CN107861770B - Application program management-control method, device, storage medium and terminal device - Google Patents
Application program management-control method, device, storage medium and terminal device Download PDFInfo
- Publication number
- CN107861770B CN107861770B CN201711046994.0A CN201711046994A CN107861770B CN 107861770 B CN107861770 B CN 107861770B CN 201711046994 A CN201711046994 A CN 201711046994A CN 107861770 B CN107861770 B CN 107861770B
- Authority
- CN
- China
- Prior art keywords
- application program
- algorithm
- module
- prediction
- terminal device
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/445—Program loading or initiating
- G06F9/44594—Unloading
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
This application provides a kind of application program management-control method, device, storage medium and terminal devices, by defining speed interval, the application program is obtained in the sample vector in friction speed section, wherein the sample vector includes the history feature information of the multiple dimensions of the application program;Sample vector is calculated using algorithm, generates multiple training patterns, wherein different training patterns correspond to friction speed section;When detecting that application program enters backstage, corresponding training pattern into is brought current characteristic information according to movement speed, prediction is obtained and closes probability;And judging whether the application program needs to close, intelligence closes application program.
Description
Technical field
This application involves field of terminal, and in particular to a kind of application program management-control method, device, storage medium and terminal are set
It is standby.
Background technique
Terminal user will use extensive application daily, after a usual application is pulled to backstage, if unclear in time comprehend
Valuable system memory resource is occupied, and will affect system power dissipation.Therefore, it is necessary to provide a kind of application program control side
Method, device, storage medium and terminal device.
Summary of the invention
The embodiment of the present application provides a kind of application program management-control method, device, storage medium and terminal device, with intelligent pass
Close application program.
The embodiment of the present application provides a kind of application program management-control method, is applied to terminal device, the application program control
Method the following steps are included:
Speed interval is defined, obtains the application program in the sample vector in friction speed section, wherein the sample vector
History feature information including the multiple dimensions of the application program;
Sample vector is calculated using algorithm, generates multiple training patterns, wherein different training patterns are corresponding different
Speed interval;
When detecting that application program enters backstage, corresponding trained mould into is brought current characteristic information according to movement speed
Type obtains prediction and closes probability;And
Judge whether the application program needs to close.
The embodiment of the present application also provides a kind of application program control device, and described device includes:
Module is obtained, speed interval is defined, the application program is obtained in the sample vector in friction speed section, wherein should
Sample vector includes the history feature information of the multiple dimensions of the application program;
Generation module generates multiple training patterns, wherein different training for calculating using algorithm sample vector
Model corresponds to friction speed section;
Computing module, for when detecting that application program enters backstage, according to movement speed by current characteristic information band
Enter corresponding training pattern, obtains prediction and close probability;And
Judgment module, for judging whether the application program needs to close.
The embodiment of the present application also provides a kind of storage medium, and a plurality of instruction, described instruction are stored in the storage medium
Above-mentioned application program management-control method is executed suitable for being loaded by processor.
The embodiment of the present application also provides a kind of terminal device, and the terminal device includes processor and memory, the end
End equipment and the memory are electrically connected, the memory for storing instruction and data, the processor for execute with
Lower step:
Speed interval is defined, obtains the application program in the sample vector in friction speed section, wherein the sample vector
History feature information including the multiple dimensions of the application program;
Sample vector is calculated using algorithm, generates multiple training patterns, wherein different training patterns are corresponding different
Speed interval;
When detecting that application program enters backstage, corresponding trained mould into is brought current characteristic information according to movement speed
Type obtains prediction and closes probability;And
Judge whether the application program needs to close.
Application program management-control method, device, storage medium and terminal device provided herein, by defining speed area
Between, according to friction speed section, history feature information is calculated, generates different training patterns, when detecting application program
When into backstage, corresponding training pattern into is brought current characteristic information according to movement speed, prediction is obtained and closes probability, to sentence
Whether the application program of breaking needs to close, so that intelligence closes application program.
Detailed description of the invention
In order to more clearly explain the technical solutions in the embodiments of the present application, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, the drawings in the following description are only some examples of the present application, for
For those skilled in the art, without creative efforts, it can also be obtained according to these attached drawings other attached
Figure.
Fig. 1 is a kind of system schematic of application program control device provided by the embodiments of the present application.
Fig. 2 is the application scenarios schematic diagram of application program control device provided by the embodiments of the present application.
Fig. 3 is a kind of flow diagram of application program management-control method provided by the embodiments of the present application.
Fig. 4 is another flow diagram of application program management-control method provided by the embodiments of the present application.
Fig. 5 is a kind of structural schematic diagram of device provided by the embodiments of the present application.
Fig. 6 is another structural schematic diagram of device provided by the embodiments of the present application.
Fig. 7 is a kind of structural schematic diagram of electronic equipment provided by the embodiments of the present application.
Fig. 8 is another structural schematic diagram of electronic equipment provided by the embodiments of the present application.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation description.Obviously, described embodiments are only a part of embodiments of the present application, instead of all the embodiments.It is based on
Embodiment in the application, those skilled in the art's every other implementation obtained without creative efforts
Example, shall fall in the protection scope of this application.
