine whether it is necessary to increase or decrease blue light to adapt to changes in ambient light; the GPS device determines the specific geographic location of the user. If it is at home, at night, and the entertainment application is used, the blue light used is less than that of the office application used during the day, so as not to affect the user's sleep. The host operating system monitor monitors and identifies the application of the current active window, which provides information on the type of application usage, estimates the user's age through pre-acquired information (which can be registration information or through face recognition, etc.), and uses the parameter settings in the formula and the environment and user information (such as age, ambient light brightness, usage time, geographic location and application type) to calculate the blue light adjustment factor. The age factor adjustment model and the time factor sine model respectively consider the user's age difference and the demand for blue light in different time periods of the day. The application type factor and geographic location factor affect the actual output level of blue light. The actual output blue light intensity is adjusted according to the calculated blue light adjustment factor to ensure that the user gets the most comfortable visual experience in the current usage environment. Dynamically adjusted blue light output can adapt to different ambient light changes and user activities, reduce eye fatigue and improve visual comfort; provide personalized blue light adjustment based on user age and application type, which helps to meet the specific needs of different users; protect eyesight and reduce potential damage to health by reducing excessive blue light output under dark conditions and moderate blue light exposure under bright conditions; save energy and increase efficiency, and reasonably adjust blue light output, which not only optimizes the user experience, but also saves energy by reducing unnecessary light output; real-time adjustment enables the system to respond quickly to environmental changes and changes in user behavior, providing a continuously optimized visual experience; blue light output can be intelligently and flexibly adjusted in different occasions to protect user eyesight and provide the best visual experience. The basic blue light value is used as the starting point for adjustment to determine the intensity of the basic blue light output, which is then used as a benchmark for further adjustments. The age factor uses logical functions and weights to take into account the different needs of users of different ages for light sensitivity. By setting the base age and age coefficient, the blue light intensity is ensured to adapt to different age groups, thus avoiding discomfort or visual damage caused by excessive blue light to younger or older users. The time factor uses a sine function to describe changes in time of day to adapt to the natural circadian rhythm.This method can dynamically adjust the blue light to match the physiological cycle of the human body. The time weight controls the fluctuation amplitude of the time factor to ensure that the adjustment is in line with the natural demand cycle of the human body for blue light. The usage occasion factor and the application type factor adjust the blue light intensity according to the current environment and application type. In a home environment, a lower blue light is adjusted to increase comfort; in an office environment, the blue light is moderately increased to improve concentration. This classified adjustment helps to personalize the user experience and adapt to the visual needs in different scenarios. The safety value control uses the minimum function min(1,) to limit the upper limit of the blue light adjustment factor to ensure that the output is not excessive and prevent the blue light from being too strong or too weak due to excessive adjustment. Improve safety by limiting conditions and using natural rhythms to ensure that blue light output does not exceed a safe range and protect the user's vision health; the weight and range of each factor are designed to provide balanced adjustments based on different user needs, avoid the dominance of a single factor, and make appropriate adjustments in different situations; dynamic adaptability: as time, environment, and usage scenarios change, the formula can dynamically adjust blue light to provide a comfortable experience for users whose needs change at any time; easy to update and adjust, flexible design, and able to make quick adjustments based on user feedback to enhance the continuous improvement of user experience; wide practicality, can be applied to a variety of devices and usage scenarios, suitable for different light conditions and user groups; by comprehensively considering multiple factors, it not only optimizes the user's personalized experience, but also enhances the safety, rationality and adaptability of blue light adjustment.

[0089] In one embodiment of the present invention, after adjusting the blue light of the liquid crystal display panel, user feedback is obtained, a deep learning model is trained according to the user feedback, and the blue light of the liquid crystal display panel is adaptively adjusted based on the trained deep learning model to meet the user's needs, including:

[0090] Adjusting the blue light output intensity of the liquid crystal display panel according to the blue light adjustment model, monitoring and recording when and under what circumstances the user manually adjusts the blue light intensity, and recording the blue light intensity values ​​before and after the adjustment and context information, wherein the context information includes: time, ambient light, application type, and user's geographic location;

[0091] Cleaning historical manual adjustment records, removing invalid and erroneous adjustment records, and extracting features from the manual adjustment records from which erroneous records have been removed, wherein the features include adjustment time, adjustment amplitude, ambient light intensity, and currently used application;

[0092] Build a deep learning model LSTM model, where the input layer receives the extracted features and the output layer predicts the blue light intensity adjustment value that the user wants;

[0093] Use historical manual adjustment data to preliminarily train the model and learn the user's blue light adjustment preferences.

