CN107807730B - Application cleaning method and device, storage medium and electronic equipment - Google Patents

Abstract

The embodiments of the present application disclose an application cleaning method, device, storage medium and electronic device, wherein the embodiments of the present application obtain multidimensional features of an application to obtain a training feature set of the application; train a ridge regression model according to the training feature set of the application to obtain a trained ridge regression model; obtain multidimensional features of the application to obtain a prediction feature set of the application; predict whether the application is cleanable according to the prediction feature set and the trained ridge regression model; so as to clean up cleanable applications; this scheme can realize automatic cleaning of applications, improve the running fluency of electronic devices, and reduce power consumption.

Description

Application cleaning method, device, storage medium and electronic device

technical field

The present application relates to the field of communication technologies, and in particular, to an application cleaning method, device, storage medium and electronic device.

Background technique

At present, on electronic devices such as smart phones, there are usually multiple applications running at the same time, wherein one application runs in the foreground and other applications run in the background. If the applications running in the background are not cleaned up for a long time, the available memory of the electronic device will become smaller, and the utilization rate of the central processing unit (CPU) will be too high, which will cause the electronic device to run slowly, freeze, and consume power. Too fast and so on. Therefore, it is necessary to provide a method to solve the above problems.

SUMMARY OF THE INVENTION

In view of this, embodiments of the present application provide an application cleaning method, device, storage medium, and electronic device, which can improve the running smoothness of the electronic device and reduce power consumption.

In the first aspect, an application cleaning method provided by the embodiment of the present application includes:

Obtain the multi-dimensional features of the application, and obtain the training feature set of the application;

The ridge regression model is trained according to the training feature set of the application, and the trained ridge regression model is obtained;

Obtain the multi-dimensional features of the application, and obtain the predicted feature set of the application;

Based on the predicted feature set and the trained ridge regression model, predict whether the application is cleanable.

In the second aspect, the embodiment of the present application provides an application cleaning device, including:

a training feature acquisition unit, used for acquiring multi-dimensional features of an application, and obtaining a training feature set of the application;

A training unit, used for training the ridge regression model according to the training feature set of the application, to obtain the trained ridge regression model;

a predictive feature acquisition unit, configured to acquire multidimensional features of the application, and obtain a predictive feature set of the application;

A prediction unit, configured to predict whether the application can be cleaned according to the predicted feature set and the trained ridge regression model.

In a third aspect, a storage medium provided by an embodiment of the present application stores a computer program thereon, and when the computer program runs on a computer, the computer causes the computer to execute the application cleaning method provided by any embodiment of the present application.

In a fourth aspect, an electronic device provided by an embodiment of the present application includes a processor and a memory, the memory has a computer program, and the processor is configured to execute the application provided by any embodiment of the present application by invoking the computer program. cleanup method.

The embodiment of the present application acquires the multi-dimensional features of the application, and obtains the training feature set of the application; trains the ridge regression model according to the training feature set of the application, and obtains the trained ridge regression model; acquires the multi-dimensional features of the application, and obtains the prediction feature set of the application ; According to the predicted feature set and the trained ridge regression model, predict whether the application can be cleaned; in order to clean the application that can be cleaned; this solution can realize the automatic cleaning of the application, improve the running smoothness of the electronic device, and reduce the power consumption .

Description of drawings

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

FIG. 1 is a schematic diagram of an application scenario of an application cleaning method provided by an embodiment of the present application.

FIG. 2 is a schematic flowchart of an application cleaning method provided by an embodiment of the present application.

FIG. 3 is another schematic flowchart of an application cleaning method provided by an embodiment of the present application.

FIG. 4 is a schematic structural diagram of an application cleaning device provided by an embodiment of the present application.

FIG. 5 is another schematic structural diagram of the application cleaning device provided by the embodiment of the present application.

FIG. 6 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

FIG. 7 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 performed by a computer processing unit of electronic signals representing data in a structured format. This operation transforms or maintains the data at a location in the computer's memory system, which can be reconfigured or otherwise alter 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 is not meant to be a limitation, and testers in the art will understand that various steps and operations described below 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 various components, modules, engines, and services described herein may be considered objects of implementation on the computing system. The apparatus and method described 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.

The embodiment of the present application provides an application cleaning method, and the execution body of the application cleaning method may be the background application cleaning device provided by the embodiment of the present application, or an electronic device integrating the application cleaning device, wherein the application cleaning device may adopt hardware or software implementation. The electronic device may be a smart phone, a tablet computer, a palmtop computer, a notebook computer, or a desktop computer and other devices.

Please refer to FIG. 1. FIG. 1 is a schematic diagram of an application scenario of an application cleaning method provided by an embodiment of the present application. Taking the integration of an application cleaning device in an electronic device as an example, the electronic device can acquire multi-dimensional features of applications and obtain training feature sets of applications; Train the ridge regression model according to the training feature set of the application to obtain the trained ridge regression model; obtain the multi-dimensional features of the application to obtain the prediction feature set of the application; according to the prediction feature set and the trained ridge regression model, predict whether the application is feasible clean up. In addition, electronic devices can be cleaned with a cleanable app.

Specifically, for example, as shown in FIG. 1 , taking the judgment of whether an application a (such as a mailbox application, a game application, etc.) running in the background can be cleaned up as an example, the multi-dimensional features of the application a (for example, the application a in the The duration of background running, the running time information of application a, etc.), the feature set of application a is obtained, and the ridge regression model is trained according to the feature set (such as the duration of application a running in the background, the running time information of application a, etc.), and the obtained Ridge regression model after training; collect multi-dimensional features corresponding to the application according to the prediction time (such as t) (for example, the duration of application a running in the background at time t, the time information of application a running, etc.), and obtain the prediction feature set of application a; Predict whether application a is cleanable based on the predicted feature set and the trained ridge regression model. In addition, when the application a is predicted to be cleanable, the electronic device cleans the application a.

Please refer to FIG. 2 , which is a schematic flowchart of an application cleaning method provided by an embodiment of the present application. The specific process of the application cleaning method provided by the embodiment of the present application may be as follows:

201. Acquire multi-dimensional features of the application, and obtain a training feature set of the application.

The application mentioned in the embodiments of this application may be any application installed on an electronic device, such as an office application, a communication application, a game application, a shopping application, and the like. The applications may include applications running in the foreground, ie, foreground applications, or applications running in the background, ie, background applications.

