CN107870791B - Application management method, device, storage medium and electronic equipment - Google Patents
Application management method, device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN107870791B CN107870791B CN201711047015.3A CN201711047015A CN107870791B CN 107870791 B CN107870791 B CN 107870791B CN 201711047015 A CN201711047015 A CN 201711047015A CN 107870791 B CN107870791 B CN 107870791B
- Authority
- CN
- China
- Prior art keywords
- application
- feature coefficient
- preset duration
- duration
- coefficient
- 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
-
- 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
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5011—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resources being hardware resources other than CPUs, Servers and Terminals
- G06F9/5022—Mechanisms to release resources
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the present application provides a kind of application management method, device, storage medium and electronic equipment, this method comprises: acquiring multiple characteristic informations of the application according to the log of application;The multiple characteristic information is learnt by self organizing neural network, to obtain the self organizing neural network model of the application;When the application enters running background, effective number of run that the application enters front stage operation within a preset period of time is obtained;The fisrt feature coefficient of the application is calculated according to the current characteristic information of the application;Second feature coefficient is determined from the feature coefficient matrix according to the fisrt feature coefficient;Judge whether the application can be cleaned according to the second feature coefficient.The program judges whether the application can be cleaned according to the second feature coefficient of application, it is possible to reduce the EMS memory occupation of electronic equipment improves the operation fluency of electronic equipment.
Description
Technical field
This application involves technical field of electronic equipment, in particular to a kind of application management method, device, storage medium and electricity
Sub- equipment.
Background technique
With the development of electronic technology, the function of the electronic equipments such as smart phone is more and more abundant.People usually exist
Multiple applications are installed on electronic equipment.When user opens multiple in application, if user retracts electronic equipment in the electronic device
Main screen or rest on the application interface of a certain application, then multiple applications that user opens still can be after electronic equipment
Platform operation.The application of running background can seriously occupy the memory of electronic equipment, reduce the operation fluency of electronic equipment.
Summary of the invention
The embodiment of the present application provides a kind of application management method, device, storage medium and electronic equipment, it is possible to reduce electronics
The EMS memory occupation of equipment improves the operation fluency of electronic equipment.
The embodiment of the present application provides a kind of application management method, comprising:
Multiple characteristic informations of the application are acquired according to the log of application;
The multiple characteristic information is learnt by self organizing neural network, to obtain the self-organizing mind of the application
Through network model, the self organizing neural network model includes the feature coefficient matrix of the application;
When the application enters running background, the application is obtained within a preset period of time into the effective of front stage operation
Number of run, effective number of run reach time of the first preset duration for the operation duration that the application enters front stage operation
Number;
The fisrt feature coefficient of the application, the current characteristic information are calculated according to the current characteristic information of the application
Including effective number of run;
Second feature coefficient is determined from the feature coefficient matrix according to the fisrt feature coefficient;
Judge whether the application can be cleaned according to the second feature coefficient.
The embodiment of the present application also provides a kind of application management device, comprising:
Acquisition module acquires multiple characteristic informations of the application for the log according to application;
Study module, it is described to obtain for being learnt by self organizing neural network to the multiple characteristic information
The self organizing neural network model of application, the self organizing neural network model include the feature coefficient matrix of the application;
Module is obtained, is entered within a preset period of time for when the application enters running background, obtaining the application
Effective number of run of front stage operation, effective number of run are that the application enters the operation duration of front stage operation and reaches the
The number of one preset duration;
Computing module, for calculating the fisrt feature coefficient of the application, institute according to the current characteristic information of the application
Stating current characteristic information includes effective number of run;
Determining module, for determining second feature system from the feature coefficient matrix according to the fisrt feature coefficient
Number;
Judgment module, for judging whether the application can be cleaned according to the second feature coefficient.
The embodiment of the present application also provides a kind of storage medium, computer program is stored in the storage medium, when described
When computer program is run on computers, so that the computer executes above-mentioned application management method.
The embodiment of the present application also provides a kind of electronic equipment, including processor and memory, is stored in the memory
Computer program, the processor is by calling the computer program stored in the memory, for executing above-mentioned answer
Use management method.
Application management method provided by the embodiments of the present application acquires multiple spies of the application according to the log of application
Reference breath;The multiple characteristic information is learnt by self organizing neural network, to obtain the self-organizing mind of the application
Through network model;When the application enters running background, the application is obtained within a preset period of time into front stage operation
Effective number of run, effective number of run reach the first preset duration for the operation duration that the application enters front stage operation
Number;The fisrt feature coefficient of the application, the current characteristic information are calculated according to the current characteristic information of the application
Including effective number of run;Second feature system is determined from the feature coefficient matrix according to the fisrt feature coefficient
Number;Judge whether the application can be cleaned according to the second feature coefficient.The program is according to the second feature coefficient of application
Judge whether the application can be cleaned, so as to being accurately judged to described answer according to the practical operation situation of the application
With when being cleaned, when the application can be cleaned, the application is closed in time to discharge the memory of electronic equipment,
And then the EMS memory occupation of electronic equipment can be reduced, improve the operation fluency of electronic equipment.
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 evident 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 the system schematic of application management device provided by the embodiments of the present application.
Fig. 2 is the application scenarios schematic diagram of application management method provided by the embodiments of the present application.
Fig. 3 is the flow diagram of application management method provided by the embodiments of the present application.
Fig. 4 is another flow diagram of application management method provided by the embodiments of the present application.
Fig. 5 is the another flow diagram of application management method provided by the embodiments of the present application.
Fig. 6 is the configuration diagram of the self organizing neural network in the embodiment of the present application.
Fig. 7 is the structural schematic diagram of application management device provided by the embodiments of the present application.
Fig. 8 is another structural schematic diagram of application management device provided by the embodiments of the present application.
Fig. 9 is the another structural schematic diagram of application management device provided by the embodiments of the present application.
Figure 10 is the structural schematic diagram of electronic equipment provided by the embodiments of the present application.
Figure 11 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 under that premise of not paying creative labor
Example, belongs to the protection scope of the application.
The description and claims of this application and term " first " in above-mentioned attached drawing, " second ", " third " etc.
(if present) is to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be appreciated that this
The object of sample description is interchangeable under appropriate circumstances.In addition, term " includes " and " having " and their any deformation, meaning
Figure, which is to cover, non-exclusive includes.For example, containing the process, method of series of steps or containing a series of modules or list
The device of member, electronic equipment, system those of are not necessarily limited to be clearly listed step or module or unit, can also include not having
The step of being clearly listed or module or unit also may include for these process, methods, device, electronic equipment or system
Intrinsic other steps or module or unit.
With reference to Fig. 1, Fig. 1 is the system schematic of application management device provided by the embodiments of the present application.Application management dress
It sets and is mainly used for: acquiring multiple characteristic informations of the application according to the log of application;Pass through self organizing neural network mould
Type learns collected multiple features, to obtain the self organizing neural network model of the application, wherein described from group
Knit the feature coefficient matrix that neural network model includes the application;Acquire the current characteristic information of the application, and according to adopting
The current characteristic information collected calculates the fisrt feature coefficient of the application;According to the fisrt feature coefficient from the feature system
Second feature coefficient is determined in matrix number;Then judge whether the application can be cleaned according to the second feature coefficient.