[0094] Collect context information in real time during user use, including time, ambient light, application type, and user's geographic location;

[0095] The data collected in real time is input into the trained deep learning model LSTM model to predict the blue light intensity desired by the user, and the blue light intensity of the LCD display panel is automatically adjusted based on the model's prediction results.

[0096] The working principle and effect of the above technical solution are as follows: data collection and recording. When the user manually adjusts the blue light intensity of the LCD screen, the system automatically records relevant context information, including the time when the adjustment occurs, the ambient light intensity, the type of application currently used, and the user's geographical location; the system also records the blue light intensity values ​​before and after the adjustment in order to analyze user preferences;

[0097] The collected manual adjustment data is cleaned to remove invalid or abnormal adjustment records, for example, filtering out erroneous input or abnormal data points, and extracting the core features of the adjustment records, including adjustment time, adjustment amplitude, ambient light intensity, and application type. These features will be used for subsequent model training; a long short-term memory (LSTM) neural network is constructed to capture the time series characteristics of the user's blue light adjustment preferences. By inputting feature data, the model is preliminarily trained to understand the user's adjustment habits and preferences in different scenarios; during the user's use, new contextual information is collected in real time, such as time, ambient light changes, current application type, and geographic location, and this real-time information is input into the trained LSTM model, and the model outputs the predicted ideal blue light intensity; based on the model's prediction results, the blue light output of the LCD display panel is automatically adjusted to meet the user's expectations and comfort requirements. Personalized user experience, personalized blue light intensity adjustment, meet users' specific preferences and visual comfort requirements, and improve user experience; dynamic response and precise adjustment, the LSTM model can identify and respond to changes in user behavior patterns, and provide more accurate blue light adjustment suggestions; improve user health and comfort, automatically adjust blue light intensity to optimize visual comfort, reduce eye fatigue and health risks; energy saving and intelligent management, by predicting user needs, avoiding unnecessary manual adjustments, optimizing energy consumption and improving resource utilization efficiency; continuous learning and self-optimization, as the usage time increases, the system continuously updates and expands training data, so that the model can continuously learn the user's latest preferences and habits, and realize an adaptive optimization process; through intelligent learning and dynamic response, while improving user experience, it also plays an important supporting role in vision protection and energy efficiency optimization.

[0098] In one embodiment of the present invention, after adaptive adjustment, new manual adjustment records of the user are collected, a data set is updated, and the updated data set is used to retrain the deep learning model, including:

[0099] When the user is still not satisfied with the automatically adjusted blue light intensity and adjusts it manually again, the new adjustment data is recorded and added to the training data set for incremental update of the model;

[0100] Retrain the deep learning model using the updated dataset.

[0101] The working principle and effect of the above technical solution are as follows: When the user is not satisfied with the automatically adjusted blue light intensity and makes manual adjustments, the system automatically records these new manual adjustment data, which include adjustment time, blue light intensity before and after adjustment, ambient light intensity, current application type, and relevant contextual information such as the user's geographic location; the newly recorded adjustment data is added to the existing training data set, so that the data set always reflects the user's latest adjustment behavior and preferences; the deep learning model (such as the LSTM model) is incrementally trained using the updated data set. The purpose of incremental training is to gradually optimize the model without starting from scratch, so that it can better capture and predict the user's adjustment preferences; incremental learning adapts to new data by adjusting model parameters, which can improve the model's adaptability to the latest user behavior patterns while maintaining existing learning results; ensure that the performance of the model is verified through cross-validation and testing to ensure that the model's predictive ability and accuracy are improved after learning new data. By collecting and learning the user's actual adjustment behavior, the system can more accurately predict user preferences, thereby improving user satisfaction with automatic blue light adjustment; incremental training enables the model to continuously adapt to new user habits and environmental changes, and maintain the effectiveness of predictive capabilities; reduce user intervention, as the model performance improves, the number of manual adjustments by users will decrease, because the system can preliminarily predict user needs, thereby reducing unnecessary manual operations; long-term optimization and personalization, the system can accumulate long-term user preference data, and gradually form a unique user adjustment model, making the user experience more personalized and optimized; system efficiency is improved, and the automated and intelligent adjustment process makes resource utilization more efficient, operation simpler, and reduces distraction of user attention; by recording and learning continuous user feedback, the flexibility and personalization of the system's blue light adjustment are enhanced, which not only improves the user experience, but also reduces the user's need for manual intervention.