In the description of the present application, it is to be understood that term " center ", " longitudinal direction ", " transverse direction ", " length ", " width ",
" thickness ", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outside", " up time
The orientation or positional relationship of the instructions such as needle ", " counterclockwise " is to be based on the orientation or positional relationship shown in the drawings, and is merely for convenience of
It describes the application and simplifies description, rather than the device or element of indication or suggestion meaning must have a particular orientation, with spy
Fixed orientation construction and operation, therefore should not be understood as the limitation to the application.In addition, term " first ", " second " are only used for
Purpose is described, relative importance is not understood to indicate or imply or implicitly indicates the quantity of indicated technical characteristic.
" first " is defined as a result, the feature of " second " can explicitly or implicitly include one or more feature.?
In the description of the present application, the meaning of " plurality " is two or more, unless otherwise specifically defined.
In the description of the present application, it should be noted that unless otherwise clearly defined and limited, term " installation ", " phase
Even ", " connection " shall be understood in a broad sense, for example, it may be being fixedly connected, may be a detachable connection, or be integrally connected;It can
To be mechanical connection, it is also possible to be electrically connected or can mutually communicate;It can be directly connected, it can also be by between intermediary
It connects connected, can be the connection inside two elements or the interaction relationship of two elements.For the ordinary skill of this field
For personnel, the concrete meaning of above-mentioned term in this application can be understood as the case may be.
In this application unless specifically defined or limited otherwise, fisrt feature second feature "upper" or "lower"
It may include that the first and second features directly contact, also may include that the first and second features are not direct contacts but pass through it
Between other characterisation contact.Moreover, fisrt feature includes the first spy above the second feature " above ", " above " and " above "
Sign is right above second feature and oblique upper, or is merely representative of first feature horizontal height higher than second feature.Fisrt feature exists
Second feature " under ", " lower section " and " following " include that fisrt feature is directly below and diagonally below the second feature, or is merely representative of
First feature horizontal height is less than second feature.
Following disclosure provides many different embodiments or example is used to realize the different structure of the application.For letter
Change disclosure herein, hereinafter the component of specific examples and setting are described.Certainly, they are merely examples, and
Purpose does not lie in limitation the application.In addition, the application can in different examples repeat reference numerals and/or reference letter, this
Kind repetition is for purposes of simplicity and clarity, itself not indicate the relationship between discussed various embodiments and/or setting.
In addition, this application provides various specific techniques and material example, but those of ordinary skill in the art will be appreciated that
To the application of other techniques and/or the use of other materials.
Please refer to the schema in attached drawing, wherein identical component symbol represents identical component, the principle of the application be with
Implement to illustrate in a computing environment appropriate.The following description is the specific implementation based on exemplified the application
Example is not construed as limitation the application other specific embodiments not detailed herein.
The application principle illustrates that be not represented as a kind of limitation, those skilled in the art can with above-mentioned text
Solving plurality of step and operation as described below also may be implemented in hardware.The principle of the application uses many other wide usages
Or specific purpose operation, communication environment or configuration are operated.
Application program management-control method provided by the present application, is mainly used in terminal device, such as: bracelet, is based on smart phone
The intelligent mobiles such as the tablet computer of apple system or Android system or laptop based on Windows or linux system are whole
End equipment.
Referring to Fig. 1, Fig. 1 is the system schematic of application program control device provided by the embodiments of the present application.It is described to answer
It is mainly used for program control device: obtains the history feature information of application program from database, then, by defines speed
Section generates different training patterns according to friction speed section, secondly, when detecting that application program enters backstage, according to shifting
Dynamic speed brings current characteristic information into corresponding training pattern, judges whether application program can close by calculated result, with
Default application program is managed, such as closes or freezes.
Specifically, referring to Fig. 2, the application scenarios that Fig. 2 is application program management-control method provided by the embodiments of the present application show
It is intended to.In one embodiment, the history feature information of application program is obtained from database, then, by defining speed area
Between, according to friction speed section, different training patterns are generated, secondly, when detecting that application program enters backstage, according to movement
Speed brings current characteristic information into corresponding training pattern, judges whether application program can close by calculated result.For example,
The history feature information that application program is obtained from database, according to friction speed section, is generated not by defining speed interval
Same training pattern brings current characteristic information into corresponding instruction according to movement speed when detecting that application program a enters backstage
Practice model, judges that application program a can be closed by calculated result, and application program a is closed;When detect application program b into
When entering backstage, corresponding training pattern into is brought current characteristic information according to movement speed, journey is applied by calculated result judgement
Sequence b needs to retain, and application program b is retained.
The embodiment of the present application provides a kind of application program management-control method, and the executing subject of the application program management-control method can
To be application program control device provided in an embodiment of the present invention, or at the electronic equipment of the application program control device,
Wherein the application program control device can be realized by the way of hardware or software.
Referring to Fig. 3, Fig. 3 is the flow diagram of application program management-control method provided by the embodiments of the present application.The application
The application program management-control method that embodiment provides is applied to electronic equipment, and detailed process can be such that
Step S101 defines speed interval, obtains the application program in the sample vector in friction speed section, wherein should
Sample vector includes the history feature information of the multiple dimensions of the application program.
Wherein, the speed interval may include First Speed section, second speed section and third speed section.It is described
First Speed section can be movement speed in the range of 0 to 2km/h namely static section;The second speed section can
Think movement speed in the range of 2km/h to 6km/h namely walking section;The third speed section can be mobile speed
Degree is greater than 6km/h, namely fast moves section.