With reference to Fig. 2, Fig. 2 is the application scenarios schematic diagram of application management method provided by the embodiments of the present application.Wherein, electronics
Equipment is managed multiple applications of running background.For example, running background has using a, using b and using c.Electronic equipment
Whether judgement can be cleaned using a, using b, using c respectively.For example, being judged as using a, using c can not be cleaned, using b
It can be cleaned, then electronic equipment can be cleaned up using b, keep continuing using a and application c in running background.To which electronics is set
It is standby to close using b, the occupied memory of b is applied with release.
With reference to Fig. 3, Fig. 3 is the flow diagram of application management method provided by the embodiments of the present application.The application management side
Method can be applied in electronic equipment.The electronic equipment can be the equipment such as smart phone, tablet computer.The application management method
It may comprise steps of:
S110 acquires multiple characteristic informations of the application according to the log of application.
Wherein, the application can be mounted in any application in electronic equipment, such as messaging application, more
Media application, game application, information application program or shopping application program etc..
Multiple characteristic informations of the application may include described using itself intrinsic characteristic information, such as described answer
Application type;Multiple characteristic informations of the application also may include feature caused by the application in the process of running
Information, for example, it is described apply the operation duration on backstage, in one day into when number, the upper once operation on foreground on backstage
Mode long or that enter backstage (such as by home key (i.e. HOME key) switching, be returned key switching or cut by other APP
Change) etc.;Multiple characteristic informations of the application can also include generated characteristic information in electronic equipment operational process, example
Such as electronic equipment puts out screen (go out screen) duration, bright screen duration, remaining capacity, network state or charged state.
In the operational process of electronic equipment, electronic equipment can be recorded the operation conditions of itself.Such as electronics
Equipment can be recorded by journal file electronic equipment at the time of put out screen every time, at the time of bright screen, information about power, network state,
Charged state etc..After above-mentioned application brings into operation, electronic equipment can also record the operation conditions of the application.
Such as the journal file in electronic equipment can recorde application at the time of bring into operation, into running background at the time of, into
Enter the switching mode etc. on backstage.
When electronic equipment receives application management request, the application can be obtained according to the log of the application
Multiple characteristic informations.Wherein, application management request can be is triggered by the instruction of user, is also possible to electronics
The operation that equipment voluntarily triggers.For example, timing can be set in electronic equipment, the timing of setting is reached whenever the time, electronics is set
Standby i.e. voluntarily triggering application management operation.
S120 learns the multiple characteristic information by self organizing neural network, with obtain the application from
Organize neural network model.
It is the configuration diagram of the self organizing neural network in the embodiment of the present application with reference to Fig. 6, Fig. 6.Self-organizing feature map
Network is by the inherent law and essential attribute in Automatic-searching sample, and self-organizing adaptively changes network parameter and structure.
Wherein, self organizing neural network has input layer and computation layer.Input layer and computation layer respectively include multiple nodes.
After electronic equipment collects multiple characteristic informations of application, multiple characteristic informations of the application are input to from group
Knit the input layer of neural network.Then, the self organizing neural network learns the multiple characteristic information, to obtain
State the self organizing neural network model of application.Wherein, the self organizing neural network model includes the characteristic coefficient of the application
Matrix, the feature coefficient matrix include multiple characteristic coefficients.
In some embodiments, as shown in figure 4, step S120, being believed the multiple feature by self organizing neural network
Breath is learnt, to obtain the self organizing neural network model of the application, comprising the following steps:
S121, according to the connection weight meter of each node in collected multiple characteristic informations and self organizing neural network
Calculate multiple characteristic coefficients of the application;
S122 obtains the self organizing neural network model of the application according to obtained multiple characteristic coefficients.
Specifically, after some node (input node) in the input layer of self organizing neural network gets characteristic information,
One determine node (calculate node) best with the node (input node) matching in computation layer according to the following formula:
Formula one:
Wherein, DistFromInput indicate computation layer in the node (input node) matching in input layer most
Good node (calculate node) arrives the distance between described input node, and I indicates the node (input being input in input layer
Node) characteristic information, W indicate field radius in all nodes connection weight, n expression be input to the node (input section
Point) characteristic information number.
Wherein, the connection weight W of all nodes two is calculated according to the following formula in the radius of field:
Formula two: W (t)=W (t-1)+Θ (t-1) L (t-1) (I (t-1)-W (t-1))
Wherein, at the time of when t expression is calculated, it is also spy calculated that W (t), which is t moment connection weight calculated,
Coefficient is levied, W (t-1) is the connection weight of (t-1) moment node, and Θ (t-1) is the field radius changing rate at (t-1) moment, L
It (t-1) is the learning rate at (t-1) moment, I (t-1) is to be input to the input node in self organizing neural network at (t-1) moment
Characteristic information.Respectively according to the following formula three and formula four calculate Θ (t-1) and L (t-1):
Formula three:
Formula four:
Wherein, e is natural constant (transcendental number), and e is definite value, and e is approximately equal to 2.71828.L0For fixed constant, such as L0It can
With value 0.3,0.5 etc..σ (t-1) indicates that the field radius at (t-1) moment, σ (t-1) five are calculated according to the following formula:
Formula five:
Wherein, σ0For initial field radius, σ0For fixed constant, such as σ0It can be with value 5,10 etc..λ (t-1) is (t-
1) iteration coefficient at moment, λ (t-1) six are calculated according to the following formula:
Formula six:
Wherein, λ0For primary iteration coefficient, λ0For fixed constant, such as λ0It can be with value 1000.
After electronic equipment collects multiple characteristic informations of above-mentioned application, fortune is iterated according to formula one to formula six
It calculates, obtains multiple connection weight W (t) of the application.Connection weight W (t) namely it is characterized coefficient.Finally, be calculated
Multiple connection weight W (t) constitutive characteristic coefficient matrixes.The feature coefficient matrix includes multiple characteristic coefficients.The feature
Multiple characteristic coefficients in coefficient matrix and feature coefficient matrix and the corresponding relationship between the time constitute the application
Self organizing neural network model.
It should be noted that electronic equipment can be according to the above public affairs in the self organizing neural network model of building application
Formula carries out the operation of a large amount of numbers.
S130 calculates the application according to the current characteristic information of the application when the application enters running background
Fisrt feature coefficient.
Wherein, when the application enters running background by front stage operation, electronic equipment can be to the application
The no judgement operation being cleaned.
Specifically, when the application enters running background, electronic equipment acquires the current characteristic information of the application.Its
In, current characteristic information may include described using itself intrinsic characteristic information, such as the application type of the application;When
Preceding characteristic information also may include characteristic information caused by the application in the process of running, such as described apply on backstage
Operation duration, in one day into the number on backstage, last operation duration on foreground or enter backstage mode (such as
By home key (i.e. HOME key) switching, it is returned key switching or is switched by other APP) etc.;Current characteristic information can be with
Including generated characteristic information in electronic equipment operational process, such as when putting out screen (go out screen) duration, bright screen of electronic equipment
Length, remaining capacity, network state or charged state etc..
