Screen brightness adjusting method and device, storage medium and electronic equipment

Abstract

The invention discloses a screen brightness adjusting method and device, a storage medium and electronic equipment, and the method comprises the steps: obtaining the feature information of a terminal user and the current environment information, and the feature information of the terminal user comprises the vision information and the use scene information; determining a terminal screen brightness value corresponding to the feature information of the terminal user and the current environment information; and adjusting the screen brightness of the terminal according to the terminal screen brightness value. Through the method and the device, the problem of poor visual experience of a user due to the fact that the screen brightness is adjusted only according to the ambient light in the prior art is solved, the screen brightness is automatically adjusted according to the vision condition of the user and the light condition of the current environment, the terminal screen brightness adjusting accuracy can be higher, and the most comfortable visual experience is provided for the user.

Description

Technical Field

[0001] The present invention relates to the field of intelligent terminal technology, and in particular to a screen brightness adjustment method, device, storage medium and electronic device. Background Art

[0002] Existing mobile phones automatically adjust screen brightness by using the mobile phone's light sensor according to the changes in ambient light. This has the problem of insufficient accuracy. Although it can adapt to changes in ambient light to a certain extent, it ignores the differences in vision between users, resulting in the adjustment effect being difficult to meet the visual needs of all users. In particular, for users with myopia, astigmatism or specific eye diseases, fixed adjustment strategies often cannot provide optimal visual comfort. Therefore, developing a system that can automatically adjust screen brightness according to the user's vision is of great significance to protecting the user's vision. Summary of the invention

[0003] The embodiments of the present invention provide a screen brightness adjustment method, device, storage medium and electronic device to solve the problem that the prior art only adjusts the screen brightness according to the ambient light, resulting in poor user visual experience, and automatically adjusts the screen brightness according to the user's eyesight and the light conditions of the current environment, thereby providing the user with the most comfortable visual experience.

[0004] In order to solve the above-mentioned technical problems, the present invention is achieved as follows:

[0005] In a first aspect, the present application provides a method for adjusting screen brightness, the method comprising:

[0006] Acquire characteristic information of the terminal user and current environment information, wherein the characteristic information of the terminal user includes: vision information and usage scenario information;

[0007] Determine a terminal screen brightness value corresponding to the characteristic information of the terminal user and the current environment information;

[0008] The screen brightness of the terminal is adjusted according to the terminal screen brightness value.

[0009] Further, the determining the terminal screen brightness value corresponding to the characteristic information of the terminal user and the current environment information includes: using a trained machine learning model to determine the terminal screen brightness value corresponding to the characteristic information of the terminal user and the current environment information;

[0010] Before acquiring the characteristic information and current environment information of the terminal user, the method further includes:

[0011] Obtain training data and preprocess the training data to generate a training set, a validation set, and a test set required for model training;

[0012] Determine a regression model, and use the training set to perform model training on the regression model to obtain a trained model;

[0013] Using the validation set to adjust parameters of the trained regression model to obtain an adjusted model;

[0014] Testing the adjusted model using the test set;

[0015] If the test passes, the adjusted model is determined as the trained machine learning model;

[0016] If the test fails, the step of adjusting the parameters of the trained regression model using the validation set is performed again.

[0017] Further, the determining the terminal screen brightness value corresponding to the characteristic information of the terminal user and the current environment information by using the trained machine learning model includes:

[0018] In a case where the trained machine learning model includes a plurality of trained base models, respectively obtaining a terminal screen brightness prediction value corresponding to the feature information of the terminal user and the current environment information predicted by each of the trained base models;

[0019] A plurality of the terminal screen brightness prediction values ​​are merged to obtain the terminal screen brightness value.

[0020] Furthermore, the fusing of the plurality of terminal screen brightness prediction values ​​to obtain the terminal screen brightness value includes one of the following methods:

[0021] Determine an average value of a plurality of the terminal screen brightness prediction values ​​as the terminal screen brightness value;

[0022] Assigning weights to a plurality of the terminal screen brightness prediction values, and determining a weighted average as the terminal screen brightness value;

[0023] The plurality of terminal screen brightness prediction values ​​are input into a trained meta-model to obtain the terminal screen brightness value, wherein the trained meta-model is used to indicate the terminal screen brightness value corresponding to the plurality of terminal screen brightness prediction values.