Wherein, the characteristic information of the multiple dimension can be with reference table 1.
Table 1
It should be noted that the characteristic information of 10 dimensions shown in the above table 1 is only one of the embodiment of the present application,
But the application is not limited to the characteristic information of 10 dimensions shown in table 1, or one of them or wherein at least
Two, perhaps all also or can also include other dimensions characteristic information, for example, current whether in charging, current electricity
Whether amount currently connects WiFi etc..
Step S102 calculates sample vector using algorithm, generates multiple training patterns, wherein different training patterns
Corresponding friction speed section.
Referring to Fig. 4, in one embodiment, the step S102 may include:
Step S1021: selection algorithm;And
Step S1022: corresponding friction speed section generates multiple training patterns.
The algorithm can be algorithm of support vector machine, neural network algorithm, Bayesian statistics algorithm, decision Tree algorithms
Deng.Wherein, friction speed section can choose different algorithms, and corresponding friction speed section generates multiple training patterns.
In one embodiment, the speed interval may include First Speed section, second speed section and third speed
Spend section.Corresponding First Speed section generates the first training pattern, and corresponding second speed section generates the second training pattern, corresponding
Third speed section generates third training pattern.
In one embodiment, First Speed section can be corresponded to using algorithm of support vector machine generates the first training mould
Type corresponds to second speed section using neural network algorithm and generates the second training pattern, using Bayesian statistics algorithm corresponding the
Three speed intervals generate third training pattern.
For example, generating training pattern using linear SVM algorithm.
Firstly, defining hyperplane, the hyperplane can be hyperplane (w, b): wTX+b=0, wherein w is hyperplane
Normal vector, wTFor the transposed vector of w, x is sample vector, and b is hyperplane intercept.
Secondly, obtaining categorised decision function according to hyperplane, the categorised decision function can beWherein, f (x) is that categorised decision value represents the application program as f (x)=1
" needing to close " represents the application program " needing to retain " as f (x)=- 1
Then, target optimization function is defined according to categorised decision function, target is obtained by sequential minimal optimization algorithm
The optimal solution of majorized function, obtains training pattern, and the objective optimization function isWherein, the target optimization function is in parameter (α1,α2,…,αi) on
It minimizes, a αiCorresponding to a sample (xi,yi), the sum of variable is equal to the capacity m of training sample.
The optimal solution can be denoted asThe training pattern can be g (sx)=wTSx+b,
In, g (x) is training pattern output valve,
For another example generating training pattern using backpropagation (Back Propagation, BP) neural network algorithm.
Firstly, setting input layer, hidden layer, classification layer, output layer, activation primitive, batch size and learning rate.
Wherein, the input layer includes N number of node, the dimension of the number of nodes of the input layer and the history feature information
It is identical.
The hidden layer includes M node.
The classification layer uses softmax function, and the softmax function isWherein, p
For prediction probability value, ZKFor median, C is the classification number of prediction result,For j-th of median.
The output layer includes 2 nodes.
The activation primitive uses sigmoid function, and the sigmoid function isWherein, the f
(x) range is 0 to 1.
The batch size is A.For example, the batch size can be 128.
The learning rate is B.For example, the learning rate can be 0.8.
Then, the sample vector is inputted in input layer to be calculated, obtain the output valve of input layer;In the hidden layer
The input input layer output valve, obtain the output valve of the hidden layer;The hidden layer is inputted in the classification layer
Output valve is calculated, and the prediction probability value [p is obtained1 p2]T, it brings the prediction probability value into output layer and calculates,
Prediction result value y is obtained, p is worked as1Greater than p2When, y=[1 0]T, work as p1Less than or equal to p2When, y=[0 1]T。
Finally, correcting the network structure according to prediction result value y, training pattern is obtained.
It should be noted that algorithm described herein is not limited to the above citing.
Step S103 brings current characteristic information pair into according to movement speed when detecting that application program enters backstage
The training pattern answered obtains prediction and closes probability.
Referring to Fig. 4, in one embodiment, the step S103 may include:
Step S1031: movement speed is obtained;
Step S1032: judge speed interval locating for movement speed;
Step S1033: the current characteristic information of application program is obtained;
Step S1034: bringing current characteristic information into corresponding training pattern and calculate, and obtains prediction and closes probability.
Wherein, when detecting that application program enters backstage, the movement speed of the terminal device is obtained, secondly, judgement
Then speed interval locating for the movement speed obtains the current characteristic information of the application program, finally, by current signature
Information is brought corresponding training pattern into and is calculated, and obtains prediction and closes probability.
In one embodiment, when detecting that application program enters backstage, it is spaced same time, what continuous n times obtained
When the movement speed of the terminal device is in same speed interval, the current signature letter of the application program is then obtained
Breath, calculates finally, bringing current characteristic information into corresponding training pattern, obtains prediction and closes probability.
In one embodiment, the dimension of current characteristic information of the application program of acquisition and the described of acquisition answer
Dimension with the history feature information of program is identical.
Step S104, judges whether the application program needs to close.
It should be noted that then closing the application program when prediction closes probability and is greater than closing threshold value;When prediction is closed
When closing probability less than threshold value is closed, then retain the application program.