Then, electronic equipment is calculated according to above-mentioned formula one to current characteristic information of the formula six to the application,
To obtain the fisrt feature coefficient of the application.
In some embodiments, the current characteristic information of the application includes before the application enters within a preset period of time
Effective number of run of platform operation.Step S130, when the application enters running background, according to the current signature of the application
Before information calculates the fisrt feature coefficient of the application, the application management method is further comprising the steps of:
When the application enters running background, the application is obtained within a preset period of time into the effective of front stage operation
Number of run, effective number of run reach time of the first preset duration for the operation duration that the application enters front stage operation
Number.
Wherein, the preset time period can be the time range preset in the electronic device.For example, default
Period can be 10 hours, 24 hours etc..It is understood that preset time period is to end a time at current time
Range.First preset duration can be the duration numerical value preset in the electronic device.First preset duration table
Certain for showing application operates to the separation for effectively running and still running in vain.For example, the first preset duration can be 10 seconds, 1
Minute etc..Effective number of run is all numbers applied and enter front stage operation in the preset time period
In, operation duration reaches the number of first preset duration.
When the application enters running background, electronic equipment obtains the application and enters foreground fortune within a preset period of time
Capable effective number of run.
In some embodiments, when the application enters running background, obtain it is described application within a preset period of time into
Enter effective number of run of front stage operation, comprising the following steps:
When the application enters running background, obtains the application and enter the first of front stage operation within a preset period of time
Number and the duration for entering front stage operation every time;
Determine that the application enters the duration of front stage operation and reaches the of the first preset duration from first number
Two numbers;
Second number is determined as effective number of run that the application enters front stage operation within a preset period of time.
Wherein, when the application enters running background, electronic equipment can be obtained according to the log of the application
The application enters the duration of front stage operation into first number of front stage operation and every time within a preset period of time.For example,
Preset time period is 10 hours.Described apply in 10 hours is 5 times into first number of front stage operation, before this 5 times enter
The duration of platform operation is respectively 30 seconds, 5 minutes, 2 minutes, 2 hours, 40 minutes.
Then, electronic equipment respectively carries out the application into the duration of front stage operation and the first preset duration each time
Compare, reaches the second of the first preset duration to determine that the application enters the duration of front stage operation from first number
Number.For example, the first preset duration is 1 minute, then in described first number 5 times, into effective number of run of front stage operation
Second number is 4 times.Then, second number is determined as the application within a preset period of time into foreground by electronic equipment
Effective number of run of operation.
In some embodiments, determine that the application enters the duration of front stage operation and reaches from first number
It is further comprising the steps of before second number of one preset duration:
Obtain the application type of the application;
Corresponding first preset duration is obtained according to the application type.
Wherein, different application types, such as social application, shopping application, music can be preset in electronic equipment
Using, Video Applications etc..Also, corresponding first preset duration can be arranged for each type of application in electronic equipment.Example
Such as, corresponding first preset duration of social application is 10 seconds, and corresponding first preset duration of shopping application is 1 minute, and music is answered
It is 30 seconds with corresponding first preset duration, corresponding first preset duration of Video Applications is 3 minutes.
Electronic equipment can determine the application type of the application, and obtain corresponding first in advance according to the application type
If duration.For example, the application is social application, then the first preset duration that electronic equipment is got is 10 seconds.
S140 determines second feature coefficient according to the fisrt feature coefficient from the feature coefficient matrix.
It wherein, can be according to the fisrt feature system after the fisrt feature coefficient of the application is calculated in electronic equipment
The self organizing neural network model of the several and described application determines the second feature coefficient of the application.
Specifically, the self organizing neural network model of the application includes the feature coefficient matrix of the application.The spy
Levying includes multiple characteristic coefficients in coefficient matrix.Electronic equipment can be respectively by the fisrt feature coefficient and the characteristic coefficient
Multiple characteristic coefficients in matrix are compared, to determine second from multiple characteristic coefficients in the feature coefficient matrix
Characteristic coefficient.
In some embodiments, as shown in figure 4, step S140, according to the fisrt feature coefficient from the characteristic coefficient
Second feature coefficient is determined in matrix, comprising the following steps:
S141 calculates separately the absolute value of the difference of the fisrt feature coefficient and the multiple characteristic coefficient;
The corresponding characteristic coefficient of the smallest difference of absolute value is determined as second feature coefficient by S142.
Wherein, after the fisrt feature coefficient of the application is calculated in electronic equipment, respectively by the fisrt feature coefficient
It is compared with multiple characteristic coefficients in the feature coefficient matrix, calculates the fisrt feature coefficient and the multiple feature
The difference of coefficient, and calculate the absolute value of the difference.
After obtaining the absolute value of multiple differences, determined from the absolute value of multiple differences one the smallest.It then, will be exhausted
Second feature coefficient is determined as to characteristic coefficient corresponding to the smallest difference of value.
S150 judges whether the application can be cleaned according to the second feature coefficient.
It wherein, can be according to the second feature system after the second feature coefficient of the application is calculated in electronic equipment
Number is judged whether can be cleaned with the determination application.If the application can not be cleaned, retains the application and continue
In running background, allow the process of the application resident in systems.If the application can be cleaned, can terminate described
The process of application discharges the memory that the application occupies to close the application.
In some embodiments, as shown in figure 4, step S150, according to the second feature coefficient judging that the application is
It is no to be cleaned, comprising the following steps:
S151 obtains the second preset duration;
The second feature coefficient is compared, to obtain comparison result by S152 with second preset duration;
S153 judges whether the application can be cleaned according to the comparison result.
Wherein, the second preset duration can be the duration value preset in the electronic device.For example, second is default
Duration can be 10 minutes.After the second feature coefficient of the application is calculated in electronic equipment, adjusted from the electronic equipment
Take second preset duration.Then, the second feature coefficient is compared with second preset duration, to be compared
Relatively result.Wherein, size relation of the comparison result between the second feature coefficient and second preset duration.Compare knot
Fruit includes that the second feature coefficient is less than or equal to second preset duration or the second feature coefficient greater than described
Second preset duration.Then, electronic equipment judges whether the application can be cleaned according to the comparison result.
In some embodiments, as shown in figure 5, step S151, the second preset duration of acquisition, comprising the following steps:
S1511, at the time of determining that the second feature coefficient corresponds to according to the second feature coefficient;
S1512 obtains the second preset duration according to period locating for the moment and default corresponding relationship, described pre-
If corresponding relationship of the corresponding relationship between period and the second preset duration.
Wherein, second feature coefficient is the characteristic coefficient determined from the self organizing neural network model of the application.
Second feature coefficient is the function about time t.Electronic equipment can determine that described second is special according to the second feature coefficient
At the time of sign coefficient corresponds to.
The corresponding relationship between period and the second preset duration can be preset in electronic equipment.For example, in one day
24 hours can be divided into 4 periods: 0:00~6:00,6:00~12:00,12:00~18:00,18:00~24:00.
