Screen brightness adjustment model training method and device, storage medium and electronic device

Abstract

The present disclosure relates to the field of mobile terminal technology, and specifically to a method and device for training a screen brightness adjustment model, a computer-readable storage medium, and an electronic device, wherein the method comprises: obtaining historical brightness adjustment data corresponding to each application in a user terminal; using the historical brightness adjustment data that meets a preset condition as target brightness adjustment data; based on the target brightness adjustment data, training a screen brightness adjustment model corresponding to the application indicated by the target brightness adjustment data; wherein the screen brightness adjustment model is used to adjust the screen brightness of the user terminal. The technical solution of the embodiment of the present disclosure meets the usage habits of different users, reduces the number of operations for users to manually adjust the brightness, and enhances the user experience.

Description

Background Art

[0002] In recent years, the number of smartphones has continued to increase, and mobile phones have become the main tool for office and entertainment, with average usage time increasing steadily. In order to meet users' needs for screen brightness in different scenarios, smart mobile devices have added a screen brightness adjustment function.

[0003] However, the screen brightness adjustment solutions in the related art cannot fully adapt to the user's usage habits, and there is no screen brightness adjustment solution for each user.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] The purpose of the present disclosure is to provide a screen brightness adjustment model training method, a screen brightness adjustment model training device, a computer-readable medium and an electronic device, so as to meet the usage habits of different users, reduce the number of operations of users manually adjusting the brightness, and enhance the user experience.

[0006] According to a first aspect of the present disclosure, a method for training a screen brightness adjustment model is provided, comprising: obtaining historical brightness adjustment data corresponding to each application in a user terminal; using the historical brightness adjustment data that meets a preset condition as target brightness adjustment data; based on the target brightness adjustment data, training a screen brightness adjustment model corresponding to the application indicated by the target brightness adjustment data; wherein the screen brightness adjustment model is used to adjust the screen brightness of the user terminal.

[0007] According to a second aspect of the present disclosure, a screen brightness adjustment method is provided, comprising: in response to a user launching a target application, adjusting the screen brightness using a screen brightness adjustment model corresponding to the target application; wherein the screen brightness adjustment model is trained by the above-mentioned screen brightness adjustment model training method.

[0008] According to a third aspect of the present disclosure, a screen brightness adjustment model training device is provided, comprising: an acquisition module for acquiring historical brightness adjustment data corresponding to each application in a user terminal; a determination module for using the historical brightness adjustment data that meets a preset condition as target brightness adjustment data; a training module for training a screen brightness adjustment model corresponding to the application indicated by the target brightness adjustment data based on the target brightness adjustment data; wherein the screen brightness adjustment model is used to adjust the screen brightness of the user terminal.

[0009] According to a fourth aspect of the present disclosure, a computer-readable medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the above method is implemented.

[0010] According to a fifth aspect of the present disclosure, an electronic device is provided, characterized in that it includes: one or more processors; and a memory for storing one or more programs, which enables the one or more processors to implement the above method when the one or more programs are executed by the one or more processors.

[0011] A screen brightness adjustment model training method provided by an embodiment of the present disclosure obtains historical brightness adjustment data corresponding to each application in a user terminal; uses the historical brightness adjustment data that meets a preset condition as target brightness adjustment data; based on the target brightness adjustment data, trains a screen brightness adjustment model corresponding to the application indicated by the target brightness adjustment data; wherein the screen brightness adjustment model is used to adjust the screen brightness of the user terminal. Compared with the prior art, different screen brightness adjustment models are trained for different users and different applications, and different models can be selected for different applications, so that the adjustment accuracy of each application is higher, thereby improving the user experience. Furthermore, the screen brightness adjustment model is used to adjust the screen brightness of the user terminal, that is, different models are used for different user terminals, and the training model of the historical brightness adjustment data in the user terminal is used, so that the obtained model is more suitable for the user corresponding to the user terminal, reducing the number of times the user manually adjusts the screen brightness, thereby enhancing the user experience.

[0012] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present disclosure, and together with the specification, are used to explain the principles of the present disclosure. Obviously, the drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0014] Figure 1 A schematic diagram showing an exemplary system architecture to which embodiments of the present disclosure may be applied;

[0015] Figure 2 A flowchart schematically illustrates a method for training a screen brightness adjustment model in an exemplary embodiment of the present disclosure;

[0016] Figure 3A flowchart of repeatability detection in an exemplary embodiment of the present disclosure is schematically shown;

[0017] Figure 4 A flowchart of training a screen brightness adjustment model in an exemplary embodiment of the present disclosure is schematically shown;

[0018] Figure 5 A flowchart schematically illustrates another method for training a screen brightness adjustment model in an exemplary embodiment of the present disclosure;

[0019] Figure 6 A flowchart schematically shows a method for adjusting screen brightness in an exemplary embodiment of the present disclosure;

[0020] Figure 7 A flowchart schematically illustrates another method for adjusting screen brightness in an exemplary embodiment of the present disclosure;

[0021] Figure 8 A flowchart schematically illustrating a model update in an exemplary embodiment of the present disclosure;

[0022] Fig. 9 A flowchart schematically illustrating another model update in an exemplary embodiment of the present disclosure;

[0023] Fig.10 A data flow diagram of a screen brightness adjustment method in an exemplary embodiment of the present disclosure is schematically shown;

[0024] Fig.11 A schematic diagram schematically shows the composition of a screen brightness adjustment model training device in an exemplary embodiment of the present disclosure;

[0025] Fig.12 A schematic diagram of an electronic device to which the embodiments of the present disclosure can be applied is shown. DETAILED DESCRIPTION

[0026] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the disclosure will be more comprehensive and complete and to fully convey the concepts of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0027] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0028] In the related technology, the general screen brightness adjustment method is to design a general backlight curve based on big data and subjective perception of the human eye, use the light sensor on the smart device to detect the intensity of the external ambient light, and output the corresponding screen brightness after a series of calculations based on the light intensity monitored by the sensor.