[0102] One embodiment of the present invention is a liquid crystal display panel control system based on artificial intelligence, the system comprising:

[0103] The user age estimation module is used to capture the user's facial image using a high-resolution camera, extract and recognize facial features through a deep learning algorithm, and estimate the user's age;

[0104] a preliminary adjustment module for adjusting the blue light of the liquid crystal display panel based on an estimated user age, time, user geographic location, and type of application used by the user;

[0105] An adaptive adjustment module, used to obtain user feedback after adjusting the blue light of the liquid crystal display panel, train a deep learning model according to the user feedback, and adaptively adjust the blue light of the liquid crystal display panel based on the trained deep learning model to suit the user's needs;

[0106] The update training module is used to collect new manual adjustment records of users after adaptive adjustment, update the data set, and use the updated data set to retrain the deep learning model.

[0107] The working principle and effect of the above technical solution are as follows: using a high-resolution camera to capture the user's facial image, applying a deep learning algorithm to extract facial features to estimate the user's age. Age estimation helps to personalize the adjustment of blue light output, because people of different ages have different sensitivity and needs for blue light; using an ambient light sensor to obtain the light brightness around the LCD panel in real time, and collect other information such as time, geographic location and application type. These data are combined to establish a comprehensive input vector for automatic adjustment of blue light output; dynamically adjust the blue light intensity and color temperature of the LCD panel through a deep learning model, taking into account factors such as the user's age, usage environment, time period, etc., so that the display effect is more suitable for personal biorhythms and preferences; collect user feedback, visual comfort scores, and manual adjustment history, and use these feedbacks to retrain the deep learning model to continuously optimize its prediction accuracy and adjustment effect; use the user's new manual adjustment records to update the data set to improve the universality and personalized response capabilities of the model; through a periodic retraining process, the model can adapt to changes in user habits and preferences. Improve user experience and adjust screen blue light based on user's personalized needs, which helps to improve visual comfort and reduce visual fatigue; blue light management for different age groups can reduce the potential health risks of blue light, such as eye damage and biorhythm interference; through machine learning and intelligent feedback mechanism, the system can continuously learn and adapt to individual needs, so that it can provide the best display effect in different situations; through intelligent management of blue light, reduce unnecessary energy consumption, and avoid excessive color temperature from interfering with user's biorhythm; with the continuous improvement and optimization of the model, user satisfaction will increase with the improvement of visual experience, encouraging longer-term use. The artificial intelligence-based LCD display panel control method is not only a blue light optimization tool, but also a comprehensive personalized display solution, combined with AI technology, to provide users with a healthy, safe and comfortable visual experience.

[0108] In one embodiment of the present invention, the module for estimating user age includes:

[0109] A user facial image capturing module is used to capture a user facial image using a high-resolution camera and perform preprocessing on the captured user facial image, wherein the preprocessing includes grayscale conversion, mean normalization and denoising;

[0110] A face detection module, used to detect a face area from a preprocessed facial image using a face detection algorithm;

[0111] The feature extraction module is used to crop the detected face area and scale it to a specified size, and use the pre-trained deep convolutional neural network model VGG-Face to extract deep features from the cropped and scaled face area;

[0112] The estimation module is used to convert the extracted deep-level features into feature vectors and input them into the pre-trained face recognition neural network model to obtain the user age estimation result.