[0024] Furthermore, the acquiring of characteristic information and current environment information of the terminal user includes:

[0025] Acquiring vision information set by the terminal user on the terminal, or collecting the vision information of the terminal user through a vision detection device set on the terminal;

[0026] Acquire usage scenario information set by the terminal user on the terminal, wherein the usage scenario information includes at least one of the following modes: work mode, reading mode, game mode, and audio-visual mode;

[0027] The current environmental information is collected through the ambient light detection device set on the terminal.

[0028] In a second aspect, the present application provides a screen brightness adjustment device, the device comprising:

[0029] A first acquisition unit is used to acquire characteristic information of a terminal user and current environment information, wherein the characteristic information of the terminal user includes: vision information and usage scenario information;

[0030] A first determining unit, configured to determine a terminal screen brightness value corresponding to the characteristic information of the terminal user and the current environment information;

[0031] The adjustment unit is used to adjust the screen brightness of the terminal according to the terminal screen brightness value.

[0032] Further, the first determination unit includes: a determination module, configured to determine a terminal screen brightness value corresponding to the characteristic information of the terminal user and the current environment information using a trained machine learning model;

[0033] The device also includes:

[0034] A second acquisition unit is used to acquire training data and pre-process the training data to generate a training set, a validation set and a test set required for model training before acquiring the characteristic information of the terminal user and the current environment information;

[0035] A training unit, used to determine a regression model, and perform model training on the regression model using the training set to obtain a trained model;

[0036] An adjustment unit, used to adjust parameters of the trained regression model using the validation set to obtain an adjusted model;

[0037] A testing unit, used for testing the adjusted model using the test set;

[0038] A second determining unit, configured to determine the adjusted model as the trained machine learning model if the test passes;

[0039] Returning to the execution unit, if the test fails, re-executes the step of adjusting the parameters of the trained regression model using the verification set.

[0040] Further, the first determining unit includes:

[0041] A first acquisition module is used to respectively acquire, when the trained machine learning model includes a plurality of trained base models, a terminal screen brightness prediction value corresponding to the feature information of the terminal user and the current environment information predicted by each of the trained base models;

[0042] A fusion module is used to fuse multiple terminal screen brightness prediction values ​​to obtain the terminal screen brightness value.

[0043] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method described in the first aspect above.

[0044] In a fourth aspect, the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the method described in the first aspect through the computer program.

[0045] The present application provides a method for adjusting screen brightness, the method comprising: obtaining characteristic information of a terminal user and current environmental information, wherein the characteristic information of the terminal user comprises: vision information and usage scenario information; determining a terminal screen brightness value corresponding to the characteristic information of the terminal user and the current environmental information; and adjusting the terminal screen brightness according to the terminal screen brightness value. In an embodiment of the present application, by determining a terminal screen brightness value corresponding to the characteristic information of the terminal user and the current environmental information, and then adjusting the terminal screen brightness, the problem that the prior art only adjusts the screen brightness according to the ambient light, resulting in poor user visual experience, is solved, and the screen brightness is automatically adjusted according to the user's vision condition and the light conditions of the current environment, so that the terminal screen brightness adjustment accuracy can be higher, thereby providing the user with the most comfortable visual experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0047] Figure 1 It is a flowchart of a method for adjusting screen brightness according to an embodiment of the present application;

[0048] Figure 2 It is a structural schematic diagram of a screen brightness adjustment device according to an embodiment of the present application. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] The present application provides a screen brightness adjustment method, which can be applied to a terminal, where the terminal may include but is not limited to: a mobile phone, a tablet, a smart home appliance (such as a smart TV), etc.