[0029] The existing methods do not take into account the user's personal usage habits and cannot perform intelligent dimming according to the user's personalized needs. For example, in a dim scene at night, a deep gaming user often adjusts the backlight brightness to the maximum value when playing a game with dark screens to improve the gaming experience. For this type of unilateral adjustment behavior, the existing technology lacks the ability to learn from this type of unilateral adjustment behavior.

[0030] Based on the above determination, the present disclosure first provides a screen brightness adjustment model training method, Figure 1 A schematic diagram of a system architecture to which the screen brightness adjustment model training method disclosed herein can be applied is shown, and the system architecture 100 may include a terminal 110 and a server 120. The terminal 110 may be a terminal device such as a smart phone, a tablet computer, a desktop computer, a laptop computer, etc., and the server 120 generally refers to a background system that provides services related to the screen brightness adjustment model training in this exemplary embodiment, and may be a server or a cluster formed by multiple servers. The terminal 110 and the server 120 may be connected via a wired or wireless communication link to exchange data.

[0031] In one implementation, the screen brightness adjustment model training method may be performed by the terminal 110. For example, the user uses the terminal 110 to extract the historical brightness adjustment data corresponding to the application programs, and the terminal 110 performs screen brightness adjustment model training on the image and outputs the screen brightness adjustment model.

[0032] In one implementation, the screen brightness adjustment model training method may be performed by the server 120. For example, after the user uses the terminal 110 to extract the historical brightness adjustment data corresponding to the application programs, the terminal 110 uploads the historical brightness adjustment data to the server 120, and the server 120 trains the screen brightness adjustment model and returns the screen brightness adjustment model corresponding to each user terminal to the terminal 110.

[0033] As can be seen from the above, the execution subject of the screen brightness adjustment model method in this exemplary embodiment can be the above-mentioned terminal 110 or server 120, and the present disclosure does not limit this.

[0034] Combine the following Figure 2 The screen brightness adjustment model training method in this exemplary embodiment is described. Figure 2 An exemplary process of the screen brightness adjustment model training method is shown, which may include:

[0035] Step S210, obtaining historical brightness adjustment data corresponding to each application in the user terminal;

[0036] Step S220, using the historical brightness adjustment data that meets the preset conditions as target brightness adjustment data;

[0037] Step S230, based on the target brightness adjustment data, training a screen brightness adjustment model corresponding to the application indicated by the target brightness adjustment data;

[0038] The screen brightness adjustment model is used to adjust the screen brightness of the user terminal.

[0039] Based on the above method, on the one hand, different screen brightness adjustment models are trained for different users and different applications, and different models can be selected for different applications, so that the adjustment accuracy of each application is higher, thereby improving the user experience. On the other hand, the screen brightness adjustment model is used to adjust the screen brightness of the user terminal, that is, different models are used for different user terminals, and the training model using the historical brightness adjustment data in the user terminal is used. The obtained model is more suitable for the user corresponding to the user terminal, reducing the number of times the user manually adjusts the screen brightness and enhancing the user experience.

[0040] Below Figure 2 Each step in the procedure is described in detail.

[0041] refer to Figure 2 In step S210, historical brightness adjustment data corresponding to each application in the user terminal is obtained.

[0042] In an example implementation of the present disclosure, the above-mentioned application is installed in the above-mentioned user terminal. One or more applications can be installed on each user terminal. The user may use different brightness when using different applications. At this time, since the user terminal cannot adjust automatically, the user will manually adjust the brightness to the user's requirements. For example, in a dim scene at night, a deep gaming user often plays games with dark screens. In order to improve the gaming experience, the backlight brightness will be adjusted upward to the maximum value.

[0043] In this example implementation, the data of the user manually adjusting the screen brightness can be used as historical brightness adjustment data, where each application can correspond to a historical brightness adjustment data. For example, if three applications A, B, and C are installed in the user terminal, the data corresponding to the user's manual brightness adjustment operations on the three applications A, B, and C are obtained respectively, and the historical brightness adjustment data corresponding to the three applications A, B, and C are established respectively.

[0044] In this example implementation, the above-mentioned historical brightness adjustment data may include the ambient light brightness before the user adjusts the application, the current screen brightness before adjustment, the target screen brightness after adjustment, etc. It may also include data such as screen color level, color temperature and contrast before adjustment, and can also be customized according to user needs, which is not specifically limited in this example implementation.

[0045] In an example implementation of the present disclosure, the above-mentioned historical brightness adjustment data may include brightness adjustment data for one month, or brightness adjustment data for 35 days. The specific time range can be customized according to user needs and is not specifically limited in this example implementation.

[0046] In step S220, the historical brightness adjustment data that meets the preset conditions is used as the target brightness adjustment data.

[0047] In this example implementation, after the historical brightness adjustment data corresponding to the above-mentioned multiple application programs are acquired, the above-mentioned historical brightness adjustment data may be detected, and the historical brightness adjustment data satisfying the preset conditions may be used as the above-mentioned target brightness adjustment data.

[0048] Specifically, the above-mentioned multiple historical brightness adjustment data can first be subjected to non-long tail detection. Specifically, for each group of historical brightness adjustment data, the number of brightness adjustments in the historical brightness adjustment data and the number of days on which brightness adjustment occurs in the historical brightness adjustment number can be detected. When the number of brightness adjustment times is greater than a first threshold and the number of days on which brightness adjustment occurs is greater than a second threshold, the above-mentioned historical brightness adjustment data is determined to have undergone non-long tail detection. The historical brightness adjustment data that meets the non-long tail detection can be determined as the target brightness adjustment data.