Corresponding second preset duration can be set in each period.For example, corresponding second preset duration of 0:00~6:00 is 8 points
Clock, corresponding second preset duration of 6:00~12:00 are 10 minutes, and corresponding second preset duration of 12:00~18:00 is 15 points
Clock, corresponding second preset duration of 18:00~24:00 are 20 minutes.
After electronic equipment is determined at the time of the second feature coefficient corresponds to, when further determining that locating for the moment
Between section.Then, the second preset duration is obtained according to the corresponding relationship between period and period and the second preset duration.
In some embodiments, as shown in figure 5, step S153, according to the comparison result judge it is described application whether may be used
It is cleaned, comprising the following steps:
S1531, when the second feature coefficient is less than or equal to second preset duration, judging result is described answers
With can not be cleaned;
S1532, when the second feature coefficient is greater than second preset duration, judging result is that the application can quilt
Cleaning.
Wherein, after electronic equipment obtains the comparison result between the second feature coefficient and the second preset duration, according to
The comparison result judges whether the application can be cleaned.
Specifically, it when the second feature coefficient is less than or equal to second preset duration, indicates described and applies
Front stage operation may be again switched in the period of second preset duration, judging result is that the application can not at this time
It is cleaned.For example, second feature coefficient less than the second preset duration 10 minutes, indicates described and applies in next 10 minutes
Front stage operation may be again switched to by user, the application can not be cleaned at this time.
When the second feature coefficient is greater than second preset duration, indicates described and apply when described second is default
Front stage operation namely user will not be again switched in the long period will not reuse the application, at this time judgement knot
Fruit is that the application can be cleaned.For example, second feature coefficient is greater than the second preset duration 15 minutes, indicates described and apply
It will not be run again by user in next 15 minutes, the application can be cleaned at this time.Then, electronic equipment can close
Close the application.
When it is implemented, the application is not limited by the execution sequence of described each step, conflict is not being generated
In the case of, certain steps can also be carried out using other sequences or be carried out simultaneously.
From the foregoing, it will be observed that application management method provided by the embodiments of the present application, is answered according to the acquisition of the log of application
Multiple characteristic informations;The multiple characteristic information is learnt by self organizing neural network, to obtain the application
Self organizing neural network model;When the application enters running background, obtains the application and enter within a preset period of time
Effective number of run of front stage operation, effective number of run are that the application enters the operation duration of front stage operation and reaches the
The number of one preset duration;The fisrt feature coefficient of the application is calculated according to the current characteristic information of the application, it is described to work as
Preceding characteristic information includes effective number of run;It is determined from the feature coefficient matrix according to the fisrt feature coefficient
Second feature coefficient;Judge whether the application can be cleaned according to the second feature coefficient.The program is according to the of application
Two characteristic coefficients come judge it is described application whether can be cleaned, so as to accurately be sentenced according to the practical operation situation of the application
When the disconnected application described out can be cleaned, and when the application can be cleaned, close the application in time to discharge electronics
The memory of equipment, and then the EMS memory occupation of electronic equipment can be reduced, improve the operation fluency of electronic equipment.
The embodiment of the present application also provides a kind of application management device, which can integrate in the electronic device, the electronics
Equipment can be the equipment such as smart phone, tablet computer.
As shown in fig. 7, application management device 200 may include: acquisition module 201, study module 202, computing module
203, determining module 204 and judgment module 205.
Acquisition module 201 acquires multiple characteristic informations of the application for the log according to application.
Wherein, the application can be mounted in any application in electronic equipment, such as messaging application, more
Media application, game application, information application program or shopping application program etc..
Multiple characteristic informations of the application may include described using itself intrinsic characteristic information, such as described answer
Application type;Multiple characteristic informations of the application also may include feature caused by the application in the process of running
Information, for example, it is described apply the operation duration on backstage, in one day into when number, the upper once operation on foreground on backstage
Mode long or that enter backstage (such as by home key (i.e. HOME key) switching, be returned key switching or cut by other APP
Change) etc.;Multiple characteristic informations of the application can also include generated characteristic information in electronic equipment operational process, example
Such as electronic equipment puts out screen (go out screen) duration, bright screen duration, remaining capacity, network state or charged state.
In the operational process of electronic equipment, application management device 200 can remember the operation conditions of electronic equipment
Record.Such as can be recorded by journal file electronic equipment at the time of put out screen every time, at the time of bright screen, it is information about power, network-like
State, charged state etc..After above-mentioned application brings into operation, application management device 200 can also be to the operation shape of the application
Condition is recorded.Such as the journal file in electronic equipment can recorde the application and transport at the time of bring into operation, into backstage
At the time of row, the switching mode into backstage etc..
When application management device 200 receives application management request, acquisition module 201 can be according to the fortune of the application
Row record obtains multiple characteristic informations of the application.Wherein, the application management request can be the instruction institute by user
Triggering, it is also possible to the operation that electronic equipment voluntarily triggers.For example, timing can be set in electronic equipment, arrived whenever the time
Up to the timing of setting, electronic equipment i.e. voluntarily triggering application management operation.
Study module 202, for being learnt by self organizing neural network to the multiple characteristic information, to obtain
State the self organizing neural network model of application.
Wherein, self organizing neural network be by the inherent law and essential attribute in Automatic-searching sample, self-organizing, from
Adaptively change network parameter and structure.Self organizing neural network has input layer and computation layer.Input layer and computation layer difference
Including multiple nodes.
After acquisition module 201 collects multiple characteristic informations of application, study module 202 is by multiple features of the application
Input layer of the information input to self organizing neural network.Then, the self organizing neural network to the multiple characteristic information into
Row study, to obtain the self organizing neural network model of the application.Wherein, the self organizing neural network model includes described
The feature coefficient matrix of application, the feature coefficient matrix include multiple characteristic coefficients.
In some embodiments, study module 202 is for executing following steps:
It is calculated according to the connection weight of each node in collected multiple characteristic informations and self organizing neural network
Multiple characteristic coefficients of the application;
The self organizing neural network model of the application is obtained according to obtained multiple characteristic coefficients.
Specifically, after some node (input node) in the input layer of self organizing neural network gets characteristic information,
Study module 202 seven determines node best with the node (input node) matching in computation layer (meter according to the following formula
Operator node):
Formula seven:
Wherein, DistFromInput indicate computation layer in the node (input node) matching in input layer most
Good node (calculate node) arrives the distance between described input node, and I indicates the node (input being input in input layer
Node) characteristic information, W indicate field radius in all nodes connection weight, n expression be input to the node (input section
Point) characteristic information number.
Wherein, the connection weight W of all nodes eight is calculated according to the following formula in the radius of field:
Formula eight: W (t)=W (t-1)+Θ (t-1) L (t-1) (I (t-1)-W (t-1))
Wherein, at the time of when t expression is calculated, it is also spy calculated that W (t), which is t moment connection weight calculated,
Coefficient is levied, W (t-1) is the connection weight of (t-1) moment node, and Θ (t-1) is the field radius changing rate at (t-1) moment, L
It (t-1) is the learning rate at (t-1) moment, I (t-1) is to be input to the input node in self organizing neural network at (t-1) moment
Characteristic information.Respectively according to the following formula nine and formula ten calculate Θ (t-1) and L (t-1):
Formula nine:
Formula ten:
Wherein, e is natural constant (transcendental number), and e is definite value, and e is approximately equal to 2.71828.L0For fixed constant, such as L0It can
With value 0.3,0.5 etc..σ (t-1) indicates that the field radius at (t-1) moment, σ (t-1) 11 are calculated according to the following formula:
Formula 11:
Wherein, σ0For initial field radius, σ0For fixed constant, such as σ0It can be with value 5,10 etc..λ (t-1) is (t-
1) iteration coefficient at moment, λ (t-1) 12 are calculated according to the following formula:
Formula 12:
Wherein, λ0For primary iteration coefficient, λ0For fixed constant, such as λ0It can be with value 1000.
After acquisition module 201 collects multiple characteristic informations of above-mentioned application, study module 202 is according to formula seven to formula
12 are iterated operation, obtain multiple connection weight W (t) of the application.Connection weight W (t) namely it is characterized coefficient.Most
Afterwards, multiple connection weight W (t) the constitutive characteristic coefficient matrixes being calculated.The feature coefficient matrix includes multiple features
Coefficient.Multiple characteristic coefficients in the feature coefficient matrix and feature coefficient matrix and corresponding relationship, that is, structure between the time
At the self organizing neural network model of the application.
It should be noted that study module 202 can be more than in the self organizing neural network model of building application
Formula carries out the operation of a large amount of numbers.
Computing module 203, for when the application enters running background, according to the current characteristic information meter of the application
Calculate the fisrt feature coefficient of the application.
Wherein, when the application enters running background by front stage operation, application management device 200 can be to the application
It is made whether that the judgement that can be cleaned operates.
Specifically, when the application enters running background, computing module 203 acquires the current feature letter of the application
Breath.Wherein, current characteristic information may include the application class using itself intrinsic characteristic information, such as the application
Type;Current characteristic information also may include characteristic information caused by the application in the process of running, such as described apply
The operation duration on backstage, the number that backstage is entered in one day, the last operation duration on foreground or the mode into backstage
(such as switched by home key (i.e. HOME key), be returned key switching or switched by other APP) etc.;Current characteristic information
Can also include electronic equipment operational process in generated characteristic information, such as electronic equipment put out screen (go out screen) duration,
Bright screen duration, remaining capacity, network state or charged state etc..
Then, computing module 203 is carried out according to the current characteristic information of above-mentioned formula seven to 12 pairs of applications of formula
It calculates, to obtain the fisrt feature coefficient of the application.
In some embodiments, the current characteristic information of the application includes before the application enters within a preset period of time
Effective number of run of platform operation.The application management device 200 further includes obtaining module.The acquisition module for execute with
Lower step:
When the application enters running background, the application is obtained within a preset period of time into the effective of front stage operation
Number of run, effective number of run reach time of the first preset duration for the operation duration that the application enters front stage operation
Number.
Wherein, the preset time period can be the time range preset in the electronic device.For example, default
Period can be 10 hours, 24 hours etc..It is understood that preset time period is to end a time at current time
Range.First preset duration can be the duration numerical value preset in the electronic device.First preset duration table
Certain for showing application operates to the separation for effectively running and still running in vain.For example, the first preset duration can be 10 seconds, 1
Minute etc..Effective number of run is all numbers applied and enter front stage operation in the preset time period
In, operation duration reaches the number of first preset duration.
When the application enters running background, obtains module and obtain the application within a preset period of time into foreground fortune
Capable effective number of run.
In some embodiments, when the application enters running background, obtain it is described application within a preset period of time into
When entering effective number of run of front stage operation, the acquisition module is for executing following steps:
When the application enters running background, obtains the application and enter the first of front stage operation within a preset period of time
Number and the duration for entering front stage operation every time;
Determine that the application enters the duration of front stage operation and reaches the of the first preset duration from first number
Two numbers;
Second number is determined as effective number of run that the application enters front stage operation within a preset period of time.
Wherein, when the application enters running background, the acquisition module can be according to the log of the application
Obtain the duration that the application enters front stage operation into first number of front stage operation and every time within a preset period of time.Example
Such as, preset time period is 10 hours.Described apply in 10 hours is 5 times into first number of front stage operation, this 5 times entrance
The duration of front stage operation is respectively 30 seconds, 5 minutes, 2 minutes, 2 hours, 40 minutes.
Then, module is obtained respectively to carry out the application into the duration of front stage operation and the first preset duration each time
Compare, reaches the second of the first preset duration to determine that the application enters the duration of front stage operation from first number
Number.For example, the first preset duration is 1 minute, then in described first number 5 times, into effective number of run of front stage operation
Second number is 4 times.Then, it obtains module and second number is determined as the application within a preset period of time into foreground
Effective number of run of operation.
In some embodiments, determine that the application enters the duration of front stage operation and reaches from first number
Before second number of one preset duration, the acquisition module is also used to execute following steps:
Obtain the application type of the application;
Corresponding first preset duration is obtained according to the application type.
Wherein, different application types, such as social application, shopping application, music can be preset in electronic equipment
Using, Video Applications etc..Also, corresponding first preset duration can be arranged for each type of application in electronic equipment.Example
Such as, corresponding first preset duration of social application is 10 seconds, and corresponding first preset duration of shopping application is 1 minute, and music is answered
It is 30 seconds with corresponding first preset duration, corresponding first preset duration of Video Applications is 3 minutes.
The module that obtains can determine the application type of the application, and obtain corresponding the according to the application type
One preset duration.For example, the application is social application, then obtaining the first preset duration that module is got is 10 seconds.
Determining module 204, for determining the second spy from the feature coefficient matrix according to the fisrt feature coefficient
Levy coefficient.
Wherein, after the fisrt feature coefficient of the application is calculated in computing module 203, determining module 204 can basis
The fisrt feature coefficient and the self organizing neural network model of the application determine the second feature coefficient of the application.
Specifically, the self organizing neural network model of the application includes the feature coefficient matrix of the application.The spy
Levying includes multiple characteristic coefficients in coefficient matrix.Determining module 204 can be respectively by the fisrt feature coefficient and the feature
Multiple characteristic coefficients in coefficient matrix are compared, to determine from multiple characteristic coefficients in the feature coefficient matrix
Second feature coefficient.
In some embodiments, as shown in figure 8, determining module 204 includes: computational submodule 2041, determines submodule
2042。
Computational submodule 2041, for calculating separately the fisrt feature coefficient and the difference of the multiple characteristic coefficient
Absolute value;
Submodule 2042 is determined, for the corresponding characteristic coefficient of the smallest difference of absolute value to be determined as second feature system
Number.
Wherein, after the fisrt feature coefficient of the application is calculated in computing module 203, computational submodule 2041 respectively will
The fisrt feature coefficient is compared with multiple characteristic coefficients in the feature coefficient matrix, calculates the fisrt feature system
Several differences with the multiple characteristic coefficient, and calculate the absolute value of the difference.
After obtaining the absolute value of multiple differences, it is the smallest to determine that submodule 2042 is determined from the absolute value of multiple differences
One.Then, characteristic coefficient corresponding to the smallest difference of absolute value is determined as second feature coefficient.
Judgment module 205, for judging whether the application can be cleaned according to the second feature coefficient.
Wherein it is determined that judgment module 205 can be according to described after module 204 obtains the second feature coefficient of the application
Second feature coefficient is judged whether can be cleaned with the determination application.If the application can not be cleaned, retain institute
It states using continuation in running background, allows the process of the application resident in systems.If the application can be cleaned, can
To terminate the process of the application, to close the application, the memory that the application occupies is discharged.
In some embodiments, as shown in figure 9, judgment module 205 includes: acquisition submodule 2051, Comparative sub-module
2052, judging submodule 2053.
Acquisition submodule 2051, for obtaining the second preset duration;
Comparative sub-module 2052, for the second feature coefficient to be compared with second preset duration, with
To comparison result;
Judging submodule 2053, for judging whether the application can be cleaned according to the comparison result.
Wherein, the second preset duration can be the duration value preset in the electronic device.For example, second is default
Duration can be 10 minutes.After determining module 204 obtains the second feature coefficient of the application, acquisition submodule 2051 is from described
Second preset duration is transferred in electronic equipment.Then, Comparative sub-module 2052 is by the second feature coefficient and described the
Two preset durations are compared, to obtain comparison result.Wherein, comparison result is that the second feature coefficient and described second are pre-
If the size relation between duration.Comparison result includes that the second feature coefficient is less than or equal to second preset duration,
Or the second feature coefficient is greater than second preset duration.Then, judging submodule 2053 is according to the comparison result
Judge whether the application can be cleaned.
In some embodiments, acquisition submodule 2051 is for executing following steps:
At the time of determining that the second feature coefficient corresponds to according to the second feature coefficient;
The second preset duration, the default correspondence are obtained according to period locating for the moment and default corresponding relationship
Corresponding relationship of the relationship between period and the second preset duration.
Wherein, second feature coefficient is the characteristic coefficient determined from the self organizing neural network model of the application.
Second feature coefficient is the function about time t.Described in acquisition submodule 2051 can be determined according to the second feature coefficient
At the time of second feature coefficient corresponds to.
The corresponding relationship between period and the second preset duration can be preset in electronic equipment.For example, in one day
24 hours can be divided into 4 periods: 0:00~6:00,6:00~12:00,12:00~18:00,18:00~24:00.
Corresponding second preset duration can be set in each period.For example, corresponding second preset duration of 0:00~6:00 is 8 points
Clock, corresponding second preset duration of 6:00~12:00 are 10 minutes, and corresponding second preset duration of 12:00~18:00 is 15 points
Clock, corresponding second preset duration of 18:00~24:00 are 20 minutes.
After acquisition submodule 2051 is determined at the time of the second feature coefficient corresponds to, the moment institute is further determined that
The period at place.Then, second is obtained according to the corresponding relationship between period and period and the second preset duration to preset
Duration.
In some embodiments, judging submodule 2053 is for executing following steps:
When the second feature coefficient is less than or equal to second preset duration, judging result is that the application can not
It is cleaned;
When the second feature coefficient is greater than second preset duration, judging result is that the application can be cleaned.
Wherein, Comparative sub-module 2052 obtains the comparison result between the second feature coefficient and the second preset duration
Afterwards, judging submodule 2053 judges whether the application can be cleaned according to the comparison result.
Specifically, it when the second feature coefficient is less than or equal to second preset duration, indicates described and applies
Front stage operation may be again switched in the period of second preset duration, judging result is that the application can not at this time
It is cleaned.For example, second feature coefficient less than the second preset duration 10 minutes, indicates described and applies in next 10 minutes
Front stage operation may be again switched to by user, the application can not be cleaned at this time.
When the second feature coefficient is greater than second preset duration, indicates described and apply when described second is default
Front stage operation namely user will not be again switched in the long period will not reuse the application, at this time judgement knot
Fruit is that the application can be cleaned.For example, second feature coefficient is greater than the second preset duration 15 minutes, indicates described and apply
It will not be run again by user in next 15 minutes, the application can be cleaned at this time.Then, application management device
200 can close the application.
When it is implemented, the above modules can be used as independent entity to realize, any combination can also be carried out, is made
It is realized for same or several entities.
From the foregoing, it will be observed that application management device 200 provided by the embodiments of the present application, by acquisition module according to the operation of application
Record acquires multiple characteristic informations of the application;Study module by self organizing neural network to the multiple characteristic information into
Row study, to obtain the self organizing neural network model of the application;Module is obtained when the application enters running background, is obtained
The application is taken to enter effective number of run of front stage operation within a preset period of time, effective number of run is the application
Reach the number of the first preset duration into the operation duration of front stage operation;Computing module is believed according to the current signature of the application
Breath calculates the fisrt feature coefficient of the application, and the current characteristic information includes effective number of run;Determining module 204
Second feature coefficient is determined from the feature coefficient matrix according to the fisrt feature coefficient;Judgment module 205 is according to institute
It states second feature coefficient and judges whether the application can be cleaned.The program judges described according to the second feature coefficient of application
Using whether being cleaned, so as to be accurately judged to the application when can be with according to the practical operation situation of the application
It is cleaned, when the application can be cleaned, closes the application in time to discharge the memory of electronic equipment, and then can subtract
The EMS memory occupation of few electronic equipment, improves the operation fluency of electronic equipment.
The embodiment of the present application also provides a kind of electronic equipment.The electronic equipment can be smart phone, tablet computer etc. and set
It is standby.As shown in Figure 10, electronic equipment 300 includes processor 301 and memory 302.Wherein, 302 electricity of processor 301 and memory
Property connection.
Processor 301 is the control centre of electronic equipment 300, utilizes various interfaces and the entire electronic equipment of connection
Various pieces, by running or calling the computer program being stored in memory 302, and calling to be stored in memory 302
Interior data execute the various functions and processing data of electronic equipment, to carry out integral monitoring to electronic equipment.
In the present embodiment, processor 301 in electronic equipment 300 can according to following step, by one or one with
On the corresponding instruction of process of computer program be loaded into memory 302, and run by processor 301 and be stored in storage
Computer program in device 302, to realize various functions:
Multiple characteristic informations of the application are acquired according to the log of application;
The multiple characteristic information is learnt by self organizing neural network, to obtain the self-organizing mind of the application
Through network model, the self organizing neural network model includes the feature coefficient matrix of the application;
When the application enters running background, the application is obtained within a preset period of time into the effective of front stage operation
Number of run, effective number of run reach time of the first preset duration for the operation duration that the application enters front stage operation
Number;
The fisrt feature coefficient of the application, the current characteristic information are calculated according to the current characteristic information of the application
Including effective number of run;
Second feature coefficient is determined from the feature coefficient matrix according to the fisrt feature coefficient;
Judge whether the application can be cleaned according to the second feature coefficient.
In some embodiments, when the application enters running background, obtain it is described application within a preset period of time into
When entering effective number of run of front stage operation, processor 301 executes following steps:
When the application enters running background, obtains the application and enter the first of front stage operation within a preset period of time
Number and the duration for entering front stage operation every time;
Determine that the application enters the duration of front stage operation and reaches the of the first preset duration from first number
Two numbers;
Second number is determined as effective number of run that the application enters front stage operation within a preset period of time.
In some embodiments, determine that the application enters the duration of front stage operation and reaches from first number
Before second number of one preset duration, processor 301 also executes following steps:
Obtain the application type of the application;
Corresponding first preset duration is obtained according to the application type.
In some embodiments, the feature coefficient matrix includes multiple characteristic coefficients, according to the fisrt feature coefficient
When determining second feature coefficient from the feature coefficient matrix, processor 301 executes following steps:
Calculate separately the absolute value of the difference of the fisrt feature coefficient and the multiple characteristic coefficient;
The corresponding characteristic coefficient of the smallest difference of absolute value is determined as second feature coefficient.
In some embodiments, when judging whether the application can be cleaned according to the second feature coefficient, processor
301 execute following steps:
Obtain the second preset duration;
The second feature coefficient is compared with second preset duration, to obtain comparison result;
Judge whether the application can be cleaned according to the comparison result.
In some embodiments, when obtaining the second preset duration, processor 301 executes following steps:
At the time of determining that the second feature coefficient corresponds to according to the second feature coefficient;
The second preset duration, the default correspondence are obtained according to period locating for the moment and default corresponding relationship
Corresponding relationship of the relationship between period and the second preset duration.
In some embodiments, when judging whether the application can be cleaned according to the comparison result, processor 301 is held
Row following steps:
When the second feature coefficient is less than or equal to second preset duration, judging result is that the application can not
It is cleaned;
When the second feature coefficient is greater than second preset duration, judging result is that the application can be cleaned.
In some embodiments, the multiple characteristic information is learnt by self organizing neural network, to obtain
When stating the self organizing neural network model of application, processor 301 executes following steps:
It is calculated according to the connection weight of each node in collected multiple characteristic informations and self organizing neural network
Multiple characteristic coefficients of the application;
The self organizing neural network model of the application is obtained according to obtained multiple characteristic coefficients.
In some embodiments, according to each node in collected multiple characteristic informations and self organizing neural network
When connection weight calculates multiple characteristic coefficients of the application, processor 301 is calculated according to the following formula:
W (t)=W (t-1)+Θ (t-1) L (t-1) (I (t-1)-W (t-1))
Wherein, W (t) is the connection weight of t moment node, and W (t) is also t moment characteristic coefficient calculated, t table
At the time of showing when being calculated, W (t-1) is the connection weight of t-1 moment node, and Θ (t-1) is the field radius at (t-1) moment
Change rate, L (t-1) are the learning rate at (t-1) moment, and I (t-1) is input to defeated in self organizing neural network for (t-1) moment
The characteristic information of ingress.
Memory 302 can be used for storing computer program and data.Include in the computer program that memory 302 stores
The instruction that can be executed in the processor.Computer program can form various functional modules.Processor 301 is stored in by calling
The computer program of memory 302, thereby executing various function application and data processing.
In some embodiments, as shown in figure 11, electronic equipment 300 further include: radio circuit 303, display screen 304, control
Circuit 305, input unit 306, voicefrequency circuit 307, sensor 308 and power supply 309 processed.Wherein, processor 301 respectively with penetrate
Frequency circuit 303, display screen 304, control circuit 305, input unit 306, voicefrequency circuit 307, sensor 308 and power supply 309
It is electrically connected.
Radio circuit 303 is used for transceiving radio frequency signal, with by wireless communication with the network equipment or other electronic equipments into
Row communication.
Display screen 304 can be used for showing information input by user or be supplied to user information and electronic equipment it is each
Kind graphical user interface, these graphical user interface can be made of image, text, icon, video and any combination thereof.
Control circuit 305 and display screen 304 are electrically connected, and show information for controlling display screen 304.
Input unit 306 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.Wherein,
Input unit 306 may include fingerprint recognition mould group.
Voicefrequency circuit 307 can provide the audio interface between user and electronic equipment by loudspeaker, microphone.
Sensor 308 is for acquiring external environmental information.Sensor 308 may include ambient light sensor, acceleration
One of sensors such as sensor, gyroscope are a variety of.
All parts of the power supply 309 for electron equipment 300 are powered.In some embodiments, power supply 309 can pass through
Power-supply management system and processor 301 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 Figure 11, electronic equipment 300 can also include camera, bluetooth module etc., and details are not described herein.
From the foregoing, it will be observed that the embodiment of the present application provides a kind of electronic equipment, the electronic equipment is according to the log of application
Acquire multiple characteristic informations of the application;The multiple characteristic information is learnt by self organizing neural network, with
To the self organizing neural network model of the application;When the application enters running background, described apply when default is obtained
Between enter effective number of run of front stage operation in section, effective number of run is the operation that the application enters front stage operation
Duration reaches the number of the first preset duration;The fisrt feature system of the application is calculated according to the current characteristic information of the application
Number, the current characteristic information includes effective number of run;According to the fisrt feature coefficient from the characteristic coefficient square
Second feature coefficient is determined in battle array;Judge whether the application can be cleaned according to the second feature coefficient.Program root
Judge whether the application can be cleaned, according to the second feature coefficient of application so as to according to the actual motion of the application
Situation is accurately judged to when the application can be cleaned, and when the application can be cleaned, closes the application in time
To discharge the memory of electronic equipment, and then the EMS memory occupation of electronic equipment can be reduced, improve the operation fluency of electronic equipment.
The embodiment of the present application also provides a kind of storage medium, is stored with computer program in the storage medium, when the calculating
When machine program is run on computers, which executes application management method described in any of the above-described embodiment.
It should be noted that those of ordinary skill in the art will appreciate that whole in the various methods of above-described embodiment or
Part steps are relevant hardware can be instructed to complete by program, which can store in computer-readable storage medium
In matter, which be can include but is not limited to: read-only memory (ROM, Read Only Memory), random access memory
Device (RAM, Random Access Memory), disk or CD etc..
Application management method, device provided by the embodiment of the present application, storage medium and electronic equipment are carried out above
It is discussed in detail, specific examples are used herein to illustrate the principle and implementation manner of the present application, above embodiments
Illustrate to be merely used to help understand the present processes and its core concept;Meanwhile for those skilled in the art, according to this
The thought of application, there will be changes in the specific implementation manner and application range, in conclusion the content of the present specification is not answered
It is interpreted as the limitation to the application.
Claims (10)
1. a kind of application management method characterized by comprising
Multiple characteristic informations of the application are acquired according to the log of application;
The multiple characteristic information is learnt by self organizing neural network, to obtain the self-organizing feature map of the application
Network model, the self organizing neural network model include the feature coefficient matrix of the application;
When the application enters running background, first number that the application enters front stage operation within a preset period of time is obtained
And enter the duration of front stage operation every time;
Determine that the application enters the duration of front stage operation and reaches the second of the first preset duration from first number
Number;
Second number is determined as effective number of run that the application enters front stage operation within a preset period of time;
The fisrt feature coefficient of the application is calculated according to the current characteristic information of the application, the current characteristic information includes
Effective number of run;
Second feature coefficient is determined from the feature coefficient matrix according to the fisrt feature coefficient;
Judge whether the application can be cleaned according to the second feature coefficient.