In one embodiment, an application cleaning request may be received, an application to be cleaned is determined according to the application cleaning request, and then multi-dimensional features of the application are acquired to obtain a training feature set of the application.

Specifically, the multi-dimensional features of the application can be obtained from the feature database, where the multi-dimensional features can be multi-dimensional features collected in historical time, that is, historical multi-dimensional features. A variety of features applied in historical time are stored in the feature database.

The training feature set may include multi-dimensional features of the application, that is, multiple features of the application.

The multi-dimensional feature of the application has a dimension of a certain length, and the parameters on each dimension correspond to a type of feature information representing the application, that is, the multi-dimensional feature information is composed of multiple features. The multiple features may include feature information related to the application itself, such as: the duration of the application being switched to the background; the duration of the screen off of the electronic device when the application was switched to the background; the number of times the application entered the foreground; the time the application was in the foreground; the application was in the background time, the way the application enters the background, such as being switched by the home key (home key), switched by the return key, switched by other applications, etc.; application types, including primary (commonly used applications), secondary (other applications) )Wait.

The multi-dimensional feature information may also include feature information about the electronic device where the application is located, such as: screen-off time, screen-on time, current battery level, wireless network connection status of the electronic device, whether the electronic device is in a charging state, etc.

The applied training samples include applied multi-dimensional features. The multi-dimensional features may be multiple features collected at a preset frequency within a historical time period. The historical time period can be, for example, the past 7 days or 10 days; the preset frequency, for example, can be collected once every 10 minutes or once every half an hour. It can be understood that the multi-dimensional feature data of the application collected at one time constitutes a training feature set.

In one embodiment, in order to facilitate application cleaning, the feature information that is not directly represented by numerical values in the multi-dimensional feature information of the application can be quantified with specific numerical values. A value of 1 indicates a normal state, and a value of 0 indicates an abnormal state (and vice versa). For another example, for the characteristic information of whether an electronic device is in a charged state, a value of 1 can be used to indicate a charged state, and a value of 0 is used to indicate an uncharged state ( vice versa).

202. Train the ridge regression model according to the applied training feature set to obtain a trained ridge regression model.

Among them, the ridge regression model can be a machine learning algorithm, and the ridge regression (Tikhonovregularization) algorithm, also known as the ridge regression, is a biased estimation regression method dedicated to the analysis of collinear data. The square estimation method, by giving up the unbiasedness of the least squares method, obtains the regression coefficients at the expense of losing some information and reducing the accuracy, which is more practical and reliable.

In this embodiment of the present application, a ridge regression model can be used to predict whether an application can be cleaned up, wherein the output of the ridge regression model includes cleanable or non-cleanable. When using the ridge regression model to predict whether the application can be cleaned, it is necessary to use the existing feature information to train the model to improve the accuracy of the prediction.

In one embodiment, the process of training the ridge regression model is the process of solving the ridge regression parameters of the ridge regression model. Set up the regression model. For example, the step "train the ridge regression model according to the applied training samples, and obtain the described ridge regression model after training", which may include:

Establish the error judgment function of the ridge regression model;

Obtain the target ridge regression parameters of the ridge regression model according to the training feature set and the error judgment function, and the target ridge regression parameters include ridge parameters and regression parameters;

The trained ridge regression model is obtained according to the target ridge regression parameters and the ridge regression model.

Among them, the ridge regression parameters can include ridge parameters and regression parameters. Ridge regression (Ridge Regression) is to add a regular term on the basis of the squared error. By determining the value of λ, a balance between variance and bias can be achieved: as λ increases increases, the model variance decreases and the bias increases. The ridge parameter can normalize the parameter λ, and the regression parameter can be the model parameter w of the ridge regression model to be solved.

In the embodiment of the present application, the error judgment function is the loss function of the ridge regression model, which is used to calculate the error between the output value of the ridge regression model on the sample and the real value.

In one embodiment, the error judgment function of the ridge regression model may include the following functions:

Among them, λ is the ridge parameter, that is, the regularization parameter, x is the feature of the sample, w is the regression parameter of the ridge regression model, and n is the dimension of the feature.

In one embodiment, the error judgment function of the ridge regression model may be deformed to obtain a regression parameter acquisition function, and then the ridge regression parameters are acquired based on the regression parameter acquisition function. For example, the error judgment function can be derived to obtain the regression parameter acquisition function, and then the ridge regression parameters can be obtained based on the regression parameter acquisition function and the training feature set.

For example, the error judgment function of the ridge regression model can include the following functions:

The error judgment function can be derived to get the function:

2X ^T (Y-XW)-2λW, X is the matrix or vector of feature x, X ^T is the transpose of X, and Y is the matrix or vector of y;

Then, let 2X ^T (Y-XW)-2λW equal to zero, the following regression parameter calculation formula can be obtained:

in, are the regression parameters to be solved.

After the regression parameter calculation formula is obtained, the regression parameter can be calculated based on the formula and the training feature set Finally, the ridge parameter λ and the corresponding regression parameter are obtained

In one embodiment, in order to improve the prediction accuracy, multiple sets of ridge regression parameters may be calculated, and then the most suitable ridge regression parameters may be selected. For example, the step "obtaining the target ridge regression parameters of the ridge regression model according to the training feature set and the error judgment function" may include:

Obtain multiple sets of ridge regression parameters according to the error judgment function, and the ridge regression parameters include: ridge parameters and regression parameters;

According to the training feature set, the ridge regression parameters and the error judgment function, the error of the training feature set for the ridge regression model under the ridge regression parameters is obtained, and the error corresponding to each group of ridge regression parameters is obtained;

According to the error corresponding to each set of ridge regression parameters, select the corresponding target ridge regression parameter from multiple sets of ridge regression parameters;

The trained ridge regression model is obtained according to the target ridge regression parameters and the ridge regression model.

Among them, the error corresponding to the ridge regression parameter is the ridge regression model under the ridge regression parameter, and the error between the predicted value obtained from the input training sample set and the actual value.

For example, the ridge regression parameters can be obtained Among them, m can be a positive integer greater than 2, and can be set according to actual needs, for example, 20, 30, 40 . . .

