CN107748682B - Background application management and control method, device, storage medium and electronic device - Google Patents

Abstract

The application discloses a background application control method, a background application control device, a storage medium and electronic equipment, wherein the method comprises the following steps: inputting the sample data into an algorithm model to obtain a plurality of first prediction results; when the plurality of first prediction results comprise correct prediction results and wrong prediction results, respectively acquiring a first characteristic parameter value of a target characteristic parameter in sample data, which corresponds to the correct prediction results, and a second characteristic parameter value, which corresponds to the wrong prediction results; calculating to obtain an initial preset compensation value according to the first characteristic parameter value and the second characteristic parameter value; inputting the sample data and the initial preset compensation value into an algorithm model for training to obtain a target preset compensation value; and applying a plurality of current characteristic parameters and a target preset compensation value to a preset background, inputting the current characteristic parameters and the target preset compensation value into an algorithm model to obtain a target prediction result, and managing and controlling the preset background application according to the target prediction result. The accuracy of predicting the preset background application is improved, and the accuracy of background application control is improved.

Description

Background application management and control method, device, storage medium and electronic device

technical field

The present application relates to the field of communication technologies, and in particular, to a background application management and control method, device, storage medium and electronic device.

Background technique

Cleaning up background applications is a common and effective way to reduce memory usage and power consumption. However, the background application cannot be cleaned at will. If the background application is about to be used, but it is cleaned up, it needs to be restarted, which takes a long time to start and increases the power consumption accordingly. Therefore, it is of great significance to accurately determine whether a background application can be cleaned. The traditional method for judging that background applications can be cleaned is based on statistics, such as keeping the most commonly used applications and cleaning up less commonly used applications. However, this cleaning method has the problem of insufficient prediction accuracy.

SUMMARY OF THE INVENTION

The present application provides a background application management and control method, device, storage medium and electronic device, which can improve the accuracy of application management and control.

In a first aspect, an embodiment of the present application provides a background application management and control method, applied to an electronic device, including the steps:

Input the sample data into the algorithm model to obtain multiple first prediction results;

When the plurality of first prediction results include a correct prediction result and an incorrect prediction result, respectively obtain the first feature parameter value of the target feature parameter corresponding to the correct prediction result and the second feature corresponding to the incorrect prediction result in the sample data parameter value;

Calculate and obtain an initial preset compensation value according to the first characteristic parameter value and the second characteristic parameter value;

Inputting the sample data and the initial preset compensation value into the algorithm model for training to obtain a target preset compensation value;

The preset background is applied with a plurality of current feature parameters and the target preset compensation value corresponding to the target feature parameter, and the algorithm model is input to obtain a target prediction result, and according to the target prediction result Preset background applications for control.

In a second aspect, an embodiment of the present application provides a background application management and control device, which is applied to an electronic device, including:

a first prediction result obtaining unit, configured to input the sample data into the algorithm model to obtain a plurality of first prediction results;

a feature parameter value obtaining unit, configured to respectively obtain a first feature parameter value corresponding to the correct prediction result of the target feature parameter in the sample data when the plurality of first prediction results include a correct prediction result and an incorrect prediction result, and the second characteristic parameter value corresponding to the wrong prediction result;

an initial compensation value obtaining unit, configured to calculate and obtain an initial preset compensation value according to the first characteristic parameter value and the second characteristic parameter value;

a target preset compensation value acquisition unit, configured to input the sample data and the initial preset compensation value into the algorithm model for training to obtain a target preset compensation value;

A management and control unit, configured to input the preset background application current multiple feature parameters and the target preset compensation value corresponding to the target feature parameter into the algorithm model to obtain a target prediction result, and according to the target The prediction result controls the preset background application.

In a third aspect, an embodiment of the present application provides a storage medium on which a computer program is stored, and when the computer program runs on a computer, the computer enables the computer to execute the above-mentioned background application management and control method.

In a fourth aspect, an embodiment of the present application provides an electronic device, including a processor and a memory, the memory having a computer program, and the processor is configured to execute the above-mentioned background application management and control method by invoking the computer program.

In the background application management and control method, device, storage medium, and electronic device provided by the embodiments of the present application, multiple first prediction results are obtained by inputting sample data into an algorithm model; when the multiple first prediction results include correct prediction results and incorrect predictions When the result is obtained, the first characteristic parameter value corresponding to the correct prediction result and the second characteristic parameter value corresponding to the wrong prediction result in the sample data are obtained respectively; the initial prediction value is calculated according to the first characteristic parameter value and the second characteristic parameter value. Set the compensation value; input the sample data and the initial preset compensation value into the algorithm model for training to obtain the target preset compensation value; apply the current multiple feature parameters and the target preset compensation value to the preset background, input the algorithm model, and obtain Target prediction results, and control the preset background applications according to the target prediction results. The accuracy of predicting preset background applications can be improved, thereby improving the accuracy of managing and controlling applications entering the background.

Description of drawings

In order to illustrate the technical solutions in the embodiments of the present application more clearly, the following briefly introduces the accompanying drawings that are used in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative effort.

FIG. 1 is a system schematic diagram of a background application management and control apparatus provided by an embodiment of the present application;

FIG. 2 is a schematic diagram of an application scenario of a background application management and control device provided by an embodiment of the present application;

3 is a schematic flowchart of a background application management and control method provided by an embodiment of the present application;

4 is a schematic flowchart of selecting target feature parameters according to an embodiment of the present application;

5 is a schematic flowchart of obtaining an initial preset compensation value according to an embodiment of the present application;

6 is another schematic flowchart of obtaining an initial preset compensation value provided by an embodiment of the present application;

7 is a schematic flowchart of obtaining a target preset compensation value according to an embodiment of the present application;

FIG. 8 is a first structural schematic diagram of a background application management and control apparatus provided by an embodiment of the present application;

FIG. 9 is a schematic structural diagram of a second type of a background application management and control apparatus provided by an embodiment of the present application;

10 is a schematic structural diagram of a third type of a background application management and control apparatus provided by an embodiment of the present application;

FIG. 11 is a schematic diagram of a fourth structure of a background application management and control apparatus provided by an embodiment of the present application;

FIG. 12 is a schematic structural diagram of a fifth type of a background application management and control apparatus provided by an embodiment of the present application;

13 is a schematic structural diagram of an electronic device provided by an embodiment of the present application;

FIG. 14 is another schematic structural diagram of an electronic device provided by an embodiment of the present application.