[0113] The working principle and effect of the above technical solution are as follows: image preprocessing, grayscale conversion converts color facial images into grayscale images to reduce computational complexity while retaining important features of the image; mean normalization makes the image pixel values ​​within a uniform range by subtracting the mean and standardizing, so as to improve the stability and accuracy of the feature extraction model; uses filters (such as Gaussian filtering) to reduce image noise and enhance image quality, thereby improving the accuracy of facial feature extraction; uses face detection algorithms (such as Haar cascade classifiers or modern deep learning models MTCNN) to identify facial areas from preprocessed images;

[0114] Ensure reliable positioning and accurate detection even when the face is partially occluded or under different lighting conditions; crop the detected face area and scale it to a specified size (for example, 224x224 pixels) to adapt to the input requirements of the deep learning model; use the VGG-Face model to extract deep features from the processed face area. VGG-Face is a pre-trained deep convolutional neural network that is optimized for face recognition tasks and can effectively extract complex and recognizable features; convert the extracted deep features into feature vectors; input them into a pre-trained face recognition neural network model for analysis, and obtain the user's age estimation result through classification or regression mechanism. High accuracy. Deep learning models such as VGG-Face can efficiently distinguish different subtle facial features, thereby improving the accuracy of age estimation. The efficient algorithm and model structure enable the system to complete the entire age recognition process in a shorter time, which is suitable for real-time applications. Good robustness. Even under different shooting conditions (such as lighting changes, partial occlusion, etc.), the system can still effectively detect and recognize facial features. Personalized display adjustment. Based on the estimated age information, the system can better adjust the display device parameters for users, such as blue light intensity and color temperature optimization.

[0115] In one embodiment of the present invention, the preliminary adjustment module includes:

[0116] A module for obtaining geographic location and time, used for the liquid crystal display panel to obtain the user's geographic location and time through a GPS device of a connected host device;

[0117] An application monitoring module, used for the liquid crystal display panel to monitor the type of application used by the user of the current active window through a monitoring program in the operating system of the connected host;

[0118] The module for calculating the blue light adjustment ratio is used to adjust the blue light of the liquid crystal display panel based on the estimated user age, time, user geographical location and user application type. The adjustment range of the blue light of the liquid crystal display panel is calculated by a blue light adjustment model. Specifically, the blue light adjustment model is:

[0119] ;

[0120] in, represents the blue light regulation factor, Indicates the basic blue light output value, represents the application type factor, represents the geographical location factor, Indicates the user's age. Indicates the base age, represents the age coefficient, represents the age constant, represents the age weight, represents the usage time weight, Indicates the maximum time of a day, Indicates the time the user uses the device;

[0121] The adjustment module is used to adjust the blue light to an adjustment ratio relative to the original blue light intensity based on the calculated blue light adjustment factor.

[0122] The base age is set to 18 years old, and the location factor is set to different values ​​according to the user's current location.

[0123] At home: Generally, the lighting at home is relatively mild. To reduce eye irritation, offices usually have brighter artificial light sources and set Balanced blue light output, Outdoor: Light conditions vary, setting To adapt to stronger natural light.

[0124] Get the type of application used by the user. If the application type is entertainment, for comfort, lower blue light is usually required. Set If the application type is office reading or writing, moderate blue light is required to maintain high readability, set , if the application type is design or color-sensitive work (such as image editing): high blue light is required to ensure color accuracy: set .

[0125] Scenario 1: A 12-year-old user uses the device at 12 o'clock in the evening and the blue light adjustment factor calculated is 58.32. Scenario 2: An 18-year-old user uses the device at 10 o'clock in the morning and the blue light adjustment factor calculated is 62.25.