Then, according to the training feature set, ridge regression parameters and the error judgment function to obtain the regression parameters in this group The error Fk of the training feature set for the ridge regression model is obtained, and the corresponding errors of each group of ridge regression parameters, such as F1, F2...Fk...Fm, are obtained. Based on the error F corresponding to each set of ridge regression parameters from the ridge regression parameters Select the corresponding target ridge regression parameters

In one embodiment, the error judgment function of the ridge regression model can be deformed to obtain a regression parameter acquisition function, and then the regression parameters are acquired based on the regression parameter acquisition function and a plurality of preset ridge parameters λ. Get multiple sets of ridge regression parameters For example, the error judgment function can be derived to obtain the regression parameter acquisition function, and then the ridge regression parameters can be obtained based on the regression parameter acquisition function and the training feature set.

For example, the error judgment function of the ridge regression model can include the following functions:

The error judgment function can be derived to get the function:

2X ^T (Y-XW)-2λW, X is the matrix or vector of feature x, X ^T is the transpose of X, and Y is the matrix or vector of y;

Then, let 2X ^T (Y-XW)-2λW equal to zero, the following regression parameter calculation formula can be obtained:

in, are the regression parameters to be solved.

After the regression parameter calculation formula is obtained, the regression parameters can be calculated based on the formula and multiple preset ridge parameters λ Finally, the ridge parameter λ and the corresponding regression parameter are obtained

For example, to initialize the ridge parameter λ to a value of 1, use the formula Calculated to obtain the corresponding λ=1 value; add 1 to λ and reuse the formula Find the corresponding to λ=2 value; add 1 to λ and reuse the formula Find λ=3 corresponding to Value...until the corresponding λ=m is obtained value, such as m=20. At this point, m groups such as 20 different groups can be obtained. value, and then get m groups such as 20 groups

In one embodiment, in order to accurately and quickly obtain the error of the training feature set for the ridge regression model, the training feature set can be divided into multiple sub-training feature sets, and each sub-training feature set is obtained under the ridge regression parameters. Then, based on the error f of each sub-training feature set under the ridge regression parameters for the ridge regression model, the error F of the entire training feature set under the ridge regression parameters for the ridge regression model is obtained.

For example, the step "acquiring the error of the training feature set for the ridge regression model under the ridge regression parameters according to the training feature set, the ridge regression parameters and the error judgment function" may include:

Divide the training feature set into multiple sub-training feature sets;

According to the sub-training feature set, the ridge regression parameters and the error judgment function, obtain the sub-error of the sub-training set for the ridge regression model under the ridge regression parameter, and obtain the sub-error corresponding to each sub-training feature set;

The sub-error corresponding to each sub-training feature set is obtained, and the error of the training feature set for the ridge regression model under the ridge regression parameters is obtained.

The number of sub-training feature sets divided can be set according to actual needs, such as 10, 20, and so on. In one embodiment, in order to improve the accuracy of error acquisition, the sub-training feature sets include the same number of features, that is, the training feature set is divided into multiple sub-training feature sets equally.

For example, the training feature set D may be divided into M sub-training feature sets to obtain sub-training feature sets D1, D2, . . . DM; where M is a positive integer greater than 1. Then, according to the error judgment function and the ridge regression parameters, calculate the sub-error of each sub-training feature set for the ridge regression model under the ridge regression parameters, such as D1 in the ridge regression parameters The following sub-errors f11, D2 for the ridge regression model are in the ridge regression parameters For the sub-error f12 of the ridge regression model, ... DM is in the ridge regression parameter Below the sub-error f1M for the ridge regression model, based on each sub-training feature set in the ridge regression parameter The following sub-errors for the ridge regression model, that is, f11, f12...f1M to obtain the training feature D in the ridge regression parameters Below is the error F1 for the ridge regression model.

Next, according to the error judgment function and the next set of ridge regression parameters, calculate the sub-errors of each sub-training feature set for the next set of ridge regression models under the ridge regression parameters, such as D1 in the ridge regression parameters The following sub-errors f21, D2 for the ridge regression model are in the ridge regression parameters For the sub-error f22 of the ridge regression model, ... DM is in the ridge regression parameter Below the sub-error f2M for the ridge regression model, based on each sub-training feature set in the ridge regression parameters For the sub-error of the ridge regression model, that is, f21, f22... f2M obtains the training feature D in the ridge regression parameter Below is the error F2 for the ridge regression model.

By analogy, the error of the training feature set in the m groups of ridge regression parameters for the ridge regression model can be calculated, and the errors F1, F2, ... Fm can be obtained.

In this embodiment of the present application, after the sub-errors corresponding to each sub-training feature set are obtained, the errors of the entire training feature set with respect to the ridge regression model can be obtained based on the sub-errors, and the obtaining methods can be various. For example, in an embodiment, in order to improve the accuracy of the errors, the average value of the sub-errors may be calculated, and then, based on the average value, the errors of the entire training feature set for the ridge regression model are obtained. For example, the step "According to the sub-error corresponding to each sub-training feature set, obtain the error of the training feature set for the ridge regression model under the ridge regression parameters", which may include:

According to the sub-error corresponding to each sub-training feature set, obtain the average error of the sub-training feature set;

According to the average error, the error of the training feature set for the ridge regression model under the ridge regression parameters is obtained.

In one embodiment, the average error can be used as the error of the ridge regression model trained on the feature set under the ridge regression parameters.

For example, taking the ridge regression parameters as For example, after calculating the sub-errors f11 and D2 of the ridge regression model under each sub-section, the ridge regression parameters For the sub-error f12 of the ridge regression model, ... DM is in the ridge regression parameter Below the sub-error f1M for the ridge regression model, based on each sub-training feature set in the ridge regression parameter For the sub-errors of the ridge regression model, that is, after f11, f12...f1M, the average error f'=(f11+f12+...+f1M)/M can be calculated; the f' is the training feature D in the ridge regression parameter Below is the error F1 for the ridge regression model.

In one embodiment, in order to improve parameter accuracy and prediction accuracy, after obtaining the error corresponding to each group of ridge regression parameters, the ridge regression parameter corresponding to the smallest error can be selected as the target ridge regression parameter of the ridge regression model, that is, the final ridge regression parameter. parameter.

For example, after obtaining the error corresponding to each set of ridge regression parameters, such as F1, F2...Fk...Fm, assuming that Fk is the smallest, at this time, the ridge regression parameter corresponding to Fk can be selected As the target ridge regression parameter of the ridge regression model.