Detailed ways

Please refer to the drawings, wherein the same component symbols represent the same components, and the principles of the present application are exemplified by being implemented in a suitable computing environment. The following description is based on illustrated specific embodiments of the present application and should not be construed as limiting other specific embodiments of the present application not detailed herein.

In the following description, specific embodiments of the present application will be described with reference to steps and symbols performed by one or more computers, unless otherwise stated. Accordingly, the steps and operations will be referred to several times as being performed by a computer, which reference herein includes operations by a computer processing unit of electronic signals representing data in a structured format. This operation transforms the data or maintains it in a location in the computer's memory system, which can be reconfigured or otherwise change the operation of the computer in a manner well known to testers in the art. The data structures maintained by the data are physical locations of the memory that have specific characteristics defined by the data format. However, the principles of the present application are described by the above text, which does not represent a limitation. Testers in the art will understand that the following various steps and operations can also be implemented in hardware.

As used herein, the term "module" can be thought of as a software object that executes on the computing system. The different components, modules, engines and services herein can be considered as implementation objects on the computing system. The apparatus and method herein can be implemented in software, and certainly can also be implemented in hardware, which are all within the protection scope of the present application.

The terms "first," "second," and "third," etc. in this application are used to distinguish different objects, rather than to describe a specific order. Furthermore, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or modules is not limited to the listed steps or modules, but some embodiments also include unlisted steps or modules, or some embodiments Other steps or modules inherent to these processes, methods, products or devices are also included.

Reference herein to an "embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor a separate or alternative embodiment that is mutually exclusive of other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

Please refer to FIG. 1 , which is a schematic diagram of a system of a background application management and control apparatus provided by an embodiment of the present application. The background application control device is mainly used for: inputting sample data into an algorithm model to obtain a plurality of first prediction results; when the plurality of first prediction results include correct prediction results and wrong prediction results, respectively acquiring target feature parameters in the sample data The first characteristic parameter value corresponding to the correct prediction result and the second characteristic parameter value corresponding to the wrong prediction result; the initial preset compensation value is calculated according to the first characteristic parameter value and the second characteristic parameter value; the sample data and the initial preset compensation value are obtained. Compensation value, input the algorithm model for training, and obtain the target preset compensation value; apply the current multiple feature parameters and the target preset compensation value to the preset background, input the algorithm model, obtain the target prediction result, and adjust the prediction result according to the target prediction result. Set up background applications for control. Such as closing, or freezing, etc.

Specifically, please refer to FIG. 2 , which is a schematic diagram of an application scenario of the background application management and control apparatus provided by the embodiment of the present application. For example, when the background application management and control device receives the management and control request, it detects that the applications running in the background of the electronic device include a preset background application a, a preset background application b, and a preset background application c; and then obtains the corresponding preset background application. a. Preset multiple characteristic parameters of background application b and preset background application c, and input multiple characteristic parameters into the algorithm model; obtain probability a', probability b' and probability c' respectively; then according to probability a', probability b ' and probability c' respectively manage and control the preset background application a, the preset background application b, and the preset background application c running in the background, for example, the preset background application b with the lowest probability is closed.

The embodiment of the present application provides a background application management and control method, and the execution body of the background application management and control method may be the background application management and control device provided by the embodiment of the present application, or an electronic device integrated with the background application management and control device, wherein the background application management and control The apparatus can be implemented in hardware or software.

The embodiments of the present application will be described from the perspective of a background application management and control apparatus, and the background application management and control apparatus may specifically be integrated in an electronic device. The background application management and control method includes: inputting sample data into an algorithm model to obtain a plurality of first prediction results; when the plurality of first prediction results include correct prediction results and incorrect prediction results, respectively obtaining the corresponding correct target feature parameters in the sample data The first characteristic parameter value of the prediction result, and the second characteristic parameter value corresponding to the wrong prediction result; the initial preset compensation value is calculated according to the first characteristic parameter value and the second characteristic parameter value; the sample data and the initial preset compensation value are calculated , input the algorithm model for training, and obtain the target preset compensation value; apply the current multiple feature parameters and the target preset compensation value to the preset background, input the algorithm model, get the target prediction result, and make the preset background according to the target prediction result. application control.

Please refer to FIG. 3 , which is a schematic flowchart of a background application management and control method provided by an embodiment of the present application. The background application management and control method provided by the embodiment of the present application is applied to an electronic device, and the specific process may be as follows:

Step 101: Input the sample data into the algorithm model to obtain a plurality of first prediction results.

The sample data includes feature parameter sets of multiple dimensions. The sample data is pre-acquired training sample data. The feature parameters in the sample data correspond to the running parameters of the background application. A specific sample data can be shown in Table 1 below, including feature information of multiple dimensions. It should be noted that Table 1 The feature parameters shown are only examples. In practice, the number of feature parameters contained in a sample data may be more than the number of feature parameters shown in Table 1, or less than the number of feature parameters shown in Table 1, so The specific characteristic parameters taken may also be different from those shown in Table 1, which are not specifically limited here.

