A display screen brightness automatic adjusting method, mobile phone and storage medium

Abstract

The application relates to the technical field of mobile phone display brightness control, in particular to a display screen brightness automatic adjusting method, a mobile phone and a storage medium, which records adjusting data and counts adjusting frequency, then sends the adjusting data to a server, compares the adjusting frequency with a preset threshold value, obtains a simplified model from the server if the adjusting frequency exceeds the preset threshold value, obtains an attention score change amount from the server if the adjusting frequency does not exceed the preset threshold value, optimizes the local simplified model according to the attention score change amount, and finally adjusts the display screen brightness according to the local simplified model. The preset neural network model is run on the server to realize the individualization of the user, the simplified model is used for automatically adjusting the brightness locally on the user's mobile phone, and the simplified model is optimized according to the change of the attention score of the preset neural network model, so that the problem that the display screen brightness adjusting model of the prior art cannot consider light weight and individualization is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of mobile phone display brightness control, and particularly relates to a display screen brightness automatic adjustment method, a mobile phone and a storage medium. BACKGROUND

[0002] The mobile phone brightness adjustment function is of great significance to improve the user experience. In a variable use environment, accurate brightness control can effectively reduce visual fatigue and protect the user's eye health. Although the simple linear model has rapid response capability and can quickly adjust the screen brightness according to the change of the ambient light, its accuracy is insufficient and it cannot adapt to different user habits.

[0003] Therefore, the brightness adjustment model based on artificial intelligence has gradually become a mainstream research direction. Compared with the simple linear model, the complex model based on artificial intelligence performs outstandingly in accuracy and can better adapt to different user habits and be personalized. However, due to the complex calculation process, it will cause great pressure on the running performance of the mobile phone, which may cause the mobile phone to heat up, consume power faster and other problems, thereby limiting its widespread application in practical application to a certain extent.

[0004] Therefore, people need a mobile phone display screen brightness adjustment method that takes into account lightness and personalization. SUMMARY

[0005] Therefore, the present application provides a display screen brightness automatic adjustment method, a mobile phone and a storage medium to solve the problem that the mobile phone display screen brightness adjustment model in the prior art cannot take into account lightness and personalization.

[0006] The present application provides a display screen brightness automatic adjustment method, comprising:

[0007] When the user actively adjusts the display screen brightness, record the adjustment data and count the adjustment frequency, the adjustment data including environmental data and brightness data;

[0008] Send the adjustment data to the server, the server being configured to train a preset neural network model according to the adjustment data, the preset neural network model being configured to calculate an attention score of each environmental data according to the adjustment data and calculate the brightness data according to the attention score;

[0009] Compare the adjustment frequency with a preset threshold;

[0010] If the adjustment frequency exceeds the preset threshold, obtain a simplified model from the server, the simplified model being configured to calculate the brightness data according to the adjustment data, the simplified model being fitted based on the calculation result of the preset neural network model;

[0011] If the adjustment frequency does not exceed the preset threshold, an attention score change amount is obtained from the server, and the local simplified model is optimized according to the attention score change amount; wherein the attention score change amount is a change amount of the attention score in the process of the preset neural network model in back propagation;

[0012] According to the local simplified model, the display screen brightness is adjusted.

[0013] The application also provides a preferred scheme: the local simplified model is optimized according to the attention score change amount, comprising:

[0014] According to the attention score change amount, the local simplified model is preliminarily adjusted to obtain a transition model;

[0015] The adjustment data corresponding to the attention score change amount is obtained as target adjustment data, and the target adjustment data comprises target environment data and target brightness data;

[0016] The target adjustment data is input into the transition model to obtain an output result;

[0017] According to the difference between the output result and the target brightness data, the transition model is adjusted to obtain an optimized simplified model.

[0018] The application also provides a preferred scheme: the simplified model comprises a plurality of coefficients, and each coefficient corresponds to environment data; according to the attention score change amount, the local simplified model is preliminarily adjusted to obtain a transition model, comprising:

[0019] According to the attention score change amount corresponding to each environment data, the value of the coefficient corresponding to the environment data is adjusted to obtain the transition model.