[0051] Figure 1 FIG. 1 is a flow chart of a method for adjusting screen brightness according to an embodiment of the present application. Figure 1 As shown, the method includes:

[0052] Step S101, acquiring characteristic information of a terminal user and current environment information, wherein the characteristic information of the terminal user includes: vision information and usage scenario information;

[0053] Step S102, determining a terminal screen brightness value corresponding to the characteristic information of the terminal user and the current environment information;

[0054] Step S103: adjusting the screen brightness of the terminal according to the terminal screen brightness value.

[0055] In the above step S101, the characteristic information of the terminal user may include: vision information, usage scenario information, wherein the vision information includes: myopia degree, astigmatism value, eye disease condition, etc., and the usage scenario information may include at least one of the following modes: work mode, reading mode, game mode, audio and video mode. In addition, this application adds other characteristic information according to actual needs, such as the age, gender, occupation, etc. of the terminal user.

[0056] Optionally, step S101, obtaining characteristic information and current environment information of the terminal user may include:

[0057] Acquiring vision information set by the terminal user on the terminal, or collecting the vision information of the terminal user through a vision detection device set on the terminal;

[0058] Acquire usage scenario information set by the terminal user on the terminal, wherein the usage scenario information includes at least one of the following modes: work mode, reading mode, game mode, and audio-visual mode;

[0059] The current environmental information is collected through the ambient light detection device set on the terminal.

[0060] It should be noted that when the terminal user logs in to the terminal for the first time, he can enter personal vision information such as myopia degree, astigmatism axis and degree, eye disease type and degree, or automatically detect and obtain this information by connecting to professional vision testing equipment. This information will then be securely stored in the system database for subsequent use. Each time the terminal user uses the terminal, he can select the current usage scene mode according to his needs. Different usage scene modes correspond to different screen brightness, so that the terminal user can get a better visual experience.

[0061] It should also be noted that the ambient light detection device can detect the light conditions of the user's environment in real time through the light sensor built into the terminal. The light sensor can accurately capture changes in light intensity and send this data to the control system.

[0062] In the above step S102, the determining of the terminal screen brightness value corresponding to the characteristic information of the terminal user and the current environment information may include: using a trained machine learning model to determine the terminal screen brightness value corresponding to the characteristic information of the terminal user and the current environment information. The acquired characteristic information of the terminal user and the current environment information are input into the trained machine learning model, and the trained machine learning model outputs the corresponding terminal screen brightness value.

[0063] The machine learning model is trained based on a large amount of user usage data and feedback, and can learn the impact of myopia and ambient light conditions on screen brightness requirements. When the control system receives the myopia and ambient light data, it inputs this information into the machine learning model, and the machine learning model outputs a recommended screen brightness value. Using deep learning or reinforcement learning algorithms, a mapping model from multiple inputs (vision data, ambient light, historical preferences) to a single output (optimal screen brightness) is constructed. A large amount of user data is used for model training, and parameters are continuously optimized and adjusted to improve prediction accuracy. It can automatically adjust the terminal screen brightness according to the user's myopia and the current ambient light conditions, thereby providing users with the most comfortable visual experience.

[0064] This application uses a machine learning algorithm to train a model, and uses the trained machine learning model to predict the terminal screen brightness value, which can improve the prediction accuracy of the screen brightness value, thereby improving the accuracy of screen brightness adjustment and providing users with the most comfortable visual experience.

[0065] The following is a detailed description of the training process of the machine learning model:

[0066] Optionally, before acquiring the characteristic information of the terminal user and the current environment information, the method needs to perform model training, which specifically includes:

[0067] Obtain training data and preprocess the training data to generate a training set, a validation set, and a test set required for model training;

[0068] Determine a regression model, and use the training set to perform model training on the regression model to obtain a trained model;

[0069] Using the validation set to adjust parameters of the trained regression model to obtain an adjusted model;

[0070] Testing the adjusted model using the test set;

[0071] If the test passes, the adjusted model is determined as the trained machine learning model;

[0072] If the test fails, the step of adjusting the parameters of the trained regression model using the validation set is performed again.

[0073] The following is a detailed description and example of the above model training process:

[0074] 1. Data preparation stage

[0075] Collect data: Collect data from multiple sources including user myopia, ambient light conditions (such as light intensity, color temperature, etc.), and screen brightness settings. This data can come from user surveys, device sensor recordings, or lab tests.