Table 1

Each time the sample data is input to the algorithm model, the feature parameters can be all, or it can be formed by selecting some feature parameters from the sample data. As shown in Table 2, one input data is 10 feature parameters selected from the sample data.

dimension Characteristic Parameters 1 The screen-off time of the electronic device during switching to the background 2 Daily time at the front desk 3 Types of applications, including primary (common applications), secondary (other applications) 4 Screen time of electronic devices 5 The current battery level of the electronic device 6 Current wireless network status 7 The amount of time the app is used in the foreground 8 The average time interval from the current foreground application entering the background to the target application entering the foreground 9 The average screen-off time between the current foreground application entering the background and the target application entering the foreground 10 The proportion of the number of times of each preset interval in the histogram of the app staying time in the background

Table 2

It should be noted that the dimensions in Table 2 are only examples of feature parameters in an input data, and do not mean that the dimensions of the feature parameters are limited. In some embodiments, characteristic parameters can be selected according to actual needs.

The training sample data includes multiple feature parameters, and the feature parameter values included in each feature parameter are different. Each sample data includes multiple feature parameters, and each feature parameter corresponds to one or more feature parameter values. These sample data are used as training The data are respectively input into the algorithm model, and the algorithm model obtains a plurality of corresponding first prediction results according to the sample data.

It should be noted that the feature parameters of the same sample data may correspond to different feature parameter values.

The characteristic parameter values of a characteristic parameter are shown in Table 3.

Table 3: On-screen off-screen records

Step 102, when the multiple first prediction results include correct prediction results and incorrect prediction results, respectively obtain the first characteristic parameter value of the target characteristic parameter corresponding to the correct prediction result in the sample data, and the second characteristic parameter corresponding to the wrong prediction result. value.

The first prediction result is a result obtained by the algorithm model predicting corresponding to different input data. Different input data may result in different results. These include correct predictions and incorrect predictions. When the multiple first prediction results include a correct prediction result and an incorrect prediction result, respectively obtain the first characteristic parameter value corresponding to the correct prediction result and the second characteristic parameter value corresponding to the incorrect prediction result in the sample data of the target characteristic parameter.

Please refer to FIG. 4 together. FIG. 4 is a schematic flowchart of selecting target feature parameters according to an embodiment of the present application. In this embodiment, the specific process of the method for obtaining target feature parameters may be as follows:

Step 1021 , modify the weights of each feature parameter of the input algorithm model in sequence.

The input data of the input algorithm model includes multiple feature parameters. When one of the feature parameters is modified each time, the weight of the feature parameter is continuously adjusted, such as continuously decreasing or increasing. A prediction result. Among them, the weight can be continuously reduced until it drops to zero, that is, the characteristic parameter is removed.

Step 1022, if the first prediction result changes, determine that the corresponding feature parameter is the target feature parameter.

The first prediction result changes, that is, from the correct prediction result to the wrong prediction result, or from the wrong prediction result to the correct prediction result, indicating that the characteristic parameter can play a key role in the correctness of the prediction result, then determine the corresponding The feature parameters of are the target feature parameters.

Step 103: Calculate and obtain an initial preset compensation value according to the first characteristic parameter value and the second characteristic parameter value.

The initial preset compensation value can be obtained by obtaining the difference between the first characteristic parameter value and the second characteristic parameter value, or the first characteristic parameter value and the second characteristic parameter value can be multiplied by different weight values and then subtracted to obtain the initial value. Preset compensation value.

Please refer to FIG. 5 together. FIG. 5 is a schematic flowchart of obtaining an initial preset compensation value according to an embodiment of the present application. In this embodiment, the specific process of obtaining the initial preset compensation value may be as follows:

Step 10131: Obtain multiple first feature parameter values corresponding to multiple correct prediction results of the target feature parameter.

Step 10132: Acquire multiple second feature parameter values corresponding to multiple error prediction results of the target feature parameter.

Step 10133: Calculate and obtain an initial preset compensation value according to an average value of a plurality of first characteristic parameter values and an average value of a plurality of second characteristic parameter values.

The initial preset compensation value is obtained by averaging a plurality of first characteristic parameter values and a plurality of second characteristic parameter values respectively, and then subtracting them. Of course, the average value of the first characteristic parameter value and the average value of the second characteristic parameter value can also be multiplied by different weight values and then subtracted to obtain the initial preset compensation value.

Please also refer to FIG. 6 . FIG. 6 is another schematic flowchart of obtaining an initial preset compensation value according to an embodiment of the present application. In this embodiment, the specific process of obtaining the initial preset compensation value may be as follows:

Step 10134: Obtain the feature parameter value of the target feature parameter and a plurality of reference feature parameter values that are gradients with the feature parameter value.

The gradient can be an increasing gradient or a decreasing gradient. First obtain the characteristic parameter value of the target characteristic parameter, then use the characteristic parameter value as the base, and then obtain an increasing and/or decreasing sequence based on the base. The value of the gradient can be one-tenth, one-half, etc. of the base. It can be an equal gradient, or it may not be equal, as the order of magnitude of the data in the sequence changes, for example, the larger the data, the larger the difference, and the smaller the data, the smaller the difference.

Step 10135: Input multiple reference feature parameter values into the algorithm model to obtain a second prediction result.

Then, the multiple reference feature parameter values are respectively input into the algorithm module to obtain multiple second prediction results. Correspondingly, the feature parameter values corresponding to other feature parameters in the input data remain unchanged.

Step 10136: If the second prediction result changes, obtain the first characteristic parameter value and the second characteristic parameter value corresponding to the adjacent correct prediction result and the wrong prediction result, respectively.

The second prediction result is also different because the input data is different. When the second prediction result changes from correct to incorrect, or from incorrect to correct, the first characteristic parameter value and the second characteristic parameter value corresponding to the adjacent correct prediction result and the incorrect prediction result are obtained. That is, two adjacent data in the gradient data.

Step 10137: Obtain an initial preset compensation value according to the difference between the first characteristic parameter value and the second characteristic parameter value.

The initial preset compensation value is obtained by subtracting the first characteristic parameter value and the second characteristic parameter value. Of course, the initial preset compensation value may also be obtained by multiplying the first characteristic parameter value and the second characteristic parameter value by different weight values respectively and then subtracting them.

Step 104: Input the sample data and the initial preset compensation value into the algorithm model for training to obtain the target preset compensation value.