[0020] The application also provides a preferred scheme: according to the difference between the output result and the target brightness data, the transition model is adjusted to obtain an optimized simplified model, comprising:

[0021] The difference between the output result and the target brightness data is calculated;

[0022] According to the difference, the partial derivative of each coefficient in the transition model is calculated;

[0023] According to the partial derivative of each coefficient, the value of each coefficient in the transition model is adjusted to obtain an optimized simplified model.

[0024] The application also provides a preferred scheme: the simplified model is;

[0025] B1 = ∑ (wX + b) ;

[0026] wherein B1 represents the output result of the simplified model, X represents an environment data, w is a coefficient corresponding to the adjustment data, and b is a bias corresponding to the adjustment data.

[0027] The transition model is:

[0028] B2=∑((w+f(s))X+b+g(s));

[0029] Where B2 represents the output of the transition model, s represents the change in attention score corresponding to this type of adjustment data, and f() and g() are different preset linear functions;

[0030] The optimized simplified model is as follows:

[0031]

[0032] Where B3 represents the output of the optimized simplified model. α is the sign of the partial derivative, and α is the preset adjustment rate.

[0033] The present invention also provides a preferred embodiment: when a user adjusts the brightness of the display screen, the adjustment data is recorded and the adjustment frequency is statistically analyzed, including:

[0034] Acquire brightness adjustment records when the user adjusts the display brightness;

[0035] In the brightness adjustment record, a dynamic length analysis window is set. The brightness adjustment record in the statistical analysis window is the proportion that the user actively adjusts, and this proportion is used as the adjustment frequency.

[0036] The present invention also provides a preferred embodiment, which further includes:

[0037] When the brightness of the mobile phone screen is adjusted, it is determined whether the adjustment is made actively by the user or automatically by the system.

[0038] If this adjustment is made proactively by the user, then reduce the length of the analysis window;

[0039] If this adjustment is done automatically by the system, then increase the length of the analysis window.

[0040] The application further provides a preferred scheme: the environmental data comprises at least one of environmental light intensity, time, temperature, mobile phone backlight intensity, current application software, screen pixel distribution, face recognition data, fingerprint recognition data and voiceprint recognition data; the preset neural network model comprises an input layer, a query vector analysis layer, a key vector analysis layer, a softmax layer, a value vector analysis layer, a linear layer and an output layer, wherein the input layer is used for inputting the environmental data, the input ends of the query vector analysis layer, the key vector analysis layer and the value vector analysis layer are connected with the input layer, and are respectively used for calculating the query vector, the key vector and the value vector of each kind of environmental data, the output ends of the query vector analysis layer and the key vector analysis layer are connected with the softmax layer, the softmax layer is used for calculating the attention score of one kind of environmental data relative to other environmental data, the output end of the softmax layer and the output end of the value vector analysis layer are connected with the linear layer, the linear layer is connected with the output layer, and the output layer is used for outputting the brightness data.

[0041] The application further provides a mobile phone, comprising:

[0042] a data recording module, used for recording adjustment data and counting adjustment frequency when a user actively adjusts the brightness of the display screen, wherein the adjustment data comprises environmental data and brightness data;

[0043] a data uploading module, used for sending the adjustment data to a server, wherein the server is used for training a preset neural network model according to the adjustment data, the preset neural network model is used for calculating the attention score of each kind of environmental data according to the adjustment data, and calculating the brightness data according to the attention score;

[0044] a comparison and optimization module, used for comparing the adjustment frequency with a preset threshold value;

[0045] if the adjustment frequency exceeds the preset threshold value, a simplified model is obtained from the server, the simplified model is used for calculating the brightness data according to the adjustment data, and the simplified model is fitted based on the calculation result of the preset neural network model;

[0046] if the adjustment frequency does not exceed the preset threshold value, an attention score change amount is obtained from the server, and a local simplified model is optimized according to the attention score change amount; wherein the attention score change amount is the change amount of the attention score in the process of reverse propagation of the preset neural network model;

[0047] a brightness adjustment module, used for adjusting the brightness of the display screen according to the local simplified model.

[0048] The application further provides a computer readable storage medium, used for storing computer readable programs or instructions, wherein the programs or instructions can realize the steps of the display screen brightness automatic adjustment method when executed by a processor.