[0076] Data cleaning: Process missing values, outliers, and noisy data. For missing values, you can consider using the mean, median, mode, or interpolation method to fill them; for outliers, you can identify and process them according to business rules or statistical methods (such as the IQR method).

[0077] Feature engineering: In addition to myopia and ambient light conditions, other relevant features can also be considered, such as time (day / night), usage scenario (reading, gaming, work, etc.), user age, gender, etc. At the same time, continuous features are normalized or standardized to improve the convergence speed and performance of the model.

[0078] Divide the data set: Divide the cleaned data into training set, validation set, and test set. Usually, the training set is used to train the model, the validation set is used to adjust the model parameters (such as hyperparameter tuning), and the test set is used to evaluate the final performance of the model. Random partitioning or stratified sampling can be used to ensure the representativeness and balance of the data set.

[0079] 2. Model selection stage

[0080] Regression model: Since the goal is to predict a continuous screen brightness value, a regression model should be selected. Common regression models include linear regression, polynomial regression, decision tree regression, random forest regression, gradient boosting tree (such as XGBoost, LightGBM) and neural network.

[0081] Model evaluation: Choose appropriate evaluation metrics to evaluate the performance of the model, such as mean squared error (MSE), root mean square error (RMSE), mean absolute error (MAE), etc. These metrics can help you understand the prediction accuracy and stability of the model.

[0082] 3. Model training phase

[0083] Initialize model: Initialize the model according to the selected algorithm and set the initial parameters.

[0084] Training model: Use the training set data to train the model. During the training process, cross-validation can be used to evaluate the generalization ability of the model and adjust hyperparameters to optimize model performance.

[0085] Save model: Save the trained model to a file for later use.

[0086] 4. Model evaluation and optimization stage

[0087] Evaluate the model: Use the test set data to evaluate the performance of the model. If the performance of the model does not meet the requirements, it needs to be optimized.

[0088] Feature Importance Analysis: Analyze which features are most important for predicting screen brightness values. This can help you understand the decision-making process of the model and further optimize feature selection.

[0089] Hyperparameter tuning: Use methods such as grid search, random search, or Bayesian optimization to find the optimal hyperparameter settings.

[0090] Model fusion: If the performance of a single model is limited, you can consider using model fusion techniques (such as stacked generalization, voting mechanism, etc.) to improve the overall prediction accuracy.

[0091] 5. Deployment and monitoring phase

[0092] Model deployment: Deploy the trained model to the actual application scenario to ensure that it can receive myopia degree and ambient light data in real time and output the recommended screen brightness value.

[0093] Performance monitoring: Continuously monitor the performance of the model, including prediction accuracy, response time, etc. If performance degradation is found, investigate and optimize in a timely manner.

[0094] It should be noted that before feeding the data into the model, a series of data preprocessing steps are required, which may include at least one of the following:

[0095] Missing value processing: Use the mean, median, mode, or interpolation method (such as linear interpolation, polynomial interpolation, etc.) to fill in the missing values ​​in the training data set. The method you choose depends on the characteristics of the data and business needs.

[0096] Outlier handling: Identify and handle outliers in the training data set based on business rules or statistical methods (such as the IQR method, i.e., the interquartile range method). Outliers may need to be deleted, replaced with the mean, median, mode, or adjusted by other methods.

[0097] Feature selection: Select the most useful features for model prediction from the raw data. This includes myopia degree, ambient light conditions (light intensity, color temperature, etc.), time (day / night), usage scenario (reading, gaming, work, etc.), user age, gender, etc. Feature selection can be based on domain knowledge, correlation analysis, feature importance assessment and other methods.

[0098] Feature encoding: For categorical features (such as time, usage scenario, gender), they need to be encoded so that the model can process them. Common encoding methods include one-hot encoding, label encoding, binary encoding, etc.

[0099] Feature scaling: Normalizing or standardizing continuous features to eliminate the dimensionality and value range differences between different features, which helps the model converge faster and improves performance.