The target feature parameters in the sample data are superimposed on the initial preset compensation value before being input into the algorithm model, and then input into the algorithm model for prediction. After a large number of training and learning, a target preset compensation value is obtained, which can allow more input data to be After superimposing the target preset compensation value, the prediction accuracy is improved.

Please also refer to FIG. 7 , which is a schematic flowchart of obtaining a target preset compensation value according to an embodiment of the present application. In this embodiment, the specific process of obtaining the target preset compensation value may be as follows:

Step 1041: Acquire a corresponding first value range according to a plurality of first characteristic parameter values.

From a plurality of first characteristic parameter values, a first value range can be obtained.

Step 1042: Acquire a corresponding second value range according to a plurality of second characteristic parameter values.

Similarly, a second value range can be obtained from the plurality of second characteristic parameter values. It is even possible to set a third value range, and the second value range is on both sides of the first value range.

Step 1043: Obtain a first target preset compensation value corresponding to the first value range and a second target preset compensation value corresponding to the second value range.

Set different target preset compensation values corresponding to different value ranges. If the prediction result corresponding to the target eigenvalue within the first value range is correct, no compensation or only less compensation is required, and the target feature parameter value within the second value range needs to be compensated, which may be increased or may be reduce.

Step 105: Apply the current multiple feature parameters and the target preset compensation value corresponding to the target feature parameter in the preset background, input the algorithm model, obtain the target prediction result, and adjust the preset value according to the target prediction result. Background applications are controlled.

Before predicting the preset background application, first obtain multiple current feature parameters of the preset background application, superimpose the target feature parameters in the multiple feature parameters with the corresponding target preset compensation value, and then input the algorithm model. It should be noted that, the target characteristic parameter may include multiple ones, and the target preset compensation value corresponds to the target characteristic parameter one-to-one.

The target prediction result may be a probability value of clearing the preset background application, and/or a probability value of not cleaning the background application, and then controlling the preset background application according to the target prediction result, such as closing or keeping the background application .

The plurality of characteristic parameters are input into the algorithm model, and the characteristic parameter values corresponding to one or more of the characteristic parameters of the algorithm model are superimposed with corresponding target preset compensation values. For example, input 10 feature parameters into the algorithm model, including two target feature parameters: current power and background running time, where the feature parameter value of current power is 10%, and the feature parameter value of background running time is 10 minutes, then The target preset compensation value -%2 corresponding to the characteristic parameter value of the current power is superimposed by 10%, that is, 10%-2%=8%, the characteristic parameter value of the input algorithm model is 8%, and the characteristic parameter value of the background running time is 8%. The target preset compensation value corresponding to the 10-minute superposition is 5 minutes, that is, 10 minutes + 5 minutes = 15 minutes, and the characteristic parameter value of the input algorithm model is 15 minutes. Then, the algorithm model performs prediction according to the characteristic parameter value after superimposing the preset compensation value of the corresponding target, and obtains the prediction result. It should be noted that this example is only an example for understanding, and does not limit the present application, and the present application may also use the target preset compensation value in other ways.

It should be noted that the training process of the algorithm model can be completed on the server side or on the electronic device side. When the training process of the algorithm model and the actual prediction process are completed on the server side, and the optimized algorithm model needs to be used, the usage status of the preset background application in multiple time periods before the current time can be input to the server, and the server can actually predict After completion, the prediction result is sent to the electronic device, and the electronic device controls the preset background application according to the prediction result.

When the training process of the algorithm model and the actual prediction process are completed on the electronic device, and the optimized algorithm model needs to be used, the usage status of the preset background application in multiple time periods before the current time can be input to the electronic device. After the actual prediction of the device is completed, the electronic device controls the preset background application according to the prediction result.

When the training process of the algorithm model is completed on the server side and the actual prediction process of the algorithm model is completed on the electronic device side, and the optimized algorithm model needs to be used, the preset background can be applied to the usage status of multiple time periods before the current time Input to the electronic device, after the actual prediction of the electronic device is completed, the electronic device controls the preset background application according to the prediction result. Optionally, the trained algorithm model file (model file) can be transplanted to the smart device. If it is necessary to determine whether the current background application can be cleaned, the usage status of the preset background application in multiple time periods before the current time is obtained, Input into the trained algorithm model file (model file), and the predicted value can be obtained by calculation.

All the above technical solutions can be combined arbitrarily to form optional embodiments of the present application, which will not be repeated here.

It can be seen from the above that the background application management and control method provided by the embodiment of the present application obtains multiple first prediction results by inputting the sample data into the algorithm model; when the multiple first prediction results include correct prediction results and incorrect prediction results, respectively. Obtain the first characteristic parameter value corresponding to the correct prediction result and the second characteristic parameter value corresponding to the wrong prediction result in the sample data of the target characteristic parameter; and obtain the initial preset compensation value by calculating according to the first characteristic parameter value and the second characteristic parameter value; Input the sample data and the initial preset compensation value into the algorithm model for training to obtain the target preset compensation value; apply the current multiple feature parameters and the target preset compensation value to the preset background, input the algorithm model, and obtain the target prediction result, And control the preset background applications according to the target prediction results. The accuracy of predicting preset background applications can be improved, thereby improving the accuracy of managing and controlling applications entering the background.

Please refer to FIG. 8 , FIG. 8 is a first structural schematic diagram of a background application management and control apparatus provided by an embodiment of the present application. The background application management and control device 300 is applied to electronic equipment, and the background application management and control device 300 includes a first prediction result obtaining unit 301, a characteristic parameter value obtaining unit 302, an initial compensation value obtaining unit 303, a target preset compensation value obtaining unit 304 and Management and control unit 305 . in:

The first prediction result obtaining unit 301 is configured to input the sample data into the algorithm model to obtain a plurality of first prediction results.