[0049] The beneficial effects of using the above embodiments are:

[0050] This invention provides a method for automatically adjusting screen brightness, a mobile phone, and a storage medium. When a user actively adjusts the screen brightness, the method records adjustment data and statistically analyzes the adjustment frequency. This data is then sent to a server. The adjustment frequency is compared to a preset threshold. If the adjustment frequency exceeds the threshold, a simplified model is retrieved from the server. If the frequency does not exceed the threshold, the change in attention score is retrieved from the server, and the local simplified model is optimized based on this change. Finally, the screen brightness is adjusted according to the local simplified model. This invention utilizes a preset neural network model running on a server to calculate brightness and uses attention scores to personalize the user's experience. The simplified model is obtained by fitting the calculation results of the preset neural network model and is used to automatically adjust brightness locally on the user's phone, achieving lightweight operation while ensuring rapid screen brightness adjustment response. Most importantly, the local simplified model can be optimized based on the changes in attention score from the preset neural network model. This allows the phone to automatically adjust the screen brightness according to user habits in most cases without waiting for a server response. Furthermore, when the local linear model is inaccurate, it can be refitted to obtain a more accurate simplified model, achieving a perfect combination of accuracy, personalization, and lightweight operation for mobile phone brightness adjustment. Attached Figure Description

[0051] Figure 1 The flowchart of the automatic brightness adjustment method for a display screen provided by the present invention;

[0052] Figure 2 for Figure 1 A detailed step diagram of step S105 in the middle section;

[0053] Figure 3 This is a schematic diagram of a mobile phone module provided by the present invention. Detailed Implementation

[0054] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0055] Combination Figure 1 As shown, the present invention provides a method for automatically adjusting the brightness of a display screen, comprising:

[0056] S101, record the adjustment data and count the adjustment frequency when the user actively adjusts the brightness of the display screen, the adjustment data including environmental data and brightness data;

[0057] S102, send the adjustment data to the server, the server being configured to train a preset neural network model according to the adjustment data, the preset neural network model being configured to calculate an attention score of each environmental data according to the adjustment data, and calculate the brightness data according to the attention score;

[0058] S103, compare the adjustment frequency with a preset threshold;

[0059] S104, if the adjustment frequency exceeds the preset threshold, obtain a simplified model from the server, the simplified model being configured to calculate the brightness data according to the adjustment data, the simplified model being fitted based on the calculation result of the preset neural network model;

[0060] S105, if the adjustment frequency does not exceed the preset threshold, obtain an attention score change amount from the server, and optimize the local simplified model according to the attention score change amount, wherein the attention score change amount is the change amount of the attention score in the process of back propagation of the preset neural network model;

[0061] S106, adjust the brightness of the display screen according to the local simplified model.

[0062] In the above process, the environmental data includes any data that can affect the user's adjustment of the brightness of the mobile phone, such as ambient light intensity, time, temperature, mobile phone backlight intensity, current application software, screen pixel distribution, face recognition data, fingerprint recognition data, and voiceprint recognition data, etc., which can be flexibly set according to actual conditions.

[0063] The preset neural network model is a model pre-trained and stored in the server, which has an attention mechanism and can analyze the combined influence of multiple environmental factors to ensure the accuracy of brightness analysis. For example, a user is used to browsing video software with low brightness after turning off the light at night, but does not actively adjust the brightness when watching video alone in a dark environment or when watching video alone. The preset neural network model based on the attention mechanism can analyze the correlation between brightness and software as two environmental factors and cope with this situation. The attention mechanism is a prior art and will not be described in detail in this embodiment.

[0064] It can be understood that training the preset neural network model requires a large amount of data, and the data of the user adjusting the brightness may be less, which cannot support the training of the preset neural network model. Therefore, the data of all users can be collected, a general model can be pre-trained, and then a preset neural network model can be individually established for each user based on the general model to realize personalized training, so as to ensure reliability and save the computing resources of the server.

[0065] It is conceivable that the preset neural network can achieve personalization, but the running cost is too high, and running through the mobile phone may affect the user experience, and it is also unrealistic for the mobile phone to request data from the server every time the brightness is adjusted. Therefore, the embodiment simplifies the preset neural network model to a simple model (for example, by fitting the input and output data of the preset neural network model, a simple linear model is obtained) on the basis of the preset neural network model, and then deploys the simplified model locally on the mobile phone, so that the mobile phone can be quickly adjusted and will not cause excessive computing pressure to the mobile phone. In practice, it can be seen that most of the user's use of the mobile phone is relatively single, for example, according to the 80-20 rule, the user uses 80% of the time to use 20% of the software in the mobile phone, so under the premise of meeting the user's use habits, a simple linear model can also meet the daily use demand.