According to the above description, the following will introduce the selection process of the target ridge regression parameters, that is, the training process of the ridge regression model, with the ridge regression parameters as 20 groups and the number of sub-training feature sets as 10, as follows:

(1), the error judgment function of establishing ridge regression is:

Derivative for , the result is:

2X ^T (Y-XW)-2λW

Set its value to 0 to obtain the value of w:

(2), initialize the value of λ to 1, follow the steps in (3) The formula calculates the corresponding value.

(3), add 1 to λ, repeat step (2) to obtain 20 different groups of value;

(4), Divide the feature set into 10 equal parts, select (3) in step A value of , the following error judgment formula calculates the different error values of each sub-feature set of 10 equal parts for ridge regression, and obtains 10 different error values:

Then calculate the average error value of the error values of ridge regression by dividing each sub-feature set into 10 equal parts, and use the average error value as the feature set in the selected and the error of ridge regression under λ;

(5), repeat step (4), respectively calculate the feature set in 20 different groups The feature error for ridge regression under the value of ;

(6), the 20 groups of characteristic errors obtained from (5) take the minimum value corresponding to the and λ values, the and λ values are the ridge regression parameters obtained by ridge regression fitting, that is, the parameters finally selected by the ridge regression model.

Through the above steps (1)-(6), the ridge regression parameters corresponding to each application can be calculated.

203. Acquire the multi-dimensional features of the application, and obtain the prediction feature set of the application.

For example, multi-dimensional features of the application can be collected as prediction samples according to the prediction time.

The forecast time can be set according to requirements, such as the current time.

For example, the multi-dimensional features of the application can be collected as prediction samples at the prediction time point.

In the embodiment of the present application, the multi-dimensional features collected in steps 201 and 203 are of the same type, such as: the duration of the application being switched to the background; the duration of the screen-off of the electronic device during the time the application was switched to the background; the number of times the application entered the foreground; Time in the foreground; how the app goes into the background.

204. Predict whether the application can be cleaned according to the predicted feature set and the trained ridge regression model.

For example, the probability that the application can be cleaned can be calculated based on the ridge regression model and the predicted feature set, and when the probability is greater than a certain threshold, it is determined that the application can be cleaned, and so on.

As can be seen from the above, the embodiment of the present application obtains the multi-dimensional features of the application, and obtains the training feature set of the application; the ridge regression model is trained according to the training feature set of the application, and the trained ridge regression model is obtained; the multi-dimensional features of the application are obtained, and the application is obtained. According to the predicted feature set and the trained ridge regression model, it is predicted whether the application can be cleaned; in order to clean up the cleanable applications; this solution can realize the automatic cleaning of the application and improve the running smoothness of the electronic equipment. Reduced power consumption and conserved resources.

Further, since the feature set includes a plurality of feature information reflecting the user's behavior habit of using the application, the embodiment of the present application can make the cleaning of the corresponding application more personalized and intelligent.

Further, implementing application cleaning prediction based on the ridge regression model can improve the accuracy of user behavior prediction, thereby improving the accuracy of cleaning. In addition, the embodiments of the present application can also calculate multiple sets of ridge regression parameters when training the model, and use the feature error to select the ridge regression parameter with the lowest error as the final parameter of the ridge regression model, which can further improve the ridge regression model The accuracy of the applied cleanup predictions.

The cleaning method of the present application will be further introduced below on the basis of the methods described in the above embodiments. Referring to Figure 3, the application cleaning method may include:

301. Acquire multi-dimensional features of the application, and obtain a training feature set of the application.

For example, the multi-dimensional features of the application are obtained from the feature database, wherein the multi-dimensional features may be multi-dimensional features collected in historical time, that is, historical multi-dimensional features. A variety of features applied in historical time are stored in the feature database.

The training feature set may include multi-dimensional features of the application, that is, multiple features of the application.

The multi-dimensional feature of the application has a dimension of a certain length, and the parameters on each dimension correspond to a type of feature information representing the application, that is, the multi-dimensional feature information is composed of multiple features. The multiple features may include feature information related to the application itself, such as: the duration of the application being switched to the background; the duration of the screen off of the electronic device when the application was switched to the background; the number of times the application entered the foreground; the time the application was in the foreground; the application was in the background time, the way the application enters the background, such as being switched by the home key (home key), switched by the return key, switched by other applications, etc.; application types, including primary (commonly used applications), secondary (other applications) )Wait.

The multi-dimensional feature information may also include feature information about the electronic device where the application is located, such as: screen-off time, screen-on time, current battery level, wireless network connection status of the electronic device, whether the electronic device is in a charging state, etc.

A specific training feature set can be as follows, including feature information of multiple dimensions (30 dimensions). It should be noted that the feature information shown below is only an example. In practice, the features included in a training feature set The quantity of information can be more than or less than the quantity of information shown below, and the specific feature information taken can also be different from the feature information shown below, which is not specifically limited here.

The last time the APP was switched to the background until now;

During the period from the last time the APP was switched to the background to the present, the cumulative screen off time length;

The number of times the APP enters the front desk in a day (by daily statistics);

The number of times the APP enters the front desk in a day (rest days are counted separately by working days and rest days). For example, if the current forecast time is a working day, the value used for this feature is the average number of times the APP is used at the front desk on a working day;

The time that the APP is in the foreground in a day (by daily statistics);

The number of times the background APP is opened after the current foreground APP, regardless of working days and rest days;

The number of times the background APP is opened after the current front-end APP is counted by working days and rest days;

The way the target APP is switched is divided into switching by the home button, switching by the recent button, and switching by other APPs;

Target APP first-level type (commonly used applications);

Target APP secondary type (other applications);

Mobile phone screen off time;

The screen time of the mobile phone;

The current screen is on and off;

current power;

current wifi status;

The duration of the last time the app was switched to the background;

The last time the APP was used in the foreground;

The last time the APP was used in the foreground;

The last time the APP was used in the foreground;

If a day is divided into 6 time segments, each segment is 4 hours, and the current forecast time point is 8:30 in the morning, it is in segment 3, then this feature indicates that the target app is used every day from 8:00 to 12:00. the length of time used;

The average interval time from the current foreground APP entering the background to the target APP entering the foreground according to the daily statistics;

The average screen off time according to the daily statistics during the period from the current foreground APP entering the background to the target APP entering the foreground;

The first bin of the histogram of the target APP staying time in the background (the proportion of times corresponding to 0-5 minutes);

The first bin of the histogram of the target APP staying time in the background (the proportion of times corresponding to 5-10 minutes);

The first bin of the histogram of the target APP staying time in the background (the proportion of times corresponding to 10-15 minutes);

The first bin of the histogram of the target APP staying time in the background (the proportion of times corresponding to 15-20 minutes);

The first bin of the histogram of the target APP staying time in the background (the proportion of times corresponding to 15-20 minutes);

The first bin of the histogram of the target APP staying time in the background (the proportion of times corresponding to 25-30 minutes);

The first bin of the histogram of the target APP's stay time in the background (the proportion of the corresponding times after 30 minutes);

Is it currently charging.