[0100] Data augmentation: Although data augmentation is often used for unstructured data such as images and text, in some cases, similar ideas can be used for structured data to generate new samples or enhance the diversity of existing samples. However, direct data augmentation may not be applicable in scenarios such as myopia and ambient light conditions. Instead, the dataset can be balanced by methods such as synthetic data (generating new samples based on the statistical distribution of existing data) or resampling (oversampling minority class samples and undersampling majority class samples).

[0101] Data batching: During model training, the training dataset is usually divided into multiple small batches, each containing a certain number of samples. This can reduce memory consumption and allow the model to perform gradient updates during training. The choice of batch size affects the training speed and stability of the model, and it is usually necessary to determine the optimal batch size through experiments.

[0102] Data loading and iteration: During the training process, you need to write a data loader to iteratively load the training data set. The data loader is responsible for reading samples from the data set, performing necessary preprocessing (such as data enhancement, feature encoding, etc.), and sending the processed samples to the model in batches for training. At the same time, the data loader also needs to support functions such as disrupting the sample order and multi-process loading to improve the efficiency of data loading.

[0103] Through the above steps, the training data set is prepared in a form suitable for model training and is effectively used in the training process.

[0104] Optionally, in the case where the trained machine learning model includes multiple trained base models, the present application can first obtain the terminal screen brightness prediction value corresponding to the characteristic information of the terminal user and the current environmental information predicted by each of the trained base models; and then fuse the multiple terminal screen brightness prediction values ​​to obtain the terminal screen brightness value.

[0105] Furthermore, the fusing of the plurality of terminal screen brightness prediction values ​​to obtain the terminal screen brightness value includes one of the following methods:

[0106] Determine an average value of a plurality of the terminal screen brightness prediction values ​​as the terminal screen brightness value;

[0107] Assigning weights to a plurality of the terminal screen brightness prediction values, and determining a weighted average as the terminal screen brightness value;

[0108] The plurality of terminal screen brightness prediction values ​​are input into a trained meta-model to obtain the terminal screen brightness value, wherein the trained meta-model is used to indicate the terminal screen brightness value corresponding to the plurality of terminal screen brightness prediction values.

[0109] Model fusion is a technique that combines the prediction results of multiple models to improve the overall prediction accuracy. The implementation process of model fusion includes:

[0110] Prepare data: Split the dataset into training and testing sets.

[0111] Train multiple base models: Train multiple base models using different algorithms or different hyperparameters of the same algorithm.

[0112] Prediction: Use the trained base model to make predictions on the test set.

[0113] Fusion prediction results: Fusion the prediction results of multiple base models to obtain the final prediction result.

[0114] Common model fusion methods include:

[0115] 1. Simple average method

[0116] The prediction results of multiple models are simply averaged.

[0117] 2. Weighted average method

[0118] Different weights are assigned to the prediction results of each model and weighted average is performed.

[0119] 3. Voting

[0120] For classification problems, voting can be used to fuse the results of multiple classifiers. Voting methods are divided into hard voting and soft voting:

[0121] Hard voting: choose the class predicted by the majority of classifiers.

[0122] Soft voting: select the class with the highest probability weighted average.

[0123] 4. Stacking

[0124] Stacking is a more complex fusion method that uses a "meta-model" to learn how to combine the outputs of the base models. Typically, the predictions of the base models are used as input features to the meta-model.

[0125] The above methods can achieve model fusion and improve the overall prediction accuracy. The model fusion method can be selected and adjusted according to the characteristics of the specific problem and data set to achieve the best effect.

[0126] In the above step S103, the control system sends the screen brightness value recommended by the trained machine learning model to the brightness adjustment module of the terminal. This module can automatically adjust the brightness of the terminal screen according to the received screen brightness value, ensuring that users can get the best visual experience when using the terminal regardless of their myopia degree or how the ambient light changes.

[0127] Users of this application can set the sensitivity of brightness adjustment in the system according to their own needs to meet the personalized needs of different users; the screen brightness change range and frequency can be automatically adjusted according to the user's usage habits and time to reduce the impact on the user's eyesight, thereby providing users with a more accurate and personalized visual comfort experience.