[0066] The initial simplified model in the mobile phone can be obtained by fitting the above general model. Similarly, because the user adjusts the brightness of the mobile phone less frequently, and optimizing the preset neural network model also requires a certain amount of data, therefore, before the preset neural network model completes the personalization training, the simplified model can be simply and preliminarily optimized locally to improve the user experience. When it is determined that the simple model is not accurate enough, the server is requested to re-fit a more accurate simplified model.

[0067] The embodiment adopts the adjustment frequency as the standard for judging the accuracy of the simplified model, and the application defaults that the mobile phone will automatically adjust the brightness according to the simplified model on a daily basis, and the adjustment frequency refers to the proportion of the user's active adjustment of the brightness in the total adjustment of the brightness of the mobile phone, that is, each time the user adjusts the brightness, it can be regarded as that the current mobile phone brightness is unreasonable, and the simplified model calculation is wrong. Compared with other standards for judging accuracy, the adjustment frequency not only represents the accuracy, but also implicitly reflects the amount of data that the mobile phone has collected, that is, when the adjustment frequency is necessarily based on the user having adjusted the brightness a certain number of times, the optimization of the preset neural network model can be artificially preset to be reliable.

[0068] The local optimization simplification model of the mobile phone can also be adopted in any manner, for example, according to the data at the last adjustment, the weight of the environmental data with the largest current change rate in the simplified model is adjusted. The embodiment provides a preferred manner, that is, the attention analysis capability of the preset neural network model is reused, and the attention score calculated by the preset neural network model is used to preliminarily optimize the simplified model. The attention score represents the association of each environmental data and other environmental data, and when the preset neural network is trained by back propagation, the change amount of each attention score is obtained, which represents the deviation degree of the model in analyzing one kind of environmental data, and can be used to optimize the local simplified model. In this way, the powerful computing capability of the server is utilized, and in the case of small computing cost of the mobile phone, the association between various environmental data is analyzed, and the influence degree of various environmental data is obtained, which greatly improves the accuracy of the optimization of the local simplified model.

[0069] It can be understood that the above attention score can refer to any data capable of representing attention information obtained when the attention mechanism is calculated. For example, in a preferred embodiment, the preset neural network model includes an input layer, a query vector analysis layer, a key vector analysis layer, a softmax layer, a value vector analysis layer, a linear layer, and an output layer, wherein the input layer is used to input environmental data, the input ends of the query vector analysis layer, the key vector analysis layer, and the value vector analysis layer are connected to the input layer, and are respectively used to calculate the query vector, the key vector, and the value vector of each environmental data, the output ends of the query vector analysis layer and the key vector analysis layer are connected to the softmax layer, the softmax layer is used to calculate the attention score of one kind of environmental data relative to other environmental data, the output end of the softmax layer and the output end of the value vector analysis layer are connected to the linear layer, the linear layer is connected to the output layer, and the output layer is used to output the brightness data.

[0070] In the above process, the result output by the softmax layer is taken as the attention score, which has been normalized and is more intuitive. In practice, the product of the query vector and the key vector, or the product of the output of the softmax layer and the value vector can also be taken as the attention score.

[0071] Further, in a preferred embodiment, the above step S101, when the user actively adjusts the brightness of the display screen, records the adjustment data and counts the adjustment frequency, specifically includes:

[0072] When the user adjusts the brightness of the display screen, the brightness adjustment record is obtained;

[0073] A dynamic length analysis window is set in the brightness adjustment record, the proportion of the brightness adjustment record in the analysis window which is actively adjusted by the user is counted, and the proportion is taken as the adjustment frequency.

[0074] Specifically, in a preferred embodiment, the analysis window in the above steps refers to the data range on the time scale of the statistical adjustment frequency, and the analysis window is designed to be dynamic in this embodiment to improve practicability and avoid extreme cases of not requesting a new fitted simplified model for a long time or frequently requesting a new fitted simplified model.