302. Establish an error judgment function of the ridge regression model, and obtain a corresponding regression parameter obtaining function according to the error judgment function.

Among them, the ridge regression model can be a machine learning algorithm, and the ridge regression (Tikhonovregularization) algorithm, also known as the ridge regression, is a biased estimation regression method dedicated to the analysis of collinear data. The square estimation method, by giving up the unbiasedness of the least squares method, obtains the regression coefficients at the expense of losing some information and reducing the accuracy, which is more practical and reliable.

For example, the error judgment function of the ridge regression model can include the following functions:

Among them, λ is the ridge parameter, that is, the regularization parameter, x is the feature of the sample, w is the regression parameter of the ridge regression model, and n is the dimension of the feature.

The error judgment function can be derived to get the function:

2X ^T (Y-XW)-2λW, X is the matrix or vector of feature x, X ^T is the transpose of X, and Y is the matrix or vector of y;

Then, let 2X ^T (Y-XW)-2λW equal to zero, the following regression parameter calculation formula can be obtained:

in, are the regression parameters to be solved.

303. Obtain a plurality of corresponding regression parameters according to a plurality of preset ridge parameters and a regression parameter obtaining function, and obtain a plurality of sets of ridge regression parameters.

Among them, the ridge regression parameters include the ridge parameter λ and the corresponding regression parameters

For example, to initialize the ridge parameter λ to a value of 1, use the formula Calculated to obtain the corresponding λ=1 value; add 1 to λ and reuse the formula Find the corresponding to λ=2 value; add 1 to λ and reuse the formula Find λ=3 corresponding to Value...until the corresponding λ=m is obtained value, such as m=20. At this point, m groups such as 20 different groups can be obtained. value, and then get m groups such as 20 groups

304. Divide the training feature set into multiple sub-training feature sets.

The number of sub-training feature sets divided can be set according to actual needs, such as 10, 20, and so on. In one embodiment, in order to improve the accuracy of error acquisition, the sub-training feature sets include the same number of features, that is, the training feature set is divided into multiple sub-training feature sets equally.

305. Obtain, according to the sub-training feature set, the ridge regression parameter, and the error judgment function, the sub-error of the sub-training set for the ridge regression model under the ridge regression parameter.

For example, the training feature set D may be divided into M sub-training feature sets to obtain sub-training feature sets D1, D2, . . . DM; where M is a positive integer greater than 1. Then, according to the error judgment function and the ridge regression parameters, calculate the sub-error of each sub-training feature set for the ridge regression model under the ridge regression parameters, such as D1 in the ridge regression parameters The following sub-errors f11, D2 for the ridge regression model are in the ridge regression parameters For the sub-error f12 of the ridge regression model, ... DM is in the ridge regression parameter Next, for the sub-error f1M of the ridge regression model, get each sub-training feature set in the ridge regression parameter For the sub-errors of the ridge regression model, f11, f12...f1M.

306. According to the sub-error of each sub-training set under the ridge regression parameter for the ridge regression model, obtain the error of the training feature set under the ridge regression parameter for the ridge regression model, and repeat steps 305 and 306 to obtain the training features under each group of ridge regression parameters Error for ridge regression model.

For example, the average error of the sub-training feature set is obtained according to the sub-error corresponding to each sub-training feature set; the error of the training feature set for the ridge regression model under the ridge regression parameters is obtained according to the average error.

In one embodiment, the average error can be used as the error of the ridge regression model trained on the feature set under the ridge regression parameters.

For example, taking the ridge regression parameters as For example, after calculating the sub-errors f11 and D2 of the ridge regression model under each sub-section, the ridge regression parameters For the sub-error f12 of the ridge regression model, ... DM is in the ridge regression parameter Below the sub-error f1M for the ridge regression model, based on each sub-training feature set in the ridge regression parameter For the sub-errors of the ridge regression model, that is, after f11, f12...f1M, the average error f'=(f11+f12+...+f1M)/M can be calculated; the f' is the training feature D in the ridge regression parameter Below is the error F1 for the ridge regression model.

Then repeat steps 305 and 306 to calculate the error of the training feature set under each group of ridge regression parameters for the ridge regression model; for example, the ridge regression parameters The corresponding errors F1, F2...Fk...Fm respectively.

307. Select the ridge regression parameter corresponding to the smallest error as the target ridge regression parameter of the ridge regression model.

For example, after obtaining the error corresponding to each set of ridge regression parameters, such as F1, F2...Fk...Fm, assuming that Fk is the smallest, at this time, the ridge regression parameter corresponding to Fk can be selected As the target ridge regression parameter of the ridge regression model.

In one embodiment, the above steps 301-307 are repeated to obtain the ridge regression parameters corresponding to each application.

308. Update corresponding parameters in the ridge regression model according to the target ridge regression parameters to obtain a trained ridge regression model.

For example, update the value of the regression parameter w in the ridge regression model.

In one embodiment, repeating the above steps 301-308 can obtain the post-training ridge regression model corresponding to each application

309. Acquire multi-dimensional features of the application, and obtain a prediction feature set of the application.

The forecast time can be set according to requirements, such as the current time.

For example, the multi-dimensional features of the application can be collected as prediction samples at the prediction time point.

In this embodiment of the present application, the multi-dimensional features collected in this step are of the same type as the features acquired in step 301, that is, the feature types included in the prediction feature set and the training feature set are the same, for example, both include: the duration of the application cutting into the background ; When the application is switched to the background, the screen-off time of the electronic device; the number of times the application enters the foreground; the time the application is in the foreground; the way the application enters the background.