[0128] The embodiments of the present application also provide a screen brightness adjustment device. The device is used to implement the above embodiments and preferred implementations, and the descriptions that have been made will not be repeated. As used below, the terms "module", "unit", "subunit", etc. can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0129] Figure 2 is a schematic diagram of the structure of a screen brightness adjustment device according to an embodiment of the present application. Figure 2 As shown, the device comprises:

[0130] The first acquisition unit 21 is used to acquire characteristic information of the terminal user and current environment information, wherein the characteristic information of the terminal user includes: vision information and usage scenario information;

[0131] A first determining unit 22, configured to determine a terminal screen brightness value corresponding to the characteristic information of the terminal user and the current environment information;

[0132] The adjustment unit 23 is used to adjust the screen brightness of the terminal according to the terminal screen brightness value.

[0133] Further, the first determination unit 22 includes: a determination module, configured to determine a terminal screen brightness value corresponding to the characteristic information of the terminal user and the current environment information using a trained machine learning model;

[0134] The device also includes:

[0135] A second acquisition unit is used to acquire training data and pre-process the training data to generate a training set, a validation set and a test set required for model training before acquiring the characteristic information of the terminal user and the current environment information;

[0136] A training unit, used to determine a regression model, and perform model training on the regression model using the training set to obtain a trained model;

[0137] An adjustment unit, used to adjust parameters of the trained regression model using the validation set to obtain an adjusted model;

[0138] A testing unit, used for testing the adjusted model using the test set;

[0139] A second determining unit, configured to determine the adjusted model as the trained machine learning model if the test passes;

[0140] Returning to the execution unit, if the test fails, re-executes the step of adjusting the parameters of the trained regression model using the verification set.

[0141] Further, the first determining unit 22 includes:

[0142] A first acquisition module is used to respectively acquire, when the trained machine learning model includes a plurality of trained base models, a terminal screen brightness prediction value corresponding to the feature information of the terminal user and the current environment information predicted by each of the trained base models;

[0143] A fusion module is used to fuse multiple terminal screen brightness prediction values ​​to obtain the terminal screen brightness value.

[0144] Furthermore, the fusion module includes:

[0145] A first determining submodule, configured to determine an average value of a plurality of terminal screen brightness prediction values ​​as the terminal screen brightness value;

[0146] A second determination submodule is used to assign weights to the plurality of terminal screen brightness prediction values, and determine a weighted average as the terminal screen brightness value;

[0147] The third determination submodule is used to input the multiple terminal screen brightness prediction values ​​into the trained meta-model to obtain the terminal screen brightness values, wherein the trained meta-model is used to indicate the terminal screen brightness values ​​corresponding to the multiple terminal screen brightness prediction values.

[0148] Furthermore, the first acquiring unit 21 includes:

[0149] A second acquisition module is used to acquire the vision information set by the terminal user on the terminal, or collect the vision information of the terminal user through a vision detection device set on the terminal;

[0150] A third acquisition module is used to acquire usage scenario information set by the terminal user on the terminal, wherein the usage scenario information includes at least one of the following modes: work mode, reading mode, game mode, and audio-visual mode;

[0151] The fourth acquisition module is used to collect current environmental information through an ambient light detection device provided on the terminal.

[0152] It should be noted that the above modules can be functional modules or program modules, and can be implemented by software or hardware. For modules implemented by hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0153] An embodiment of the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes any method described in the above method embodiments through the computer program.

[0154] The embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, each process of the above method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it is not repeated here. The computer-readable storage medium is, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0155] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0156] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0157] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0158] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0159] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0160] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0161] Computer-readable media include permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. According to the definition in this article, computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0162] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0163] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0164] The above are only embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.

Claims

1. A screen brightness adjustment method, characterized in that: The method comprises: Acquire characteristic information of the terminal user and current environment information, wherein the characteristic information of the terminal user includes: vision information and usage scenario information; Determine a terminal screen brightness value corresponding to the characteristic information of the terminal user and the current environment information; The screen brightness of the terminal is adjusted according to the terminal screen brightness value.