[0075] Specifically, in a preferred embodiment, the length of the analysis window is dynamically adjusted in the following manner:

[0076] When the brightness of the mobile phone display screen is adjusted, it is determined whether the current adjustment is a user-initiated adjustment or a system automatic adjustment;

[0077] If the current adjustment is a user-initiated adjustment, the length of the analysis window is reduced;

[0078] If the current adjustment is a system automatic adjustment, the length of the analysis window is increased.

[0079] In this embodiment, system automatic adjustment indicates that the simplified model calculation is accurate, and user-initiated adjustment indicates that the simplified model calculation is inaccurate. When the calculation is accurate, the length of the analysis window is increased, the field of view of the statistical adjustment frequency is widened, and the specific calculation value of the adjustment frequency is further reduced, making the algorithm more stable, i.e., the mobile phone is more inclined to adjust the local simplified model, avoiding frequent requests for a new fitted simplified model, thereby not damaging the original brightness adjustment preference of the mobile phone, ensuring user experience, and reducing server pressure.

[0080] When the calculation is inaccurate, the length of the analysis window is shortened, and in the case of frequent user adjustment, the statistical adjustment frequency rises sharply, which can ensure that the mobile phone will request a more accurate model in time, improve response speed, and ensure user experience.

[0081] Further, in combination with Figure 2 shown, in a preferred embodiment, the step S105 of optimizing the local simplified model according to the attention score change amount specifically includes:

[0082] S201, preliminarily adjusting the local simplified model according to the attention score change amount to obtain a transition model;

[0083] S202, obtaining adjustment data corresponding to the attention score change amount as target adjustment data, the target adjustment data including target environment data and target brightness data;

[0084] S203, inputting the target adjustment data into the transition model to obtain an output result;

[0085] S204, adjusting the transition model according to the difference between the output result and the target brightness data to obtain an optimized simplified model.

[0086] The embodiment optimizes the simplified model twice, once according to the attention score change amount, and once again according to the target adjustment data, for common analysis from two dimensions to improve the accuracy of optimization.

[0087] Specifically, in a preferred embodiment, the simplified model includes a plurality of coefficients, each of which corresponds to environmental data. The above step S201 preliminarily adjusts the local simplified model according to the attention score change amount to obtain a transition model, specifically including:

[0088] According to the attention score change amount corresponding to each environmental data, the value of the coefficient corresponding to the environmental data is adjusted to obtain a transition model.

[0089] Further, in a preferred embodiment, the above step S204 adjusts the transition model according to the difference between the output result and the target brightness data to obtain an optimized simplified model, specifically including:

[0090] Calculate the difference between the output result and the target brightness data;

[0091] Calculate the partial derivative of each coefficient in the transition model according to the difference;

[0092] Adjust the value of each coefficient in the transition model according to the partial derivative of each coefficient to obtain an optimized simplified model.

[0093] In the above process, the way to optimize the transition model refers to the way of gradient descent in neural network, which has fast operation speed, high accuracy and less occupation of mobile phone computing resources.

[0094] Specifically, in a preferred embodiment, the specific steps of the above steps S201-S204 are:

[0095] The simplified model is:

[0096] B1 = ∑(wX + b);

[0097] Where B1 represents the output result of the simplified model, X represents an environmental data, w is the coefficient corresponding to the adjustment data, and b is the bias corresponding to the adjustment data;

[0098] The transition model is:

[0099] B2 = ∑((w + f(s))X + b + g(s));

[0100] Where B2 represents the output result of the transition model, s represents the attention score change amount corresponding to the adjustment data, f() and g() are different preset linear functions, which can be obtained according to experiments or experience;

[0101] The optimized simplified model is:

[0102]

[0103] B3 represents an output result of the optimized simplified model, is a partial derivative symbol, and a is a preset adjustment rate, which can also be obtained according to experiments or experience.

[0104] In combination with Figure 3 The application further provides a mobile phone, comprising:

[0105] The data recording module 310 is configured to record adjustment data and count adjustment frequency when the user actively adjusts the brightness of the display screen, the adjustment data including environmental data and brightness data.

[0106] The data uploading module 320 is configured to send the adjustment data to a server, the server being configured to train a preset neural network model according to the adjustment data, the preset neural network model being configured to calculate an attention score of each type of environmental data according to the adjustment data and calculate the brightness data according to the attention score.

[0107] The comparison optimization module 330 is configured to compare the adjustment frequency with a preset threshold.