310. Predict whether the application can be cleaned according to the predicted feature set and the trained ridge regression model.

For example, the probability that the application can be cleaned can be calculated based on the ridge regression model and the predicted feature set, and when the probability is greater than a certain threshold, it is determined that the application can be cleaned, and so on.

In a specific example, the post-training ridge regression model of each background application can be obtained through the above steps 301-308; As shown in Table 1, it is determined that the application A1 and the application A3 running in the background can be cleaned up, while the state of the application A2 running in the background remains unchanged.

application forecast result Application A1 cleanable Application A2 Not cleanable Apply A3 cleanable

Table 1

As can be seen from the above, the embodiment of the present application obtains the multi-dimensional features of the application, and obtains the training feature set of the application; the ridge regression model is trained according to the training feature set of the application, and the trained ridge regression model is obtained; the multi-dimensional features of the application are obtained, and the application is obtained. According to the predicted feature set and the trained ridge regression model, it is predicted whether the application can be cleaned; in order to clean up the cleanable applications; this solution can realize the automatic cleaning of the application and improve the running smoothness of the electronic equipment. Reduced power consumption and conserved resources.

Further, since the feature set includes a plurality of feature information reflecting the user's behavior habit of using the application, the embodiment of the present application can make the cleaning of the corresponding application more personalized and intelligent.

Further, implementing application cleaning prediction based on the ridge regression model can improve the accuracy of user behavior prediction, thereby improving the accuracy of cleaning. In addition, the embodiments of the present application can also calculate multiple sets of ridge regression parameters when training the model, and use the feature error to select the ridge regression parameter with the lowest error as the final parameter of the ridge regression model, which can further improve the ridge regression model The accuracy of the applied cleanup predictions.

In one embodiment, an application cleaning device is also provided. Please refer to FIG. 4 , which is a schematic structural diagram of an application cleaning device provided by an embodiment of the present application. The application cleaning device is applied to electronic equipment, and the application cleaning device includes a training feature acquisition unit 401, a training unit 402, a prediction feature acquisition unit 403, and a prediction unit 404, as follows:

The training feature acquisition unit 401 is used to obtain the multi-dimensional features of the application, and obtain the training feature set of the application;

The training unit 402 is used for training the ridge regression model according to the training feature set of the application to obtain the trained ridge regression model;

A predictive feature acquisition unit 403, configured to acquire multi-dimensional features of the application, and obtain a predictive feature set of the application;

The prediction unit 404 is configured to predict whether the application can be cleaned according to the predicted feature set and the trained ridge regression model.

In one embodiment, referring to FIG. 5, the training unit 402 includes:

Establishing subunit 4021, for establishing the error judgment function of the ridge regression model;

A parameter obtaining subunit 4022, configured to obtain a target ridge regression parameter of the ridge regression model according to the training feature set and the error judgment function, where the target ridge regression parameter includes a ridge parameter and a regression parameter;

The training subunit 4023 is configured to obtain a trained ridge regression model according to the target ridge regression parameter and the ridge regression model.

In one embodiment, the parameter acquisition subunit 4022 can be used to:

Obtain multiple sets of ridge regression parameters according to the error judgment function, and the ridge regression parameters include: ridge parameters and regression parameters;

According to the training feature set, the ridge regression parameter and the error judgment function, the error of the training feature set for the ridge regression model under the ridge regression parameter is obtained, and the error corresponding to each group of ridge regression parameters is obtained ;

According to the error corresponding to each group of ridge regression parameters, the corresponding target ridge regression parameter is selected from the multiple groups of ridge regression parameters.

In one embodiment, the parameter acquisition subunit 4022 can be specifically used for:

Obtain a corresponding regression parameter obtaining function according to the error judgment function;

According to a plurality of preset ridge parameters and the regression parameter obtaining function, a regression parameter corresponding to each preset ridge parameter is obtained, and multiple sets of ridge regression parameters are obtained.

In one embodiment, the parameter acquisition subunit 4022 can be specifically used for:

dividing the training feature set into a plurality of sub-training feature sets;

According to the sub-training feature set, the ridge regression parameter and the error judgment function, obtain the sub-error of the sub-training set for the ridge regression model under the ridge regression parameter, and obtain the corresponding sub-training feature set for each sub-training feature set. Descriptor error;

According to the sub-error corresponding to each sub-training feature set, the error of the training feature set for the ridge regression model under the ridge regression parameter is obtained.

In one embodiment, the parameter acquisition subunit 4022 can be specifically used for:

According to the sub-error corresponding to each sub-training feature set, obtain the average error of the sub-training feature set;

The error of the training feature set for the ridge regression model under the ridge regression parameter is obtained according to the average error.

In one embodiment, the parameter acquisition subunit 4022 can be specifically used for:

Determine the minimum error from the errors corresponding to each set of ridge regression parameters;

The ridge regression parameter corresponding to the minimum error is selected from the multiple sets of ridge regression parameters as the target ridge regression parameter.

For the steps performed by each unit in the application cleaning device, reference may be made to the method steps described in the foregoing method embodiments. The application cleaning device can be integrated in electronic devices, such as mobile phones, tablet computers, and the like.

During specific implementation, the above units can be implemented as independent entities, or can be arbitrarily combined, implemented as the same or several entities, the specific implementation of the above units can refer to the previous embodiments, which will not be repeated here.

As can be seen from the above, the application cleaning device in this embodiment can obtain the multi-dimensional features of the application by the training feature obtaining unit 401, and obtain the training feature set of the application; the training unit 402 trains the ridge regression model according to the training feature set of the application, and obtains The multi-dimensional feature of the application is obtained by the predictive feature acquisition unit 403, and the predictive feature set of the application is obtained; the prediction unit 404 predicts whether the application can be cleaned according to the predictive feature set and the trained ridge regression model; The application is cleaned up; the solution can realize the automatic cleaning of the application, improve the running smoothness of the electronic device, reduce the power consumption and save the resources.

The embodiments of the present application also provide an electronic device. Referring to FIG. 6 , the electronic device 500 includes a processor 501 and a memory 502 . The processor 501 is electrically connected to the memory 502 .

The processor 500 is the control center of the electronic device 500, using various interfaces and lines to connect various parts of the entire electronic device, by running or loading the computer program stored in the memory 502, and calling the data stored in the memory 502, Various functions of the electronic device 500 are performed and data is processed, so as to monitor the electronic device 500 as a whole.

