WO2019062404A1 - Application program processing method and apparatus, storage medium, and electronic device - Google Patents

Abstract

Disclosed are an application program processing method and apparatus, a storage medium, and an electronic device. The application program processing method comprises: acquiring usage information about a sample application program at each sampling time point in a historical time period; generating a training sample according to the sampling time point and the usage information; training a pre-set Gaussian mixture model according to the training sample; and processing a background application program in an electronic device on the basis of the trained Gaussian mixture model.

Description

Application processing method, device, storage medium and electronic device

This application claims the priority of the Chinese Patent Application filed on Sep. 30, 2017, the Chinese Patent Office, Application No. 201710939548.6, entitled "Application Processing Method, Apparatus, Storage Medium, and Electronic Equipment", the entire contents of which are hereby incorporated by reference. The citations are incorporated herein by reference.

Technical field

The present application relates to the field of electronic device technologies, and in particular, to a method, an apparatus, a storage medium, and an electronic device for processing an application.

Background technique

With the development of the Internet and the development of mobile communication networks, along with the rapid development of processing capabilities and storage capabilities of electronic devices, massive applications have been rapidly spread and used; commonly used applications are convenient for users to work and live. There are also many newly developed applications that enter the daily life of users, improving the quality of life of users, the frequency of using terminals, and the sense of entertainment in use.

When there are multiple applications in the electronic device, the application running in the background will seriously occupy the resources of the electronic device, reduce the running fluency of the electronic device, and cause the power consumption of the electronic device to be large.

technical problem

The embodiment of the present application provides a processing method, an apparatus, a storage medium, and an electronic device of an application program, which can intelligently control an application program and reduce power consumption of the electronic device.

Technical solution

In a first aspect, an embodiment of the present application provides a processing method of an application, which is applied to an electronic device, where the method includes:

Obtaining usage information of the sample application at each sampling time point in the historical time period;

Generating a training sample according to the sampling time point and the usage information;

Training a preset mixed Gaussian model according to the training sample;

The background application in the electronic device is processed based on the trained mixed Gaussian model.

In a second aspect, the embodiment of the present application provides an application processing device, which is applied to an electronic device, where the device includes:

An obtaining module, configured to acquire usage information of a sample application at each sampling time point in a historical time period;

a generating module, configured to generate a training sample according to the sampling time point and the usage information;

a training module, configured to train the preset mixed Gaussian model according to the training sample;

And a processing module, configured to process a background application in the electronic device based on the trained mixed Gaussian model.

In a third aspect, the embodiment of the present application further provides a storage medium, where the storage medium stores a plurality of instructions, and the instructions are adapted to be loaded by a processor to perform the following steps:

Obtaining usage information of the sample application at each sampling time point in the historical time period;

Generating a training sample according to the sampling time point and the usage information;

Training a preset mixed Gaussian model according to the training sample;

The background application in the electronic device is processed based on the trained mixed Gaussian model.

In a fourth aspect, an embodiment of the present application further provides an electronic device, including a processor and a memory, the processor is electrically connected to the memory, the memory is used to store instructions and data, and the processor is configured to execute The following steps:

Obtaining usage information of the sample application at each sampling time point in the historical time period;

Generating a training sample according to the sampling time point and the usage information;

Training a preset mixed Gaussian model according to the training sample;

The background application in the electronic device is processed based on the trained mixed Gaussian model.

Beneficial effect

Intelligently manage applications and reduce power consumption in electronic devices.

DRAWINGS

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings used in the description of the embodiments will be briefly described below. It is obvious that the drawings in the following description are only some embodiments of the present application. Other drawings can also be obtained from those skilled in the art based on these drawings without paying any creative effort.

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

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

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

4 is a schematic diagram of a Gaussian model provided by an embodiment of the present application.

FIG. 5 is a schematic diagram of a hybrid Gaussian model provided by an embodiment of the present application.

FIG. 6 is a schematic structural diagram of a processing device of an application program according to an embodiment of the present application.

FIG. 7 is another schematic structural diagram of a processing device of an application program according to an embodiment of the present application.

FIG. 8 is still another schematic structural diagram of a processing device of an application program according to an embodiment of the present application.

FIG. 9 is still another schematic structural diagram of a processing device of an application program according to an embodiment of the present application;

FIG. 10 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

FIG. 11 is another schematic structural diagram of an electronic device according to an embodiment of the present application.

Embodiments of the invention

The technical solutions in the embodiments of the present application are clearly and completely described in the following with reference to the drawings in the embodiments of the present application. It is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments obtained by a person skilled in the art based on the embodiments of the present application without creative efforts are within the scope of the present application.

The embodiment of the present application provides a processing method, device, storage medium, and electronic device of an application program. The details will be described separately below.

Referring to FIG. 1 , FIG. 1 is a schematic diagram of a scenario structure of an application processing method according to an embodiment of the present application.

As shown in Figure 1, the application running in the background is processed from A to E as an example. First, data collection is performed to record the usage information of the electronic device in each application, such as recording the time when each application is opened within one month. Then, according to the usage record of the collected application, the usage probability of each application at different times is counted, and the usage time and the corresponding usage probability are used as training samples, and the preset mixed Gaussian model is trained according to the input The sample adjusts the parameter information in the mixed Gaussian model to obtain a trained mixed Gaussian model corresponding to each application. Based on the trained mixed Gaussian model corresponding to each application, the usage probability of the background application at time T is calculated, and the target background whose usage probability is lower than the preset probability P is determined from the plurality of background applications A to E. Application and close the target background application. Therefore, the control of the background application is implemented based on the user's usage habits, and the occupation of the electronic device resources by the application is reduced.

The electronic device may be a mobile terminal, such as a mobile phone, a tablet computer, a notebook computer, etc., which is not limited in this embodiment.