[0108] If the adjustment frequency exceeds the preset threshold, a simplified model is obtained from the server, the simplified model being configured to calculate the brightness data according to the adjustment data, the simplified model being fitted based on a calculation result of the preset neural network model.

[0109] If the adjustment frequency does not exceed the preset threshold, an attention score change amount is obtained from the server, and the local simplified model is optimized according to the attention score change amount, the attention score change amount being an amount of change of the attention score in a process of back propagation of the preset neural network model.

[0110] The brightness adjustment module 340 is configured to adjust the brightness of the display screen according to the local simplified model.

[0111] It should be noted that the corresponding modules provided in the above embodiments can implement the technical solutions described in the above method embodiments, and the principles of implementation of the above modules or units can be referred to the corresponding content in the above method embodiments, which will not be described herein.

[0112] The embodiment further provides a computer readable storage medium having a display screen brightness automatic adjustment program stored thereon, the display screen brightness automatic adjustment program being executable by a processor to implement the steps in the above embodiments.

[0113] The application provides a display screen brightness automatic adjustment method, a mobile phone and a storage medium, which records adjustment data and counts adjustment frequency when a user actively adjusts the display screen brightness, then sends the adjustment data to a server, then compares the adjustment frequency with a preset threshold, if the adjustment frequency exceeds the preset threshold, acquires a simplified model from the server, if the adjustment frequency does not exceed the preset threshold, acquires an attention score change from the server, optimizes the local simplified model according to the attention score change, and finally adjusts the display screen brightness according to the local simplified model. The preset neural network model is used for calculating brightness and realizing user personalization by using the attention score through the server, the simplified model is obtained by fitting based on the calculation result of the preset neural network model, and is used for automatically adjusting brightness locally on the user's mobile phone, realizing lightweight, and ensuring the rapidness of screen brightness adjustment response. Most importantly, the local simplified model in the application can be optimized according to the change of the attention score of the preset neural network model, so that the mobile phone can complete automatic adjustment in line with the user's use habit without waiting for the server to respond when adjusting the screen in most cases, and when the local linear model is inaccurate, the simplified model can be refitted to obtain a more accurate simplified model, realizing the perfect combination of accuracy, personalization and lightweight of the mobile phone brightness adjustment.

[0114] It should be noted that each of the embodiments in the specification adopts a progressive manner for description, and each embodiment focuses on the difference from other embodiments, and the same and similar parts of each embodiment can be referred to each other.

[0115] The above description of the disclosed embodiments enables a person skilled in the art to implement or use the application. Various modifications to the embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the application. Therefore, the application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for automatically adjusting the brightness of a display screen, characterized in that, include: When a user actively adjusts the screen brightness, the adjustment data is recorded and the adjustment frequency is statistically analyzed. The adjustment data includes environmental data and brightness data. The environmental data includes data that can affect the user's adjustment of the phone's brightness. The adjustment data is sent to the server, which is used to train a preset neural network model based on the adjustment data. The preset neural network model is used to calculate the attention score for each type of environmental data based on the adjustment data, and to calculate the brightness data based on the attention score. The attention score is used to represent the correlation between each type of environmental data and other environmental data. Compare the adjustment frequency with the preset threshold; If the adjustment frequency exceeds the preset threshold, a simplified model is obtained from the server. The simplified model is used to calculate the brightness data based on the adjustment data. The simplified model is obtained by fitting the calculation results of the preset neural network model. If the adjustment frequency does not exceed the preset threshold, the change in attention score is obtained from the server, and the local simplified model is optimized based on the change in attention score; where the change in attention score is the change in attention score of the preset neural network model during backpropagation. Adjust the display brightness based on the local simplified model.

2. The automatic brightness adjustment method for a display screen according to claim 1, characterized in that, Optimize the local simplified model based on the change in attention score, including: Based on the change in attention score, the local simplified model is initially adjusted to obtain the transition model; Acquire the adjustment data corresponding to the change in attention score as target adjustment data. The target adjustment data includes target environment data and target brightness data. The target adjustment data is input into the transition model to obtain the output results; Based on the difference between the output results and the target brightness data, the transition model is adjusted to obtain an optimized simplified model.