[0049] In this example implementation, it is assumed that the total number of days in the above-mentioned historical brightness adjustment data is 35 days. At this time, the first threshold value can be 100 times, 120 times or more times, or 49 times, 55 times, etc., and can also be customized according to user needs. The above-mentioned second threshold value can be 20 days, 28 days, etc., and can also be customized according to user needs. There is no specific limitation in this example implementation.

[0050] It should be noted that the first threshold and the second threshold can be determined according to the results of big data statistics, so that the accuracy of the obtained target historical data is higher.

[0051] In another exemplary implementation of the present disclosure, a repeatability test may be performed on each set of historical brightness adjustment data. Specifically, referring to Figure 3 As shown, it may include steps S310 to S340.

[0052] In step S310, the standard deviation and mean of the number of daily brightness adjustment times corresponding to the application program in the historical brightness adjustment data are determined.

[0053] In an example implementation of the present disclosure, the number of brightness adjustments corresponding to all days in the above-mentioned historical brightness adjustment data can be determined, and the standard deviation and mean corresponding to the brightness adjustments in multiple days can be calculated. It should be noted that the brightness adjustment here refers to the number of times the user manually adjusts the screen backlight brightness.

[0054] In step S320, the total number of days in each of the historical brightness adjustment data and the number of days on which brightness adjustment occurs are determined.

[0055] In step S330, a coefficient of variation is calculated based on the standard deviation, the mean, the total number of days, and the number of days on which brightness adjustment occurs.

[0056] In an exemplary implementation of the present disclosure, the total number of days in the historical brightness adjustment data may be determined, that is, one month, 35 days, etc., and then the number of days in which brightness adjustment occurs in the historical brightness adjustment data may be determined.

[0057] After obtaining the above data, the coefficient of variation can be calculated using the standard deviation, mean, total number of days, and number of days with brightness adjustment. Specifically, the coefficient of variation can be calculated using the coefficient of variation calculation formula, which is:

[0058]

[0059] Where i represents the serial number of the historical brightness adjustment data, or the serial number of the application, σ i represents the above standard deviation, μi represents the above average, P represents the total number of days in the above historical brightness adjustment data, and Q represents the number of days when brightness adjustment occurs.

[0060] In step S340, in response to the coefficient of variation being less than or equal to a third threshold, the historical brightness adjustment data is used as the target brightness adjustment data.

[0061] In this exemplary embodiment, after obtaining the above-mentioned coefficient of variation, the magnitude of the above-mentioned coefficient of variation and the third threshold value is determined, and the historical brightness adjustment data with a coefficient of variation less than or equal to the above-mentioned third threshold value is used as the above-mentioned target brightness adjustment data. i <CV thres When CV i The corresponding historical brightness adjustment data meets the repeatability test, and the historical brightness adjustment data meeting the repeatability test is used as the target brightness adjustment data.

[0062] In an exemplary embodiment disclosed herein, all historical brightness adjustment data that pass the non-long-tail detection and the repeatability detection may be used as the target brightness adjustment data.

[0063] In another example implementation of the present disclosure, the above historical brightness adjustment data may also be subjected to unilateral significance detection. Specifically, the total number of brightness adjustment of each historical brightness adjustment data may be determined first; then the number of brightness increase adjustment and the number of brightness decrease adjustment of each historical brightness adjustment data may be determined; based on the number of brightness increase adjustment, the number of brightness decrease adjustment and the total number of brightness adjustment, a first adjustment coefficient and a second adjustment coefficient may be determined; in response to the first brightness coefficient or the second adjustment coefficient being greater than a fourth threshold, the historical brightness adjustment data may be used as target brightness adjustment data. The first brightness coefficient is the ratio of the number of brightness increase adjustment to the total number of brightness adjustment, and the second brightness coefficient is the ratio of the number of brightness decrease adjustment to the total number of brightness adjustment.

[0064] Specifically, the first coefficient can be calculated using the following formula:

[0065]

[0066] Specifically, the second coefficient can be calculated using the following formula:

[0067]

[0068] In this example implementation, the range of the fourth threshold may be 80%, or 85%, 90%, etc., and may be customized according to user needs, which is not specifically limited in this example implementation.

[0069] In an example implementation, when the sum of the first coefficient and the second coefficient corresponding to each set of historical brightness adjustment data is 1, and when either the first coefficient or the second coefficient is greater than the fourth threshold, it can be determined that the historical brightness adjustment data satisfies the unilateral significance detection. The historical brightness adjustment data that satisfies the unilateral significance detection can be used as the target brightness adjustment data.

[0070] In an exemplary implementation of the present disclosure, the historical brightness image adjustment data that simultaneously satisfies the above-mentioned non-long-tail detection, repeatability detection, and unilateral saliency detection may be used as the above-mentioned target brightness adjustment data.

[0071] In the process of screening the target brightness adjustment data, that is, the process of selecting an application that can use the model to adjust the brightness, that is, the application corresponding to the target brightness adjustment data can use the screen brightness adjustment model trained by the present disclosure to adjust the screen backlight brightness.

[0072] In step S230, based on the target brightness adjustment data, a screen brightness adjustment model corresponding to the application indicated by the target brightness adjustment data is trained;

[0073] The screen brightness adjustment model is used to adjust the screen brightness of the user terminal.

[0074] In an example implementation of the present disclosure, after obtaining the above-mentioned target brightness adjustment data, the above-mentioned target brightness adjustment data can be updated using empirical rules. For example, assuming that the adjusted target screen brightness in the above-mentioned target brightness data is L, that is, the adjusted target screen brightness in each group of target brightness data should be normally distributed. If there is a target screen brightness that does not conform to the above-mentioned normal distribution in the above-mentioned target brightness adjustment data, it will be eliminated. The elimination can be carried out using empirical rules, that is, the 3-sigma rule, and repeated iterations are performed until all target screen brightnesses are within 3-sigma.