An embodiment of the present application provides a processing method of an application, where the method includes:

Obtaining usage information of the sample application at each sampling time point in the historical time period;

Generating a training sample according to the sampling time point and the usage information;

Training a preset mixed Gaussian model according to the training sample;

The background application in the electronic device is processed based on the trained mixed Gaussian model.

In some embodiments, the historical time period includes a plurality of time periods, each time period being divided into a plurality of sampling periods;

The step of generating a training sample according to the sampling time point and the usage information includes:

Determining a time period and a sampling period corresponding to each sampling time point, wherein the sampling time point corresponds to the sampling period one-to-one in each time period;

The usage information corresponding to the same sampling period in different time periods is processed to obtain a sample usage probability corresponding to the sample application in each sampling period;

The training samples are generated based on the sampling period and the corresponding sample usage probability.

In some embodiments, the processing information corresponding to the same sampling period in different time periods is processed to obtain a sample usage probability corresponding to the sample application in each sampling period, including:

Determining whether the usage information meets a preset condition;

Determining, by each sample, the number of sampling time points in which the corresponding usage information in the same sampling period satisfies a preset condition;

Obtaining a total number of sampling time points for which each sample application uses information in a plurality of time periods to satisfy a preset condition;

A sample usage probability corresponding to each sample application period is calculated according to the number of sampling time points and the total number of sampling time points.

In some embodiments, the usage information is running state information of the sample application; and the step of determining whether the usage information meets a preset condition comprises:

Determining whether the running state is running in the foreground;

If yes, determining that the usage information meets a preset condition;

If not, it is determined that the usage information does not satisfy the preset condition.

In some embodiments, the sampling period includes [t ₁ , t ₂ ... t _m ], and the sample usage probability includes [P ₁ , P ₂ . . . P _m ];

The step of training the preset mixed Gaussian model according to the training sample includes:

Inputting the sampling period and the corresponding sample usage probability into the first formula, where the first preset formula is:

Where Ai represents the sample application i, t represents the sampling period, k represents the number of sub-Gaussian models, μk represents the mathematical expectation, σk represents the variance, ωk represents the weight, and N(t|μk, σk) represents the random variable t obeys a mathematics It is expected that the normal distribution is μk and the variance is σk, and P(t|Ai) represents the probability that the running state of the sample application i is the sampling period of the foreground running time is t;

And training the first preset formula to obtain a plurality of trained sub-Gaussian models based on the input sampling period and the sample usage probability;

A plurality of trained sub-Gaussian models are superimposed to obtain a mixed Gaussian model after training.

In some embodiments, each application corresponds to a uniquely trained mixed Gaussian model;

The step of processing the background application in the electronic device based on the trained mixed Gaussian model includes:

Obtain application processing instructions;

Determining a background application in the electronic device according to the application processing instruction;

The usage probability of each background application at the target time is calculated by using the second preset formula based on the mixed Gaussian model corresponding to each application, and the second preset formula is:

Where T is the time, N is the number of mixed Gaussian models after training, P(Ai|T) is the probability that the application running in the foreground is the application i when the sampling period is T, and P(T|Ai) is the sample application. The running state of the program i is the probability that the sampling period is T when the foreground is running, and P(T|Aj) indicates the probability that the running state of the application j is the sampling period of the foreground running time is T;

The background application is processed according to the usage probability.

In some embodiments, the step of processing the background application according to the usage probability includes:

Determining a target background application whose usage probability is less than a preset threshold from the current background application;

Close the target background application.

In an embodiment, a processing method of an application is provided, which is applied to an electronic device, and the electronic device may be a mobile terminal such as a smart phone, a tablet computer, or a notebook computer. As shown in Figure 2, the process can be as follows:

101. Obtain usage information of the sample application at each sampling time point in the historical time period.

The application mentioned in this embodiment may be any application installed on the electronic device, such as an office application, a social application, a game application, a shopping application, and the like.

The sample application can be multiple or all installed applications in the electronic device. The application usage information can be a usage record of the application, such as the opening time record of each application. The sampling time point can be set according to actual needs. If you want to get higher accuracy results, you can set the collection time point to be more dense, such as every 1min as a sampling time point; if you want to save resources of electronic equipment If the accuracy of the result is not required, the sampling time point can be set loosely, for example, every 10 minutes is a sampling time point.

In some embodiments, from the application installation, the usage information of each installed application may be recorded and converted into corresponding data storage into a preset storage area. When the usage information of one or some applications needs to be used, data corresponding to the certain application or some applications may be retrieved from the storage area, and the acquired data is parsed to obtain corresponding information, as The usage information of the application or the application, and the application or the application is used as a sample application, and the usage information in the required time period is selected from the obtained usage information.

In some embodiments, in order to reduce the power consumption of the electronic device and save the terminal resources of the electronic device, the time period of the required recording may be directly set, and then the usage information of the sample application for each sampling time point is selected within the time period. Record it for later use.

102. Generate a training sample according to the sampling time point and the usage information.

Specifically, the usage information of the obtained sample application may be preprocessed, the usage probability of each sample application at different sampling time points is calculated, and the probability distribution of the usage of each sample application over time is further obtained. The training sample is generated by one-to-one correspondence between the sampling time point and the usage probability.

103. Train the preset mixed Gaussian model according to the training sample.

Specifically, the training sample generated above is input into a preset mixed Gaussian model, and relevant parameters in the preset mixed Gaussian model are continuously corrected according to the input training sample, so that the trained mixed Gaussian model can be applied to All training samples, and finally a mixed Gaussian model is trained for each sample application. Among them, each mixed Gaussian model is composed of multiple sub-Gaussian models.

104. The background application in the electronic device is processed based on the trained mixed Gaussian model.

In the embodiment of the present application, if there are N number of sample applications, there are corresponding N mixed Gaussian models after training. Obtain identity information (such as application name, application identifier, etc.) of each background application, and select a target mixed Gaussian model from the N trained mixed Gaussian models according to the identity information of the background application (ie, for the background application) Train the mixed Gaussian model) and blend the Gaussian model based on the target against the background application.