2. The method according to claim 1, characterized in that The determining of the terminal screen brightness value corresponding to the characteristic information of the terminal user and the current environment information comprises: using a trained machine learning model to determine the terminal screen brightness value corresponding to the characteristic information of the terminal user and the current environment information; Before acquiring the characteristic information and current environment information of the terminal user, the method further includes: Obtain training data and preprocess the training data to generate a training set, a validation set, and a test set required for model training; Determine a regression model, and use the training set to perform model training on the regression model to obtain a trained model; Using the validation set to adjust parameters of the trained regression model to obtain an adjusted model; Testing the adjusted model using the test set; If the test passes, the adjusted model is determined as the trained machine learning model; If the test fails, the step of adjusting the parameters of the trained regression model using the validation set is performed again.

3. The method according to claim 2, characterized in that The determining of the terminal screen brightness value corresponding to the characteristic information of the terminal user and the current environment information by using the trained machine learning model includes: In a case where the trained machine learning model includes a plurality of trained base models, respectively obtaining a terminal screen brightness prediction value corresponding to the feature information of the terminal user and the current environment information predicted by each of the trained base models; A plurality of the terminal screen brightness prediction values ​​are merged to obtain the terminal screen brightness value.

4. The method according to claim 3, characterized in that The merging of the plurality of terminal screen brightness prediction values ​​to obtain the terminal screen brightness value includes one of the following methods: Determine an average value of a plurality of the terminal screen brightness prediction values ​​as the terminal screen brightness value; Assigning weights to a plurality of the terminal screen brightness prediction values, and determining a weighted average as the terminal screen brightness value; The plurality of terminal screen brightness prediction values ​​are input into a trained meta-model to obtain the terminal screen brightness value, wherein the trained meta-model is used to indicate the terminal screen brightness value corresponding to the plurality of terminal screen brightness prediction values.

5. The method according to any one of claims 1 to 4, characterized in that The obtaining of the terminal user's characteristic information and current environment information includes: Acquiring vision information set by the terminal user on the terminal, or collecting the vision information of the terminal user through a vision detection device set on the terminal; Acquire usage scenario information set by the terminal user on the terminal, wherein the usage scenario information includes at least one of the following modes: work mode, reading mode, game mode, and audio-visual mode; The current environmental information is collected through the ambient light detection device set on the terminal.

6. A screen brightness adjustment device, characterized in that: The device comprises: A first acquisition unit is used to acquire characteristic information of a terminal user and current environment information, wherein the characteristic information of the terminal user includes: vision information and usage scenario information; A first determining unit, configured to determine a terminal screen brightness value corresponding to the characteristic information of the terminal user and the current environment information; The adjustment unit is used to adjust the screen brightness of the terminal according to the terminal screen brightness value.

7. The device according to claim 6, characterized in that The first determination unit includes: a determination module, configured to determine a terminal screen brightness value corresponding to the characteristic information of the terminal user and the current environment information using a trained machine learning model; The device also includes: A second acquisition unit is used to acquire training data and pre-process the training data to generate a training set, a validation set and a test set required for model training before acquiring the characteristic information of the terminal user and the current environment information; A training unit, used to determine a regression model, and perform model training on the regression model using the training set to obtain a trained model; An adjustment unit, used to adjust parameters of the trained regression model using the validation set to obtain an adjusted model; A testing unit, used for testing the adjusted model using the test set; A second determining unit, configured to determine the adjusted model as the trained machine learning model if the test passes; Returning to the execution unit, if the test fails, re-executes the step of adjusting the parameters of the trained regression model using the verification set.

8. The device according to claim 7, characterized in that The first determining unit includes: A first acquisition module is used to respectively acquire, when the trained machine learning model includes a plurality of trained base models, a terminal screen brightness prediction value corresponding to the feature information of the terminal user and the current environment information predicted by each of the trained base models; A fusion module is used to fuse multiple terminal screen brightness prediction values ​​to obtain the terminal screen brightness value.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, performs the method described in any one of claims 1 to 5.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: The processor executes the method described in any one of claims 1 to 5 through the computer program.

Images