[0075] In an example implementation of the present disclosure, when updating the target brightness adjustment data, it is not limited to the target screen brightness after adjustment, but the difference between the target screen brightness after adjustment and the brightness before adjustment, that is, the adjustment amplitude, can also be adjusted. Similarly, the adjustment amplitude conforms to the normal distribution, and the mean and variance of the adjustment amplitude are calculated. The empirical rule, that is, the 3-sigma rule, is used to eliminate the data corresponding to the adjustment that does not conform, and the iteration is repeated until all adjustment amplitudes are within 3-sigma.

[0076] In this example implementation, the brightness value before adjustment can be the brightness value automatically adjusted by the terminal according to the ambient light, that is, the brightness value common to all interfaces of the terminal, or it can be the brightness value set for the interface where the application is located when the user last started the application. No specific limitation is made in this example implementation.

[0077] In an example implementation of the present disclosure, when updating the target brightness adjustment data, the difference between the target screen brightness and the original curve backlight can also be adjusted, and the difference conforms to the normal distribution, that is, when calculating the multi-measurement brightness adjustment, the mean and variance of the difference, and then the empirical rule, that is, the 3-sigma rule, is used to eliminate the data corresponding to the adjustment that does not conform, and iterate repeatedly until all the above differences are within 3-sigma. In this example implementation, the original curve backlight represents the brightness value after the terminal is automatically adjusted according to the ambient light, that is, the brightness value common to all interfaces of the terminal.

[0078] After the above-mentioned processing of the above-mentioned target brightness data, the above-mentioned target brightness adjustment data can be used to train the screen brightness adjustment model corresponding to the application indicated by the target brightness adjustment data. Specifically, it can refer to Figure 4 As shown, it includes steps S410 to S440.

[0079] In step S410, multiple screen brightness adjustment schemes are obtained.

[0080] In this example implementation, the multiple screen brightness adjustment schemes herein are different from the models, for example, the real data corresponding to the above model outputs are different, such as the difference between the target screen brightness and the original curve backlight, the adjusted target screen brightness, the adjustment amplitude, etc.

[0081] For instructions on the difference between the target screen brightness and the original curve backlight, the adjusted target screen brightness, the adjustment range, etc., please refer to the updating process of the above-mentioned target brightness adjustment data, which will not be repeated here.

[0082] In step S420, the credibility of each of the screen brightness adjustment schemes is evaluated.

[0083] In step S430, an initial model corresponding to the application indicated by the target brightness adjustment data is established based on the screen brightness adjustment solution with the highest credibility.

[0084] In this example implementation, the corresponding credibility is determined based on the difference between the target screen brightness and the original curve backlight, the adjusted target screen brightness, and the variance corresponding to the adjustment amplitude.

[0085] Specifically, after calculating the variance of the difference between the target screen brightness and the original curve backlight, the variance of the adjusted target screen brightness, and the variance of the adjustment amplitude, the three variances are compared. The smaller the variance, the higher the credibility. The one with the smallest variance, that is, the highest credibility, can be used as the real data corresponding to the output of the above model.

[0086] At this point, an initial model can be constructed. The input of the initial model may include the ambient light brightness before adjustment, the current screen brightness before adjustment, and data such as the screen color level, color temperature, and contrast before adjustment. The model may also be customized according to user needs.

[0087] The output of the model can be determined based on the brightness adjustment scheme with the highest credibility. For example, if the variance corresponding to the adjusted target screen flatness is the smallest among the three variances mentioned above, the output of the model is the adjusted reference screen brightness.

[0088] In step S440, the initial model is trained using the target brightness adjustment data to obtain the screen brightness adjustment model.

[0089] The parameters of the model are updated based on the difference between the target screen brightness and the reference screen brightness to complete the training of the initial model, thereby obtaining the screen brightness adjustment model.

[0090] Refer to the following Figure 5 The training method of the above-mentioned screen brightness adjustment model is generally summarized. First, step S510 can be executed to obtain historical brightness adjustment data, and then step S520 can be executed to determine whether the above-mentioned historical brightness adjustment data meets the non-long-tail detection test. If not, then the process ends. If it does, step S530 is executed to determine whether the above-mentioned historical brightness adjustment data meets the repeatability test. If not, then the process ends. If it does, step S540 is executed to determine whether the above-mentioned historical brightness adjustment data meets the unilateral significance test. If not, then the process ends. If it does, step S550 is executed to determine the historical brightness adjustment data as the target brightness adjustment data, and then step S560 is executed to update the target brightness adjustment data using empirical rules to complete the outlier sample proposal. At the same time, step S570 can be executed to select the screen brightness adjustment scheme, and then step S580 is executed to determine the brightness adjustment scheme with the highest credibility and establish an initial model; then step S590 is executed to train the above-mentioned initial model using the target brightness adjustment data to obtain the screen brightness adjustment model.

[0091] In summary, in this exemplary embodiment, different screen brightness adjustment models are trained for different users and the same application programs, and different models can be selected for different applications, so that the adjustment accuracy for each application program is higher, thereby improving the user experience. Furthermore, the screen brightness adjustment model is used to adjust the screen brightness of the user terminal, that is, different models are used for different user terminals, and the training model of the historical brightness adjustment data in the user terminal is used, so that the obtained model is more suitable for the user corresponding to the user terminal, thereby enhancing the user experience. Furthermore, the above historical adjustment data is subjected to non-long-tail detection, repeatability detection and unilateral significance detection, which can enhance the accuracy of the obtained target brightness adjustment data, and at the same time, the above target brightness adjustment data is subjected to outlier samples using empirical rules, which further improves the accuracy of the target brightness adjustment data, so that the adjustment accuracy of the trained screen brightness data is higher, and the number of times the user manually adjusts the screen brightness is reduced, thereby greatly enhancing the user experience.