2. application management method according to claim 1, which is characterized in that described to determine institute from first number
The duration for stating application into front stage operation reaches before second number of the first preset duration, further includes:
Obtain the application type of the application;
Corresponding first preset duration is obtained according to the application type.
3. according to claim 1 to 2 described in any item application management methods, which is characterized in that the feature coefficient matrix packet
Multiple characteristic coefficients are included, it is described that second feature coefficient is determined from the feature coefficient matrix according to the fisrt feature coefficient
The step of include:
Calculate separately the absolute value of the difference of the fisrt feature coefficient and the multiple characteristic coefficient;
The corresponding characteristic coefficient of the smallest difference of absolute value is determined as second feature coefficient.
4. according to claim 1 to 2 described in any item application management methods, which is characterized in that described special according to described second
Sign coefficient judges that the step of whether application can be cleaned includes:
Obtain the second preset duration;
The second feature coefficient is compared with second preset duration, to obtain comparison result;
Judge whether the application can be cleaned according to the comparison result.
5. application management method according to claim 4, which is characterized in that the step of the second preset duration of the acquisition wraps
It includes:
At the time of determining that the second feature coefficient corresponds to according to the second feature coefficient;
The second preset duration, the default corresponding relationship are obtained according to period locating for the moment and default corresponding relationship
For the corresponding relationship between period and the second preset duration.
6. application management method according to claim 4, which is characterized in that described according to comparison result judgement
Using whether can be cleaned the step of include:
When the second feature coefficient is less than or equal to second preset duration, judging result is that the application can not be clear
Reason;
When the second feature coefficient is greater than second preset duration, judging result is that the application can be cleaned.
7. a kind of application management device characterized by comprising
Acquisition module acquires multiple characteristic informations of the application for the log according to application;
Study module, for being learnt by self organizing neural network to the multiple characteristic information, to obtain the application
Self organizing neural network model, the self organizing neural network model includes the feature coefficient matrix of the application;
Module is obtained, enters foreground within a preset period of time for when the application enters running background, obtaining the application
First number of operation and the duration for entering front stage operation every time;Before determining that the application enters in first number
The duration of platform operation reaches second number of the first preset duration;Second number is determined as described apply in preset time
Enter effective number of run of front stage operation in section;
Computing module, it is described to work as calculating the fisrt feature coefficient of the application according to the current characteristic information of the application
Preceding characteristic information includes effective number of run;
Determining module, for determining second feature coefficient from the feature coefficient matrix according to the fisrt feature coefficient;
Judgment module, for judging whether the application can be cleaned according to the second feature coefficient.
8. application management device according to claim 7, which is characterized in that described to determine institute from first number
Before stating second number for reaching the first preset duration using the duration for entering front stage operation, the acquisition module is also used to:
Obtain the application type of the application;
Corresponding first preset duration is obtained according to the application type.
9. a kind of storage medium, which is characterized in that computer program is stored in the storage medium, when the computer program
When running on computers, so that the computer perform claim requires 1 to 6 described in any item application management methods.
10. a kind of electronic equipment, which is characterized in that including processor and memory, computer journey is stored in the memory
Sequence, the processor require 1 to 6 by calling the computer program stored in the memory, for perform claim
Application management method described in one.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711047015.3A CN107870791B (en) | 2017-10-31 | 2017-10-31 | Application management method, device, storage medium and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711047015.3A CN107870791B (en) | 2017-10-31 | 2017-10-31 | Application management method, device, storage medium and electronic equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107870791A CN107870791A (en) | 2018-04-03 |
CN107870791B true CN107870791B (en) | 2019-07-16 |
Family
ID=61752764
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711047015.3A Active CN107870791B (en) | 2017-10-31 | 2017-10-31 | Application management method, device, storage medium and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107870791B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107729081B (en) | 2017-09-30 | 2020-07-07 | Oppo广东移动通信有限公司 | Application management method and device, storage medium and electronic equipment |
CN111050385A (en) * | 2018-10-15 | 2020-04-21 | 中兴通讯股份有限公司 | Application cleaning method, device, equipment and readable storage medium |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20160091786A (en) * | 2015-01-26 | 2016-08-03 | 삼성전자주식회사 | Method and apparatus for managing user |
CN106155695A (en) * | 2016-07-28 | 2016-11-23 | 努比亚技术有限公司 | The removing control device and method of background application |
CN107729081B (en) * | 2017-09-30 | 2020-07-07 | Oppo广东移动通信有限公司 | Application management method and device, storage medium and electronic equipment |
CN107832848B (en) * | 2017-10-31 | 2019-09-24 | Oppo广东移动通信有限公司 | Application management method, device, storage medium and electronic equipment |
-
2017
- 2017-10-31 CN CN201711047015.3A patent/CN107870791B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN107870791A (en) | 2018-04-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107729081B (en) | Application management method and device, storage medium and electronic equipment | |
CN110032670B (en) | Method, device and equipment for detecting abnormity of time sequence data and storage medium | |
CN107678845B (en) | Application program control method and device, storage medium and electronic equipment | |
CN110738211A (en) | object detection method, related device and equipment | |
CN107832848B (en) | Application management method, device, storage medium and electronic equipment | |
CN107765853A (en) | Using method for closing, device, storage medium and electronic equipment | |
CN107885544B (en) | Application program control method, device, medium and electronic equipment | |
CN111797854B (en) | Scene model building method and device, storage medium and electronic equipment | |
CN108961267A (en) | Image processing method, picture processing unit and terminal device | |
CN107870791B (en) | Application management method, device, storage medium and electronic equipment | |
CN111798811A (en) | Screen backlight brightness adjusting method and device, storage medium and electronic equipment | |
CN107943570B (en) | Application management method and device, storage medium and electronic equipment | |
CN111800445B (en) | Message pushing method and device, storage medium and electronic equipment | |
CN108200282A (en) | Using startup method, apparatus, storage medium and electronic equipment | |
CN112052399A (en) | Data processing method and device and computer readable storage medium | |
CN111797867A (en) | System resource optimization method and device, storage medium and electronic equipment | |
CN111797849A (en) | User activity identification method and device, storage medium and electronic equipment | |
CN111797986A (en) | Data processing method, data processing device, storage medium and electronic equipment | |
CN108932704A (en) | Image processing method, picture processing unit and terminal device | |
CN107844375B (en) | Using method for closing, device, storage medium and electronic equipment | |
CN111797860B (en) | Feature extraction method and device, storage medium and electronic equipment | |
CN113360908A (en) | Data processing method, violation recognition model training method and related equipment | |
CN108093466A (en) | A kind of method, mobile terminal and server for controlling network switching | |
CN109064416A (en) | Image processing method, device, storage medium and electronic equipment | |
CN115357461B (en) | Abnormality detection method, abnormality detection device, electronic device, and computer-readable storage medium |
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 |
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. |
|
CB02 | Change of applicant information | ||
GR01 | Patent grant | ||
GR01 | Patent grant |