The sample data includes feature parameter sets of multiple dimensions. The sample data is pre-acquired training sample data, the characteristic parameters in the sample data correspond to the running parameters of the background application, and a specific sample data includes characteristic information of multiple dimensions.

The feature parameters of the sample data input to the algorithm model each time can be all, or can be formed by selecting some of the feature parameters from the sample data.

The training sample data includes multiple feature parameters, and the feature parameter values included in each feature parameter are different. Each sample data includes multiple feature parameters, and each feature parameter corresponds to one or more feature parameter values. These sample data are used as training The data are respectively input into the algorithm model, and the algorithm model obtains a plurality of corresponding first prediction results according to the sample data.

The feature parameter value obtaining unit 302 is configured to respectively obtain the first feature parameter value corresponding to the correct prediction result of the target feature parameter in the sample data, and the corresponding incorrect prediction result when the multiple first prediction results include a correct prediction result and an incorrect prediction result. The second eigenparameter value of the result.

The first prediction result is a result obtained by the algorithm model predicting corresponding to different input data. Different input data may result in different results. These include correct predictions and incorrect predictions. When the multiple first prediction results include a correct prediction result and an incorrect prediction result, respectively obtain the first characteristic parameter value corresponding to the correct prediction result and the second characteristic parameter value corresponding to the incorrect prediction result in the sample data of the target characteristic parameter.

Please refer to FIG. 9 , FIG. 9 is a schematic structural diagram of a second type of a background application management and control apparatus provided by an embodiment of the present application. In this embodiment, the feature parameter value obtaining unit 302 includes a weight obtaining subunit 3021 and a target feature parameter obtaining subunit 3022 .

The weight obtaining subunit 3021 is used for sequentially modifying the weight of each characteristic parameter of the input algorithm model.

The input data of the input algorithm model includes multiple feature parameters. When one of the feature parameters is modified each time, the weight of the feature parameter is continuously adjusted, such as continuously decreasing or increasing. A prediction result. Among them, the weight can be continuously reduced until it drops to zero, that is, the characteristic parameter is removed.

The target feature parameter acquisition subunit 3022 is configured to determine the corresponding feature parameter as the target feature parameter if the first prediction result changes.

The first prediction result changes, that is, from the correct prediction result to the wrong prediction result, or from the wrong prediction result to the correct prediction result, indicating that the characteristic parameter can play a key role in the correctness of the prediction result, then determine the corresponding The feature parameters of are the target feature parameters.

The initial compensation value obtaining unit 303 is configured to calculate and obtain an initial preset compensation value according to the first characteristic parameter value and the second characteristic parameter value.

The initial preset compensation value can be obtained by obtaining the difference between the first characteristic parameter value and the second characteristic parameter value, or the first characteristic parameter value and the second characteristic parameter value can be multiplied by different weight values and then subtracted to obtain the initial value. Preset compensation value.

Please refer to FIG. 10. FIG. 10 is a schematic structural diagram of a third type of a background application management and control apparatus provided by an embodiment of the present application. In this embodiment, the initial compensation value acquisition unit 303 includes a first characteristic parameter value acquisition subunit 3031, a second characteristic parameter value acquisition subunit 3032, and an initial compensation value acquisition subunit 3033. Wherein:

The first feature parameter value obtaining subunit 3031 is configured to obtain multiple first feature parameter values corresponding to multiple correct prediction results of the target feature parameter.

The second feature parameter value obtaining subunit 3032 is configured to obtain multiple second feature parameter values corresponding to multiple error prediction results of the target feature parameter.

The initial compensation value obtaining subunit 3033 is configured to calculate and obtain the initial preset compensation value according to the average value of the plurality of first characteristic parameter values and the average value of the plurality of second characteristic parameter values.

The initial preset compensation value is obtained by averaging a plurality of first characteristic parameter values and a plurality of second characteristic parameter values respectively, and then subtracting them. Of course, the average value of the first characteristic parameter value and the average value of the second characteristic parameter value can also be multiplied by different weight values and then subtracted to obtain the initial preset compensation value.

Please refer to FIG. 11 . FIG. 11 is a schematic diagram of a fourth structure of a background application management and control apparatus provided by an embodiment of the present application. In this embodiment, the initial compensation value obtaining unit 303 includes a reference characteristic parameter value obtaining subunit 3034 , a second prediction result obtaining subunit 3035 , a characteristic parameter value obtaining subunit 3036 and an initial preset compensation value obtaining subunit 3033 . in:

The reference feature parameter value obtaining subunit 3034 is configured to obtain the feature parameter value of the target feature parameter and a plurality of reference feature parameter values that are gradients with the feature parameter value.

The gradient can be an increasing gradient or a decreasing gradient. First obtain the characteristic parameter value of the target characteristic parameter, then use the characteristic parameter value as the base, and then obtain an increasing and/or decreasing sequence based on the base. The value of the gradient can be one-tenth, one-half, etc. of the base. It can be an equal gradient, or it may not be equal, as the order of magnitude of the data in the sequence changes, for example, the larger the data, the larger the difference, and the smaller the data, the smaller the difference.

The second prediction result obtaining subunit 3035 is configured to input multiple reference feature parameter values into the algorithm model to obtain the second prediction result.

Then, the multiple reference feature parameter values are respectively input into the algorithm module to obtain multiple second prediction results. Correspondingly, the feature parameter values corresponding to other feature parameters in the input data remain unchanged.

The characteristic parameter value obtaining subunit 3036 is configured to obtain the first characteristic parameter value and the second characteristic parameter value corresponding to the adjacent correct prediction result and the wrong prediction result respectively if the second prediction result changes.

The second prediction result is also different because the input data is different. When the second prediction result changes from correct to incorrect, or from incorrect to correct, the first characteristic parameter value and the second characteristic parameter value corresponding to the adjacent correct prediction result and the incorrect prediction result are obtained. That is, two adjacent data in the gradient data.

The initial preset compensation value obtaining subunit 3033 is configured to obtain the initial preset compensation value according to the difference between the first characteristic parameter value and the second characteristic parameter value.