In some embodiments, the usage probability of each background application at the time may be calculated based on the mixed Gaussian model corresponding to each of the different background applications, combined with the current time. According to the calculated usage probabilities of the respective applications, the background application whose usage probability meets certain conditions is cleaned or closed to reduce the occupation of the electronic device resources by the application.

As can be seen from the above, the application is a processing method of an application provided by an embodiment, which acquires usage information of a sample application at each sampling time point in a historical time period, generates a training sample according to a sampling time point and usage information, and then, according to the training sample. The preset mixed Gaussian model is trained, and the background application in the electronic device is processed based on the trained mixed Gaussian model. The solution can reduce the occupation of the final resources of the electronic device, improve the running fluency of the electronic device, and reduce the power consumption of the electronic device.

In an embodiment, another application processing method is also provided, which is applied to an electronic device, and the electronic device may be a mobile terminal such as a smart phone, a tablet computer, or a notebook computer. As shown in Figure 3, the process can be as follows:

201. Obtain usage information of the sample application at each sampling time point in the historical time period.

The sample application can be multiple or all installed applications in an electronic device. The sampling time point can be set according to actual needs. If you want to get higher accuracy results, you can set the collection time point to be more dense, such as every 1min as a sampling time point; if you want to save resources of electronic equipment, the result is If the accuracy is not required, the sampling time point can be loosely set, such as every 10 minutes as a sampling time point. The usage information of the application can be related information of the application during use.

For example, the historical time period can be the past month, and each time point can be the time stamp of the current time. The usage parameters can be extracted from the database, which can store the open records of the applications in the electronic device in the past month, as shown in Table 1 below:

Application package name	Open the timestamp of this app
Com.tencent.mobileqq	1457550655465
Com.android.setings	1457605107522
...	...

Table 1

After that, open the records of these applications as the usage information of each sample application at each sampling time point.

202. Determine a time period and a sampling period corresponding to each sampling time point, where the sampling time point corresponds to the sampling period one-to-one in each time period.

In some embodiments, the historical time period includes a plurality of time periods, such as the historical time period being the past month, and the time period may be each of the past one month. Each time period can be divided into multiple sampling periods, such as every minute of the day. Specifically, the time period to which the sampling time point corresponds and the specific sampling period may be determined, such as xx months xx days xx minutes. Take September 481 as an example, September is the historical time period, 9 is the time period, and 481 is the sampling period.

The sample collection can be completed on a terminal device such as a smart phone or a tablet computer, and the application information currently being used on the current terminal device is acquired every 1 minute and stored in the database of the terminal device, then one for one user. The monthly usage record can extract tens of thousands of usage information samples.

203. Process usage information corresponding to the same sampling period in different time periods to obtain a sample usage probability corresponding to the sample application in each sampling period.

In some embodiments, the step of “processing the usage information corresponding to the same sampling period in different time periods to obtain the sample usage probability corresponding to the sample application in each sampling period” may include the following processes:

Determining whether the usage information satisfies a preset condition;

Determining, by each sample, the number of sampling time points in which the corresponding usage information in the same sampling period satisfies a preset condition;

Obtaining a total number of sampling time points for which each sample application uses information in a plurality of time periods to satisfy a preset condition;

The sample usage probability corresponding to each sample application period is calculated according to the number of sampling time points and the total number of sampling time points.

Specifically, according to the collected user usage application record, the N sample application programs most commonly used by the user may be counted, where N is configurable. In order to properly allocate electronic equipment resources and reduce the amount of computation, usually N=5.

In some embodiments, the usage information may be operational status information of the sample application; then the step “determining whether the usage information satisfies the preset condition” may include the following processes:

Determine whether the running status is running in the foreground;

If yes, it is determined that the usage information satisfies the preset condition;

If not, it is determined that the usage information does not satisfy the preset condition.

Among them, the running state is running in the foreground, which means that the current user is using the sample application. Then for the N sample applications, each sample application is counted for the same time period in each day of the past month (eg, 1440 minutes per day, then 481 minutes and September 31st of September 1st) The number of sampling time points running in the foreground in the same time period; the 1440 minutes on September 1 and the 1440 minutes on September 31 are the same time period, recorded as X=[x ₁ , x ₂ , x ₃ ... x _i ..., x _n ], where xi represents the number of times the application was used during the ith minute of the day of September.

For example, take the 30 days from September 1st to September 30th as the historical time period. If there are 25 days, 25 days of users use WeChat from 8:01 to 8:10 in the morning, while others Time does not use WeChat. Then the statistical method is: convert 8:01 to the time zone as the 481th (8*60+1=481), and convert 8:10 to the time zone as the 490th (8*60+10=490) . Then the user's WeChat usage information statistics can be as shown in Table 2 below:

application	x 1	...	x 481	...	x 490	...	x 1440
WeChat	0	0	25	25	25	0	0
QQ	...	...	...	...	...	...	...
...
...

Table 2

In the embodiment of the present application, the probability of the sample use probability corresponding to each sample application period in each sampling period may be defined as Pi, and the specific algorithm of the probability Pi may refer to the following formula:

Where xj is the same as the definition of xi, both indicate the number of times the application is used during the ith or j minutes of the day. n is a positive integer greater than one. Based on the above data and the probability algorithm, the probability distribution of the sample use probability corresponding to each sample application period in each sampling period can be obtained, as shown in Table 3 below:

application	P 1	...	P 481	...	P 490	...	P 1440
WeChat	0	0	0.1	0.1	0.1	0	0
QQ	...	...	...	...	...	...	...
...
...

table 3

204. Generate a training sample based on the sampling period and the corresponding sample usage probability.

Specifically, according to the probability distribution of the sample use probability of each sample application in the above Table 2, the sampling time point and the sample use probability are generated in one-to-one correspondence to generate a training sample.

In some embodiments, if the sampling period is recorded as t, the sampling period includes [t ₁ , t ₂ ... t _m ], the sample usage probability is denoted as P, and the sample usage probability includes [P ₁ , P ₂ ... P _m ]. Specifically, the generated training sample can be recorded as (t _m , P _m ), and the training sample corresponding to the 481th minute is (481, 0.1).

205. Input the training sample into the first formula to train the first preset formula to obtain a plurality of trained sub-Gaussian models.

The first preset formula in the embodiment of the present application is a probability spectral density function of the mixed Gaussian model, as follows:

Where A _i represents the sample application i, t represents the sampling period, k represents the number of sub-Gaussian models, μ _k represents the mathematical expectation, σ _k represents the variance, ω _k represents the weight, and N(t|μ _k , σ _k ) represents The random variable t obeys a normal distribution with a mathematical expectation of μ _k and a variance of σ _k , and P(t|A _i ) can represent the probability that the running state of the sample application i is the sampling period of the foreground running time is t.

It is a Gaussian distribution probability model.

Referring to Figure 4, it can be used as an initialized Gaussian model. Then, based on the input sampling period and the sample usage probability, the first preset formula is trained to obtain a plurality of trained sub-Gaussian models. Specifically, the mixed Gaussian model can be modeled when the training sample corresponding to the first minute is read; then the training sample corresponding to the second minute is read, the Gaussian model parameters are updated; and the training sample corresponding to the third minute is read, and the processing is continued. Update the mixed Gaussian model parameters... and so on, until all training samples are read, update the Gaussian model parameters to get the final trained mixed Gaussian model.

The mixed Gaussian model is generally constructed using 3 to 5 sub-Gaussian models. In the modeling process, some parameters such as variance σ _k , mathematical expectation μ _k , weight ω _k in the mixed Gaussian model need to be initialized, and the data required for modeling is obtained through these parameters. In the initialization process, the variance can be set as large as possible, and the weight (ie ω _k ) is as small as possible (such as 0.001). This setup is due to the fact that the initialized Gaussian model is an inaccurate model that needs to constantly shrink its range and update its parameter values to get the most probable Gaussian model. To set the variance larger, in order to include as many pixels as possible into a model, find the parameter k, the corresponding weights ω _k , and the corresponding parameters μ _k and σ _{k in} all the sub-Gaussian models.

In some embodiments, maximum likelihood estimation may be employed to determine these model parameters such as ω _k , μ _{k ,} and σ _k . Among them, the likelihood function of the mixed Gaussian model is:

The likelihood function of (μ _k , σ _k ) is maximized using an expectation maximization (EM) algorithm. Then the maximum values corresponding to ω _k , μ _k and σ _k are our estimates. Finally, [(ω ₁ , μ ₁ , σ ₁ ), (ω ₁ , μ ₁ , σ ₁ ), ... (ω _k , μ _k , σ _k )] are obtained.

206. Superimpose the plurality of trained sub-Gaussian models to obtain a mixed Gaussian model after training.

Specifically, after weighting each sub-Gaussian model according to the estimated weight ω _k , the weighted k sub-Gaussian models are superimposed to obtain a mixed Gaussian model after training. Referring to Figure 5, the resulting mixed Gaussian model consists of four sub-Gaussian models.

Assuming that the user has N sample applications, there are N mixed Gaussian models, namely [P(t|A ₁ ), P(t|A ₂ ),...P(t|A _N )].

207. Determine a background application in the electronic device.

In some embodiments, the application processing instructions may be triggered when the central processing unit (CPU) of the electronic device occupies a large amount, the running memory resource is occupied, and/or the remaining power of the electronic device is insufficient. The electronic device acquires the application processing instruction, and then determines a background application running in the background according to the application processing instruction, so as to subsequently process the background application.

208. Calculate a usage probability of each background application at a target time by using a second preset formula based on the mixed Gaussian model corresponding to each application.

In the embodiment of the present application, each application corresponds to a uniquely trained mixed Gaussian model. Based on the mixed Gaussian model after training, the probability of use of the application at different times can be accurately estimated. The second preset formula is:

Where T represents time, T can be every minute of the day, ie T∈[1,2,3,...1440]; N represents the number of mixed Gaussian models after training; P(A _i |T) The application running in the foreground when the sampling period is T is the probability of the application i; P(T|A _i ) indicates the probability that the running state of the sample application i is the sampling period of the foreground running time is T; P(T|A _j ) Indicates the running state of the application j is the probability that the sampling period is T when the foreground is running.

Specifically, firstly, based on the mixed Gaussian model after training, the initial usage probability corresponding to each application in the target time is estimated, and then the second preset formula is used to calculate the initial usage probability corresponding to the target background application. The occupancy rate of the initial usage probability of the program is used as the usage probability of the application at the target time to improve the accuracy of the usage probability.

209. Process the background application according to the usage probability.

In some embodiments, the probability threshold can be set as a basis for processing the application. That is, the step "Processing the background application according to the probability of use" may include the following process:

Determining a target background application whose usage probability is less than a preset threshold from the current background application;

Close the target background app.

The preset threshold may be set by a person skilled in the art or a product manufacturer. For example, the predetermined threshold is set to 0.5, then T is opened when the background application probability P of A _i in the next period (T | A _i) is less than 0.5, the background application program A _i is clean, if not less than 0.5, Keep the background application A _i running in the background.

It can be seen that the processing method of the application program provided by the embodiment of the present application obtains the usage information of the sample application at each sampling time point in the historical time period, and then determines the time period and the sampling period corresponding to each sampling time point, and then The usage information corresponding to the same sampling period in different time periods is processed to obtain a sample usage probability corresponding to the sample application in each sampling period. The training samples are generated based on the sampling period and the corresponding sample use probability, and are input into a preset mixed Gaussian model for model training, and a new mixed Gaussian model composed of a plurality of trained sub-Gaussian models is obtained. Finally, the new mixed Gaussian model is used to estimate the usage probability of each background application at the target time, and the corresponding background application is processed according to the obtained probability. The solution can reduce the occupation of the final resources of the electronic device, improve the running fluency of the electronic device, and reduce the power consumption of the electronic device.

In another embodiment of the present application, a processing device for an application is further provided. The processing device of the application may be integrated into the electronic device in the form of software or hardware, and the electronic device may specifically include a mobile phone, a tablet computer, and a notebook computer. And other equipment. As shown in FIG. 6, the processing device 30 of the application may include a receiving module 31, a determining module 32, a receiving module 33, and a processing module 34, where:

The obtaining module 31 is configured to acquire usage information of the sample application at each sampling time point in the historical time period;

a generating module 32, configured to generate a training sample according to the sampling time point and the usage information;

The training module 33 is configured to train the preset mixed Gaussian model according to the training sample;

The processing module 34 is configured to process the background application in the electronic device based on the trained mixed Gaussian model.

In some embodiments, the historical time period includes a plurality of time periods, each time period being divided into a plurality of sampling periods. Referring to FIG. 7, the generating module 32 may include:

The first determining submodule 321 is configured to determine a time period and a sampling period corresponding to each sampling time point, wherein the sampling time point corresponds to the sampling period one-to-one in each time period;

The information processing sub-module 322 is configured to process the usage information corresponding to the same sampling period in different time periods to obtain a sample usage probability corresponding to the sample application in each sampling period;

The generating submodule 323 is configured to generate a training sample based on the sampling period and the corresponding sample usage probability.

In some embodiments, the processing sub-module 322 can include:

a determining unit, configured to determine whether the usage information meets a preset condition;

a first determining unit, configured to determine, by each sample, a number of sampling time points that the corresponding usage information in the same sampling period meets the preset condition;

An obtaining unit, configured to acquire a total number of sampling time points in which each sample application uses the information to satisfy the preset condition in multiple time periods;

The calculating unit is configured to calculate, according to the number of sampling time points and the total number of sampling time points, a sample usage probability corresponding to each sample application period in each sampling period.

In some embodiments, the usage information is operational state information of the sample application; the determining unit can be used to:

Determine whether the running status is running in the foreground;

If yes, it is determined that the usage information satisfies the preset condition;

If not, it is determined that the usage information does not satisfy the preset condition

In some embodiments, the sampling period includes [t ₁ , t ₂ ... t _m ], and the sample usage probability includes [P ₁ , P ₂ . . . P _m ]; referring to FIG. 8 , the training module 33 may include:

The input sub-module 331 is configured to input the sampling period and the corresponding sample usage probability into the first formula, where the first preset formula is:

Where A _i represents the sample application i, t represents the sampling period, k represents the number of sub-Gaussian models, μ _k represents the mathematical expectation, σ _k represents the variance, ω _k represents the weight, and N(t|μ _k , σ _k ) represents The random variable t obeys a normal distribution with a mathematical expectation of μ _k and a variance of σ _k , and P(t|A _i ) represents the probability that the running state of the sample application i is the sampling period of the foreground running time is t;

The training sub-module 332 is configured to train the first preset formula based on the input sampling period and the sample usage probability to obtain a plurality of trained sub-Gauss models;

The superposition sub-module 333 is configured to superimpose the plurality of trained sub-Gaussian models to obtain the trained mixed Gaussian model.

In some embodiments, each application corresponds to a uniquely trained mixed Gaussian model; with reference to Figure 9, the processing module 34 can include:

The obtaining submodule 341 is configured to acquire an application processing instruction;

a second determining submodule 342, configured to determine a background application in the electronic device according to the application processing instruction;

The calculation sub-module 343 is configured to calculate the usage probability of each background application at the target time by using the second preset formula based on the mixed Gaussian model corresponding to each application, and the second preset formula is:

Where T is the time, N is the number of mixed Gaussian models after training, and P(A _i |T) is the probability that the application running in the foreground is the application i when the sampling period is T, and P(T|A _i ) is expressed. The running state of the sample application i is the probability that the sampling period is T when the foreground is running, and P(T|A _j ) indicates the probability that the running state of the application j is the sampling period of the foreground running time is T;

The application processing sub-module 344 is configured to process the background application according to the usage probability.

In some embodiments, the application processing sub-module 344 can include:

a second determining unit, configured to determine, from the current background application, a target background application whose usage probability is less than a preset threshold;

Close the unit to close the target background application.

It can be seen that the processing device of the application program provided by the embodiment of the present application generates the training sample according to the sampling time point and the usage information by acquiring the usage information of the sample application at each sampling time point in the historical time period, and then according to the training sample pair. The preset mixed Gaussian model is trained, and the background application in the electronic device is processed based on the trained mixed Gaussian model. The solution can reduce the occupation of the final resources of the electronic device, improve the running fluency of the electronic device, and reduce the power consumption of the electronic device.

In another embodiment of the present application, an electronic device is further provided, and the electronic device may be a device such as a smart phone or a tablet computer. As shown in FIG. 10, the electronic device 400 includes a processor 401 and a memory 402. The processor 401 is electrically connected to the memory 402.

The processor 401 is a control center of the electronic device 400, and connects various parts of the entire electronic device using various interfaces and lines, executes the electronic device by running or loading an application stored in the memory 402, and calling data stored in the memory 402. The various functions and processing of data to provide overall monitoring of the electronic device.

In this embodiment, the processor 401 in the electronic device 400 loads the instructions corresponding to the process of one or more applications into the memory 402 according to the following steps, and is stored in the memory 402 by the processor 401. Application to achieve various functions:

Obtaining usage information of the sample application at each sampling time point in the historical time period;

Generating training samples based on sampling time points and usage information;

Training the preset mixed Gaussian model according to the training sample;

The background application in the electronic device is processed based on the trained mixed Gaussian model.

In some embodiments, the historical time period includes a plurality of time periods, each time period being divided into a plurality of sampling periods; the processor 401 is further configured to perform the following steps:

Determining a time period and a sampling period corresponding to each sampling time point, wherein the sampling time point corresponds to the sampling period one-to-one in each time period;

The usage information corresponding to the same sampling period in different time periods is processed to obtain a sample usage probability corresponding to the sample application in each sampling period;

The training samples are generated based on the sampling period and the corresponding sample usage probability.

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

Determining whether the usage information satisfies a preset condition;

Determining, by each sample, the number of sampling time points in which the corresponding usage information in the same sampling period satisfies a preset condition;

Obtaining a total number of sampling time points for which each sample application uses information in a plurality of time periods to satisfy a preset condition;

The sample usage probability corresponding to each sample application period is calculated according to the number of sampling time points and the total number of sampling time points.

In some embodiments, the usage information is operational state information of the sample application, and the processor 401 is further configured to perform the following steps:

Determine whether the running status is running in the foreground;

If yes, it is determined that the usage information satisfies the preset condition;

If not, it is determined that the usage information does not satisfy the preset condition.

In some embodiments, the sampling period includes [t ₁ , t ₂ ... t _m ], and the sample usage probability includes [P ₁ , P ₂ . . . P _m ]; the processor 401 is further configured to perform the following steps:

The sampling period and the corresponding sample usage probability are input into the first formula, and the first preset formula is:

Where Ai represents the sample application i, t represents the sampling period, k represents the number of sub-Gaussian models, μk represents the mathematical expectation, σk represents the variance, ωk represents the weight, and N(t|μk, σk) represents the random variable t obeys a mathematics It is expected that the normal distribution is μk and the variance is σk, and P(t|Ai) represents the probability that the running state of the sample application i is the sampling period of the foreground running time is t;

The first preset formula is trained based on the input sampling period and the sample usage probability to obtain a plurality of trained sub-Gauss models;

A plurality of trained sub-Gaussian models are superimposed to obtain a mixed Gaussian model after training.

In some embodiments, each application corresponds to a uniquely trained mixed Gaussian model; the processor 401 is further configured to perform the following steps:

Obtain application processing instructions;

Determining a background application in the electronic device according to the application processing instruction;

Based on the trained mixed Gaussian model of each application, the second preset formula is used to calculate the usage probability of each background application at the target time. The second preset formula is:

Where T is the time, N is the number of mixed Gaussian models after training, P(Ai|T) is the probability that the application running in the foreground is the application i when the sampling period is T, and P(T|Ai) is the sample application. The running state of the program i is the probability that the sampling period is T when the foreground is running, and P(T|Aj) indicates the probability that the running state of the application j is the sampling period of the foreground running time is T;

The background application is processed according to the probability of use.

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

Determining a target background application whose usage probability is less than a preset threshold from the current background application;

Close the target background app.

Memory 402 can be used to store applications and data. The application stored in memory 402 contains instructions that are executable in the processor. Applications can form various functional modules. The processor 401 executes various functional applications and data processing by running an application stored in the memory 402.

In some embodiments, as shown in FIG. 11, the electronic device 400 further includes a display screen 403, a control circuit 404, a radio frequency circuit 405, an input unit 406, an audio circuit 407, a sensor 408, and a power source 409. The processor 401 is electrically connected to the display screen 403, the control circuit 404, the radio frequency circuit 405, the input unit 406, the audio circuit 407, the sensor 408, and the power source 409, respectively.

The display screen 403 can be used to display information entered by the user or information provided to the user as well as various graphical user interfaces of the electronic device, which can be composed of images, text, icons, video, and any combination thereof.

The control circuit 404 is electrically connected to the display screen 403 for controlling the display screen 403 to display information.

The radio frequency circuit 405 is configured to transmit and receive radio frequency signals to establish wireless communication with network devices or other electronic devices through wireless communication, and to transmit and receive signals with network devices or other electronic devices.

The input unit 406 can be configured to receive input digits, character information, or user characteristic information (eg, fingerprints), and to generate keyboard, mouse, joystick, optical, or trackball signal inputs related to user settings and function controls. The input unit 406 can include a fingerprint identification module.

The audio circuit 407 can provide an audio interface between the user and the electronic device through a speaker and a microphone.

Sensor 408 is used to collect external environmental information. Sensor 408 can include ambient brightness sensors, acceleration sensors, light sensors, motion sensors, and other sensors.

Power source 409 is used to power various components of electronic device 400. In some embodiments, the power supply 409 can be logically coupled to the processor 401 through a power management system to enable functions such as managing charging, discharging, and power management through the power management system.

Although not shown in FIG. 11, the electronic device 400 may further include a camera, a Bluetooth module, and the like, and details are not described herein.

It can be seen that the electronic device provided by the embodiment of the present application generates the training sample according to the sampling time point and the usage information by acquiring the usage information of the sample application at each sampling time point in the historical time period, and then presets according to the training sample. The mixed Gaussian model is trained to process the background application in the electronic device based on the trained mixed Gaussian model. The solution can reduce the occupation of the final resources of the electronic device, improve the running fluency of the electronic device, and reduce the power consumption of the electronic device.

In some embodiments, a storage medium is also provided having stored therein a plurality of instructions adapted to be loaded by a processor to perform a processing method of any of the applications described above. For example, the stored plurality of instructions are adapted to be loaded by the processor to perform the following steps:

Obtaining usage information of the sample application at each sampling time point in the historical time period;

Generating a training sample according to the sampling time point and the usage information;

Training a preset mixed Gaussian model according to the training sample;

The background application in the electronic device is processed based on the trained mixed Gaussian model.

A person skilled in the art may understand that all or part of the various steps of the foregoing embodiments may be performed by a program to instruct related hardware. The program may be stored in a computer readable storage medium, and the storage medium may include: Read Only Memory (ROM), Random Access Memory (RAM), disk or optical disk.

The terms "a", "an", "the", and "the" In addition, unless otherwise stated herein, the recitation of numerical ranges herein is merely referring to each of the individual These values are stated separately in this article. In addition, the steps of all methods described herein can be performed in any suitable order unless otherwise indicated herein or otherwise indicated. Changes to the application are not limited to the sequence of steps described. The use of any and all examples or exemplary language, such as "a" Numerous modifications and adaptations will be apparent to those skilled in the art without departing from the scope of the invention.

The processing method, device, storage medium and electronic device of the application program provided by the embodiments of the present application are described in detail. The principles and implementation manners of the application are described in the specific examples. The description of the above embodiments is only The method for understanding the present application and its core idea; at the same time, those skilled in the art, according to the idea of the present application, there will be changes in the specific embodiment and the scope of application, in summary, the present specification The content should not be construed as limiting the application.

Claims (20)

1. An application processing method is applied to an electronic device, wherein the method includes:

   Obtaining usage information of the sample application at each sampling time point in the historical time period;

   Generating a training sample according to the sampling time point and the usage information;

   Training a preset mixed Gaussian model according to the training sample;

   The background application in the electronic device is processed based on the trained mixed Gaussian model.
2. The processing method of an application program according to claim 1, wherein the historical time period comprises a plurality of time periods, each time period being divided into a plurality of sampling periods;

   The step of generating a training sample according to the sampling time point and the usage information includes:

   Determining a time period and a sampling period corresponding to each sampling time point, wherein the sampling time point corresponds to the sampling period one-to-one in each time period;

   The usage information corresponding to the same sampling period in different time periods is processed to obtain a sample usage probability corresponding to the sample application in each sampling period;

   The training samples are generated based on the sampling period and the corresponding sample usage probability.
3. The processing method of the application program according to claim 2, wherein the step of processing the usage information corresponding to the same sampling period in different time periods to obtain the sample usage probability corresponding to the sample application in each sampling period comprises:

   Determining whether the usage information meets a preset condition;

   Determining, by each sample, the number of sampling time points in which the corresponding usage information in the same sampling period satisfies a preset condition;

   Obtaining a total number of sampling time points for which each sample application uses information in a plurality of time periods to satisfy a preset condition;

   A sample usage probability corresponding to each sample application period is calculated according to the number of sampling time points and the total number of sampling time points.
4. The processing method of the application program according to claim 3, wherein the usage information is operation state information of the sample application; and the step of determining whether the usage information satisfies a preset condition comprises:

   Determining whether the running state is running in the foreground;

   If yes, determining that the usage information meets a preset condition;

   If not, it is determined that the usage information does not satisfy the preset condition.
5. The processing method of an application according to claim 2, wherein said sampling period includes [t ₁ , t ₂ ... t _m ], and said sample use probability includes [P ₁ , P ₂ ... P _m ];

   The step of training the preset mixed Gaussian model according to the training sample includes:

   Inputting the sampling period and the corresponding sample usage probability into the first formula, where the first preset formula is:

   

   Where Ai represents the sample application i, t represents the sampling period, k represents the number of sub-Gaussian models, μk represents the mathematical expectation, σk represents the variance, ωk represents the weight, and N(t|μk, σk) represents the random variable t obeys a mathematics It is expected that the normal distribution is μk and the variance is σk, and P(t|Ai) represents the probability that the running state of the sample application i is the sampling period of the foreground running time is t;

   And training the first preset formula to obtain a plurality of trained sub-Gaussian models based on the input sampling period and the sample usage probability;

   A plurality of trained sub-Gaussian models are superimposed to obtain a mixed Gaussian model after training.
6. The processing method of an application according to claim 5, wherein each application corresponds to a uniquely trained mixed Gaussian model;

   The step of processing the background application in the electronic device based on the trained mixed Gaussian model includes:

   Obtain application processing instructions;

   Determining a background application in the electronic device according to the application processing instruction;

   The usage probability of each background application at the target time is calculated by using the second preset formula based on the mixed Gaussian model corresponding to each application, and the second preset formula is:

   

   Where T is the time, N is the number of mixed Gaussian models after training, P(Ai|T) is the probability that the application running in the foreground is the application i when the sampling period is T, and P(T|Ai) is the sample application. The running state of the program i is the probability that the sampling period is T when the foreground is running, and P(T|Aj) indicates the probability that the running state of the application j is the sampling period of the foreground running time is T;

   The background application is processed according to the usage probability.
7. The processing method of the application program according to claim 6, wherein the step of processing the background application according to the usage probability comprises:

   Determining a target background application whose usage probability is less than a preset threshold from the current background application;

   Close the target background application.
8. An application processing device, wherein the device comprises:

   An obtaining module, configured to acquire usage information of a sample application at each sampling time point in a historical time period;

   a generating module, configured to generate a training sample according to the sampling time point and the usage information;

   a training module, configured to train the preset mixed Gaussian model according to the training sample;

   And a processing module, configured to process a background application in the electronic device based on the trained mixed Gaussian model.
9. The processing device of the application according to claim 8, wherein the historical time period comprises a plurality of time periods, each time period being divided into a plurality of sampling periods;

   The generating module includes:

   a first determining submodule, configured to determine a time period and a sampling period corresponding to each sampling time point, wherein the sampling time point corresponds to the sampling period one-to-one in each time period;

   An information processing sub-module, configured to process usage information corresponding to the same sampling period in different time periods, to obtain a sample usage probability corresponding to the sample application in each sampling period;

   Generating a sub-module for generating a training sample based on the sampling period and the corresponding sample usage probability.
10. The processing device of the application of claim 9, wherein the processing sub-module comprises:

    a determining unit, configured to determine whether the usage information meets a preset condition;

    a first determining unit, configured to determine, by using each sample, a number of sampling time points in which the corresponding usage information in the same sampling period meets the preset condition;

    An obtaining unit, configured to acquire a total number of sampling time points in which each sample application uses the information to satisfy the preset condition in multiple time periods;

    And a calculating unit, configured to calculate, according to the number of sampling time points and the total number of sampling time points, a sample usage probability corresponding to each sample application period in each sampling period.
11. The processing device of the application according to claim 10, wherein the usage information is operating state information of the sample application; the determining unit is configured to:

    Determining whether the running state is running in the foreground;

    If yes, determining that the usage information meets a preset condition;

    If not, it is determined that the usage information does not satisfy the preset condition
12. The processing device of an application according to claim 9, wherein said sampling period includes [t ₁ , t ₂ ... t _m ], and said sample use probability includes [P ₁ , P ₂ ... P _m ]; The training module includes:

    The input submodule is configured to input the sampling period and the corresponding sample usage probability into the first formula, where the first preset formula is:

    

    Where Ai represents the sample application i, t represents the sampling period, k represents the number of sub-Gaussian models, μk represents the mathematical expectation, σk represents the variance, ωk represents the weight, and N(t|μk, σk) represents the random variable t obeys a mathematics It is expected that the normal distribution is μk and the variance is σk, and P(t|Ai) represents the probability that the running state of the sample application i is the sampling period of the foreground running time is t;

    a training sub-module, configured to train the first preset formula based on the input sampling period and the sample usage probability to obtain a plurality of trained sub-Gauss models;

    The superposition sub-module is used to superimpose a plurality of trained sub-Gaussian models to obtain a mixed Gaussian model after training.
13. The processing device of the application according to claim 12, wherein each application corresponds to a uniquely trained mixed Gaussian model; and the processing module comprises:

    Obtaining a submodule for obtaining an application processing instruction;

    a second determining submodule, configured to determine, according to the application processing instruction, a background application in the electronic device;

    The calculation sub-module is configured to calculate a usage probability of each background application at a target time by using a second preset formula based on the mixed Gaussian model corresponding to each application, and the second preset formula is:

    

    Where T is the time, N is the number of mixed Gaussian models after training, P(Ai|T) is the probability that the application running in the foreground is the application i when the sampling period is T, and P(T|Ai) is the sample application. The running state of the program i is the probability that the sampling period is T when the foreground is running, and P(T|Aj) indicates the probability that the running state of the application j is the sampling period of the foreground running time is T;

    An application processing submodule is configured to process the background application according to the usage probability.
14. The processing device of the application of claim 13, wherein the application processing sub-module comprises:

    a second determining unit, configured to determine, from the current background application, a target background application whose usage probability is less than a preset threshold;

    A close unit that closes the target background application.
15. A storage medium, wherein the storage medium stores a plurality of instructions adapted to be loaded by a processor to perform the following steps:

    Obtaining usage information of the sample application at each sampling time point in the historical time period;

    Generating a training sample according to the sampling time point and the usage information;

    Training a preset mixed Gaussian model according to the training sample;

    The background application in the electronic device is processed based on the trained mixed Gaussian model.
16. An electronic device, comprising a processor and a memory, the processor being electrically connected to the memory, the memory for storing instructions and data; the processor for performing the following steps:

    Obtaining usage information of the sample application at each sampling time point in the historical time period;

    Generating a training sample according to the sampling time point and the usage information;

    Training a preset mixed Gaussian model according to the training sample;

    The background application in the electronic device is processed based on the trained mixed Gaussian model.
17. The electronic device of claim 16, wherein the historical time period comprises a plurality of time periods, each time period being divided into a plurality of sampling periods;

    The processor is configured to perform the following steps when generating the training samples according to the sampling time point and the usage information:

    Determining a time period and a sampling period corresponding to each sampling time point, wherein the sampling time point corresponds to the sampling period one-to-one in each time period;

    The usage information corresponding to the same sampling period in different time periods is processed to obtain a sample usage probability corresponding to the sample application in each sampling period;

    The training samples are generated based on the sampling period and the corresponding sample usage probability.
18. The electronic device according to claim 17, wherein the processor is configured to perform the following steps when the usage information corresponding to the same sampling period in different time periods is processed to obtain a sample usage probability corresponding to the sample application in each sampling period. :

    Determining whether the usage information meets a preset condition;

    Determining, by each sample, the number of sampling time points in which the corresponding usage information in the same sampling period satisfies a preset condition;

    Obtaining a total number of sampling time points for which each sample application uses information in a plurality of time periods to satisfy a preset condition;

    A sample usage probability corresponding to each sample application period is calculated according to the number of sampling time points and the total number of sampling time points.
19. The processing method of the application program according to claim 18, wherein the usage information is operation state information of the sample application; and when determining whether the usage information satisfies a preset condition, the processor is configured to perform the following steps:

    Determining whether the running state is running in the foreground;

    If yes, determining that the usage information meets a preset condition;

    If not, it is determined that the usage information does not satisfy the preset condition.
20. The electronic device of claim 17, wherein the sampling period comprises [t ₁ , t ₂ ... t _m ], and the sample usage probability comprises [P ₁ , P ₂ ... P _m ];

    When training the preset mixed Gaussian model according to the training sample, the processor is configured to perform the following steps:

    Inputting the sampling period and the corresponding sample usage probability into the first formula, where the first preset formula is:

    

    Where Ai represents the sample application i, t represents the sampling period, k represents the number of sub-Gaussian models, μk represents the mathematical expectation, σk represents the variance, ωk represents the weight, and N(t|μk, σk) represents the random variable t obeys a mathematics It is expected that the normal distribution is μk and the variance is σk, and P(t|Ai) represents the probability that the running state of the sample application i is the sampling period of the foreground running time is t;

    And training the first preset formula to obtain a plurality of trained sub-Gaussian models based on the input sampling period and the sample usage probability;

    A plurality of trained sub-Gaussian models are superimposed to obtain a mixed Gaussian model after training.

Images