Application program management-control method provided herein, by defining speed interval, according to friction speed section, to going through
History characteristic information is calculated, and different training patterns are generated, will according to movement speed when detecting that application program enters backstage
Current characteristic information brings corresponding training pattern into, obtains prediction and closes probability, to judge whether the application program needs to close
It closes, so that intelligence closes application program.
Referring to Fig. 5, the embodiment of the present application also provides a kind of device 30, described device 30 includes obtaining module 31, is generated
Module 32, computing module 33 and judgment module 34.
It should be noted that the application program can be chat application, video application, music application journey
Sequence, shopping application program, shared bicycle application program or Mobile banking's application program etc..
The acquisition module 31 for defining speed interval, obtain the application program friction speed section sample to
Amount, wherein the sample vector includes the history feature information of the multiple dimensions of the application program.
Referring to Fig. 6, described device 30 can also include storage module 36.The storage module 36 applies journey for storing
The characteristic information of sequence.The acquisition module 31 obtains history feature information from storage module 36.
The acquisition module 31 includes definition module 311 and the first acquisition module 312.
The definition module 311 is for defining speed interval.
Wherein, the speed interval may include First Speed section, second speed section and third speed section.It is described
First Speed section can be movement speed in the range of 0 to 2km/h namely static section;The second speed section can
Think movement speed in the range of 2km/h to 6km/h namely walking section;The third speed section can be mobile speed
Degree is greater than 6km/h, namely fast moves section.
First acquisition module 312 is used to obtain the application program in the sample vector in friction speed section, wherein
The sample vector includes the history feature information of the multiple dimensions of the application program.
Wherein, the characteristic information of the multiple dimension can be with reference table 2.
Table 2
It should be noted that the characteristic information of 10 dimensions shown in the above table 2 is only one of the embodiment of the present application,
But the application is not limited to the characteristic information of 10 dimensions shown in table 1, or one of them or wherein at least
Two, perhaps all also or can also include other dimensions characteristic information, for example, current whether in charging, current electricity
Whether amount currently connects WiFi etc..
The generation module 32 is used to calculate sample vector using algorithm, multiple training patterns is generated, wherein not
Friction speed section is corresponded to training pattern.
Referring to Fig. 6, the generation module 32 includes selecting module 321 and multiple training modules 322.
The selecting module 321 is used for selection algorithm.
Wherein, the algorithm can be algorithm of support vector machine, neural network algorithm, Bayesian statistics algorithm, decision tree
Algorithm etc..
The multiple training module 322 generates multiple training patterns for corresponding to friction speed section.
Wherein, friction speed section can choose different algorithms, and corresponding friction speed section generates multiple training patterns.
In one embodiment, the training module 322 may include the first training module 3221, the second training module
3222 and third training module 3223.
First training module 3221 generates the first training pattern for corresponding to First Speed section.
Second training module 3222 generates the second training pattern for corresponding to second speed section.
The third training module 3223 generates third training pattern for corresponding to third speed section.
In one embodiment, first training module 3221 can correspond to First Speed using algorithm of support vector machine
Section generates the first training pattern, and second training module 3222 can correspond to second speed section using neural network algorithm
The second training pattern is generated, it is raw that the third training module 3223 can correspond to third speed section using Bayesian statistics algorithm
At third training pattern.
For example, generating training pattern using linear SVM algorithm.
Firstly, defining hyperplane, the hyperplane can be hyperplane (w, b): wTX+b=0, wherein w is hyperplane
Normal vector, wTFor the transposed vector of w, x is sample vector, and b is hyperplane intercept.
Secondly, obtaining categorised decision function according to hyperplane, the categorised decision function can beWherein, f (x) is that categorised decision value represents the application program as f (x)=1
" needing to close " represents the application program " needing to retain " as f (x)=- 1.
Then, target optimization function is defined according to categorised decision function, target is obtained by sequential minimal optimization algorithm
The optimal solution of majorized function, obtains training pattern, and the objective optimization function isWherein, the target optimization function is in parameter (α1,α2,…,αi) on
It minimizes, a αiCorresponding to a sample (xi,yi), the sum of variable is equal to the capacity m of training sample.
The optimal solution can be denoted asThe training pattern can be g (sx)=wTSx+b,
In, g (x) is training pattern output valve,
For another example generating training pattern using backpropagation (Back Propagation, BP) neural network algorithm.
Firstly, setting input layer, hidden layer, classification layer, output layer, activation primitive, batch size and learning rate.
Wherein, the input layer includes N number of node, the dimension of the number of nodes of the input layer and the history feature information
It is identical.
The hidden layer includes M node.
The classification layer uses softmax function, and the softmax function isWherein, p
For prediction probability value, ZKFor median, C is the classification number of prediction result,For j-th of median.
The output layer includes 2 nodes.
The activation primitive uses sigmoid function, and the sigmoid function isWherein, the f
(x) range is 0 to 1.
The batch size is A.For example, the batch size can be 128.
The learning rate is B.For example, the learning rate can be 0.8.
Then, the sample vector is inputted in input layer to be calculated, obtain the output valve of input layer;In the hidden layer
The input input layer output valve, obtain the output valve of the hidden layer;The hidden layer is inputted in the classification layer
Output valve is calculated, and the prediction probability value [p is obtained1 p2]T, it brings the prediction probability value into output layer and calculates,
Prediction result value y is obtained, p is worked as1Greater than p2When, y=[1 0]T, work as p1Less than or equal to p2When, y=[0 1]T。
Finally, correcting the network structure according to prediction result value y, training pattern is obtained.