The memory 502 can be used to store software programs and modules, and the processor 501 executes various functional applications and data processing by running the computer programs and modules stored in the memory 502 . The memory 502 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 (such as a sound playback function, an image playback function, etc.) required for at least one function, and the like; Data created by the use of electronic equipment, etc. Additionally, memory 502 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 502 may also include a memory controller to provide processor 501 access to memory 502 .

In this embodiment of the present application, the processor 501 in the electronic device 500 loads the instructions corresponding to the processes of one or more computer programs into the memory 502 according to the following steps, and is executed by the processor 501 and stored in the memory 502 The computer program in , so as to realize various functions, as follows:

Obtain the multi-dimensional features of the application, and obtain the training feature set of the application;

The ridge regression model is trained according to the training feature set of the application, and the trained ridge regression model is obtained;

Obtain the multi-dimensional features of the application, and obtain the predicted feature set of the application;

According to the predicted feature set and the trained ridge regression model, it is predicted whether the application is clear.

In some embodiments, when the ridge regression model is trained according to the training samples of the application and the trained ridge regression model is obtained, the processor 501 may specifically perform the following steps:

establishing an error judgment function of the ridge regression model;

Obtain the target ridge regression parameter of the ridge regression model according to the training feature set and the error judgment function, and the target ridge regression parameter includes a ridge parameter and a regression parameter;

A trained ridge regression model is obtained according to the target ridge regression parameters and the ridge regression model.

In some embodiments, when acquiring the target ridge regression parameters of the ridge regression model according to the training feature set and the error judgment function, the processor 501 may specifically perform the following steps:

Obtain multiple sets of ridge regression parameters according to the error judgment function, and the ridge regression parameters include: ridge parameters and regression parameters;

According to the training feature set, the ridge regression parameter and the error judgment function, the error of the training feature set for the ridge regression model under the ridge regression parameter is obtained, and the error corresponding to each group of ridge regression parameters is obtained ;

According to the error corresponding to each group of ridge regression parameters, the corresponding target ridge regression parameter is selected from the multiple groups of ridge regression parameters.

In some embodiments, when acquiring multiple sets of ridge regression parameters according to the error judgment function, the processor 501 may specifically perform the following steps:

Obtain a corresponding regression parameter obtaining function according to the error judgment function;

According to a plurality of preset ridge parameters and the regression parameter obtaining function, a regression parameter corresponding to each preset ridge parameter is obtained, and multiple sets of ridge regression parameters are obtained.

In some embodiments, when obtaining the error of the training feature set with respect to the ridge regression model under the ridge regression parameter according to the training feature set, the ridge regression parameter and the error judgment function, The processor 501 may specifically perform the following steps:

dividing the training feature set into a plurality of sub-training feature sets;

According to the sub-training feature set, the ridge regression parameter and the error judgment function, obtain the sub-error of the sub-training set for the ridge regression model under the ridge regression parameter, and obtain the corresponding sub-training feature set for each sub-training feature set. Descriptor error;

According to the sub-error corresponding to each sub-training feature set, the error of the training feature set for the ridge regression model under the ridge regression parameter is obtained.

In some embodiments, when obtaining the error of the training feature set with respect to the ridge regression model under the ridge regression parameter according to the sub-error corresponding to each sub-training feature set, the processor 501 may specifically perform the following steps :

According to the sub-error corresponding to each sub-training feature set, obtain the average error of the sub-training feature set;

The error of the training feature set for the ridge regression model under the ridge regression parameter is obtained according to the average error.

In some embodiments, when selecting a corresponding target ridge regression parameter from the multiple groups of ridge regression parameters according to the error corresponding to each group of ridge regression parameters, the processor 501 may specifically perform the following steps:

Determine the minimum error from the errors corresponding to each set of ridge regression parameters;

The ridge regression parameter corresponding to the minimum error is selected from the multiple sets of ridge regression parameters as the target ridge regression parameter.

It can be seen from the above that the electronic device of the embodiment of the present application obtains the multi-dimensional features of the application, and obtains the training feature set of the application; trains the ridge regression model according to the training feature set of the application, and obtains the trained ridge regression model; obtains the multi-dimensional feature of the application. According to the predicted feature set and the trained ridge regression model, it is predicted whether the application can be cleaned; in order to clean the cleanable applications; this solution can realize the automatic cleaning of the application and improve the performance of the electronic device. Runs smoothly and reduces power consumption.

Please also refer to FIG. 7 , in some embodiments, the electronic device 500 may further include: a display 503 , a radio frequency circuit 504 , an audio circuit 505 and a power supply 506 . Among them, the display 503 , the radio frequency circuit 504 , the audio circuit 505 and the power supply 506 are respectively electrically connected to the processor 501 .

The display 503 can be used to display information input by the user or information provided to the user and various graphical user interfaces, which can be composed of graphics, text, icons, videos, and any combination thereof. The display 503 may include a display panel, and in some embodiments, the display panel may be configured in the form of a liquid crystal display (Liquid Crystal Display, LCD), or an organic light-emitting diode (Organic Light-Emitting Diode, OLED).

The radio frequency circuit 504 can be used to send and receive radio frequency signals, so as to establish wireless communication with a 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 505 can be used to provide an audio interface between a user and an electronic device through a speaker and a microphone.

The power supply 506 may be used to power various components of the electronic device 500 . In some embodiments, the power supply 506 may be logically connected to the processor 501 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. 7 , the electronic device 500 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 is run on a computer, the computer is made to execute the application cleaning method in any of the foregoing embodiments, such as: obtaining The multi-dimensional features of the application are obtained, and the training feature set of the application is obtained; the ridge regression model is trained according to the training feature set of the application, and the trained ridge regression model is obtained; the multi-dimensional features of the application are obtained, and the prediction feature set of the application is obtained; according to the prediction feature set And the trained ridge regression model to predict whether the application is cleanable or not.

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 application cleaning 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 application cleaning method of the embodiment of the present application can be completed by controlling the relevant hardware through a computer program , the computer program can be stored in a computer-readable storage medium, such as stored in the memory of an electronic device, and executed by at least one processor in the electronic device, and the execution process can include processes such as applying a cleaning method. Example flow. The storage medium may be a magnetic disk, an optical disk, a read-only memory, a random access memory, or the like.