3. The automatic brightness adjustment method for a display screen according to claim 2, characterized in that, The simplified model includes multiple coefficients, each corresponding to environmental data; Based on the change in attention score, the local simplified model is initially adjusted to obtain an interim model, including: Based on the change in attention score for each environmental data point, the values ​​of the coefficients corresponding to that environmental data point are adjusted to obtain the transition model.

4. The automatic brightness adjustment method for a display screen according to claim 3, characterized in that, Based on the difference between the output results and the target brightness data, the transition model is adjusted to obtain an optimized simplified model, including: Calculate the difference between the output result and the target brightness data; Calculate the partial derivative of each coefficient in the transition model based on the difference; By adjusting the value of each coefficient in the transition model based on the partial derivative of each coefficient, an optimized simplified model is obtained.

5. The automatic brightness adjustment method for a display screen according to claim 4, characterized in that, The simplified model is as follows: ； in, This represents the simplified model's output. This represents a type of environmental data. The coefficient corresponding to this type of adjustment data. This is the bias corresponding to this type of adjustment data; The transition model is: ； in, This represents the output of the transition model. This indicates the change in attention score corresponding to this type of adjustment data. and These are different preset linear functions; The optimized simplified model is as follows: ； in, This represents the output of the optimized simplified model. The sign of the partial derivative. This is the preset adjustment rate.

6. The automatic brightness adjustment method for a display screen according to claim 1, characterized in that, When a user adjusts the display brightness, the adjustment data is recorded and the adjustment frequency is statistically analyzed, including: Acquire brightness adjustment records when the user adjusts the display brightness; In the brightness adjustment record, a dynamic length analysis window is set. The brightness adjustment record in the statistical analysis window is the proportion that the user actively adjusts, and this proportion is used as the adjustment frequency.

7. The automatic brightness adjustment method for a display screen according to claim 6, characterized in that, Also includes: When the brightness of the mobile phone screen is adjusted, it is determined whether the adjustment is made actively by the user or automatically by the system. If this adjustment is made proactively by the user, then reduce the length of the analysis window; If this adjustment is done automatically by the system, then increase the length of the analysis window.

8. The automatic brightness adjustment method for a display screen according to claim 1, characterized in that, The environmental data includes at least one of the following: ambient light intensity, time, temperature, mobile phone backlight intensity, current application software, screen pixel distribution, face recognition data, fingerprint recognition data, and voiceprint recognition data. The preset neural network model includes an input layer, a query vector analysis layer, a key vector analysis layer, a softmax layer, a value vector analysis layer, a linear layer, and an output layer. The input layer is used to input the environmental data. The input ends of the query vector analysis layer, the key vector analysis layer, and the value vector analysis layer are all connected to the input layer and are used to calculate the query vector, key vector, and value vector for each type of environmental data, respectively. The output ends of the query vector analysis layer and the key vector analysis layer are both connected to the softmax layer. The softmax layer is used to calculate the attention score of one type of environmental data relative to other environmental data. The output ends of the softmax layer and the value vector analysis layer are both connected to the linear layer. The linear layer is connected to the output layer, which is used to output the brightness data.

9. A mobile phone, characterized in that, include: The data recording module is used to record adjustment data and count the adjustment frequency when the user actively adjusts the screen brightness. The adjustment data includes environmental data and brightness data. The environmental data includes data that can affect the user's adjustment of the phone brightness. The data upload module is used to send the adjustment data to the server. The server is used to train a preset neural network model based on the adjustment data. The preset neural network model is used to calculate the attention score for each type of environmental data based on the adjustment data, and to calculate the brightness data based on the attention score. The attention score is used to represent the correlation between each type of environmental data and other environmental data. The comparison and optimization module is used to compare the adjustment frequency with a preset threshold. If the adjustment frequency exceeds the preset threshold, a simplified model is obtained from the server. The simplified model is used to calculate the brightness data based on the adjustment data. The simplified model is obtained by fitting the calculation results of the preset neural network model. If the adjustment frequency does not exceed the preset threshold, the change in attention score is obtained from the server, and the local simplified model is optimized based on the change in attention score; where the change in attention score is the change in attention score of the preset neural network model during backpropagation. The brightness adjustment module is used to adjust the display brightness based on a local simplified model.

10. A computer-readable storage medium, characterized in that, Used to store computer-readable programs or instructions, which, when executed by a processor, can implement the steps in the automatic brightness adjustment method for a display screen as described in any one of claims 1-8.

Images