It should be noted that algorithm described herein is not limited to the above citing.
The computing module 33 is used for when detecting that application program enters backstage, is believed current signature according to movement speed
Breath brings corresponding training pattern into, obtains prediction and closes probability.
Referring to Fig. 6, in one embodiment, the computing module 33 may include the second acquisition module 331, analysis mould
Block 332, third acquisition module 333 and solution module 334.
Second acquisition module 331 is for obtaining movement speed.
The analysis module 332 is for judging speed interval locating for movement speed.
The third acquisition module 333 is used to obtain the current characteristic information of application program.
The solution module 334 is calculated for bringing current characteristic information into corresponding training pattern, is predicted
Close probability.
In one embodiment, referring to Fig. 6, described device 30 further includes detection module 35, for detecting the application
Program enters backstage.
Wherein, when the detection module 35 detects that application program enters backstage, second acquisition module 331 is obtained
The movement speed of the terminal device, secondly, the analysis module 332 judges speed interval locating for the movement speed, so
The third acquisition module 333 obtains the current characteristic information of the application program afterwards, finally, the solution module 334 will be worked as
Preceding characteristic information is brought corresponding training pattern into and is calculated, and obtains prediction and closes probability.
In one embodiment, when the detection module 35 detects that application program enters backstage, it is spaced same time,
When the movement speed for the terminal device that the continuous n times of second acquisition module 331 obtain is in same speed interval, so
The third acquisition module 333 obtains the current characteristic information of the application program afterwards, finally, the solution module 334 will be worked as
Preceding characteristic information is brought corresponding training pattern into and is calculated, and obtains prediction and closes probability.
In one embodiment, the dimension of current characteristic information of the application program of acquisition and the described of acquisition answer
Dimension with the history feature information of program is identical.
The judgment module 34 is for judging whether the application program needs to close.
It should be noted that then closing the application program when prediction closes probability and is greater than closing threshold value;When prediction is closed
When closing probability less than threshold value is closed, then retain the application program.
Described device 30 can also include closedown module 37, for being answered by described in when judging that application program needs to close
Use stop.
Application program control device provided herein, by defining speed interval, according to friction speed section, to going through
History characteristic information is calculated, and different training patterns are generated, will according to movement speed when detecting that application program enters backstage
Current characteristic information brings corresponding training pattern into, obtains prediction and closes probability, to judge whether the application program needs to close
It closes, so that intelligence closes application program.
Referring to Fig. 7, the embodiment of the present application also provides a kind of terminal device 500.The terminal device 500 includes: processing
Device 501 and memory 502.Wherein, processor 501 and memory 502 are electrically connected.
Processor 501 is the control centre of terminal device 500, utilizes various interfaces and the entire terminal device of connection
500 various pieces by the application program of operation or load store in memory 502, and are called and are stored in memory
Data in 502 execute the various functions and processing data of terminal device, to carry out integral monitoring to terminal device 500.
In the present embodiment, processor 501 in terminal device 500 can according to following step, by one or one with
On the corresponding instruction of process of application program be loaded into memory 502, and be stored in memory by processor 501 to run
Application program in 502, to realize various functions:
Speed interval is defined, obtains the application program in the sample vector in friction speed section, wherein the sample vector
History feature information including the multiple dimensions of the application program;
Sample vector is calculated using algorithm, generates multiple training patterns, wherein different training patterns are corresponding different
Speed interval;
When detecting that application program enters backstage, corresponding trained mould into is brought current characteristic information according to movement speed
Type obtains prediction and closes probability;And
Judge whether the application program needs to close.
It should be noted that the application program can be chat application, video application, music application journey
Sequence, shopping application program, shared bicycle application program or Mobile banking's application program etc..
Wherein, the speed interval may include First Speed section, second speed section and third speed section.It is described
First Speed section can be movement speed in the range of 0 to 2km/h namely static section;The second speed section can
Think movement speed in the range of 2km/h to 6km/h namely walking section;The third speed section can be mobile speed
Degree is greater than 6km/h, namely fast moves section.
Wherein, the characteristic information of the multiple dimension can be with reference table 3.
Table 3
It should be noted that the characteristic information of 10 dimensions shown in the above table 3 is only one of the embodiment of the present application,
But the application is not limited to the characteristic information of 10 dimensions shown in table 1, or one of them or wherein at least
Two, perhaps all also or can also include other dimensions characteristic information, for example, current whether in charging, current electricity
Whether amount currently connects WiFi etc..
In one embodiment, sample vector is calculated using algorithm, generates multiple training patterns, wherein different instructions
Practice model and correspond to friction speed section further include:
Selection algorithm;And
Corresponding friction speed section generates multiple training patterns.
The algorithm can be algorithm of support vector machine, neural network algorithm, Bayesian statistics algorithm, decision Tree algorithms
Deng.Wherein, friction speed section can choose different algorithms, and corresponding friction speed section generates multiple training patterns.
In one embodiment, the speed interval may include First Speed section, second speed section and third speed
Spend section.Corresponding First Speed section generates the first training pattern, and corresponding second speed section generates the second training pattern, corresponding
Third speed section generates third training pattern.