For the application cleaning device of the embodiment of the present application, each functional module thereof may be integrated into 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 module is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium, such as a read-only memory, a magnetic disk or an optical disk, etc. .

The application cleaning method, device, storage medium, and electronic device provided by the embodiments of the present application have been described in detail above. The principles and implementations of the present application are described with specific examples. The descriptions of the above embodiments are only It is used to help understand the method and the core idea of the present application; meanwhile, for those skilled in the art, according to the idea of the present application, there will be changes in the specific embodiments and application scope. In summary, this specification The content should not be construed as a limitation on this application.

Claims (12)

1. an application cleaning method, is characterized in that, comprises: Obtain the multi-dimensional features of the application, and obtain the training feature set of the application; The ridge regression model is trained according to the training feature set of the application, and the trained ridge regression model is obtained; it specifically includes: establishing an error judgment function of the ridge regression model; obtaining according to the training feature set and the error judgment function The target ridge regression parameter of the ridge regression model, the target ridge regression parameter includes a ridge parameter and a regression parameter; obtain a trained ridge regression model according to the target ridge regression parameter and the ridge regression model; Obtain the multi-dimensional features of the application, and obtain the predicted feature set of the application; Based on the predicted feature set and the trained ridge regression model, predict whether the application is cleanable. 2. The application cleaning method as claimed in claim 1, wherein the target ridge regression parameters of the ridge regression model are obtained according to the training feature set and the error judgment function, comprising: Obtain multiple sets of ridge regression parameters according to the error judgment function, and the ridge regression parameters include: ridge parameters and regression parameters; According to the training feature set, the ridge regression parameter and the error judgment function, the error of the training feature set for the ridge regression model under the ridge regression parameter is obtained, and the error corresponding to each group of ridge regression parameters is obtained ; According to the error corresponding to each group of ridge regression parameters, the corresponding target ridge regression parameter is selected from the multiple groups of ridge regression parameters. 3. application cleaning method as claimed in claim 2, is characterized in that, obtains multiple groups of ridge regression parameters according to described error judgment function, comprises: Obtain a corresponding regression parameter obtaining function according to the error judgment function; According to a plurality of preset ridge parameters and the regression parameter obtaining function, a regression parameter corresponding to each preset ridge parameter is obtained, and multiple sets of ridge regression parameters are obtained. 4. The application cleaning method according to claim 2, wherein, according to the training feature set, the ridge regression parameter and the error judgment function, it is obtained that the training feature set under the ridge regression parameter is for The error of the ridge regression model, including: dividing the training feature set into a plurality of sub-training feature sets; According to the sub-training feature set, the ridge regression parameter and the error judgment function, obtain the sub-error of the sub-training set for the ridge regression model under the ridge regression parameter, and obtain the corresponding sub-training feature set for each sub-training feature set. Descriptor error; According to the sub-error corresponding to each sub-training feature set, the error of the training feature set for the ridge regression model under the ridge regression parameter is obtained. 5. The application cleaning method according to claim 4, wherein, according to the corresponding sub-error of each sub-training feature set, the error of the training feature set for the ridge regression model under the ridge regression parameter is obtained, include: According to the sub-error corresponding to each sub-training feature set, obtain the average error of the sub-training feature set; The error of the training feature set for the ridge regression model under the ridge regression parameter is obtained according to the average error. 6. application cleaning method as claimed in claim 2 is characterized in that, according to the error corresponding to each group of ridge regression parameters, from described multiple groups of ridge regression parameters, select corresponding target ridge regression parameters, comprising: Determine the minimum error from the errors corresponding to each set of ridge regression parameters; The ridge regression parameter corresponding to the minimum error is selected from the multiple sets of ridge regression parameters as the target ridge regression parameter. 7. An application cleaning device, characterized in that, comprising: a training feature acquisition unit, used for acquiring multi-dimensional features of an application, and obtaining a training feature set of the application; A training unit, used for training the ridge regression model according to the training feature set of the application, to obtain the trained ridge regression model; a predictive feature acquisition unit, configured to acquire multidimensional features of the application, and obtain a predictive feature set of the application; a prediction unit, configured to predict whether the application can be cleaned according to the predicted feature set and the trained ridge regression model; Wherein, the training unit includes: establishing a subunit for establishing an error judgment function of the ridge regression model; a parameter obtaining subunit, configured to obtain a target ridge regression parameter of the ridge regression model according to the training feature set and the error judgment function, where the target ridge regression parameter includes a ridge parameter and a regression parameter; A training subunit, configured to obtain a trained ridge regression model according to the target ridge regression parameters and the ridge regression model. 8. The application cleaning device according to claim 7, wherein the parameter acquisition subunit is used for: Obtain multiple sets of ridge regression parameters according to the error judgment function, and the ridge regression parameters include: ridge parameters and regression parameters; According to the training feature set, the ridge regression parameter and the error judgment function, the error of the training feature set for the ridge regression model under the ridge regression parameter is obtained, and the error corresponding to each group of ridge regression parameters is obtained ; According to the error corresponding to each group of ridge regression parameters, the corresponding target ridge regression parameter is selected from the multiple groups of ridge regression parameters. 9. The application cleaning device according to claim 8, wherein the parameter acquisition subunit is specifically used for: Obtain a corresponding regression parameter obtaining function according to the error judgment function; According to a plurality of preset ridge parameters and the regression parameter obtaining function, a regression parameter corresponding to each preset ridge parameter is obtained, and multiple sets of ridge regression parameters are obtained. 10. The application cleaning device according to claim 8, wherein the parameter acquisition subunit is specifically used for: dividing the training feature set into a plurality of sub-training feature sets; According to the sub-training feature set, the ridge regression parameter and the error judgment function, obtain the sub-error of the sub-training set for the ridge regression model under the ridge regression parameter, and obtain the corresponding sub-training feature set for each sub-training feature set. Descriptor error; According to the sub-error corresponding to each sub-training feature set, the error of the training feature set for the ridge regression model under the ridge regression parameter is obtained. 11. A storage medium on which a computer program is stored, characterized in that, when the computer program runs on a computer, the computer is caused to execute the application cleaning method according to any one of claims 1 to 6. 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 6 by invoking the computer program. Apply the cleanup method.