The initial preset compensation value is obtained by subtracting the first characteristic parameter value and the second characteristic parameter value. Of course, the initial preset compensation value may also be obtained by multiplying the first characteristic parameter value and the second characteristic parameter value by different weight values respectively and then subtracting them.

The target preset compensation value acquiring unit 304 is configured to input the sample data and the initial preset compensation value into the algorithm model for training to obtain the target preset compensation value.

The target feature parameters in the sample data are superimposed on the initial preset compensation value before being input into the algorithm model, and then input into the algorithm model for prediction. After a large number of training and learning, a target preset compensation value is obtained, which can allow more input data to be After superimposing the target preset compensation value, the prediction accuracy is improved.

Please refer to FIG. 12 . FIG. 12 is a schematic structural diagram of a fifth type of a background application management and control apparatus provided by an embodiment of the present application. In this embodiment, the target preset compensation value acquisition unit 304 includes:

The first value range obtaining subunit 3041 is configured to obtain a corresponding first value range according to a plurality of first characteristic parameter values.

From a plurality of first characteristic parameter values, a first value range can be obtained.

The second value range obtaining subunit 3042 is configured to obtain a corresponding second value range according to a plurality of second characteristic parameter values.

Similarly, a second value range can be obtained from the plurality of second characteristic parameter values. It is even possible to set a third value range, and the second value range is on both sides of the first value range.

The first target preset compensation value determination subunit 3043 is configured to acquire the first target preset compensation value corresponding to the first value range.

Set different target preset compensation values corresponding to different value ranges. If the prediction result corresponding to the target eigenvalue within the first value range is correct, no compensation or only less compensation is required, and the target feature parameter value within the second value range needs to be compensated, which may be increased or may be reduce.

The second target preset compensation value determination subunit 3044 is configured to acquire the second target preset compensation value corresponding to the second value range.

The management and control unit 305 is configured to input the current plurality of characteristic parameters and target preset compensation values of the preset background application into the algorithm model, obtain the target prediction result, and manage and control the preset background application according to the target prediction result.

Before predicting the preset background application, first obtain multiple current feature parameters of the preset background application, superimpose the target feature parameters in the multiple feature parameters with the corresponding target preset compensation value, and then input the algorithm model. It should be noted that, the target characteristic parameter may include multiple ones, and the target preset compensation value corresponds to the target characteristic parameter one-to-one.

The target prediction result may be a probability value of clearing the preset background application, and/or a probability value of not cleaning the background application, and then controlling the preset background application according to the target prediction result, such as closing or keeping the background application .

All the above technical solutions can be combined arbitrarily to form optional embodiments of the present application, which will not be repeated here.

It can be seen from the above that the background application management and control device provided by the embodiment of the present application obtains multiple first prediction results by inputting sample data into the algorithm model; when the multiple first prediction results include correct prediction results and incorrect prediction results, they are respectively Obtain the first characteristic parameter value corresponding to the correct prediction result and the second characteristic parameter value corresponding to the wrong prediction result in the sample data of the target characteristic parameter; and obtain the initial preset compensation value by calculating according to the first characteristic parameter value and the second characteristic parameter value; Input the sample data and the initial preset compensation value into the algorithm model for training to obtain the target preset compensation value; apply the current multiple feature parameters and the target preset compensation value to the preset background, input the algorithm model, and obtain the target prediction result, And control the preset background applications according to the target prediction results. The accuracy of predicting preset background applications can be improved, thereby improving the accuracy of managing and controlling applications entering the background.

In the embodiments of the present application, the background application management and control apparatus and the background application management and control method in the above embodiments belong to the same concept, and any method provided in the background application management and control method embodiments can be executed on the background application management and control apparatus, and the specific implementation process thereof For details, please refer to the embodiment of the background application management and control method, which will not be repeated here.

The embodiments of the present application also provide an electronic device. Referring to FIG. 13 , the electronic device 400 includes a processor 401 and a memory 402 . The processor 401 is electrically connected to the memory 402 .

The processor 400 is the control center of the electronic device 400, uses various interfaces and lines to connect various parts of the entire electronic device, executes the electronic device by running or loading the computer program stored in the memory 402, and calling the data stored in the memory 402. Various functions of the device 400 and data processing are performed to monitor the electronic device 400 as a whole.

The memory 402 can be used to store software programs and modules, and the processor 401 executes various functional applications and data processing by running the computer programs and modules stored in the memory 402 . The memory 402 may mainly include a stored program area and a stored data area, wherein the stored program area may store an operating system, a computer program required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; Data created by the use of electronic equipment, etc. Additionally, memory 402 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, memory 402 may also include a memory controller to provide processor 401 access to memory 402 .

In the embodiment of the present application, the processor 401 in the electronic device 400 loads the instructions corresponding to the processes of one or more computer programs into the memory 402 according to the following steps, and is executed by the processor 401 and stored in the memory 402 The computer program in , so as to realize various functions, as follows:

Input the sample data into the algorithm model to obtain multiple first prediction results;

When the plurality of first prediction results include a correct prediction result and an incorrect prediction result, obtain the first characteristic parameter value of the target characteristic parameter corresponding to the correct prediction result and the second characteristic parameter value corresponding to the incorrect prediction result in the sample data respectively;

Calculate the initial preset compensation value according to the first characteristic parameter value and the second characteristic parameter value;

Input the sample data and the initial preset compensation value into the algorithm model for training to obtain the target preset compensation value;

The preset background application current multiple feature parameters and target preset compensation values are input into the algorithm model to obtain the target prediction result, and the preset background application is managed and controlled according to the target prediction result.

In some embodiments, the processor 401 is further configured to perform the following steps:

obtaining multiple first feature parameter values corresponding to multiple correct prediction results of the target feature parameter;

obtaining multiple second feature parameter values corresponding to multiple error prediction results of the target feature parameter;

The initial preset compensation value is calculated according to the average value of the plurality of first characteristic parameter values and the average value of the plurality of second characteristic parameter values.

In some embodiments, the processor 401 is further configured to perform the following steps:

Obtain the feature parameter value of the target feature parameter, and multiple reference feature parameter values that are gradients with the feature parameter value;

Inputting multiple reference feature parameter values into the algorithm model to obtain a second prediction result;

If the second prediction result changes, obtain the first characteristic parameter value and the second characteristic parameter value corresponding to the adjacent correct prediction result and the wrong prediction result respectively;

The initial preset compensation value is obtained according to the difference between the first characteristic parameter value and the second characteristic parameter value.

In some embodiments, the processor 401 is further configured to perform the following steps:

Modify the weights of each feature parameter of the input algorithm model in turn;

If the first prediction result changes, the corresponding feature parameter is determined to be the target feature parameter.

In some embodiments, the processor 401 is further configured to perform the following steps:

obtaining a plurality of first characteristic parameter values and a plurality of second characteristic parameter values of the target characteristic parameter;

obtaining a corresponding first value range according to a plurality of first characteristic parameter values;

obtaining a corresponding second value range according to the plurality of second characteristic parameter values;

The first target preset compensation value corresponding to the first value range and the second target preset compensation value corresponding to the second value range are acquired.

It can be seen from the above that the electronic device provided by the embodiment of the present application obtains multiple first prediction results by inputting sample data into the algorithm model; when the multiple first prediction results include correct prediction results and wrong prediction results, samples are obtained respectively. The target feature parameter in the data corresponds to the first feature parameter value of the correct prediction result, and the second feature parameter value corresponding to the wrong prediction result; the initial preset compensation value is calculated according to the first feature parameter value and the second feature parameter value; The data and the initial preset compensation value are input into the algorithm model for training, and the target preset compensation value is obtained; the preset background is applied with the current multiple feature parameters and the target preset compensation value, and the algorithm model is input to obtain the target prediction result. The target prediction result controls the preset background application. The accuracy of predicting preset background applications can be improved, thereby improving the accuracy of managing and controlling applications entering the background.

Please also refer to FIG. 14 , in some embodiments, the electronic device 400 may further include: a display 403 , a radio frequency circuit 404 , an audio circuit 405 and a power supply 406 . Among them, the display 403 , the radio frequency circuit 404 , the audio circuit 405 and the power supply 406 are respectively electrically connected to the processor 401 .

The display 403 may be used to display information input by or provided to the user and various graphical user interfaces, which may be composed of graphics, text, icons, video, and any combination thereof. The display 403 may include a display panel, and in some embodiments, the display panel may be configured in the form of a Liquid Crystal Display (LCD), or an Organic Light-Emitting Diode (OLED).

The radio frequency circuit 404 can be used to send and receive radio frequency signals, so as to establish wireless communication with the network device or other electronic devices through wireless communication, and to send and receive signals with the network device or other electronic devices.

The audio circuit 405 may be used to provide an audio interface between the user and the electronic device through speakers and microphones.

Power supply 406 may be used to power various components of electronic device 400 . In some embodiments, the power supply 406 may be logically connected to the processor 401 through a power management system, so as to implement functions such as managing charging, discharging, and power consumption through the power management system.

Although not shown in FIG. 14 , the electronic device 400 may further include a camera, a Bluetooth module, and the like, which will not be repeated here.

Embodiments of the present application further provide a storage medium, where a computer program is stored in the storage medium, and when the computer program runs on the computer, the computer is made to execute the application program management and control method in any of the above-mentioned embodiments, for example, by inputting sample data into an algorithm model to obtain multiple first prediction results; when the multiple first prediction results include correct prediction results and incorrect prediction results, obtain the first feature parameter values of the target feature parameters in the sample data corresponding to the correct prediction results, and the corresponding error The second characteristic parameter value of the prediction result; the initial preset compensation value is calculated according to the first characteristic parameter value and the second characteristic parameter value; the sample data and the initial preset compensation value are input into the algorithm model for training to obtain the target preset compensation value; apply the current multiple feature parameters and target preset compensation values in the preset background, input the algorithm model, obtain the target prediction result, and manage and control the preset background application according to the target prediction result.

In this embodiment of the present application, the storage medium may be a magnetic disk, an optical disk, a read only memory (Read Only Memory, ROM), or a random access memory (Random Access Memory, RAM), or the like.

In the above-mentioned embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

It should be noted that, for the background application management and control method of the embodiment of the present application, ordinary testers in the art can understand that all or part of the process of implementing the background application management and control method of the embodiment of the present application can be controlled by a computer program. After completion, the computer program can be stored in a computer-readable storage medium, such as a memory of an electronic device, and executed by at least one processor in the electronic device, and the execution process can include methods such as background application management and control methods. Example flow. The storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, or the like.

For the background application management and control apparatus of the embodiment of the present application, each functional module thereof may be integrated in one processing chip, or each module may exist physically alone, or two or more modules may be integrated into one module. The above-mentioned integrated modules can be implemented in the form of hardware, and can also be implemented in the form of software function modules. If the integrated modules are implemented in the form of software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium, such as a read-only memory, a magnetic disk or an optical disk.

The background application management and control method, device, storage medium, and electronic device provided by the embodiments of the present application have been described above in detail. The principles and implementations of the present application are described with specific examples in this article. It is only used to help understand the method of the present application and its core idea; at the same time, for those skilled in the art, according to the idea of the present application, there will be changes in the specific implementation and application scope. The contents of the description should not be construed as limiting the application.

Claims (12)

1. a background application management and control method, applied to electronic equipment, is characterized in that, comprises the steps: Input the sample data into the algorithm model to obtain multiple first prediction results; When the plurality of first prediction results include a correct prediction result and an incorrect prediction result, respectively obtain the first feature parameter value of the target feature parameter corresponding to the correct prediction result and the second feature corresponding to the incorrect prediction result in the sample data parameter value; Calculate and obtain an initial preset compensation value according to the first characteristic parameter value and the second characteristic parameter value; Inputting the sample data and the initial preset compensation value into the algorithm model for training to obtain a target preset compensation value; The preset background is applied with a plurality of current feature parameters and the target preset compensation value corresponding to the target feature parameter, and the algorithm model is input to obtain a target prediction result, and according to the target prediction result Preset background applications for control. 2 . The background application management and control method according to claim 1 , wherein the step of calculating and obtaining an initial preset compensation value according to the first characteristic parameter value and the second characteristic parameter value comprises: 2 . obtaining multiple first feature parameter values corresponding to multiple correct prediction results of the target feature parameter; acquiring multiple second feature parameter values corresponding to multiple error prediction results of the target feature parameter; The initial preset compensation value is calculated according to the average value of the plurality of first characteristic parameter values and the average value of the plurality of second characteristic parameter values. 3. The background application management and control method according to claim 1, wherein the step of obtaining an initial preset compensation value according to the first characteristic parameter value and the second characteristic parameter value comprises: Obtain the feature parameter value of the target feature parameter, and a plurality of reference feature parameter values that are gradients with the feature parameter value; Inputting the multiple reference feature parameter values into the algorithm model to obtain a second prediction result; If the second prediction result changes, obtain the first characteristic parameter value and the second characteristic parameter value corresponding to the adjacent correct prediction result and the wrong prediction result respectively; An initial preset compensation value is obtained according to the difference between the first characteristic parameter value and the second characteristic parameter value. 4. The background application management and control method according to claim 1, wherein the step of acquiring the target characteristic parameter comprises: Modifying the weights of each characteristic parameter input to the algorithm model in turn; If the first prediction result changes, the corresponding feature parameter is determined to be the target feature parameter. 5. The background application management and control method according to claim 1, wherein the step of obtaining the target preset compensation value comprises: acquiring a plurality of the first characteristic parameter values and a plurality of the second characteristic parameter values of the target characteristic parameter; obtaining a corresponding first value range according to a plurality of the first characteristic parameter values; obtaining a corresponding second value range according to a plurality of the second characteristic parameter values; A first target preset compensation value corresponding to the first value range and a second target preset compensation value corresponding to the second value range are acquired. 6. A background application management and control device, applied to electronic equipment, wherein the device comprises: a first prediction result obtaining unit, configured to input the sample data into the algorithm model to obtain a plurality of first prediction results; a feature parameter value obtaining unit, configured to respectively obtain a first feature parameter value corresponding to the correct prediction result of the target feature parameter in the sample data when the plurality of first prediction results include a correct prediction result and an incorrect prediction result, and the second characteristic parameter value corresponding to the wrong prediction result; an initial compensation value obtaining unit, configured to calculate and obtain an initial preset compensation value according to the first characteristic parameter value and the second characteristic parameter value; a target preset compensation value acquisition unit, configured to input the sample data and the initial preset compensation value into the algorithm model for training to obtain a target preset compensation value; A management and control unit, configured to input the preset background application current multiple feature parameters and the target preset compensation value corresponding to the target feature parameter into the algorithm model to obtain a target prediction result, and according to the target The prediction result controls the preset background application. 7. The background application management and control device according to claim 6, wherein the initial compensation value acquisition unit comprises: a first characteristic parameter value obtaining subunit, used for obtaining a plurality of first characteristic parameter values corresponding to a plurality of correct prediction results of the target characteristic parameter; A second characteristic parameter value obtaining subunit, configured to obtain a plurality of second characteristic parameter values corresponding to the plurality of wrong prediction results of the target characteristic parameter; The initial compensation value acquisition subunit is configured to calculate and obtain an initial preset compensation value according to the average value of the plurality of first characteristic parameter values and the average value of the plurality of second characteristic parameter values. 8. The background application management and control device according to claim 6, wherein the initial compensation value acquisition unit comprises: a reference feature parameter value obtaining subunit, used for obtaining the feature parameter value of the target feature parameter, and a plurality of reference feature parameter values that form a gradient with the feature parameter value; The second prediction result obtaining subunit is used to input the multiple reference feature parameter values into the algorithm model to obtain the second prediction result; a characteristic parameter value obtaining subunit, configured to obtain the first characteristic parameter value and the second characteristic parameter value corresponding to the adjacent correct prediction result and the wrong prediction result respectively if the second prediction result changes; The initial preset compensation value obtaining subunit is configured to obtain an initial preset compensation value according to the difference between the first characteristic parameter value and the second characteristic parameter value. 9. The background application management and control device according to claim 6, wherein the characteristic parameter value acquisition unit comprises: a weight acquisition subunit, used for sequentially modifying the weights of each characteristic parameter input to the algorithm model; The target feature parameter acquisition subunit is configured to determine the corresponding feature parameter as the target feature parameter if the first prediction result changes. 10 . The background application management and control device according to claim 6 , wherein the characteristic parameter value obtaining unit is further configured to obtain a plurality of the first characteristic parameter values and a plurality of the first characteristic parameter values of the target characteristic parameter. 11 . the second characteristic parameter value; The target preset compensation value acquisition unit includes: a first value range obtaining subunit, configured to obtain a corresponding first value range according to a plurality of the first characteristic parameter values; The second value range obtaining subunit is configured to obtain a corresponding second value range according to a plurality of the second characteristic parameter values; a first target preset compensation value determination subunit, configured to obtain a first target preset compensation value corresponding to the first value range; The second target preset compensation value determination subunit is configured to acquire a second target preset compensation value corresponding to the second value range. 11. A storage medium having a computer program stored thereon, wherein when the computer program is run on a computer, the computer is made to execute the background application management and control method according to any one of claims 1 to 5 . 12. An electronic device, comprising a processor and a memory, wherein the memory has a computer program, wherein the processor is used to execute the computer program according to any one of claims 1 to 5 by invoking the computer program. Background application control method.

Images