In one embodiment, First Speed section can be corresponded to using algorithm of support vector machine generates the first training mould
Type corresponds to second speed section using neural network algorithm and generates the second training pattern, using Bayesian statistics algorithm corresponding the
Three speed intervals generate third training pattern.
For example, generating training pattern using linear SVM algorithm.
Firstly, defining hyperplane, the hyperplane can be hyperplane (w, b): wTX+b=0, wherein w is hyperplane
Normal vector, wTFor the transposed vector of w, x is sample vector, and b is hyperplane intercept.
Secondly, obtaining categorised decision function according to hyperplane, the categorised decision function can beWherein, f (x) is that categorised decision value represents the application program as f (x)=1
" needing to close " represents the application program " needing to retain " as f (x)=- 1
Then, target optimization function is defined according to categorised decision function, target is obtained by sequential minimal optimization algorithm
The optimal solution of majorized function, obtains training pattern, and the objective optimization function isWherein, the target optimization function is in parameter (α1,α2,…,αi) on
It minimizes, a αiCorresponding to a sample (xi,yi), the sum of variable is equal to the capacity m of training sample.
The optimal solution can be denoted asThe training pattern can be g (sx)=wTSx+b,
In, g (x) is training pattern output valve,
For another example generating training pattern using backpropagation (Back Propagation, BP) neural network algorithm.
Firstly, setting input layer, hidden layer, classification layer, output layer, activation primitive, batch size and learning rate.
Wherein, the input layer includes N number of node, the dimension of the number of nodes of the input layer and the history feature information
It is identical.
The hidden layer includes M node.
The classification layer uses softmax function, and the softmax function isWherein, p
For prediction probability value, ZKFor median, C is the classification number of prediction result,For j-th of median.
The output layer includes 2 nodes.
The activation primitive uses sigmoid function, and the sigmoid function isWherein, the f
(x) range is 0 to 1.
The batch size is A.For example, the batch size can be 128.
The learning rate is B.For example, the learning rate can be 0.8.
Then, the sample vector is inputted in input layer to be calculated, obtain the output valve of input layer;In the hidden layer
The input input layer output valve, obtain the output valve of the hidden layer;The hidden layer is inputted in the classification layer
Output valve is calculated, and the prediction probability value [p is obtained1 p2]T, it brings the prediction probability value into output layer and calculates,
Prediction result value y is obtained, p is worked as1Greater than p2When, y=[1 0]T, work as p1Less than or equal to p2When, y=[0 1]T。
Finally, correcting the network structure according to prediction result value y, training pattern is obtained.
It should be noted that algorithm described herein is not limited to the above citing.
In one embodiment, when detecting that application program enters backstage, the processor 501 will according to movement speed
Current characteristic information brings corresponding training pattern into, obtains prediction and closes probability further include:
Obtain movement speed;
Judge speed interval locating for movement speed;
Obtain the current characteristic information of application program;
It brings current characteristic information into corresponding training pattern to calculate, obtains prediction and close probability.
Wherein, when detecting that application program enters backstage, the movement speed of the terminal device is obtained, secondly, judgement
Then speed interval locating for the movement speed obtains the current characteristic information of the application program, finally, by current signature
Information is brought corresponding training pattern into and is calculated, and obtains prediction and closes probability.
In one embodiment, when detecting that application program enters backstage, it is spaced same time, what continuous n times obtained
When the movement speed of the terminal device is in same speed interval, the current signature letter of the application program is then obtained
Breath, calculates finally, bringing current characteristic information into corresponding training pattern, obtains prediction and closes probability.
In one embodiment, the dimension of current characteristic information of the application program of acquisition and the described of acquisition answer
Dimension with the history feature information of program is identical.
In one embodiment, the processor 501 judges whether the application program needs to close.When prediction is closed
When probability is greater than closing threshold value, then the application program is closed;When probability is closed in prediction is less than closing threshold value, then described in reservation
Application program.
Memory 502 can be used for storing application program and data.It include that can handle in the program that memory 502 stores
The instruction executed in device.Described program can form various functional modules.Processor 501 is stored in memory 502 by operation
Program, thereby executing various function application and data processing.
In some embodiments, as shown in figure 8, terminal device 500 further include: radio circuit 503, display screen 504, control
Circuit 505, input unit 506, voicefrequency circuit 507, sensor 508 and power supply 509.Wherein, processor 501 respectively with radio frequency
Circuit 503, display screen 504, control circuit 505, input unit 506,509 electricity of voicefrequency circuit 507, sensor 508 and power supply
Property connection.
Radio circuit 503 is used for transceiving radio frequency signal, with network by wireless communication and server or other electronic equipments
It is communicated.
Display screen 504 can be used for showing information input by user or be supplied to the information of user and the various figures of terminal
Shape user interface, these graphical user interface can be made of image, text, icon, video and any combination thereof.
Control circuit 505 and display screen 504 are electrically connected, and show information for controlling display screen 504.
Input unit 506 can be used for receiving number, character information or the user's characteristic information (such as fingerprint) of input, and
Generate keyboard related with user setting and function control, mouse, operating stick, optics or trackball signal input.
Voicefrequency circuit 507 can provide the audio interface between user and terminal by loudspeaker, microphone.
Sensor 508 is for acquiring external environmental information.Sensor 508 may include ambient light sensor, acceleration
One of sensors such as sensor, gyroscope are a variety of.