[0092] Furthermore, the present disclosure also provides a method for adjusting screen brightness, referring to Figure 6 As shown, the process includes the following step S610.

[0093] In step S610, in response to the user starting a target application, the screen brightness is adjusted using a screen brightness adjustment model corresponding to the target application.

[0094] The screen brightness adjustment model is obtained by training the screen brightness adjustment model training method. The training method of the screen brightness adjustment model has been described in detail above, so it will not be repeated here.

[0095] In this example implementation, refer to Figure 7 As shown, in response to a user launching a target application, adjusting the screen brightness using a screen brightness adjustment model corresponding to the target application may include step S710 and step S720.

[0096] In step S710, in response to a user starting a target application, it is determined whether the target application has a corresponding screen brightness adjustment model.

[0097] In this example implementation, when the user starts the target application, the processor can first determine whether there is a corresponding screen brightness adjustment model for the above application. If not, the brightness value at this time is adjusted to the brightness value when the application was last started, or the brightness value at this time is directly adjusted to the general brightness adjusted by the user according to the ambient light brightness.

[0098] In step S720, in response to the target application having a corresponding screen brightness adjustment model, the screen brightness is adjusted using the screen brightness adjustment model corresponding to the target application.

[0099] In this example implementation, in this example real-time mode, if the above-mentioned target application has a corresponding screen brightness adjustment model, the screen brightness adjustment model corresponding to the above-mentioned target application is used to obtain the required target brightness, and then the screen brightness of the interface corresponding to the target application is adjusted to the above-mentioned target brightness.

[0100] In this example implementation, when the screen brightness of the interface corresponding to the target application is adjusted to the above-mentioned target brightness, it can be adjusted successively, that is, the brightness values ​​of all interfaces within the target application are adjusted to the target brightness within a preset number of times. For example, when the user starts the target application, the general brightness of the user terminal is 200Nit, and the calculated target brightness is 200Nit. At this time, after the user starts the target application, the brightness within the above-mentioned target application can be first adjusted to 280Nit, and when the user starts the above-mentioned target application for the second time, the brightness is adjusted to the target brightness, that is, 300Nit.

[0101] It should be noted that the above-mentioned preset number of times can be two times, three times, etc., and can also be customized according to user needs, and is not specifically limited in this example implementation.

[0102] In an exemplary embodiment of the present disclosure, referring to Figure 8 As shown, the above-mentioned screen brightness adjustment method may further include steps S810 to S830.

[0103] In step S810, the total number of times the target application uses the screen brightness adjustment model is determined;

[0104] In step S820, the number of times the target application is adjusted using the screen brightness adjustment model without the user performing a second manual adjustment is determined.

[0105] In this example implementation, after a time threshold of weeks has passed using the screen brightness adjustment model, the total number of times the target application has used the screen brightness adjustment model can be determined, as well as the number of times the user did not perform a secondary manual adjustment after the target application used the screen brightness adjustment model.

[0106] In step S830, in response to the ratio of the practical number of times to the total number of times being less than a fifth threshold, the screen brightness adjustment model corresponding to the target application is updated using the screen brightness adjustment data after the user's second manual adjustment.

[0107] In this example implementation, the ratio of the practical times to the total times may be calculated as a profit coefficient. Specifically:

[0108]

[0109] Among them, n represents the number of practical times, N represents the total number of times, and R represents the profit coefficient.

[0110] In this example implementation, when the above-mentioned profit coefficient is greater than the above-mentioned fifth threshold value, it means that the accuracy of the above-mentioned screen brightness model is relatively high and does not need to be updated. If the above-mentioned profit coefficient is less than the above-mentioned fifth threshold value, it means that the accuracy of the above-mentioned screen brightness model can no longer meet the user's needs. At this time, the screen brightness data after the user's second manual adjustment can be used to update the screen brightness adjustment model corresponding to the above-mentioned target application, wherein the above-mentioned fifth threshold value can be 90%, 95%, etc., and can also be customized according to user needs, which is not specifically limited in this example implementation.

[0111] In an exemplary embodiment of the present disclosure, referring to Fig. 9 As shown, the above-mentioned screen brightness adjustment method may further include steps S910 to S950.

[0112] In step S910, a first difference between the screen brightness value after the second manual adjustment by the user and the target brightness is determined;

[0113] In step S920, a second difference between the screen brightness value after the second manual adjustment by the user and the initial brightness before adjustment by the brightness adjustment model is determined;

[0114] In step S930, a first expected optimization range of the model is calculated based on the first difference and the second difference.

[0115] In an exemplary implementation of the present disclosure, after obtaining the first difference and the second difference, the first expected optimization range can be calculated using the following formula. Specifically,

[0116]

[0117]

[0118] 5=abs(L 二次手动调节过后的屏幕亮度值 -L 目标亮度 )

[0119] 5 * = abs(L 二次手动调节过后的屏幕亮度值 -L 初始亮度 )

[0120] Among them, 5 represents the absolute value of the first difference, 5 *represents the absolute value of the second difference, p i represents weight, tanh() is the hyperbolic tangent function, EI 模型建议值 Represents the first expected optimization amplitude.

[0121] In step S940, a second expected optimization range of the original adjustment solution of the terminal is obtained;

[0122] In step S950, a target expected optimization range is determined based on the first expected optimization range and the second expected optimization range.

