WO2019085749A1 - Application program control method and apparatus, medium, and electronic device - Google Patents

Abstract

The present application provides an application program control method and apparatus, a medium, and an electronic device. The method comprises: obtaining history feature information x i ; generating a training model by using a back propagation (BP) neural network algorithm; and when it is detected that an application program enters the background, bringing current feature information s of the application program into the training model; and then determining whether the application program needs to be closed, and intelligently closing the application program.

Description

Application management method, device, medium and electronic device

This application claims the priority of the Chinese patent application filed on October 31, 2017, the Chinese Patent Office, the application number is 201711044959.5, and the application name is "application control method, device, medium and electronic device", the entire contents of which are incorporated by reference. In this application.

Technical field

The present application relates to the field of electronic device terminals, and in particular, to an application management method, device, medium, and electronic device.

Background technique

End users use a large number of applications every day. Usually, after an application is pushed to the background, if it is not cleaned up in time, it will take up valuable system memory resources and affect system power consumption. Therefore, it is necessary to provide an application management method, device, medium and electronic device.

technical problem

The embodiment of the present application provides an application management method, device, medium, and electronic device to intelligently close an application.

Technical solution

An embodiment of the present application provides an application management and control method, which is applied to an electronic device, where the application management method includes the following steps:

Obtaining the application sample vector set, wherein the sample vector in the sample vector set includes historical feature information x _{i of the} plurality of dimensions of the application;

The Back Propagation (BP) neural network algorithm is used to calculate the sample vector set to generate a training model.

When the application enters the background, the current feature information s of the application is input into the training model for calculation;

Determine if the application needs to be closed.

The embodiment of the present application further provides an application management method device, where the device includes:

An obtaining module, configured to obtain the application sample vector set, where the sample vector in the sample vector set includes historical feature information x _{i of} multiple dimensions of the application;

a generating module for calculating a sample vector set by using a BP neural network algorithm to generate a training model;

a calculation module, configured to input the current feature information s of the application into the training model for calculation when the application enters the background;

The determining module is configured to determine whether the application needs to be closed.

The embodiment of the present application further provides a medium in which a plurality of instructions are stored, the instructions being adapted to be loaded by a processor to execute the application management method described above.

The embodiment of the present application further provides an electronic device, where the electronic device includes a processor and a memory, the electronic device is electrically connected to the memory, the memory is used to store instructions and data, and the processor is configured to execute the following step:

Obtaining the application sample vector set, wherein the sample vector in the sample vector set includes historical feature information x _{i of the} plurality of dimensions of the application;

The BP neural network algorithm is used to calculate the sample vector set to generate a training model.

When the application enters the background, the current feature information s of the application is input into the training model for calculation;

Determine if the application needs to be closed.

Beneficial effect

The embodiment of the present application provides an application management method, device, medium, and electronic device to intelligently close an application.

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 system of an application management device according to an embodiment of the present application.

FIG. 2 is a schematic diagram of an application scenario of an application management and control device according to an embodiment of the present disclosure.

FIG. 3 is a schematic flowchart of an application management and control method according to an embodiment of the present application.

FIG. 4 is another schematic flowchart of an application management and control method according to an embodiment of the present application.

FIG. 5 is a schematic structural diagram of an apparatus according to an embodiment of the present application.

FIG. 6 is another schematic structural diagram of an apparatus according to an embodiment of the present application.

FIG. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure.

FIG. 8 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 invention will be clearly and completely described in the following with reference to the accompanying drawings. It is apparent that the described embodiments are only a part of the embodiments of the invention, and not all of the embodiments. All other embodiments obtained by a person skilled in the art based on the embodiments of the present invention without creative efforts are within the scope of the present invention.

An application management method is applied to an electronic device, wherein the application management method comprises the following steps:

Obtaining the application sample vector set, wherein the sample vector in the sample vector set includes historical feature information x _{i of the} plurality of dimensions of the application;

The Back Propagation (BP) neural network algorithm is used to calculate the sample vector set to generate a training model.

When the application enters the background, the current feature information s of the application is input into the training model for calculation;

Determine if the application needs to be closed.

In the application management method, the BP neural network algorithm is used to calculate the sample vector set, and the steps of generating the training model include:

Define the network structure;

The sample vector set is brought into the network structure for calculation to obtain a training model.

In the application management method, in the step of defining a network structure, the method includes:

Setting an input layer, the input layer includes N nodes, and the number of nodes of the input layer is the same as the dimension of the historical feature information x _i ;

Setting a hidden layer, the hidden layer including M nodes;

Setting a classification layer, the classification layer adopts a Softmax function, and the Softmax function is

Where p is the predicted probability value, Z _K is the intermediate value, and C is the number of categories of the predicted result.

Is the jth intermediate value;

Setting an output layer, the output layer comprising 2 nodes;

Setting an activation function, the activation function adopting a sigmoid function, and the sigmoid function is

Wherein the range of f(x) is 0 to 1;

Set the batch size, the batch size is A;

The learning rate is set, and the learning rate is B.

In the application management method, the hidden layer includes a first implicit layer, a second implicit layer, and a third implicit layer, the first implicit layer, and the second implicit layer The number of nodes in each of the layer and the third implicit layer is less than 10.

In the application management method, the dimension of the historical feature information x _i is less than 10, and the number of nodes of the input layer is less than 10.

In the application management method, the step of bringing a sample vector set into a network structure for calculation, and obtaining the training model includes:

Inputting the sample vector set at the input layer to perform calculation, and obtaining an output value of the input layer;

Inputting an output value of the input layer at the hidden layer to obtain an output value of the hidden layer;

Inputting, at the classification layer, an output value of the hidden layer to calculate, to obtain the predicted probability value [p ₁ p ₂ ] ^T ;

The predicted probability value is brought into the output layer for calculation to obtain a predicted result value y. When p _{1 is} greater than p ₂ , y=[1 0] ^T , when p _{1 is} less than or equal to p ₂ , y=[0 1] ^T ; and

The network structure is modified according to the predicted result value y to obtain a training model.

In the application management method, in the step of inputting the current feature information s of the application into the training model for calculation, the current feature information s is input into the training model to calculate a predicted probability value of the classification layer. [p ₁ ' p ₂ '] ^T , when p ₁ ' is greater than p ₂ ', y = [1 0] ^T , when p ₁ ' is less than or equal to p ₂ ', y = [0 1] ^T .

In the application management method, in the step of determining whether the application needs to be closed, the method includes:

When y=[1 0] ^T , it is determined that the application needs to be closed;

When y = [0 1] ^T , it is determined that the application needs to be retained.

among them,

In the application management method, when the application enters the background, the current feature information s of the application is input into the training model for calculation, including:

Collecting current feature information s of the application;

The current feature information s is brought into the training model for calculation.

An application management device, wherein the device comprises:

An obtaining module, configured to obtain the application sample vector set, where the sample vector in the sample vector set includes historical feature information x _{i of} multiple dimensions of the application;

a generating module for calculating a sample vector set by using a BP neural network algorithm to generate a training model;

a calculation module, configured to input the current feature information s of the application into the training model for calculation when the application enters the background;

The determining module is configured to determine whether the application needs to be closed.

A medium in which a plurality of instructions are stored, the instructions being adapted to be loaded by a processor to perform an application management method as previously described.

An electronic device, comprising: a processor and a memory, the electronic device being electrically connected to the memory, the memory for storing instructions and data, the processor for performing:

Obtaining the application sample vector set, wherein the sample vector in the sample vector set includes historical feature information x _{i of the} plurality of dimensions of the application;

The Back Propagation (BP) neural network algorithm is used to calculate the sample vector set to generate a training model.

When the application enters the background, the current feature information s of the application is input into the training model for calculation;

Determine if the application needs to be closed.

In the electronic device, the BP neural network algorithm is used to calculate the sample vector set, and the steps of generating the training model include:

Define the network structure;

The sample vector set is brought into the network structure for calculation to obtain a training model.

In the electronic device, in the step of defining a network structure, the method includes:

Setting an input layer, the input layer includes N nodes, and the number of nodes of the input layer is the same as the dimension of the historical feature information x _i ;

Setting a hidden layer, the hidden layer including M nodes;

Setting a classification layer, the classification layer adopts a Softmax function, and the Softmax function is

Where p is the predicted probability value, Z _K is the intermediate value, and C is the number of categories of the predicted result.

Is the jth intermediate value;

Setting an output layer, the output layer comprising 2 nodes;

Setting an activation function, the activation function adopting a sigmoid function, and the sigmoid function is

Wherein the range of f(x) is 0 to 1;

Set the batch size, the batch size is A;

The learning rate is set, and the learning rate is B.

In the electronic device, the hidden layer includes a first implicit layer, a second implicit layer, and a third hidden layer, the first implicit layer, the second hidden layer, and The number of nodes in each layer in the third implicit layer is less than 10.

In the electronic device, the dimension of the historical feature information x _i is less than 10, and the number of nodes of the input layer is less than 10.

In the electronic device, the step of bringing the sample vector set into the network structure for calculation, and obtaining the training model includes:

Inputting the sample vector set at the input layer to perform calculation, and obtaining an output value of the input layer;

Inputting an output value of the input layer at the hidden layer to obtain an output value of the hidden layer;

Inputting, at the classification layer, an output value of the hidden layer to calculate, to obtain the predicted probability value [p ₁ p ₂ ] ^T ;

The predicted probability value is brought into the output layer for calculation to obtain a predicted result value y. When p _{1 is} greater than p ₂ , y=[1 0] ^T , when p _{1 is} less than or equal to p ₂ , y=[0 1] ^T ; and

The network structure is modified according to the predicted result value y to obtain a training model.

In the electronic device, in the step of inputting the current feature information s of the application into the training model for calculation, the current feature information s is input into the training model to calculate a predicted probability value of the classification layer [p ₁ ' p ₂ '] ^T , when p ₁ ' is greater than p ₂ ', y = [1 0] ^T , when p ₁ ' is less than or equal to p ₂ ', y = [0 1] ^T .

In the electronic device, in the step of determining whether the application needs to be closed, the method includes:

When y=[1 0] ^T , it is determined that the application needs to be closed;

When y = [0 1] ^T , it is determined that the application needs to be retained.

The application management method provided by the present application is mainly applied to electronic devices such as a wristband, a smart phone, a tablet based on an Apple system or an Android system, or a smart mobile electronic device such as a Windows or Linux based notebook computer. It should be noted that the application may be a chat application, a video application, a music application, a shopping application, a shared bicycle application, or a mobile banking application.

Please refer to FIG. 1. FIG. 1 is a schematic diagram of a system for controlling an application program according to an embodiment of the present application. The application management device is mainly configured to: obtain historical feature information x _{i of the} application from a database, and then calculate the historical feature information x _i by an algorithm to obtain a training model, and secondly, the current feature information of the application The training model is input for calculation, and the calculation result is used to judge whether the application can be closed to control the preset application, such as closing, or freezing.

Specifically, please refer to FIG. 2 , which is a schematic diagram of an application scenario of an application management and control method according to an embodiment of the present application. In an embodiment, the historical feature information x _{i of the} application is obtained from the database, and then the historical feature information x _i is calculated by an algorithm to obtain a training model, and secondly, when the application control device detects that the application enters When the electronic device is in the background, the current feature information s of the application is input into the training model for calculation, and the calculation result determines whether the application can be closed. For example, the historical feature information x _{i of the} application a is obtained from the database, and then the historical feature information x _i is calculated by an algorithm to obtain a training model, and secondly, when the application control device detects that the application a enters the electronic device In the background, the current feature information s of the application is input into the training model for calculation, and the calculation result determines that the application a can be closed, and the application a is closed, when the application control device detects that the application b enters the background of the electronic device. At this time, the current feature information s of the application b is input into the training model for calculation, and it is judged by the calculation result that the application b needs to be retained, and the application b is retained.

The embodiment of the present application provides an application management method, and the execution entity of the application management method may be an application management device provided by an embodiment of the present invention, or an electronic device of the application management device, where the application The control device can be implemented in hardware or software.

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

Step S101: Acquire the application sample vector set, wherein the sample vector in the sample vector set includes historical feature information x _{i of the} plurality of dimensions of the application.

Wherein, the application sample vector set is obtained from a sample database, wherein the sample vector in the sample vector set includes historical feature information x _{i of the} plurality of dimensions of the application.

The feature information of the multiple dimensions may refer to Table 1.

Table 1

It should be noted that the feature information of the ten dimensions shown in Table 1 above is only one of the embodiments in the present application, but the application is not limited to the feature information of the ten dimensions shown in Table 1, and may also be One of them, or at least two of them, or all of them, may also include feature information of other dimensions, for example, whether it is currently charging, current power, or whether WiFi is currently connected.

In one embodiment, historical features of six dimensions can be selected:

A, the time the application resides in the background;

B, whether the screen is bright, for example, the screen is bright, recorded as 1, the screen is off, recorded as 0;

C. Statistics of the total number of uses in the week;

D. Total usage time statistics for the week;

E, whether WiFi is turned on, for example, WiFi is turned on, recorded as 1, WiFi is turned off, and recorded as 0;

F. Is it currently charging? For example, it is currently charging, recorded as 1, currently not charging, and recorded as 0.

In step S102, the BP neural network algorithm is used to calculate the sample vector set to generate a training model.

Please refer to FIG. 4. FIG. 4 is a schematic flowchart diagram of an application management and control method according to an embodiment of the present application. In an embodiment, the step S102 may include:

Step S1021: defining a network structure;

Step S1022: Bring the sample vector set into the network structure for calculation, and obtain a training model.

In step S1021, the defining the network structure includes:

Step S1021a, setting an input layer, the input layer includes N nodes, and the number of nodes of the input layer is the same as the dimension of the historical feature information x _i .

The dimension of the historical feature information x _i is less than 10, and the number of nodes of the input layer is less than 10 to simplify the operation process.

In one embodiment, the historical feature information x _{i has} a dimension of 6 dimensions, and the input layer includes 6 nodes.

Step S1021b, setting a hidden layer, the hidden layer including M nodes.

Wherein, the hidden layer may include a plurality of implicit layers. The number of nodes in each of the implicit layers is less than 10 to simplify the operation process.

In an embodiment, the hidden layer may include a first implicit layer, a second hidden layer, and a third hidden layer. The first implicit layering includes 10 nodes, the second implicit layering includes 5 nodes, and the third implicit layering includes 5 nodes.

Step S1021c, setting a classification layer, the classification layer adopts a softmax function, and the softmax function is

Where p is the predicted probability value, Z _K is the intermediate value, and C is the number of categories of the predicted result.

Is the jth intermediate value.

In step S1021d, an output layer is set, and the output layer includes two nodes.

Step S1021e, setting an activation function, the activation function adopting a sigmoid function, and the sigmoid function is

Wherein the range of f(x) is 0 to 1.

In step S1021f, the batch size is set, and the batch size is A.

The batch size can be flexibly adjusted according to actual conditions. The batch size can be 50-200.

In one embodiment, the batch size is 128.

In step S1021g, a learning rate is set, and the learning rate is B.

The learning rate can be flexibly adjusted according to actual conditions. The learning rate can be from 0.1 to 1.5.

In one embodiment, the learning rate is 0.9.

It should be noted that the order of the steps S1021a, S1021b, S1021c, S1021d, S1021e, S1021f, and S1021g can be flexibly adjusted.

In step S1022, the step of bringing the sample vector set into the network structure for calculation, the step of obtaining the training model may include:

In step S1022a, the sample vector set is input at the input layer for calculation, and an output value of the input layer is obtained.

Step S1022b: inputting an output value of the input layer in the hidden layer to obtain an output value of the hidden layer.

Wherein, the output value of the input layer is an input value of the hidden layer.

In an embodiment, the hidden layer may include a plurality of hidden layers. The output of the input layer is the input value of the first implicit layer. The output value of the first implicit layer is an input value of the second implicit layer. The output value of the second implicit layer is an input value of the third implicit layer, and so on.

Step S1022c: inputting an output value of the hidden layer in the classification layer to perform calculation to obtain the predicted probability value [p ₁ p ₂ ] ^T .

The output value of the hidden layer is an input value of the classification layer.

In an embodiment, the hidden layer may include a plurality of hidden layers. The output value of the last implicit layer is the input value of the classification layer.

Step S1022d: Bring the predicted probability value into the output layer for calculation to obtain a predicted result value y. When p _{1 is} greater than p ₂ , y=[1 0] ^T , when p _{1 is} less than or equal to p ₂ , y=[ 0 1] ^T .

The output value of the classification layer is an input value of the output layer.

In step S1022e, the network structure is modified according to the prediction result value y to obtain a training model.

Step S103, when the application enters the background, the current feature information s of the application is input into the training model for calculation.

Referring to FIG. 4, in an embodiment, the step S103 may include:

Step S1031: Collect current feature information s of the application.

The dimension of the current feature information s of the collected application is the same as the dimension of the collected historical feature information x _i of the application.

Step S1032: Bring the current feature information s into the training model for calculation.

Wherein, the current feature information s is input into the training model to calculate a predicted probability value [p ₁ ' p ₂ '] ^{T of the} classification layer, and when p ₁ ' is greater than p ₂ ', y=[1 0] ^T , when When p ₁ ' is less than or equal to p ₂ ', y=[0 1] ^T .

In step S104, it is determined whether the application needs to be closed.

It should be noted that when y=[1 0] ^T , it is determined that the application needs to be closed; when y=[0 1] ^T , it is determined that the application needs to be retained.

The application management method provided by the present application generates the training model by using the BP neural network algorithm by acquiring the historical feature information x _i , and brings the current feature information s of the application into the training model when the detection application enters the background, and further Determine if the application needs to be closed and intelligently close the application.

Referring to FIG. 5, FIG. 5 is a schematic structural diagram of an application program management apparatus according to an embodiment of the present application. The device 30 includes an acquisition module 31, a generation module 32, a calculation module 33, and a determination module 34.

It should be noted that the application may be a chat application, a video application, a music application, a shopping application, a shared bicycle application, or a mobile banking application.

The obtaining module 31 is configured to obtain the application sample vector set, wherein the sample vector in the sample vector set includes historical feature information x _{i of the} plurality of dimensions of the application.

Wherein, the application sample vector set is obtained from a sample database, wherein the sample vector in the sample vector set includes historical feature information x _{i of the} plurality of dimensions of the application.

Please refer to FIG. 6. FIG. 6 is a schematic structural diagram of an application program management apparatus according to an embodiment of the present application. The device 30 further includes a detection module 35 for detecting that the application enters the background.

The device 30 can also include a storage module 36. The storage module 36 is configured to store historical feature information x _{i of the application} .

The feature information of the multiple dimensions may refer to Table 2.

Table 2

It should be noted that the feature information of the ten dimensions shown in Table 2 above is only one of the embodiments in the present application, but the application is not limited to the feature information of the ten dimensions shown in Table 1, and may also be One of them, or at least two of them, or all of them, may also include feature information of other dimensions, for example, whether it is currently charging, current power, or whether WiFi is currently connected.

In one embodiment, historical features of six dimensions can be selected:

A, the time the application resides in the background;

B, whether the screen is bright, for example, the screen is bright, recorded as 1, the screen is off, recorded as 0;

C. Statistics of the total number of uses in the week;

D. Total usage time statistics for the week;

E, whether WiFi is turned on, for example, WiFi is turned on, recorded as 1, WiFi is turned off, and recorded as 0;

F. Is it currently charging? For example, it is currently charging, recorded as 1, currently not charging, and recorded as 0.

The generating module 32 is configured to calculate a sample vector set by using a BP neural network algorithm to generate a training model.

The generating module 32 trains the historical feature information x _i acquired by the obtaining module 31, and inputs the historical feature information x _i in the BP neural network algorithm.

Referring to FIG. 6, the generating module 32 includes a defining module 321 and a solving module 322.

The definition module 321 is used to define a network structure.

The definition module 321 may include an input layer definition module 3211, an implicit layer definition module 3212, a classification layer definition module 3213, an output layer definition module 3214, an activation function definition module 3215, a batch size definition module 3216, and a learning rate definition module 3217.

The input layer definition module 3211 is configured to set an input layer, where the input layer includes N nodes, and the number of nodes of the input layer is the same as the dimension of the historical feature information x _i .

The dimension of the historical feature information x _i is less than 10, and the number of nodes of the input layer is less than 10 to simplify the operation process.

In one embodiment, the historical feature information x _{i has} a dimension of 6 dimensions, and the input layer includes 6 nodes.

The hidden layer definition module 3212 is configured to set an implicit layer, and the hidden layer includes M nodes.

Wherein, the hidden layer may include a plurality of implicit layers. The number of nodes in each of the implicit layers is less than 10 to simplify the operation process.

In an embodiment, the hidden layer may include a first implicit layer, a second hidden layer, and a third hidden layer. The first implicit layering includes 10 nodes, the second implicit layering includes 5 nodes, and the third implicit layering includes 5 nodes.

The classification layer definition module 3213 is configured to set a classification layer, the classification layer adopts a softmax function, and the softmax function is

Where p is the predicted probability value, Z _K is the intermediate value, and C is the number of categories of the predicted result.

Is the jth intermediate value.

The output layer definition module 3214 is configured to set an output layer, and the output layer includes 2 nodes.

The activation function definition module 3215 is configured to set an activation function, the activation function adopts a sigmoid function, and the sigmoid function is

Wherein the range of f(x) is 0 to 1.

The batch size definition module 3216 is configured to set a batch size, and the batch size is A.

The batch size can be flexibly adjusted according to actual conditions. The batch size can be 50-200.

In one embodiment, the batch size is 128.

The learning rate definition module 3217 is configured to set a learning rate, and the learning rate is B.

The learning rate can be flexibly adjusted according to actual conditions. The learning rate can be from 0.1 to 1.5.

In one embodiment, the learning rate is 0.9.

It should be noted that the input layer definition module 3211 sets the input layer, the hidden layer definition module 3212 sets the hidden layer, the classification layer definition module 3213 sets the classification layer, and the output layer definition module 3214 The setting output layer, the activation function definition module 3215 sets the activation function, the batch size definition module 3216 sets the batch size, and the learning order definition module 3217 sets the learning order in a sequence that can be flexibly adjusted.

The solving module 322 is configured to bring the sample vector set into the network structure for calculation to obtain a training model.

The solution module 322 can include a first solution module 3221, a second solution module 3222, a third solution module 3223, a fourth solution module 3224, and a correction module.

The first solving module 3221 is configured to input the sample vector set at the input layer for calculation to obtain an output value of the input layer.

The second solving module 3222 is configured to input an output value of the input layer at the hidden layer to obtain an output value of the hidden layer.

Wherein, the output value of the input layer is an input value of the hidden layer.

In an embodiment, the hidden layer may include a plurality of hidden layers. The output of the input layer is the input value of the first implicit layer. The output value of the first implicit layer is an input value of the second implicit layer. The output value of the second implicit layer is an input value of the third implicit layer, and so on.

The third solving module 3223 is configured to input an output value of the hidden layer in the classification layer to calculate, to obtain the predicted probability value [p ₁ p ₂ ] ^T .

The output value of the hidden layer is an input value of the classification layer.

The fourth solving module 3224 is configured to bring the predicted probability value into the output layer for calculation to obtain a predicted result value y. When p _{1 is} greater than p ₂ , y=[1 0] ^T , when p _{1 is} less than or equal to p ₂ , y = [0 1] ^T .

The output value of the classification layer is an input value of the output layer.

The modification module 3225 is configured to modify the network structure according to the prediction result value y to obtain a training model.

The calculating module 33 is configured to input the current feature information s of the application into the training model for calculation when the application enters the background.

Referring to FIG. 6 , in an embodiment, the calculation module 33 may include an acquisition module 331 and an operation module 332 .

The collecting module 331 is configured to collect current feature information s of the application.

The dimension of the current feature information s of the collected application is the same as the dimension of the collected historical feature information x _i of the application.

The operation module 332 is configured to bring the current feature information s into the training model for calculation.

Wherein, the current feature information s is input into the training model to calculate a predicted probability value [p ₁ ' p ₂ '] ^{T of the} classification layer, and when p ₁ ' is greater than p ₂ ', y=[1 0] ^T , when When p ₁ ' is less than or equal to p ₂ ', y=[0 1] ^T .

In an embodiment, the collecting module 331 is configured to collect the current feature information s according to a predetermined acquisition time, and store the current feature information s in the storage module 36. The collecting module 331 is further configured to collect and detect the application. The current feature information s corresponding to the time point entering the background is used, and the current feature information s is input into the operation module 332 for being brought into the training model for calculation.

The determining module 34 is configured to determine whether the application needs to be closed.

It should be noted that when y=[1 0] ^T , it is determined that the application needs to be closed; when y=[0 1] ^T , it is determined that the application needs to be retained.

The apparatus 30 can also include a shutdown module 37 for shutting down the application when it is determined that the application needs to be closed.

The apparatus for application management and control provided by the application obtains the historical feature information x _i , generates a training model by using a BP neural network algorithm, and brings the current feature information s of the application into the background when the detection application enters the background. Train the model to determine if the application needs to be closed and intelligently close the application.

Please refer to FIG. 7. FIG. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application. The electronic device 500 includes a processor 501 and a memory 502. The processor 501 is electrically connected to the memory 502.

The processor 501 is a control center of the electronic device 500, and connects various parts of the entire electronic device 500 by various interfaces and lines, by running or loading an application stored in the memory 502, and calling data stored in the memory 502, executing The various functions of the electronic device and the processing of the data enable overall monitoring of the electronic device 500.

In this embodiment, the processor 501 in the electronic device 500 loads the instructions corresponding to the process of one or more applications into the memory 502 according to the following steps, and is stored and stored in the memory 502 by the processor 501. In the application, thus implementing various functions:

Obtaining the application sample vector set, wherein the sample vector in the sample vector set includes historical feature information x _{i of the} plurality of dimensions of the application;

The neural network algorithm is used to calculate the sample vector set to generate a training model;

When the application enters the background, the current feature information s of the application is input into the training model for calculation;

Determine if the application needs to be closed.

It should be noted that the application may be a chat application, a video application, a music application, a shopping application, a shared bicycle application, or a mobile banking application.

Wherein, the application sample vector set is obtained from a sample database, wherein the sample vector in the sample vector set includes historical feature information x _{i of the} plurality of dimensions of the application.

The feature information of the multiple dimensions may refer to Table 3.

table 3

It should be noted that the feature information of the ten dimensions shown in Table 3 above is only one of the embodiments in the present application, but the application is not limited to the feature information of the ten dimensions shown in Table 1, and may also be One of them, or at least two of them, or all of them, may also include feature information of other dimensions, for example, whether it is currently charging, current power, or whether WiFi is currently connected.

In one embodiment, historical features of six dimensions can be selected:

A, the time the application resides in the background;

B, whether the screen is bright, for example, the screen is bright, recorded as 1, the screen is off, recorded as 0;

C. Statistics of the total number of uses in the week;

D. Total usage time statistics for the week;

E, whether WiFi is turned on, for example, WiFi is turned on, recorded as 1, WiFi is turned off, and recorded as 0;

F. Is it currently charging? For example, it is currently charging, recorded as 1, currently not charging, and recorded as 0.

In an embodiment, the processor 501 calculates a sample vector set by using a BP neural network algorithm, and the generating the training model further includes:

Define the network structure;

The sample vector set is brought into the network structure for calculation to obtain a training model.

Wherein, the defined network structure includes:

Setting an input layer, the input layer includes N nodes, and the number of nodes of the input layer is the same as the dimension of the historical feature information x _i ;

The dimension of the historical feature information x _i is less than 10, and the number of nodes of the input layer is less than 10 to simplify the operation process.

In one embodiment, the historical feature information x _{i has} a dimension of 6 dimensions, and the input layer includes 6 nodes.

A hidden layer is set, the hidden layer including M nodes.

Wherein, the hidden layer may include a plurality of implicit layers. The number of nodes in each of the implicit layers is less than 10 to simplify the operation process.

In an embodiment, the hidden layer may include a first implicit layer, a second hidden layer, and a third hidden layer. The first implicit layering includes 10 nodes, the second implicit layering includes 5 nodes, and the third implicit layering includes 5 nodes.

Setting a classification layer, the classification layer adopts a softmax function, and the softmax function is

Where p is the predicted probability value, Z _K is the intermediate value, and C is the number of categories of the predicted result.

Is the jth intermediate value.

An output layer is set, the output layer comprising 2 nodes.

Setting an activation function, the activation function adopting a sigmoid function, and the sigmoid function is

Wherein the range of f(x) is 0 to 1.

Set the batch size, which is A.

The batch size can be flexibly adjusted according to actual conditions. The batch size can be 50-200.

In one embodiment, the batch size is 128.

The learning rate is set, and the learning rate is B.

The learning rate can be flexibly adjusted according to actual conditions. The learning rate can be from 0.1 to 1.5.

In one embodiment, the learning rate is 0.9.

It should be noted that the order of setting the input layer, setting the hidden layer, setting the classification layer, setting the output layer, setting the activation function, setting the batch size, and setting the learning rate can be flexibly adjusted.

The step of bringing the sample vector set into the network structure for calculation, and obtaining the training model may include:

The sample vector set is input at the input layer for calculation to obtain an output value of the input layer.

An output value of the input layer is input to the hidden layer to obtain an output value of the hidden layer.

Wherein, the output value of the input layer is an input value of the hidden layer.

In an embodiment, the hidden layer may include a plurality of hidden layers. The output of the input layer is the input value of the first implicit layer. The output value of the first implicit layer is an input value of the second implicit layer. The output value of the second implicit layer is an input value of the third implicit layer, and so on.

The output value of the hidden layer is input at the classification layer to calculate, and the predicted probability value [p ₁ p ₂ ] ^{T is obtained} .

The output value of the hidden layer is an input value of the classification layer.

In an embodiment, the hidden layer may include a plurality of hidden layers. The output value of the last implicit layer is the input value of the classification layer.

The predicted probability value is brought into the output layer for calculation to obtain a predicted result value y. When p _{1 is} greater than p ₂ , y=[1 0] ^T , when p _{1 is} less than or equal to p ₂ , y=[0 1] ^T.

The output value of the classification layer is an input value of the output layer.

The network structure is modified according to the predicted result value y to obtain a training model.

When the application enters the background, the step of inputting the current feature information s of the application into the training model for calculation includes:

The current feature information s of the application is collected.

The dimension of the current feature information s of the collected application is the same as the dimension of the collected historical feature information x _i of the application.

The current feature information s is brought into the training model for calculation.

Wherein, the current feature information s is input into the training model to calculate a predicted probability value [p ₁ ' p ₂ '] ^{T of the} classification layer, and when p ₁ ' is greater than p ₂ ', y=[1 0] ^T , when When p ₁ ' is less than or equal to p ₂ ', y=[0 1] ^T .

In the step of determining whether the application needs to be closed, when y=[1 0] ^T , it is determined that the application needs to be closed; when y=[0 1] ^T , it is determined that the application needs to be retained.

Memory 502 can be used to store applications and data. The program stored in the memory 502 contains instructions executable in the processor. The program can constitute various functional modules. The processor 501 executes various function applications and data processing by running a program stored in the memory 502.

In some embodiments, as shown in FIG. 8, FIG. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present application. The electronic device 500 further includes a radio frequency circuit 503, a display screen 504, a control circuit 505, an input unit 506, an audio circuit 507, a sensor 508, and a power source 509. The processor 501 is electrically connected to the radio frequency circuit 503, the display screen 504, the control circuit 505, the input unit 506, the audio circuit 507, the sensor 508, and the power source 509, respectively.

The radio frequency circuit 503 is configured to transceive radio frequency signals to communicate with a server or other electronic device over a wireless communication network.

The display screen 504 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 terminal, which can be composed of images, text, icons, video, and any combination thereof.

The control circuit 505 is electrically connected to the display screen 504 for controlling the display screen 504 to display information.

The input unit 506 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 audio circuit 507 can provide an audio interface between the user and the terminal through a speaker and a microphone.

Sensor 508 is used to collect external environmental information. Sensor 508 can include one or more of ambient brightness sensors, acceleration sensors, gyroscopes, and the like.

Power source 509 is used to power various components of electronic device 500. In some embodiments, the power supply 509 can be logically coupled to the processor 501 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. 8, the electronic device 500 may further include a camera, a Bluetooth module, and the like, and details are not described herein again.

The electronic device provided by the present application generates the training model by using the BP neural network algorithm by acquiring the historical feature information x _i , and when the detection application enters the background, the current feature information s of the application is brought into the training model, and then the judgment is performed. Whether the application needs to be closed, intelligently close the application.

The embodiment of the present invention further provides a medium in which a plurality of instructions are stored, the instructions being adapted to be loaded by a processor to execute the application management method described in any of the above embodiments.

The application management method, the device, the medium, and the electronic device provided by the embodiments of the present invention belong to the same concept, and the specific implementation process thereof is described in the full text of the specification, and details are not described herein again.

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 application management method, apparatus, medium, and electronic device provided by the embodiments of the present application are described in detail. The principles and embodiments of the application are described in the specific examples. The description of the above embodiments is only for helping. Understand this application. In the meantime, those skilled in the art will be able to change the specific embodiments and the scope of the application according to the idea of the present application. In the above, the content of the specification should not be construed as limiting the present application.

Claims (19)

1. An application management method is applied to an electronic device, wherein the application management method comprises the following steps:

   Obtaining the application sample vector set, wherein the sample vector in the sample vector set includes historical feature information x _{i of the} plurality of dimensions of the application;

   The Back Propagation (BP) neural network algorithm is used to calculate the sample vector set to generate a training model.

   When the application enters the background, the current feature information s of the application is input into the training model for calculation;

   Determine if the application needs to be closed.
2. The application management method according to claim 1, wherein the BP neural network algorithm is used to calculate the sample vector set, and the step of generating the training model comprises:

   Define the network structure;

   The sample vector set is brought into the network structure for calculation to obtain a training model.
3. The application management method according to claim 2, wherein in the step of defining the network structure, the method comprises:

   Setting an input layer, the input layer includes N nodes, and the number of nodes of the input layer is the same as the dimension of the historical feature information x _i ;

   Setting a hidden layer, the hidden layer including M nodes;

   Setting a classification layer, the classification layer adopts a Softmax function, and the Softmax function is

   

   Where p is the predicted probability value, Z _K is the intermediate value, and C is the number of categories of the predicted result.

   

   Is the jth intermediate value;

   Setting an output layer, the output layer comprising 2 nodes;

   Setting an activation function, the activation function adopting a sigmoid function, and the sigmoid function is

   

   Wherein the range of f(x) is 0 to 1;

   Set the batch size, the batch size is A;

   The learning rate is set, and the learning rate is B.
4. The application management method of claim 3, wherein the hidden layer comprises a first implicit layer, a second implicit layer and a third implicit layer, the first implicit layering, The number of nodes in each of the second implicit layer and the third implicit layer is less than 10.
5. The application management method according to claim 3, wherein the history feature information x _{i has} a dimension less than 10, and the number of nodes of the input layer is less than 10.
6. The application management method according to claim 3, wherein the step of bringing the sample vector set into the network structure for calculation, and obtaining the training model comprises:

   Inputting the sample vector set at the input layer to perform calculation, and obtaining an output value of the input layer;

   Inputting an output value of the input layer at the hidden layer to obtain an output value of the hidden layer;

   Inputting, at the classification layer, an output value of the hidden layer to calculate, to obtain the predicted probability value [p ₁ p ₂ ] ^T ;

   The predicted probability value is brought into the output layer for calculation to obtain a predicted result value y. When p _{1 is} greater than p ₂ , y=[1 0] ^T , when p _{1 is} less than or equal to p ₂ , y=[0 1] ^T ; and

   The network structure is modified according to the predicted result value y to obtain a training model.
7. The application management method according to claim 6, wherein in the step of inputting the current feature information s of the application into the training model for calculation, the current feature information s is input into the training model for calculation and classification. The predicted probability value of the layer [p ₁ ' p ₂ '] ^T , when p ₁ ' is greater than p ₂ ', y = [1 0] ^T , when p ₁ ' is less than or equal to p ₂ ', y = [0 1] ^T.
8. The application management method according to claim 7, wherein in the step of determining whether the application needs to be closed, the method comprises:

   When y=[1 0] ^T , it is determined that the application needs to be closed;

   When y = [0 1] ^T , it is determined that the application needs to be retained.
9. The application management method according to claim 1, wherein, when the application enters the background, the current feature information s of the application is input into the training model for calculation, including:

   Collecting current feature information s of the application;

   The current feature information s is brought into the training model for calculation.
10. An application management device, wherein the device comprises:

    An obtaining module, configured to obtain the application sample vector set, where the sample vector in the sample vector set includes historical feature information x _{i of} multiple dimensions of the application;

    a generating module for calculating a sample vector set by using a BP neural network algorithm to generate a training model;

    a calculation module, configured to input the current feature information s of the application into the training model for calculation when the application enters the background;

    The determining module is configured to determine whether the application needs to be closed.
11. A medium in which a plurality of instructions are stored in the medium, the instructions being adapted to be loaded by a processor to perform the application management method according to any one of claims 1 to 9.
12. An electronic device, comprising: a processor and a memory, the electronic device being electrically connected to the memory, the memory for storing instructions and data, the processor for performing:

    Obtaining the application sample vector set, wherein the sample vector in the sample vector set includes historical feature information x _{i of the} plurality of dimensions of the application;

    The Back Propagation (BP) neural network algorithm is used to calculate the sample vector set to generate a training model.

    When the application enters the background, the current feature information s of the application is input into the training model for calculation;

    Determine if the application needs to be closed.
13. The electronic device of claim 12, wherein the step of calculating the sample vector set using the BP neural network algorithm, the step of generating the training model comprises:

    Define the network structure;

    The sample vector set is brought into the network structure for calculation to obtain a training model.
14. The electronic device of claim 13, wherein in the step of defining a network structure, the method comprises:

    Setting an input layer, the input layer includes N nodes, and the number of nodes of the input layer is the same as the dimension of the historical feature information x _i ;

    Setting a hidden layer, the hidden layer including M nodes;

    Setting a classification layer, the classification layer adopts a Softmax function, and the Softmax function is

    

    Where p is the predicted probability value, Z _K is the intermediate value, and C is the number of categories of the predicted result.

    

    Is the jth intermediate value;

    Setting an output layer, the output layer comprising 2 nodes;

    Setting an activation function, the activation function adopting a sigmoid function, and the sigmoid function is

    

    Wherein the range of f(x) is 0 to 1;

    Set the batch size, the batch size is A;

    The learning rate is set, and the learning rate is B.
15. The electronic device of claim 14, wherein the hidden layer comprises a first implicit layer, a second implicit layer and a third implicit layer, the first implicit layer, the second The number of nodes in each of the implicit layered and third implicit layers is less than 10.
16. The electronic device of claim 14, wherein the historical feature information x _{i has} a dimension less than 10 and the input layer has a node number less than 10.
17. The electronic device of claim 14, wherein the step of bringing the set of sample vectors into the network structure for calculation, the step of obtaining the training model comprises:

    Inputting the sample vector set at the input layer to perform calculation, and obtaining an output value of the input layer;

    Inputting an output value of the input layer at the hidden layer to obtain an output value of the hidden layer;

    Inputting, at the classification layer, an output value of the hidden layer to calculate, to obtain the predicted probability value [p ₁ p ₂ ] ^T ;

    The predicted probability value is brought into the output layer for calculation to obtain a predicted result value y. When p _{1 is} greater than p ₂ , y=[1 0] ^T , when p _{1 is} less than or equal to p ₂ , y=[0 1] ^T ; and

    The network structure is modified according to the predicted result value y to obtain a training model.
18. The electronic device according to claim 17, wherein in the step of inputting the current feature information s of the application into the training model for calculation, the current feature information s is input to the training model for calculation to obtain a classification layer. The predicted probability value [p ₁ ' p ₂ '] ^T , when p ₁ ' is greater than p ₂ ', y = [1 0] ^T , when p ₁ ' is less than or equal to p ₂ ', y = [0 1] ^T .
19. The electronic device of claim 18, wherein in the step of determining whether the application needs to be closed, the method comprises:

    When y=[1 0] ^T , it is determined that the application needs to be closed;

    When y = [0 1] ^T , it is determined that the application needs to be retained.

Images