Power supply 509 is used to power to all parts of terminal device 500.In some embodiments, power supply 509 can pass through
Power-supply management system and processor 501 are logically contiguous, to realize management charging, electric discharge, Yi Jigong by power-supply management system
The functions such as consumption management.
Although being not shown in Fig. 8, terminal device 500 can also include camera, bluetooth module etc., and details are not described herein.
Terminal device provided herein enters backstage by detecting application program, by defining speed interval, obtains
The application program is in the sample vector in friction speed section, and wherein the sample vector includes the multiple dimensions of the application program
History feature information;Sample vector is calculated using algorithm, generates multiple training patterns, wherein different training patterns are corresponding
Friction speed section;When detecting that application program enters backstage, current characteristic information brought into according to movement speed corresponding
Training pattern obtains prediction and closes probability;And judging whether the application program needs to close, intelligence closes application program.
The embodiment of the present invention also provides a kind of storage medium, and a plurality of instruction is stored in the storage medium, which is suitable for
It is loaded as processor to execute application program management-control method described in any of the above-described embodiment.
Application program management-control method, device, storage medium and terminal device provided in an embodiment of the present invention belong to same structure
Think, specific implementation process is detailed in specification full text, and details are not described herein again.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of above-described embodiment is can
It is completed with instructing relevant hardware by program, which can store in a computer-readable storage medium,
Storage medium may include: read-only memory (ROM, Read Only Memory), random access memory (RAM,
Random Access Memory), disk or CD etc..
Application program management-control method provided by the embodiments of the present application, device, storage medium and terminal device are carried out above
It is discussed in detail, specific case used herein is expounded the principle and embodiment of the application, above embodiments
Illustrate to be merely used to help understand the application.Meanwhile for those skilled in the art, according to the thought of the application, specific
There will be changes in embodiment and application range, in conclusion the content of the present specification should not be construed as the limit to the application
System.
Claims (14)
1. a kind of application program management-control method, it is applied to terminal device, which is characterized in that the application program management-control method includes
Following steps:
The speed interval for defining the terminal device obtains the application program in the sample in terminal device friction speed section
This vector, wherein the sample vector includes the history feature information of the multiple dimensions of the application program;
Sample vector is calculated using algorithm, generates multiple training patterns, wherein different training patterns correspond to friction speed
Section, wherein input data of the sample vector as the algorithm, the algorithm are predicted according to the input data
End value corrects the algorithm according to the prediction result value and obtains revised algorithm, and using revised algorithm as instruction
Practice model;
When detecting that application program enters backstage, according to the movement speed of the terminal device by the current of the application program
Characteristic information substitutes into corresponding training pattern, obtains prediction and closes probability;And
Whether need to close according to application program described in prediction closing probabilistic determination.
2. application program management-control method as described in claim 1, it is characterised in that: counted using algorithm to sample vector
It calculates, generates multiple training patterns, wherein different training patterns include: the step of corresponding to friction speed section
Selection algorithm;And
Corresponding friction speed section generates multiple training patterns.
3. application program management-control method as claimed in claim 2, it is characterised in that: described after detecting that application program enters
When platform, current characteristic information is substituted by corresponding training pattern according to movement speed, obtaining the step of probability is closed in prediction includes:
Obtain movement speed;
Judge speed interval locating for movement speed;
Obtain the current characteristic information of application program;And
Current characteristic information is substituted into the corresponding training pattern of the speed interval to calculate, prediction is obtained and closes probability.
4. application program management-control method as claimed in claim 3, it is characterised in that: described to judge whether the application program needs
The step of closing includes: then to close the application program when prediction closes probability and is greater than closing threshold value;When prediction is closed generally
When rate is less than closing threshold value, then retain the application program.
5. a kind of application program control device, it is applied to terminal device, which is characterized in that described device includes:
Module is obtained, the speed interval of the terminal device is defined, it is not synchronized in the terminal device to obtain the application program
The sample vector in section is spent, wherein the sample vector includes the history feature information of the multiple dimensions of the application program;
Generation module generates multiple training patterns, wherein different training patterns for calculating using algorithm sample vector
Corresponding friction speed section, wherein input data of the sample vector as the algorithm, the algorithm is according to the input
Data obtain prediction result value, correct the algorithm according to the prediction result value and obtain revised algorithm, and will be after amendment
Algorithm as training pattern;
Computing module will be described according to the movement speed of the terminal device for when detecting that application program enters backstage
The current characteristic information of application program substitutes into corresponding training pattern, obtains prediction and closes probability;And
Whether judgment module needs to close for the application program according to prediction closing probabilistic determination.
6. application program control device as claimed in claim 5, it is characterised in that: the acquisition module includes:
Definition module, for defining speed interval;And
First acquisition module obtains the application program in the sample vector in friction speed section, and wherein the sample vector includes
The history feature information of the multiple dimensions of application program.
7. application program control device as claimed in claim 5, it is characterised in that: the generation module includes:
Selecting module is used for selection algorithm;And
Multiple training modules generate multiple training patterns for corresponding to friction speed section.
8. program control device the use as claimed in claim 7, it is characterised in that: the generation module includes:
Second acquisition module, for obtaining movement speed;
Analysis module, for judging speed interval locating for movement speed;
Third acquisition module, for obtaining the current characteristic information of application program;And
Module is solved, is calculated for current characteristic information to be substituted into the corresponding training pattern of the speed interval, is obtained pre-
It surveys and closes probability.