[0123] In an example implementation of the present disclosure, the second expected optimization range is an optimization range corresponding to a general adjustment method for adjusting brightness according to ambient light set by the user, and can be directly obtained in the user terminal.

[0124] After obtaining the first expected optimization range and the second expected optimization range, the difference between the first expected optimization range and the second expected optimization range can be used as the target expected optimization range. Specifically:

[0125] ΔEI=EI 模型建议值 -EI 通用曲线建议值

[0126] Among them, ΔEI represents the expected optimization range of the target, EI 通用曲线建议值 Represents the second expected optimization magnitude.

[0127] In step S960, in response to the target expected optimization amplitude being less than a sixth threshold, the screen brightness adjustment model corresponding to the target application is updated using the screen brightness adjustment data after the user's second manual adjustment.

[0128] In this example implementation, after obtaining the above target expected optimization range, the relationship between the above target expected optimization range and the sixth threshold value can be determined. If the above target expected optimization range is greater than or equal to the above sixth threshold value, the accuracy of the screen brightness adjustment model is relatively high. If the target expected optimization range is less than the above sixth threshold value, it means that the accuracy of the screen brightness model can no longer meet the user's needs. At this time, the screen brightness data after the user's second manual adjustment can be used to update the screen brightness adjustment model corresponding to the above target application. Among them, the above sixth threshold value can be customized according to user needs and is not specifically limited in this example implementation.

[0129] Refer to the following Fig.10The specific application of the above-mentioned screen brightness adjustment method is described in detail. First, step S1001 can be executed to read in data, that is, to read the screen intensity adjustment data in the application using a step length of 200 milliseconds, and then step S1002 can be executed to clean up the abnormal data read in during reading, and step S1003 can be executed at the same time to store the cleaned data in the real-time storage queue 1010, and then step S1004 can be executed to determine whether the application has a corresponding screen brightness adjustment model, and step S1005 can be executed to store the screen brightness adjustment model. It is determined that when a corresponding screen brightness adjustment model exists in the application, the screen brightness adjustment data is stored in the long-term storage module 1020, and the processor obtains the historical brightness adjustment in the long-term storage module 1020 through the timer 1030, and then executes step S1006. Model training, after training, the model is evaluated by the evaluation module 1040, and then step S1007 is executed, model deployment, the model corresponding to the application level is deployed in the adjustment stage corresponding to the application level, and then the brightness of the above model is adjusted through the probe system 1050 and the simulator 1060.

[0130] In this example implementation, if the user performs a secondary manual adjustment, step S1008 is executed to label the secondary adjusted data; and at the same time, the secondary adjusted data is stored in the long-term storage module 1020, and step S1009 is executed to terminate the policy judgment. Specifically, the step of terminating the policy activation judgment is performed by the prevention system 1070, and step S1004 is terminated.

[0131] It should be noted that the above figures are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present disclosure, and are not intended to be limiting. It is easy to understand that the processes shown in the above figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0132] For further reference, Fig.11 As shown, in the implementation of this example, a screen brightness adjustment model training device 1100 is also provided, including an acquisition module 1110, a determination module 1120 and a training module 1130. Among them:

[0133] The acquisition module 1120 may be configured to acquire historical brightness adjustment data corresponding to each application in the user terminal.

[0134] The determination module 1120 may be configured to use the historical brightness adjustment data satisfying a preset condition as the target brightness adjustment data.

[0135] In an example implementation of the present disclosure, the determination module 1120 may be configured to use the historical brightness adjustment data as the target brightness adjustment data in response to the number of brightness adjustments in the historical brightness adjustment data being greater than a first threshold and the number of days in which brightness adjustment occurs in the historical brightness adjustment data being greater than a second threshold.

[0136] In an example implementation of the present disclosure, the determination module 1120 may be configured to determine the standard deviation and mean of the number of daily brightness adjustments corresponding to the application in the historical brightness adjustment data; determine the total number of days in each of the historical brightness adjustment data, and the number of days on which brightness adjustment occurs; calculate the coefficient of variation based on the standard deviation, the mean, the total number of days, and the number of days on which brightness adjustment occurs; and in response to the coefficient of variation being less than or equal to a third threshold, use the historical brightness adjustment data as the target brightness adjustment data.

[0137] In an example implementation of the present disclosure, the determination module 1120 may be configured to determine the total number of brightness adjustments of each of the historical brightness adjustment data; determine the number of brightness increase adjustments and the number of brightness decrease adjustments of each of the historical brightness adjustment data; determine a first adjustment coefficient and a second adjustment coefficient based on the number of brightness increase adjustments, the number of brightness decrease adjustments, and the total number of brightness adjustments; in response to the first brightness coefficient or the second adjustment coefficient being greater than the fourth threshold, use the historical brightness adjustment data as the target brightness adjustment data. The first brightness coefficient is the ratio of the number of brightness increase adjustments to the total number of brightness adjustments, and the first brightness coefficient is the ratio of the number of brightness decrease adjustments to the total number of brightness adjustments.

[0138] The training module 1130 may be configured to train a screen brightness adjustment model corresponding to the application indicated by the target brightness adjustment data based on the target brightness adjustment data.

[0139] In an example implementation, the training module 1130 may be configured to obtain a plurality of screen brightness adjustment schemes; perform credibility assessment on each of the screen brightness adjustment schemes; establish an initial model corresponding to the application indicated by the target brightness adjustment data based on the screen brightness adjustment scheme with the highest credibility; and train the initial model using the target brightness adjustment data to obtain the screen brightness adjustment model.

[0140] The specific details of each module in the above device have been described in detail in the implementation method of the method part. The undisclosed details can be found in the implementation method of the method part, so they will not be repeated here.

[0141] The exemplary embodiment of the present disclosure also provides an electronic device for executing the above-mentioned screen brightness adjustment model method, and the electronic device may be the above-mentioned terminal 110 or server 120. Generally, the electronic device may include a processor and a memory, the memory is used to store executable instructions of the processor, and the processor is configured to execute the above-mentioned screen brightness adjustment model method by executing the executable instructions.

[0142] Below Fig.12 The mobile terminal 1200 in FIG. 1 is taken as an example to exemplify the structure of the electronic device. It should be understood by those skilled in the art that, in addition to the components specifically used for mobile purposes, Fig.12 The construction in can also be applied to fixed type equipment.

[0143] like Fig.12 As shown, the mobile terminal 1200 may specifically include: a processor 1201, a memory 1202, a bus 1203, a mobile communication module 1204, an antenna 1, a wireless communication module 1205, an antenna 2, a display screen 1206, a camera module 1207, an audio module 1208, a power module 1209 and a sensor module 1210.

[0144] The processor 1201 may include one or more processing units, for example, the processor 1201 may include an AP (Application Processor), a modem processor, a GPU (Graphics Processing Unit), an ISP (Image Signal Processor), a controller, an encoder, a decoder, a DSP (Digital Signal Processor), a baseband processor and / or an NPU (Neural-Network Processing Unit), etc. The screen brightness adjustment model training method in this exemplary embodiment may be executed by an AP, a GPU or a DSP, and when the method involves processing related to a neural network, it may be executed by an NPU.

[0145] The processor 1201 may be connected to the memory 1202 or other components via a bus 1203 .

[0146] The memory 1202 may be used to store computer executable program codes, which include instructions. The processor 1201 executes various functional applications and data processing of the mobile terminal 1200 by running the instructions stored in the memory 1202. The memory 1202 may also store application data, such as images, videos and other files.

[0147] The communication function of the mobile terminal 1200 can be implemented by the mobile communication module 1204, antenna 1, wireless communication module 1205, antenna 2, modulation and demodulation processor and baseband processor. Antenna 1 and antenna 2 are used to transmit and receive electromagnetic wave signals. The mobile communication module 204 can provide 2G, 3G, 4G, 5G and other mobile communication solutions applied to the mobile terminal 1200. The wireless communication module 1205 can provide wireless communication solutions such as wireless LAN, Bluetooth, near field communication, etc. applied to the mobile terminal 1200.

[0148] The display screen 1206 is used to implement display functions, such as displaying user interfaces, images, videos, etc. The camera module 1207 is used to implement shooting functions, such as shooting images, videos, etc. The audio module 1208 is used to implement audio functions, such as playing audio, collecting voice, etc. The power module 1209 is used to implement power management functions, such as charging the battery, powering the device, monitoring the battery status, etc. The sensor module 1210 may include a depth sensor 12101, a pressure sensor 12102, a gyroscope sensor 12103, an air pressure sensor 12104, etc., to implement corresponding sensing detection functions.

[0149] Those skilled in the art will appreciate that various aspects of the present disclosure may be implemented as systems, methods or program products. Therefore, various aspects of the present disclosure may be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to herein as "circuits", "modules" or "systems".

[0150] The exemplary embodiments of the present disclosure also provide a computer-readable storage medium on which a program product capable of implementing the above-mentioned method of the present specification is stored. In some possible implementations, various aspects of the present disclosure may also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary embodiments of the present disclosure described in the above-mentioned "Exemplary Method" section of the present specification.

[0151] It should be noted that the computer-readable medium shown in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0152] In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus, or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0153] In addition, program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0154] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and examples are to be considered as exemplary only, and the true scope and spirit of the present disclosure are indicated by the claims.

[0155] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A screen brightness adjustment model training method, characterized in that: include: Acquire historical brightness adjustment data corresponding to each application in the user terminal; the historical brightness adjustment data is data of screen brightness manually adjusted by the user, and each application corresponds to one historical brightness adjustment data; Using the historical brightness adjustment data that meets the preset conditions as target brightness adjustment data; The preset condition includes at least one of non-long-tail detection, repeatability detection and unilateral significance detection; Based on the target brightness adjustment data, training a screen brightness adjustment model corresponding to the application indicated by the target brightness adjustment data; Wherein, the screen brightness adjustment model is used to adjust the screen brightness of the user terminal; In the non-long-tail detection, the taking the historical brightness adjustment data that meets the preset conditions as the target brightness adjustment data includes: In response to the number of brightness adjustments in the historical brightness adjustment data being greater than a first threshold, and the number of days in which brightness adjustment occurs in the historical brightness adjustment data being greater than a second threshold, using the historical brightness adjustment data as the target brightness adjustment data; In the repeatability detection, the step of using the historical brightness adjustment data that meets a preset condition as target brightness adjustment data includes: Determine the standard deviation and mean of the number of daily brightness adjustment times corresponding to the application in the historical brightness adjustment data; Determine the total number of days in each of the historical brightness adjustment data, and the number of days on which brightness adjustment occurs; Calculate the coefficient of variation based on the standard deviation, the mean, the total number of days, and the number of days on which brightness adjustment occurs; In response to the coefficient of variation being less than or equal to a third threshold, using the historical brightness adjustment data as the target brightness adjustment data; In the unilateral saliency detection, the step of using the historical brightness adjustment data satisfying a preset condition as target brightness adjustment data includes: Determine the total number of brightness adjustments of each of the historical brightness adjustment data; Determine the number of times the brightness is increased and the number of times the brightness is decreased for each of the historical brightness adjustment data; Determining a first adjustment coefficient and a second adjustment coefficient based on the number of adjustments to increase the brightness, the number of adjustments to decrease the brightness, and the total number of brightness adjustments; In response to the first adjustment coefficient or the second adjustment coefficient being greater than a fourth threshold, using the historical brightness adjustment data as the target brightness adjustment data; The first adjustment coefficient is the ratio of the number of adjustments to increase the brightness to the total number of brightness adjustments, and the second adjustment coefficient is the ratio of the number of adjustments to reduce the brightness to the total number of brightness adjustments.

2. The method according to claim 1, characterized in that The training of the screen brightness adjustment model corresponding to the application indicated by the target brightness adjustment data based on the target brightness adjustment data comprises: Get multiple screen brightness adjustment solutions; Conducting credibility evaluation on each of the screen brightness adjustment schemes; Establishing an initial model corresponding to the application indicated by the target brightness adjustment data based on the screen brightness adjustment solution with the highest credibility; The target brightness adjustment data is used to train the initial model to obtain the screen brightness adjustment model.

3. The method according to claim 1, characterized in that The method further comprises: The target brightness adjustment data is updated based on an empirical rule to eliminate outlier samples of the target brightness adjustment data.

4. A screen brightness adjustment method, characterized in that: include: In response to a user launching a target application, adjusting the screen brightness using a screen brightness adjustment model corresponding to the target application; The screen brightness adjustment model is obtained by training using the screen brightness adjustment model training method described in any one of claims 1 to 3.

5. The method according to claim 4, characterized in that In response to a user starting a target application, adjusting the screen brightness using a screen brightness adjustment model corresponding to the target application, including: In response to a user launching a target application, determining whether the target application has a corresponding screen brightness adjustment model; In response to the target application having a corresponding screen brightness adjustment model, the screen brightness is adjusted using the screen brightness adjustment model corresponding to the target application.

6. The method according to claim 4, characterized in that The adjusting the screen brightness by using the screen brightness adjustment model corresponding to the target application comprises: Determining a target brightness based on an output of the screen brightness adjustment model; The screen brightness is adjusted to the target brightness within a preset number of times.

7. The method according to claim 5, characterized in that The method further comprises: Determine the total number of times the target application is adjusted using the screen brightness adjustment model; Determine the number of times the target application is adjusted using the screen brightness adjustment model without the user performing a second manual adjustment; In response to the ratio of the practical number of times to the total number of times being less than a fifth threshold, the screen brightness adjustment model corresponding to the target application is updated using the screen brightness adjustment data after the user manually adjusts it for the second time.

8. The method according to claim 7, characterized in that The method further comprises: Determine a first difference between the screen brightness value after the second manual adjustment by the user and the target brightness; Determine a second difference between the screen brightness value after the second manual adjustment by the user and the initial brightness before adjustment by the brightness adjustment model; Calculating a first expected optimization amplitude of the model based on the first difference and the second difference; Acquire a second expected optimization range of the original adjustment solution of the terminal; Determining a target expected optimization range based on the first expected optimization range and the second expected optimization range; In response to the target expected optimization amplitude being less than a sixth threshold, the screen brightness adjustment model corresponding to the target application is updated using the screen brightness adjustment data after the user's second manual adjustment.

9. A screen brightness adjustment model training device, characterized in that: include: An acquisition module is used to acquire historical brightness adjustment data corresponding to each application in the user terminal; the historical brightness adjustment data is data of the screen brightness manually adjusted by the user, and each application corresponds to one historical brightness adjustment data; A determination module, configured to use the historical brightness adjustment data satisfying a preset condition as target brightness adjustment data; The preset condition includes at least one of non-long-tail detection, repeatability detection and unilateral significance detection; A training module, configured to train a screen brightness adjustment model corresponding to the application indicated by the target brightness adjustment data based on the target brightness adjustment data; Wherein, the screen brightness adjustment model is used to adjust the screen brightness of the user terminal; In the non-long-tail detection, the determination module is specifically configured to respond to the number of brightness adjustments in the historical brightness adjustment data being greater than a first threshold, and the number of days in which brightness adjustment occurs in the historical brightness adjustment data being greater than a second threshold, using the historical brightness adjustment data as the target brightness adjustment data; In the repeatability detection, the determination module is specifically used to determine the standard deviation and mean of the number of daily brightness adjustment times corresponding to the application in the historical brightness adjustment data; determine the total number of days in each of the historical brightness adjustment data, and the number of days on which brightness adjustment occurs; calculate the coefficient of variation based on the standard deviation, the mean, the total number of days, and the number of days on which brightness adjustment occurs; in response to the coefficient of variation being less than or equal to a third threshold, use the historical brightness adjustment data as the target brightness adjustment data; In the unilateral significance detection, the determination module is specifically used to determine the total number of brightness adjustments of each of the historical brightness adjustment data; determine the number of adjustments to increase the brightness and the number of adjustments to decrease the brightness of each of the historical brightness adjustment data; determine a first adjustment coefficient and a second adjustment coefficient based on the number of adjustments to increase the brightness, the number of adjustments to decrease the brightness, and the total number of brightness adjustments; in response to the first adjustment coefficient or the second adjustment coefficient being greater than a fourth threshold, use the historical brightness adjustment data as the target brightness adjustment data; wherein the first adjustment coefficient is the ratio of the number of adjustments to increase the brightness to the total number of brightness adjustments, and the second adjustment coefficient is the ratio of the number of adjustments to decrease the brightness to the total number of brightness adjustments.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the screen brightness adjustment model training method as described in any one of claims 1 to 3 or the screen brightness adjustment method as described in any one of claims 4 to 8 is implemented.

11. An electronic device, characterized in that: include: one or more processors; as well as A memory for storing one or more programs, which, when executed by the one or more processors, enables the one or more processors to implement the screen brightness adjustment model training method as described in any one of claims 1 to 3, or the screen brightness adjustment method as described in any one of claims 4 to 8.

Images