[0126] The working principle and effect of the above technical solution are as follows: The ambient light sensor detects the ambient light brightness around the LCD panel. This helps to determine whether it is necessary to increase or decrease blue light to adapt to changes in ambient light; the GPS device determines the specific geographic location of the user. If it is at home, at night, and the entertainment application is used, the blue light used is less than that of the office application used during the day, so as not to affect the user's sleep. The host operating system monitor monitors and identifies the application of the current active window, which provides information on the type of application usage, estimates the user's age through pre-acquired information (which can be registration information or through face recognition, etc.), and uses the parameter settings in the formula and the environment and user information (such as age, ambient light brightness, usage time, geographic location and application type) to calculate the blue light adjustment factor. The age factor adjustment model and the time factor sine model respectively consider the user's age difference and the demand for blue light in different time periods of the day. The application type factor and geographic location factor affect the actual output level of blue light. The actual output blue light intensity is adjusted according to the calculated blue light adjustment factor to ensure that the user gets the most comfortable visual experience in the current usage environment. Dynamically adjusted blue light output can adapt to different ambient light changes and user activities, reduce eye fatigue and improve visual comfort; provide personalized blue light adjustment based on user age and application type, which helps to meet the specific needs of different users; protect eyesight and reduce potential damage to health by reducing excessive blue light output under dark conditions and moderate blue light exposure under bright conditions; save energy and increase efficiency, and reasonably adjust blue light output, which not only optimizes the user experience, but also saves energy by reducing unnecessary light output; real-time adjustment enables the system to respond quickly to environmental changes and changes in user behavior, providing a continuously optimized visual experience; blue light output can be intelligently and flexibly adjusted in different occasions to protect user eyesight and provide the best visual experience. The basic blue light value is used as the starting point for adjustment to determine the intensity of the basic blue light output, which is then used as a benchmark for further adjustments. The age factor uses logical functions and weights to take into account the different needs of users of different ages for light sensitivity. By setting the base age and age coefficient, the blue light intensity is ensured to adapt to different age groups, thus avoiding discomfort or visual damage caused by excessive blue light to younger or older users. The time factor uses a sine function to describe changes in time of day to adapt to the natural circadian rhythm.This method can dynamically adjust the blue light to match the physiological cycle of the human body. The time weight controls the fluctuation amplitude of the time factor to ensure that the adjustment is in line with the natural demand cycle of the human body for blue light. The usage occasion factor and the application type factor adjust the blue light intensity according to the current environment and application type. In a home environment, a lower blue light is adjusted to increase comfort; in an office environment, the blue light is moderately increased to improve concentration. This classified adjustment helps to personalize the user experience and adapt to the visual needs in different scenarios. The safety value control uses the minimum function min(1,) to limit the upper limit of the blue light adjustment factor to ensure that the output is not excessive and prevent the blue light from being too strong or too weak due to excessive adjustment. Improve safety by limiting conditions and using natural rhythms to ensure that blue light output does not exceed a safe range and protect the user's vision health; the weight and range of each factor are designed to provide balanced adjustments based on different user needs, avoid the dominance of a single factor, and make appropriate adjustments in different situations; dynamic adaptability: as time, environment, and usage scenarios change, the formula can dynamically adjust blue light to provide a comfortable experience for users whose needs change at any time; easy to update and adjust, flexible design, and able to make quick adjustments based on user feedback to enhance the continuous improvement of user experience; wide practicality, can be applied to a variety of devices and usage scenarios, suitable for different light conditions and user groups; by comprehensively considering multiple factors, it not only optimizes the user's personalized experience, but also enhances the safety, rationality and adaptability of blue light adjustment.

[0127] In one embodiment of the present invention, the adaptive adjustment module includes:

[0128] Obtain a manual adjustment recording module, which is used to adjust the blue light output intensity of the liquid crystal display panel according to the blue light adjustment model, monitor and record when and under what circumstances the user manually adjusts the blue light intensity, and record the blue light intensity value before and after the adjustment and context information, wherein the context information includes: time, ambient light, application type, and user's geographical location;

[0129] A cleaning module, used to clean the historical manual adjustment records, remove invalid and erroneous adjustment records, and extract features from the manual adjustment records without erroneous records, wherein the features include adjustment time, adjustment amplitude, ambient light intensity, and currently used application;

[0130] Build a deep learning model module, which is used to build a deep learning model LSTM model. The input layer receives the extracted features, and the output layer predicts the blue light intensity adjustment value desired by the user;

[0131] A preliminary training module, used to perform preliminary training on the model using historical manual adjustment data, and to preliminarily learn the user's blue light adjustment preference;

[0132] A context information collection module is used to collect context information in real time during the user's use process, and the context information includes: time, ambient light, application type and user's geographical location;

[0133] The prediction module is used to input the real-time collected data into the trained deep learning model LSTM model to predict the blue light intensity desired by the user, and automatically adjust the blue light intensity of the LCD display panel according to the prediction results of the model.

[0134] The working principle and effect of the above technical solution are as follows: data collection and recording, when the user manually adjusts the blue light intensity of the LCD screen, the system automatically records the relevant context information, including the time when the adjustment occurs, the ambient light intensity, the type of application currently used, and the user's geographical location; the system also records the blue light intensity values ​​before and after the adjustment to analyze user preferences; for the collected manual adjustment data, clean it to remove invalid or abnormal adjustment records, for example, filter out incorrect input or abnormal data points, and extract the core features of the adjustment records, including adjustment time, adjustment amplitude, ambient light intensity, and the type of application used. These features will be used for subsequent model training; build a long short-term memory (LSTM) neural network to capture the time series characteristics of the user's blue light adjustment preference, and perform preliminary training on the model by inputting feature data to enable it to understand the user's adjustment habits and preferences in different situations; during the user's use, collect new context information in real time, such as time, ambient light changes, current application type, and geographical location, and input these real-time information into the trained LSTM model, and the model outputs the predicted ideal blue light intensity; according to the model's prediction results, automatically adjust the blue light output of the LCD panel to meet the user's expectations and comfort requirements. Personalized user experience, personalized blue light intensity adjustment, meet users' specific preferences and visual comfort requirements, and improve user experience; dynamic response and precise adjustment, the LSTM model can identify and respond to changes in user behavior patterns, and provide more accurate blue light adjustment suggestions; improve user health and comfort, automatically adjust blue light intensity to optimize visual comfort, reduce eye fatigue and health risks; energy saving and intelligent management, by predicting user needs, avoiding unnecessary manual adjustments, optimizing energy consumption and improving resource utilization efficiency; continuous learning and self-optimization, as the usage time increases, the system continuously updates and expands training data, so that the model can continuously learn the user's latest preferences and habits, and realize an adaptive optimization process; through intelligent learning and dynamic response, while improving user experience, it also plays an important supporting role in vision protection and energy efficiency optimization.

[0135] In one embodiment of the present invention, the updating training module includes:

[0136] The update data set module is used to record the new adjustment data when the user is still not satisfied with the blue light intensity after automatic adjustment and adjusts it manually again, and add the new manual adjustment data to the training data set for incremental update of the model;

[0137] Retraining module, used to retrain the deep learning model using the updated dataset.

[0138] The working principle and effect of the above technical solution are as follows: When the user is not satisfied with the automatically adjusted blue light intensity and makes manual adjustments, the system automatically records these new manual adjustment data, which include adjustment time, blue light intensity before and after adjustment, ambient light intensity, current application type, and relevant contextual information such as the user's geographic location; the newly recorded adjustment data is added to the existing training data set, so that the data set always reflects the user's latest adjustment behavior and preferences; the deep learning model (such as the LSTM model) is incrementally trained using the updated data set. The purpose of incremental training is to gradually optimize the model without starting from scratch, so that it can better capture and predict the user's adjustment preferences; incremental learning adapts to new data by adjusting model parameters, which can improve the model's adaptability to the latest user behavior patterns while maintaining existing learning results; ensure that the performance of the model is verified through cross-validation and testing to ensure that the model's predictive ability and accuracy are improved after learning new data. By collecting and learning the user's actual adjustment behavior, the system can more accurately predict user preferences, thereby improving user satisfaction with automatic blue light adjustment; incremental training enables the model to continuously adapt to new user habits and environmental changes, and maintain the effectiveness of predictive capabilities; reduce user intervention, as the model performance improves, the number of manual adjustments by users will decrease, because the system can preliminarily predict user needs, thereby reducing unnecessary manual operations; long-term optimization and personalization, the system can accumulate long-term user preference data, and gradually form a unique user adjustment model, making the user experience more personalized and optimized; system efficiency is improved, and the automated and intelligent adjustment process makes resource utilization more efficient, operation simpler, and reduces distraction of user attention; by recording and learning continuous user feedback, the flexibility and personalization of the system's blue light adjustment are enhanced, which not only improves the user experience, but also reduces the user's need for manual intervention.

[0139] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A liquid crystal display panel control method based on artificial intelligence, characterized in that: The method comprises: Use a high-resolution camera to capture the user's facial image, extract and recognize facial features through a deep learning algorithm, and estimate the user's age; Adjusts the blue light of the LCD panel based on the estimated user age, time of day, user location, and the type of applications used by the user, including: The liquid crystal display panel obtains the user's geographical location and time through the GPS device of the connected host device; The liquid crystal display panel monitors the type of application used by the user of the current active window through a monitoring program in the operating system of the connected host; The blue light of the liquid crystal display panel is adjusted based on the estimated user age, time, user geographic location, and user application type. The adjustment range of the blue light of the liquid crystal display panel is calculated by a blue light adjustment model. Specifically, the blue light adjustment model is: ； in, represents the blue light regulation factor, Indicates the basic blue light output value, represents the application type factor, represents the geographical location factor, Indicates the user's age. Indicates the base age, represents the age coefficient, represents the age constant, represents the age weight, represents the usage time weight, Indicates the maximum time of a day, Indicates the time the user uses the device; Based on the calculated blue light adjustment factor, the blue light is adjusted to an adjustment ratio relative to the original blue light intensity; After adjusting the blue light of the liquid crystal display panel, obtaining user feedback, training a deep learning model according to the user feedback, and adaptively adjusting the blue light of the liquid crystal display panel to suit the user's needs based on the trained deep learning model; After adaptive adjustment, new manual adjustment records of users are collected, the data set is updated, and the deep learning model is retrained using the updated data set.

2. The liquid crystal display panel control method based on artificial intelligence according to claim 1, characterized in that: Use a high-resolution camera to capture the user's facial image, extract and recognize facial features through a deep learning algorithm, and estimate the user's age, including: Using a high-resolution camera to capture a user's facial image, and preprocessing the captured user's facial image, wherein the preprocessing includes grayscale conversion, mean normalization, and denoising; Using a face detection algorithm to detect the face area from the preprocessed face image; The detected face area is cropped and scaled to a specified size, and the pre-trained deep convolutional neural network model VGG-Face is used to extract deep features from the cropped and scaled face area; The extracted deep features are converted into feature vectors and input into the pre-trained face recognition neural network model to obtain the user age estimation result.

3. The liquid crystal display panel control method based on artificial intelligence according to claim 1, characterized in that: After adjusting the blue light of the liquid crystal display panel, obtaining user feedback, training a deep learning model according to the user feedback, and adaptively adjusting the blue light of the liquid crystal display panel to suit the user's needs based on the trained deep learning model, including: Adjusting the blue light output intensity of the liquid crystal display panel according to the blue light adjustment model, monitoring and recording when and under what circumstances the user manually adjusts the blue light intensity, and recording the blue light intensity values ​​before and after the adjustment and context information, wherein the context information includes: time, ambient light, application type, and user's geographic location; Cleaning historical manual adjustment records, removing invalid and erroneous adjustment records, and extracting features from the manual adjustment records from which erroneous records have been removed, wherein the features include adjustment time, adjustment amplitude, ambient light intensity, and currently used application; Build a deep learning model LSTM model, where the input layer receives the extracted features and the output layer predicts the blue light intensity adjustment value that the user wants; Use historical manual adjustment data to preliminarily train the model and learn the user's blue light adjustment preferences. Collect context information in real time during user use, including time, ambient light, application type, and user's geographic location; The data collected in real time is input into the trained deep learning model LSTM model to predict the blue light intensity desired by the user, and the blue light intensity of the LCD display panel is automatically adjusted based on the model's prediction results.

4. The liquid crystal display panel control method based on artificial intelligence according to claim 1, characterized in that: After adaptive adjustment, new manual adjustment records of users are collected, the data set is updated, and the deep learning model is retrained using the updated data set, including: When the user is still not satisfied with the automatically adjusted blue light intensity and adjusts it manually again, the new adjustment data is recorded and added to the training data set for incremental update of the model; Retrain the deep learning model using the updated dataset.

5. A liquid crystal display panel control system based on artificial intelligence, characterized in that: The system comprises: The user age estimation module is used to capture the user's facial image using a high-resolution camera, extract and recognize facial features through a deep learning algorithm, and estimate the user's age; A preliminary adjustment module, for adjusting the blue light of the LCD panel based on the estimated user age, time, user geographic location, and type of application used by the user, including: A module for obtaining geographic location and time, used for the liquid crystal display panel to obtain the user's geographic location and time through a GPS device of a connected host device; An application monitoring module, used for the liquid crystal display panel to monitor the type of application used by the user of the current active window through a monitoring program in the operating system of the connected host; The module for calculating the blue light adjustment ratio is used to adjust the blue light of the liquid crystal display panel based on the estimated user age, time, user geographical location and user application type. The adjustment range of the blue light of the liquid crystal display panel is calculated by a blue light adjustment model. Specifically, the blue light adjustment model is: ； in, represents the blue light regulation factor, Indicates the basic blue light output value, represents the application type factor, represents the geographical location factor, Indicates the user's age. Indicates the base age, represents the age coefficient, represents the age constant, represents the age weight, represents the usage time weight, Indicates the maximum time of a day, Indicates the time the user uses the device; An adjustment module, configured to adjust the blue light to an adjustment ratio relative to the original blue light intensity based on the calculated blue light adjustment factor; An adaptive adjustment module, used to obtain user feedback after adjusting the blue light of the liquid crystal display panel, train a deep learning model according to the user feedback, and adaptively adjust the blue light of the liquid crystal display panel based on the trained deep learning model to suit the user's needs; The update training module is used to collect new manual adjustment records of users after adaptive adjustment, update the data set, and use the updated data set to retrain the deep learning model.

6. The liquid crystal display panel control system based on artificial intelligence according to claim 5, characterized in that: The module for estimating user age includes: A user facial image capturing module is used to capture a user facial image using a high-resolution camera and perform preprocessing on the captured user facial image, wherein the preprocessing includes grayscale conversion, mean normalization and denoising; A face detection module, used to detect a face area from a preprocessed facial image using a face detection algorithm; The feature extraction module is used to crop the detected face area and scale it to a specified size, and use the pre-trained deep convolutional neural network model VGG-Face to extract deep features from the cropped and scaled face area; The estimation module is used to convert the extracted deep-level features into feature vectors and input them into the pre-trained face recognition neural network model to obtain the user age estimation result.

7. The liquid crystal display panel control system based on artificial intelligence according to claim 5, characterized in that: The adaptive adjustment module comprises: Obtain a manual adjustment recording module, which is used to adjust the blue light output intensity of the liquid crystal display panel according to the blue light adjustment model, monitor and record when and under what circumstances the user manually adjusts the blue light intensity, and record the blue light intensity value before and after the adjustment and context information, wherein the context information includes: time, ambient light, application type, and user's geographical location; A cleaning module, used to clean the historical manual adjustment records, remove invalid and erroneous adjustment records, and extract features from the manual adjustment records without erroneous records, wherein the features include adjustment time, adjustment amplitude, ambient light intensity, and currently used application; Build a deep learning model module, which is used to build a deep learning model LSTM model. The input layer receives the extracted features, and the output layer predicts the blue light intensity adjustment value desired by the user; A preliminary training module, used to perform preliminary training on the model using historical manual adjustment data, and to preliminarily learn the user's blue light adjustment preference; A context information collection module is used to collect context information in real time during the user's use process, and the context information includes: time, ambient light, application type and user's geographical location; The prediction module is used to input the real-time collected data into the trained deep learning model LSTM model to predict the blue light intensity desired by the user, and automatically adjust the blue light intensity of the LCD display panel according to the prediction results of the model.

8. The liquid crystal display panel control system based on artificial intelligence according to claim 5, characterized in that: The update training module includes: The update data set module is used to record the new adjustment data when the user is still not satisfied with the blue light intensity after automatic adjustment and adjusts it manually again, and add the new manual adjustment data to the training data set for incremental update of the model; Retraining module, used to retrain the deep learning model using the updated dataset.

Images