9. application program control device as claimed in claim 5, it is characterised in that: close probability when prediction and be greater than closing threshold value
When, then close the application program;When probability is closed in prediction is less than closing threshold value, then retain the application program.
10. application program control device as claimed in claim 5, it is characterised in that: further include detection module, for detecting
It states application program and enters backstage.
11. application program control device as claimed in claim 5, it is characterised in that: further include storage module, answered for storing
With the characteristic information of program.
12. application program control device as claimed in claim 5, it is characterised in that: further include closedown module, for when judgement
When application program needs to close, by the closing application program.
13. a kind of storage medium, it is characterised in that: be stored with a plurality of instruction in the storage medium, described instruction be suitable for by
Device load is managed to execute application program management-control method according to any one of claims 1 to 4.
14. a kind of terminal device, it is characterised in that: the terminal device includes processor and memory, the terminal device with
The memory is electrically connected, and the memory is for storing instruction and data, the processor are used to execute such as claim 1
To application program management-control method described in any one of 4.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711046994.0A CN107861770B (en) | 2017-10-31 | 2017-10-31 | Application program management-control method, device, storage medium and terminal device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711046994.0A CN107861770B (en) | 2017-10-31 | 2017-10-31 | Application program management-control method, device, storage medium and terminal device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107861770A CN107861770A (en) | 2018-03-30 |
CN107861770B true CN107861770B (en) | 2019-08-06 |
Family
ID=61697084
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711046994.0A Active CN107861770B (en) | 2017-10-31 | 2017-10-31 | Application program management-control method, device, storage medium and terminal device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107861770B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113439253B (en) * | 2019-04-12 | 2023-08-22 | 深圳市欢太科技有限公司 | Application cleaning method and device, storage medium and electronic equipment |
CN114372978B (en) * | 2022-02-10 | 2022-06-28 | 北京安德医智科技有限公司 | Ultrasonic contrast image classification method and device, electronic equipment and storage medium |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102929500B (en) * | 2012-09-27 | 2016-02-10 | 东莞宇龙通信科技有限公司 | The closing process method of mobile terminal and application program |
KR20160091786A (en) * | 2015-01-26 | 2016-08-03 | 삼성전자주식회사 | Method and apparatus for managing user |
CN105912370B (en) * | 2016-05-03 | 2020-02-14 | Oppo广东移动通信有限公司 | Control method and device for background application program of mobile terminal and mobile terminal |
CN107045443A (en) * | 2017-04-14 | 2017-08-15 | 北京安云世纪科技有限公司 | background process control method, device and intelligent terminal |
-
2017
- 2017-10-31 CN CN201711046994.0A patent/CN107861770B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN107861770A (en) | 2018-03-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107678799B (en) | Application program management-control method, device, storage medium and electronic equipment | |
US11169827B2 (en) | Resource loading at application startup using attributes of historical data groups | |
CN107608748B (en) | Application program management-control method, device, storage medium and terminal device | |
US10673707B2 (en) | Systems and methods for managing lifecycle and reducing power consumption by learning an IoT device | |
CN111046227B (en) | Video duplicate checking method and device | |
EP3553676A1 (en) | Smart recommendation method and terminal | |
CN107643948A (en) | Application program management-control method, device, medium and electronic equipment | |
CN107885544A (en) | Application program management-control method, device, medium and electronic equipment | |
CN113284142B (en) | Image detection method, image detection device, computer-readable storage medium and computer equipment | |
CN109948633A (en) | User gender prediction method, apparatus, storage medium and electronic equipment | |
US11249645B2 (en) | Application management method, storage medium, and electronic apparatus | |
CN103106027A (en) | Method and apparatus for designating entire area using partial area touch in a portable equipment | |
CN107704070A (en) | Using method for cleaning, device, storage medium and electronic equipment | |
CN108197225B (en) | Image classification method and device, storage medium and electronic equipment | |
US20200241483A1 (en) | Method and Device for Managing and Controlling Application, Medium, and Electronic Device | |
CN108108455A (en) | Method for pushing, device, storage medium and the electronic equipment of destination | |
CN107861770B (en) | Application program management-control method, device, storage medium and terminal device | |
CN107943534A (en) | Method for closing, device, storage medium and the electronic equipment of background application | |
CN111797870A (en) | Optimization method and device of algorithm model, storage medium and electronic equipment | |
CN114781766B (en) | Hydrological information prediction method, device, equipment and storage medium for hydrological site | |
US9165256B2 (en) | Efficient prediction | |
CN107729078B (en) | Background application management-control method, device, storage medium and electronic equipment | |
CN109961163A (en) | Gender prediction's method, apparatus, storage medium and electronic equipment | |
CN107870809A (en) | Using method for closing, device, storage medium and electronic equipment | |
CN108681480B (en) | Background application program control method and device, storage medium and electronic equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: 523860 No. 18, Wu Sha Beach Road, Changan Town, Dongguan, Guangdong Applicant after: OPPO Guangdong Mobile Communications Co., Ltd. Address before: 523860 No. 18, Wu Sha Beach Road, Changan Town, Dongguan, Guangdong Applicant before: Guangdong OPPO Mobile Communications Co., Ltd. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |