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

Using method for cleaning, device, storage medium and electronic equipment Download PDF

Info

Publication number
CN107807730B
CN107807730B CN201711050187.6A CN201711050187A CN107807730B CN 107807730 B CN107807730 B CN 107807730B CN 201711050187 A CN201711050187 A CN 201711050187A CN 107807730 B CN107807730 B CN 107807730B
Authority
CN
China
Prior art keywords
ridge regression
parameter
error
ridge
characteristics set
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
Application number
CN201711050187.6A
Other languages
Chinese (zh)
Other versions
CN107807730A (en
Inventor
曾元清
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong Oppo Mobile Telecommunications Corp Ltd
Original Assignee
Guangdong Oppo Mobile Telecommunications Corp Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangdong Oppo Mobile Telecommunications Corp Ltd filed Critical Guangdong Oppo Mobile Telecommunications Corp Ltd
Priority to CN201711050187.6A priority Critical patent/CN107807730B/en
Publication of CN107807730A publication Critical patent/CN107807730A/en
Priority to PCT/CN2018/110632 priority patent/WO2019085754A1/en
Application granted granted Critical
Publication of CN107807730B publication Critical patent/CN107807730B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
    • G06F1/26—Power supply means, e.g. regulation thereof
    • G06F1/32—Means for saving power
    • G06F1/3203—Power management, i.e. event-based initiation of a power-saving mode
    • G06F1/3234—Power saving characterised by the action undertaken
    • G06F1/329—Power saving characterised by the action undertaken by task scheduling
    • 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
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Image Analysis (AREA)

Abstract

The embodiment of the present application discloses a kind of application method for cleaning, device, storage medium and electronic equipment, wherein the embodiment of the present application obtains the multidimensional characteristic of application, the training characteristics set being applied；Ridge regression model is trained according to the training characteristics set of application, the ridge regression model after being trained；Obtain the multidimensional characteristic of application, the predicted characteristics set being applied；According to the ridge regression model after predicted characteristics set and training, whether prediction application can be cleared up；To clear up the application that can be cleared up；The automatic cleaning of application may be implemented in the program, improves the operation fluency of electronic equipment, reduces power consumption.

Description

Using method for cleaning, device, storage medium and electronic equipment
Technical field
This application involves fields of communication technology, and in particular to a kind of application method for cleaning, device, storage medium and electronics are set It is standby.
Background technique
Currently, on the electronic equipments such as smart phone, it will usually have multiple applications while run, wherein one is applied preceding Platform operation, other application is in running background.If not clearing up the application of running background for a long time, will lead to electronic equipment can Become smaller with memory, central processing unit (central processing unit, CPU) occupancy it is excessively high, cause electronic equipment to occur The problems such as speed of service is slack-off, Caton, power consumption is too fast.It solves the above problems therefore, it is necessary to provide a kind of method.
Summary of the invention
In view of this, the embodiment of the present application provides a kind of application method for cleaning, device, storage medium and electronic equipment, It can be improved the operation fluency of electronic equipment, reduce power consumption.
In a first aspect, the embodiment of the present application provide it is a kind of using method for cleaning, comprising:
The multidimensional characteristic for obtaining application, obtains the training characteristics set of the application；
Ridge regression model is trained according to the training characteristics set of the application, the ridge regression mould after being trained Type；
The multidimensional characteristic for obtaining the application obtains the predicted characteristics set of the application；
According to the ridge regression model after the predicted characteristics set and the training, predict whether the application can be clear Reason.
Second aspect, the embodiment of the present application provide a kind of using cleaning plant, comprising:
Training characteristics acquiring unit obtains the training characteristics set of the application for obtaining the multidimensional characteristic of application；
Training unit is trained for being trained according to the training characteristics set of the application to ridge regression model Ridge regression model afterwards；
Predicted characteristics acquiring unit obtains the predicted characteristics collection of the application for obtaining the multidimensional characteristic of the application It closes；
Predicting unit, for according to the ridge regression model after the predicted characteristics set and the training, described in prediction Using whether can clearing up.
The third aspect, storage medium provided by the embodiments of the present application, is stored thereon with computer program, when the computer When program is run on computers, so that the computer is executed as what the application any embodiment provided applies method for cleaning.
Fourth aspect, electronic equipment provided by the embodiments of the present application, including processor and memory, the memory have meter Calculation machine program, the processor is by calling the computer program, for executing as what the application any embodiment provided answers Use method for cleaning.
The embodiment of the present application obtains the multidimensional characteristic of application, the training characteristics set being applied；According to the training of application Characteristic set is trained ridge regression model, the ridge regression model after being trained；The multidimensional characteristic for obtaining application, is answered Predicted characteristics set；According to the ridge regression model after predicted characteristics set and training, whether prediction application can be cleared up；With Just the application that can be cleared up is cleared up；The automatic cleaning of application may be implemented in the program, improves the operation stream of electronic equipment Smooth degree, reduces power consumption.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, 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 application scenarios schematic diagram provided by the embodiments of the present application using method for cleaning.
Fig. 2 is a flow diagram provided by the embodiments of the present application using method for cleaning.
Fig. 3 is another flow diagram provided by the embodiments of the present application using method for cleaning.
Fig. 4 is a structural schematic diagram provided by the embodiments of the present application using cleaning plant.
Fig. 5 is another structural schematic diagram provided by the embodiments of the present application using cleaning plant.
Fig. 6 is a structural schematic diagram of electronic equipment provided by the embodiments of the present application.
Fig. 7 is another structural schematic diagram of electronic equipment provided by the embodiments of the present application.
Specific embodiment
Schema is please referred to, wherein identical component symbol represents identical component, the principle of the application is to implement one It is illustrated in computing environment appropriate.The following description be based on illustrated by the application specific embodiment, should not be by It is considered as limitation the application other specific embodiments not detailed herein.
In the following description, the specific embodiment of the application will refer to the step as performed by one or multi-section computer And symbol illustrates, unless otherwise stating clearly.Therefore, these steps and operation will have to mention for several times is executed by computer, this paper institute The computer execution of finger includes by representing with the computer processing unit of the electronic signal of the data in a structuring pattern Operation.This operation is converted at the data or the position being maintained in the memory system of the computer, reconfigurable Or in addition change the running of the computer in mode known to the tester of this field.The maintained data structure of the data For the provider location of the memory, there is the specific feature as defined in the data format.But the application principle is with above-mentioned text Word illustrates that be not represented as a kind of limitation, this field tester will appreciate that plurality of step and behaviour as described below Also it may be implemented in hardware.
Term as used herein " module " can regard the software object to execute in the arithmetic system as.It is as described herein Different components, module, engine and service can be regarded as the objective for implementation in the arithmetic system.And device as described herein and side Method can be implemented in the form of software, can also be implemented on hardware certainly, within the application protection scope.
Term " first ", " second " and " third " in the application etc. are for distinguishing different objects, rather than for retouching State particular order.In addition, term " includes " and " having " and their any deformations, it is intended that cover and non-exclusive include. Such as contain series of steps or module process, method, system, product or equipment be not limited to listed step or Module, but some embodiments further include the steps that not listing or module or some embodiments further include for these processes, Method, product or equipment intrinsic other steps or module.
Referenced herein " embodiment " is it is meant that a particular feature, structure, or characteristic described can wrap in conjunction with the embodiments It is contained at least one embodiment of the application.Each position in the description occur the phrase might not each mean it is identical Embodiment, nor the independent or alternative embodiment with other embodiments mutual exclusion.Those skilled in the art explicitly and Implicitly understand, embodiment described herein can be combined with other embodiments.
The embodiment of the present application provides a kind of using method for cleaning, this can be the application using the executing subject of method for cleaning The background application cleaning plant that embodiment provides, or it is integrated with the electronic equipment for applying cleaning plant, wherein the application is clear Reason device can be realized by the way of hardware or software.Wherein, electronic equipment can be smart phone, tablet computer, the palm The equipment such as upper computer, laptop or desktop computer.
Referring to Fig. 1, Fig. 1 is the application scenarios schematic diagram provided by the embodiments of the present application using method for cleaning, with application For cleaning plant integrates in the electronic device, the multidimensional characteristic of the available application of electronic equipment, the training spy being applied Collection is closed；Ridge regression model is trained according to the training characteristics set of application, the ridge regression model after being trained；It obtains The multidimensional characteristic of application, the predicted characteristics set being applied；Ridge regression model according to predicted characteristics set and after training, Whether prediction application can clear up.In addition, electronic equipment can be cleared up with the application that can be cleared up.
Specifically, such as shown in Fig. 1, to judge that the application program a (such as mailbox application, game application) of running background is It is no can clear up for, can in historical time section, the multidimensional characteristic of acquisition applications a (such as using a running background when Long, temporal information using a operation etc.), the characteristic set for a that is applied (such as is transported using a on backstage according to characteristic set Capable duration, using temporal information of a operation etc.) ridge regression model is trained, the ridge regression model after being trained；Root It is predicted that the time (such as t) the corresponding multidimensional characteristic of acquisition applications (such as t moment application a in the duration of running background, using a The temporal information etc. of operation), the predicted characteristics set for a that is applied；According to the ridge regression mould after predicted characteristics set and training Whether type prediction can clear up using a.In addition, electronic equipment is cleared up using a when prediction can be cleared up using a.
Referring to Fig. 2, Fig. 2 is the flow diagram provided by the embodiments of the present application using method for cleaning.The application is implemented What example provided can be such that using the detailed process of method for cleaning
201, the multidimensional characteristic of application, the training characteristics set being applied are obtained.
Application mentioned by the embodiment of the present application can be any one application installed on electronic equipment, such as handle official business Using, communications applications, game application, shopping application etc..Wherein, using the application that may include front stage operation, i.e. foreground application, It also may include the application of running background, i.e. background application.
In one embodiment, it can receive using cleaning request, request cleared up according to application and determines application for clearance, so Afterwards, the multidimensional characteristic for obtaining application, the training characteristics set being applied.
Specifically, the multidimensional characteristic of application can be obtained from property data base, wherein when multidimensional characteristic can be history Between collected multidimensional characteristic namely history multidimensional characteristic.The a variety of spies applied in historical time are stored in property data base Sign.
Wherein, training characteristics set may include the multidimensional characteristic of application, that is, the multiple features applied.
Wherein, the multidimensional characteristic of application has the dimension of certain length, and the corresponding characterization of the parameter in each of which dimension is answered A kind of characteristic information, the i.e. multidimensional characteristic breath are made of multiple features.Multiple feature may include related using itself Characteristic information, such as: application is cut into the duration on backstage；Using during being cut into backstage, duration is shielded in going out for electronic equipment；It answers With the number for entering foreground；Using the time for being in foreground；Using in backstage time, using enter backstage mode, example It such as switched by homepage key (home key), be returned key and switch into, switched by other application；The type of application, Including level-one (common application), second level (other application) etc..
The multidimensional characteristic information can also include using place electronic equipment correlated characteristic information, such as: electronics is set Standby going out is shielded time, bright screen time, current electric quantity, and whether the wireless network connection state of electronic equipment, electronic equipment is charging State etc..
Wherein, the training sample of application includes the multidimensional characteristic of application.The multidimensional characteristic can be in historical time section, The multiple features acquired according to predeterminated frequency.Historical time section, such as can be over 7 days, 10 days；Predeterminated frequency, such as can To be that acquisition in every 10 minutes is primary, per half an hour acquisition is primary.It is understood that the multidimensional characteristic number of the application of one acquisition According to one training characteristics set of composition.
In one embodiment, can be by the multidimensional characteristic information of application for convenient for application cleaning, the unused direct table of numerical value The characteristic information shown is come out with specific numerical quantization, such as is believed for this feature of the wireless network connection status of electronic equipment Breath, can indicate normal state with numerical value 1, indicate abnormal state with numerical value 0 (vice versa)；For another example being directed to electronics Whether equipment can indicate charged state with numerical value 1, indicate uncharged state with numerical value 0 in this characteristic information of charged state (vice versa).
202, ridge regression model is trained according to the training characteristics set of application, the ridge regression mould after being trained Type.
Wherein, ridge regression model can a kind of machine learning algorithm, ridge regression (ridge regression, Tikhonov Regularization it is a kind of Biased estimator homing method for being exclusively used in the analysis of synteny data that) algorithm, which is also known as ridge regression, Substantially a kind of least squares estimate of improvement, by abandoning the unbiasedness of least square method, to lose partial information, drop Low precision is that cost acquisition regression coefficient more meets practical, more reliable homing method, is better than to the fitting of ill data Least square method.
In the embodiment of the present application, ridge regression model can use to predict to apply and whether can clear up, wherein ridge regression model Output include can clear up or can not clear up.When that whether can be cleared up using ridge regression model prediction application, need using existing Characteristic information model is trained, promote the accuracy of prediction.
In one embodiment, the mistake of the ridge regression parameter of ridge regression model is just to solve for the process of ridge regression model training Journey, for example, ridge regression parameter needed for can first calculating ridge regression model, then, based on the ridge regression parameter to ridge regression Model is configured.For example, step " is trained ridge regression model according to the training sample of application, stating after being trained Ridge regression model " may include:
Establish the error judgment function of ridge regression model；
The target ridge regression parameter of ridge regression model is obtained according to training characteristics set and error judgment function, target ridge is returned Returning parameter includes ridge parameter and regression parameter；
According to the ridge regression model after target ridge regression parameter and ridge regression model training.
Wherein, ridge regression parameter may include ridge parameter and regression parameter, ridge regression (Ridge Regression) be Increase regular terms on the basis of square error, by determining that the value of λ can to reach balance between variance and deviation: with The increase of λ, model variance reduces and deviation increases.Ridge parameter can be able to be to be solved with regularization parameter λ, the regression parameter The model parameter w of ridge regression model.
In the embodiment of the present application, error judgment function is the loss function of ridge regression model, for calculating ridge regression model In the output valve on sample and the error between true value.
In one embodiment, the error judgment function of ridge regression model may include such as minor function:
Wherein, λ is ridge parameter, i.e. regularization parameter, and x is the feature of sample, and w is the regression parameter of ridge regression model, and n is The dimension of feature.
In one embodiment, can the error judgment function to ridge regression model deform, obtain regression parameter acquisition Then function obtains function based on regression parameter to obtain ridge regression parameter.For example, can ask error judgment function It leads, obtains function to obtain regression parameter, then, function is obtained based on the regression parameter and training characteristics set obtains ridge regression Parameter.
For example, the error judgment function of ridge regression model may include such as minor function:
Derivation can be carried out to error judgment function, obtain function:
2XT(Y-XW) -2 λ W, X are characterized the matrix or vector of x, XTFor the transposition of X, Y is the matrix or vector of y；
Then, 2X is enabledT(Y-XW) -2 λ W etc. zero, available following regression parameter calculation formula:
Wherein,For regression parameter to be solved.
After obtaining regression parameter calculation formula, regression parameter can be calculated based on the formula and training characteristics setFinally obtain ridge parameter λ and corresponding regression parameter
In one embodiment, in order to promote forecasting accuracy, multiple groups ridge regression parameter can be calculated, then, is chosen most Suitable ridge regression parameter.For example, step " obtains the target of ridge regression model according to training characteristics set and error judgment function Ridge regression parameter " may include:
Multiple groups ridge regression parameter is obtained according to error judgment function, ridge regression parameter includes: ridge parameter and regression parameter；
According to training characteristics set, ridge regression parameter and error judgment function, the training characteristics under ridge regression parameter are obtained Gather the error for ridge regression model, obtains the corresponding error of every group of ridge regression parameter；
According to the corresponding error of every group of ridge regression parameter, corresponding target ridge regression ginseng is chosen from multiple groups ridge regression parameter Number；
According to the ridge regression model after target ridge regression parameter and ridge regression model training.
Wherein, the corresponding error of ridge regression parameter is the ridge regression model under the ridge regression parameter, inputs training sample set Close the error between the predicted value obtained and true value.
For example, available ridge regression parameter Wherein, m can be the positive integer greater than 2, can set according to actual needs, for example, 20,30,40 ....
Then, according to training characteristics set, ridge regression parameterAnd error judgment function, it obtains at this Group regression parameterLower training characteristics set obtains every group of ridge regression parameter for the error Fk of ridge regression model Corresponding error such as F1, F2 ... Fk ... Fm.Based on the corresponding error F of every group of ridge regression parameter from ridge regression parameterChoose corresponding target ridge regression parameter
In one embodiment, can the error judgment function to ridge regression model deform, obtain regression parameter acquisition Then function obtains function and multiple default ridge parameter λ based on regression parameter to obtain regression parameterObtain multiple groups ridge Regression parameterFor example, derivation can be carried out to error judgment function, function is obtained to obtain regression parameter, so Afterwards, function is obtained based on the regression parameter and training characteristics set obtains ridge regression parameter.
For example, the error judgment function of ridge regression model may include such as minor function:
Derivation can be carried out to error judgment function, obtain function:
2XT(Y-XW) -2 λ W, X are characterized the matrix or vector of x, XTFor the transposition of X, Y is the matrix or vector of y；
Then, 2X is enabledT(Y-XW) -2 λ W etc. zero, available following regression parameter calculation formula:
Wherein,For regression parameter to be solved.
After obtaining regression parameter calculation formula, recurrence can be calculated based on the formula and multiple default ridge parameter λ ParameterFinally obtain ridge parameter λ and corresponding regression parameter
For example, the value of initialization ridge parameter λ is 1, formula is utilizedIt is corresponding that calculating acquires λ=1Value；λ adds 1, reuses formulaIt is corresponding to acquire λ=2Value；λ adds 1 again, reuses formulaIt is corresponding to acquire λ=3Value ... is corresponding until acquiring λ=mValue, such as m=20.At this point, Can obtain such as 20 groups of m group it is differentValue, and then obtain such as 20 groups of m group
In one embodiment, training characteristics set in order to accuracy and is rapidly obtained for ridge regression model Training characteristics set can be divided into multiple sub- training characteristics set by error, obtained each sub- training characteristics and be integrated into ridge regression For the error f of ridge regression model under parameter, then, it is integrated under ridge regression parameter based on each sub- training characteristics for ridge regression The error of model obtains entire training characteristics and is integrated into the ridge regression parameter of error F under to(for) ridge regression model.
For example, step " according to training characteristics set, ridge regression parameter and error judgment function, is obtained in ridge regression parameter Error of the lower training characteristics set for ridge regression model " may include:
Training characteristics set is divided into multiple sub- training characteristics set；
According to sub- training characteristics set, ridge regression parameter and error judgment function, the son instruction under ridge regression parameter is obtained Practice set for the sub- error of ridge regression model, obtains the corresponding sub- error of every sub- training characteristics set；
The corresponding sub- error of every sub- training characteristics set, obtains the training characteristics set under ridge regression parameter and ridge is returned Return the error of model.
Wherein, sub- training characteristics set division numbers can be set according to actual needs, such as 10,20 etc..In In one embodiment, to promote the accuracy that error obtains, the feature quantity that sub- training characteristics set includes is equal, will also train Characteristic set is divided into multiple sub- training characteristics set.
For example, training characteristics set D can be divided into M sub- training characteristics set, obtain sub- training characteristics set D1, D2……DM；Wherein, M is the positive integer greater than 1.Then, according to error judgment function and ridge regression parameter, every height is calculated Training characteristics are integrated into the sub- error under ridge regression parameter for ridge regression model, if D1 is in ridge regression parameter Under for ridge regression model sub- error f11, D2 in ridge regression parameterUnder for ridge regression model son accidentally Poor f12 ... DM is in ridge regression parameterUnder for ridge regression model sub- error f1M, based on every height instruct Practice characteristic set this in ridge regression parameterUnder for ridge regression model sub- error, i.e. f11, f12 ... F1M obtains training characteristics D in ridge regression parameterUnder for ridge regression model error F1.
Then, according to error judgment function and next group of ridge regression parameter, every sub- training characteristics is calculated and are integrated into ridge For the sub- error of next group of ridge regression model under regression parameter, if D1 is in ridge regression parameter Under for ridge return Return sub- error f21, D2 of model in ridge regression parameterUnder for ridge regression model sub- error f22 ... DM is in ridge regression parameterUnder for ridge regression model sub- error f2M, based on every sub- training characteristics set This in ridge regression parameterUnder for ridge regression model sub- error, i.e. f21, f22 ... f2M obtain training Feature D is in ridge regression parameter Under for ridge regression model error F2.
And so on, training characteristics can be calculated and be integrated into m group ridge regression parameter for the error of ridge regression model, obtained To error F1, F2 ... Fm.
The embodiment of the present application can be obtained after obtaining the corresponding sub- error of every sub- training characteristics set based on sub- error A training characteristics set is rounded for the error of ridge regression model, the acquisition modes can there are many.For example, in an embodiment In, in order to promote the accuracy of error, the average value of sub- error can be calculated, then, it is special that entire training is obtained based on average value The error for ridge regression model is closed in collection.It " according to the corresponding sub- error of every sub- training characteristics set, obtains for example, step Error of the training characteristics set for ridge regression model under ridge regression parameter " may include:
According to the corresponding sub- error of every sub- training characteristics set, the mean error of sub- training characteristics set is obtained；
Error of the training characteristics set for ridge regression model under ridge regression parameter is obtained according to mean error.
In one embodiment, can using the mean error as under ridge regression parameter training characteristics set for ridge regression The error of model.
For example, being with ridge regression parameterFor, in the case where calculating each son for the son of ridge regression model Error f11, D2 is in ridge regression parameterUnder for ridge regression model sub- error f12 ... DM is in ridge regression ParameterUnder for ridge regression model sub- error f1M, being integrated into based on every sub- training characteristics should be in ridge time Return parameterUnder for ridge regression model sub- error, i.e. after f11, f12 ... f1M, average mistake can be calculated Poor f '=(f11+f12+ ...+f1M)/M；The f ' is training characteristics D in ridge regression parameterUnder for ridge The error F1 of regression model.
In one embodiment, in order to promote parameter accuracy and accuracy of forecast, every group of ridge regression ginseng can obtained After the corresponding error of number, the minimum corresponding ridge regression parameter of error can be chosen and joined as the target ridge regression of ridge regression model Number, i.e. final argument.
For example, after obtaining corresponding error such as F1, F2 ... the Fk ... Fm of every group of ridge regression parameter, it is assumed that Fk is minimum, At this point it is possible to choose the corresponding ridge regression parameter of FkTarget ridge regression parameter as ridge regression model.
It below will be 20 groups with ridge regression parameter, sub- training characteristics collective number is 10 to introduce mesh according to foregoing description The selection process of ridge regression parameter namely the training process of ridge regression model are marked, as follows:
(1), the error judgment function of ridge regression is established are as follows:
To derivation is carried out, as a result are as follows:
2XT(Y-XW)-2λW
Enabling its value is 0 value that can acquire w are as follows:
(2), the value for initializing λ is 1, according in (3) stepFormula calculating acquires correspondingValue.
(3), λ adds 1, repeat (2) step acquire 20 groups it is differentValue；
(4), characteristic set is divided into 10 equal parts, selected in (3) stepA numerical value, following error judgment formula point Different error amounts of each subcharacter set for ridge regression for not calculating 10 equal parts, obtain 10 different error amounts:
Then the average error value by each subcharacter set of 10 equal parts for the error amount of ridge regression is calculated, and will averagely be missed Difference is as characteristic set in selectionWith under λ to the error of ridge regression；
(5), (4) step is repeated, it is different at 20 groups to calculate separately out characteristic setFor the feature of ridge regression under value Error；
(6), the 20 groups of characteristic errors acquired from (5) are minimized correspondingAnd λ value, it shouldIt is ridge regression with λ value Fitting obtains ridge regression parameter, the i.e. parameter of ridge regression model final choice.
(1)-(6) can calculate the corresponding ridge regression parameter of each application through the above steps.
203, the multidimensional characteristic of application, the predicted characteristics set being applied are obtained.
For example, can be according to the multidimensional characteristic of predicted time acquisition applications as forecast sample.
Wherein, predicted time can be set according to demand, such as can be current time.
For example, can predicted time point acquisition applications multidimensional characteristic as forecast sample.
In the embodiment of the present application, the multidimensional characteristic acquired in step 201 and 203 is same type feature, such as: application is cut Enter the duration to backstage；Using during being cut into backstage, duration is shielded in going out for electronic equipment；Using the number for entering foreground；Using Time in foreground；Using the mode for entering backstage.
204, according to the ridge regression model after predicted characteristics set and training, whether prediction application can be cleared up.
For example, can be calculated based on ridge regression model and predicted characteristics set using the probability that can be cleared up, when probability is big When some threshold value, determine that the application can clear up.
From the foregoing, it will be observed that the embodiment of the present application obtains the multidimensional characteristic of application, the training characteristics set being applied；According to answering Training characteristics set is trained ridge regression model, the ridge regression model after being trained；The multidimensional for obtaining application is special Sign, the predicted characteristics set being applied；According to the ridge regression model after predicted characteristics set and training, whether prediction application It can clear up；To clear up the application that can be cleared up；The automatic cleaning of application may be implemented in the program, improves electronic equipment Operation fluency, reduce and power consumption and save resource.
Further, due in characteristic set, including reflecting that user is believed using multiple features of the behavioural habits of application Breath, therefore the embodiment of the present application can make the cleaning to corresponding application more personalized and intelligent.
Further, it is realized based on ridge regression model using cleaning prediction, the accurate of user's behavior prediction can be promoted Property, and then improve the accuracy of cleaning.In addition, the embodiment of the present application can also calculate multiple groups ridge regression when to model training Parameter, and using characteristic error choose error most under ridge regression parameter, using the final argument as ridge regression model, Ke Yijin Ridge regression model is promoted to one step to the accuracy of application cleaning prediction.
Below by the basis of the method that above-described embodiment describes, the method for cleaning of the application is described further.Ginseng Fig. 3 is examined, this may include: using method for cleaning
301, the multidimensional characteristic of application, the training characteristics set being applied are obtained.
For example, obtaining the multidimensional characteristic of application from property data base, wherein multidimensional characteristic can acquire for historical time The multidimensional characteristic namely history multidimensional characteristic arrived.The various features applied in historical time are stored in property data base.
Wherein, training characteristics set may include the multidimensional characteristic of application, that is, the multiple features applied.
Wherein, the multidimensional characteristic of application has the dimension of certain length, and the corresponding characterization of the parameter in each of which dimension is answered A kind of characteristic information, the i.e. multidimensional characteristic breath are made of multiple features.Multiple feature may include related using itself Characteristic information, such as: application is cut into the duration on backstage；Using during being cut into backstage, duration is shielded in going out for electronic equipment；It answers With the number for entering foreground；Using the time for being in foreground；Using in backstage time, using enter backstage mode, example It such as switched by homepage key (home key), be returned key and switch into, switched by other application；The type of application, Including level-one (common application), second level (other application) etc..
The multidimensional characteristic information can also include using place electronic equipment correlated characteristic information, such as: electronics is set Standby going out is shielded time, bright screen time, current electric quantity, and whether the wireless network connection state of electronic equipment, electronic equipment is charging State etc..
One specific training characteristics set can be as follows, the characteristic information including multiple dimensions (30 dimensions), needs It is noted that characteristic information as follows is only for example, and in practice, the characteristic information that a training characteristics set is included Quantity, can be more than information as follows quantity, can also be less than information as follows quantity, the specific features taken Information can also be different from characteristic information as follows, are not especially limited herein.
The APP last time cuts the duration of backstage till now；
The APP last time cut backstage till now during in, add up screen shut-in time length；
Enter the number on foreground in APP mono- day (by statistics daily)；
(day off is separately counted by working day, day off) enters the number on foreground in APP mono- day, if than current predictive Time is working day, then this feature is average every workday for counting on working day in foreground access times using numerical value；
The time on foreground is in (by statistics daily) in APP mono- day；
Backstage APP counts gained immediately following the number that is opened after current foreground APP, regardless of day off on working day；
Backstage APP divides day off on working day to count immediately following the number that is opened after current foreground APP；
The mode that target APP is switched is divided into and switching by the switching of home key, by the switching of recent key, by other APP；
Target APP level-one type (common application)；
Target APP two-level type (other application)；
Mobile phone screen, which goes out, shields the time；
The mobile phone screen bright screen time；
Current screen light on and off state；
Current electricity；
Current wifi state；
The App last time cuts the duration of backstage till now；
The APP last time is used duration on foreground；
The APP upper last time is used duration on foreground；
The upper last time is used duration on foreground on APP；
If 6 periods an of natural gift, every section 4 hours, current predictive time point is 8:30 in morning, then is in the 3rd section, then What this feature indicated is the time span that target app is used in this period of 8:00~12:00 daily；
Current foreground APP enters backstage and enters foreground by the Mean Time Between Replacement counted daily to target APP；
Current foreground APP entered during backstage enters foreground to target APP by the average screen fall time counted daily；
Target APP is in first bin of backstage dwell histogram (0-5 minutes corresponding number accountings)；
Target APP is in first bin of backstage dwell histogram (5-10 minutes corresponding number accountings)；
Target APP is in first bin of backstage dwell histogram (10-15 minutes corresponding number accountings)；
Target APP is in first bin of backstage dwell histogram (15-20 minutes corresponding number accountings)；
Target APP is in first bin of backstage dwell histogram (15-20 minutes corresponding number accountings)；
Target APP is in first bin of backstage dwell histogram (25-30 minutes corresponding number accountings)；
Target APP is in first bin of backstage dwell histogram (corresponding number accounting after 30 minutes)；
Currently whether have and is charging.
302, the error judgment function for establishing ridge regression model obtains corresponding regression parameter according to error judgment function and obtains Take function.
Wherein, ridge regression model can a kind of machine learning algorithm, ridge regression (ridge regression, Tikhonov Regularization it is a kind of Biased estimator homing method for being exclusively used in the analysis of synteny data that) algorithm, which is also known as ridge regression, Substantially a kind of least squares estimate of improvement, by abandoning the unbiasedness of least square method, to lose partial information, drop Low precision is that cost acquisition regression coefficient more meets practical, more reliable homing method, is better than to the fitting of ill data Least square method.
For example, the error judgment function of ridge regression model may include such as minor function:
Wherein, λ is ridge parameter, i.e. regularization parameter, and x is the feature of sample, and w is the regression parameter of ridge regression model, and n is The dimension of feature.
Derivation can be carried out to error judgment function, obtain function:
2XT(Y-XW) -2 λ W, X are characterized the matrix or vector of x, XTFor the transposition of X, Y is the matrix or vector of y；
Then, 2X is enabledT(Y-XW) -2 λ W etc. zero, available following regression parameter calculation formula:
Wherein,For regression parameter to be solved.
303, function is obtained according to multiple default ridge parameters and regression parameter, obtains corresponding multiple regression parameters, obtains To multiple groups ridge regression parameter.
Wherein, ridge regression parameter includes ridge parameter λ and corresponding regression parameter
For example, the value of initialization ridge parameter λ is 1, formula is utilizedIt is corresponding that calculating acquires λ=1Value；λ adds 1, reuses formulaIt is corresponding to acquire λ=2Value；λ adds 1 again, reuses formulaIt is corresponding to acquire λ=3Value ... is corresponding until acquiring λ=mValue, such as m=20.At this point, Can obtain such as 20 groups of m group it is differentValue, and then obtain such as 20 groups of m group
304, training characteristics set is divided into multiple sub- training characteristics set.
Wherein, sub- training characteristics set division numbers can be set according to actual needs, such as 10,20 etc..In In one embodiment, to promote the accuracy that error obtains, the feature quantity that sub- training characteristics set includes is equal, will also train Characteristic set is divided into multiple sub- training characteristics set.
305, it according to sub- training characteristics set, ridge regression parameter and error judgment function, obtains under ridge regression parameter Sub- error of the son training set for ridge regression model.
For example, training characteristics set D can be divided into M sub- training characteristics set, obtain sub- training characteristics set D1, D2……DM；Wherein, M is the positive integer greater than 1.Then, according to error judgment function and ridge regression parameter, every height is calculated Training characteristics are integrated into the sub- error under ridge regression parameter for ridge regression model, if D1 is in ridge regression parameter Under for ridge regression model sub- error f11, D2 in ridge regression parameterUnder for ridge regression model son accidentally Poor f12 ... DM is in ridge regression parameterUnder for ridge regression model sub- error f1M, obtain every height instruction Practice characteristic set this in ridge regression parameterUnder for ridge regression model sub- error, f11, f12 ... f1M。
306, according under ridge regression parameter, every sub- training set conjunction is for the sub- error of ridge regression model, and acquisition is in ridge time Training characteristics set under parameter is returned to repeat step 305 and 306 and obtain under every group of ridge regression parameter the error of ridge regression model Error of the training characteristics for ridge regression model.
For example, obtaining the mean error of sub- training characteristics set according to the corresponding sub- error of every sub- training characteristics set； Error of the training characteristics set for ridge regression model under ridge regression parameter is obtained according to mean error.
In one embodiment, can using the mean error as under ridge regression parameter training characteristics set for ridge regression The error of model.
For example, being with ridge regression parameterFor, in the case where calculating each son for the son of ridge regression model Error f11, D2 is in ridge regression parameterUnder for ridge regression model sub- error f12 ... DM is in ridge regression ParameterUnder for ridge regression model sub- error f1M, being integrated into based on every sub- training characteristics should be in ridge time Return parameterUnder for ridge regression model sub- error, i.e. after f11, f12 ... f1M, average mistake can be calculated Poor f '=(f11+f12+ ...+f1M)/M；The f ' is training characteristics D in ridge regression parameterUnder for ridge The error F1 of regression model.
Then training characteristics set can be calculated under every group of ridge regression parameter for ridge regression by repeating step 305 and 306 The error of model；Such as ridge regression parameterIt is corresponding Error F1, F2 ... Fk ... Fm.
307, target ridge regression parameter of the minimum corresponding ridge regression parameter of error as ridge regression model is chosen.
For example, after obtaining corresponding error such as F1, F2 ... the Fk ... Fm of every group of ridge regression parameter, it is assumed that Fk is minimum, At this point it is possible to choose the corresponding ridge regression parameter of FkTarget ridge regression parameter as ridge regression model.
In one embodiment, the corresponding ridge regression parameter of the available each application of the 301-307 that repeats the above steps.
308, relevant parameter in ridge regression model is updated according to target ridge regression parameter, the ridge regression mould after being trained Type.
For example, being updated to the value of regression parameter w in ridge regression model.
In one embodiment, the available each ridge regression mould after applying corresponding training of the 301-308 that repeats the above steps Type
309, the multidimensional characteristic of application, the predicted characteristics set being applied are obtained.
Wherein, predicted time can be set according to demand, such as can be current time.
For example, can predicted time point acquisition applications multidimensional characteristic as forecast sample.
In the embodiment of the present application, is obtained in the multidimensional characteristic and step 301 of step acquisition and be characterized in same type spy Sign namely predicted characteristics set are identical as the characteristic type that training characteristics set is included, such as include: using after being cut into The duration of platform；Using during being cut into backstage, duration is shielded in going out for electronic equipment；Using the number for entering foreground；Before being in The time of platform；Using the mode for entering backstage.
310, according to the ridge regression model after predicted characteristics set and training, whether prediction application can be cleared up.
For example, can be calculated based on ridge regression model and predicted characteristics set using the probability that can be cleared up, when probability is big When some threshold value, determine that the application can clear up.
In a specific example, ridge after the training of each background application can be obtained with 301-308 through the above steps Regression model；Then, whether multiple applications of ridge regression model prediction running background may be used after the training based on each background application Cleaning, as shown in table 1, it is determined that the application A1 of running background can be cleared up and apply A3, and kept using A2 in running background State it is constant.
Using Prediction result
Using A1 It can clear up
Using A2 It can not clear up
Using A3 It can clear up
Table 1
From the foregoing, it will be observed that the embodiment of the present application obtains the multidimensional characteristic of application, the training characteristics set being applied；According to answering Training characteristics set is trained ridge regression model, the ridge regression model after being trained；The multidimensional for obtaining application is special Sign, the predicted characteristics set being applied；According to the ridge regression model after predicted characteristics set and training, whether prediction application It can clear up；To clear up the application that can be cleared up；The automatic cleaning of application may be implemented in the program, improves electronic equipment Operation fluency, reduce and power consumption and save resource.
Further, due in characteristic set, including reflecting that user is believed using multiple features of the behavioural habits of application Breath, therefore the embodiment of the present application can make the cleaning to corresponding application more personalized and intelligent.
Further, it is realized based on ridge regression model using cleaning prediction, the accurate of user's behavior prediction can be promoted Property, and then improve the accuracy of cleaning.In addition, the embodiment of the present application can also calculate multiple groups ridge regression when to model training Parameter, and using characteristic error choose error most under ridge regression parameter, using the final argument as ridge regression model, Ke Yijin Ridge regression model is promoted to one step to the accuracy of application cleaning prediction.
It additionally provides in one embodiment a kind of using cleaning plant.Referring to Fig. 4, Fig. 4 provides for the embodiment of the present application The structural schematic diagram using cleaning plant.Wherein this is applied to electronic equipment using cleaning plant, this applies cleaning plant packet Training characteristics acquiring unit 401, training unit 402, predicted characteristics acquiring unit 403 and predicting unit 404 are included, as follows:
Training characteristics acquiring unit 401, for obtaining the multidimensional characteristic of application, the training characteristics set being applied；
Training unit 402 is instructed for being trained according to the training characteristics set of the application to ridge regression model Ridge regression model after white silk；
Predicted characteristics acquiring unit 403 obtains the predicted characteristics of the application for obtaining the multidimensional characteristic of the application Set；
Predicting unit 404, for predicting institute according to the ridge regression model after the predicted characteristics set and the training Whether state to apply can clear up.
In one embodiment, with reference to Fig. 5, wherein training unit 402, comprising:
Subelement 4021 is established, for establishing the error judgment function of the ridge regression model；
Parameter obtains subelement 4022, for according to the training characteristics set and error judgment function acquisition The target ridge regression parameter of ridge regression model, the target ridge regression parameter includes ridge parameter and regression parameter；
Training subelement 4023, after according to the target ridge regression parameter and the ridge regression model training Ridge regression model.
In one embodiment, parameter obtains subelement 4022, can be used for:
Multiple groups ridge regression parameter is obtained according to the error judgment function, the ridge regression parameter includes: ridge parameter and returns Return parameter；
According to the training characteristics set, the ridge regression parameter and the error judgment function, obtains and returned in the ridge The training characteristics set under parameter is returned to obtain the corresponding mistake of every group of ridge regression parameter for the error of the ridge regression model Difference；
According to the corresponding error of every group of ridge regression parameter, corresponding target ridge is chosen from the multiple groups ridge regression parameter and is returned Return parameter.
In one embodiment, parameter obtains subelement 4022, can be specifically used for:
Corresponding regression parameter, which is obtained, according to the error judgment function obtains function；
Function is obtained according to multiple default ridge parameters and the regression parameter, is obtained each default ridge parameter corresponding time Return parameter, obtains multiple groups ridge regression parameter.
In one embodiment, parameter obtains subelement 4022, can be specifically used for:
The training characteristics set is divided into multiple sub- training characteristics set；
According to the sub- training characteristics set, the ridge regression parameter and the error judgment function, obtain described It is corresponding to obtain every sub- training characteristics set for the sub- error of ridge regression model for the son training set under ridge regression parameter The sub- error；
According to the corresponding sub- error of every sub- training characteristics set, the training characteristics under the ridge regression parameter are obtained Gather the error for the ridge regression model.
In one embodiment, parameter obtains subelement 4022, can be specifically used for:
According to the corresponding sub- error of every sub- training characteristics set, the mean error of sub- training characteristics set is obtained；
According to the mean error obtain under the ridge regression parameter training characteristics set for the ridge regression The error of model.
In one embodiment, parameter obtains subelement 4022, can be specifically used for:
Minimal error is determined from the corresponding error of every group of ridge regression parameter；
The corresponding ridge regression parameter of the minimal error is chosen from the multiple groups ridge regression parameter as target ridge regression Parameter.
Wherein, the step of executing using each unit in the cleaning plant method that reference can be made to the above method embodiment describes walks Suddenly.This can integrate in the electronic device using cleaning plant, such as mobile phone, tablet computer.
It is realized when it is implemented, above each unit can be used as independent entity, any combination can also be carried out, as Same or several entities realize that the specific implementation of above each unit can be found in the embodiment of front, and details are not described herein.
From the foregoing, it will be observed that the present embodiment application cleaning plant can be obtained the multidimensional of application by training characteristics acquiring unit 401 Feature, the training characteristics set being applied；By training unit 402 according to the training characteristics set of application to ridge regression model into Row training, the ridge regression model after being trained；The multidimensional characteristic that application is obtained by predicted characteristics acquiring unit 403, is answered Predicted characteristics set；By predicting unit 404 according to the ridge regression model after predicted characteristics set and training, prediction application Whether can clear up；To clear up the application that can be cleared up；The automatic cleaning of application may be implemented in the program, improves electronics The operation fluency of equipment reduces power consumption and saves resource.
The embodiment of the present application also provides a kind of electronic equipment.Referring to Fig. 6, electronic equipment 500 include processor 501 and Memory 502.Wherein, processor 501 and memory 502 are electrically connected.
The processor 500 is the control centre of electronic equipment 500, is set using various interfaces and the entire electronics of connection Standby various pieces by the computer program of operation or load store in memory 502, and are called and are stored in memory Data in 502 execute the various functions of electronic equipment 500 and handle data, to carry out whole prison to electronic equipment 500 Control.
The memory 502 can be used for storing software program and module, and processor 501 is stored in memory by operation 502 computer program and module, thereby executing various function application and data processing.Memory 502 can mainly include Storing program area and storage data area, wherein storing program area can computer needed for storage program area, at least one function Program (such as sound-playing function, image player function etc.) etc.；Storage data area, which can be stored, uses institute according to electronic equipment The data etc. of creation.In addition, memory 502 may include high-speed random access memory, it can also include non-volatile memories Device, for example, at least a disk memory, flush memory device or other volatile solid-state parts.Correspondingly, memory 502 can also include Memory Controller, to provide access of the processor 501 to memory 502.
In the embodiment of the present application, the processor 501 in electronic equipment 500 can be according to following step, by one or one The corresponding instruction of the process of a above computer program is loaded into memory 502, and is stored in by the operation of processor 501 Computer program in reservoir 502, thus realize various functions, it is as follows:
Obtain the multidimensional characteristic of application, the training characteristics set being applied；
Ridge regression model is trained according to the training characteristics set of the application, the ridge regression mould after being trained Type；
The multidimensional characteristic for obtaining the application obtains the predicted characteristics set of the application；
According to the ridge regression model after the predicted characteristics set and the training, predict whether the application can be clear.
In some embodiments, ridge regression model is trained according to the training sample of the application, is instructed After white silk when stating ridge regression model, processor 501 can specifically execute following steps:
Establish the error judgment function of the ridge regression model；
The target ridge regression of the ridge regression model is obtained according to the training characteristics set and the error judgment function Parameter, the target ridge regression parameter includes ridge parameter and regression parameter；
According to the ridge regression model after the target ridge regression parameter and the ridge regression model training.
In some embodiments, the ridge time is being obtained according to the training characteristics set and the error judgment function When returning the target ridge regression parameter of model, processor 501 can specifically execute following steps:
Multiple groups ridge regression parameter is obtained according to the error judgment function, the ridge regression parameter includes: ridge parameter and returns Return parameter；
According to the training characteristics set, the ridge regression parameter and the error judgment function, obtains and returned in the ridge The training characteristics set under parameter is returned to obtain the corresponding mistake of every group of ridge regression parameter for the error of the ridge regression model Difference；
According to the corresponding error of every group of ridge regression parameter, corresponding target ridge is chosen from the multiple groups ridge regression parameter and is returned Return parameter.
In some embodiments, when obtaining multiple groups ridge regression parameter according to the error judgment function, processor 501 Following steps can specifically be executed:
Corresponding regression parameter, which is obtained, according to the error judgment function obtains function；
Function is obtained according to multiple default ridge parameters and the regression parameter, is obtained each default ridge parameter corresponding time Return parameter, obtains multiple groups ridge regression parameter.
In some embodiments, according to the training characteristics set, the ridge regression parameter and the error judgment Function, obtain under the ridge regression parameter training characteristics set for the ridge regression model error when, processor 501 can specifically execute following steps:
The training characteristics set is divided into multiple sub- training characteristics set；
According to the sub- training characteristics set, the ridge regression parameter and the error judgment function, obtain described It is corresponding to obtain every sub- training characteristics set for the sub- error of ridge regression model for the son training set under ridge regression parameter The sub- error；
According to the corresponding sub- error of every sub- training characteristics set, the training characteristics under the ridge regression parameter are obtained Gather the error for the ridge regression model.
In some embodiments, it according to the corresponding sub- error of every sub- training characteristics set, obtains and is returned in the ridge When returning error for the ridge regression model of the training characteristics set under parameter, processor 501 can specifically execute following Step:
According to the corresponding sub- error of every sub- training characteristics set, the mean error of sub- training characteristics set is obtained；
According to the mean error obtain under the ridge regression parameter training characteristics set for the ridge regression The error of model.
In some embodiments, according to the corresponding error of every group of ridge regression parameter, from the multiple groups ridge regression parameter When the corresponding target ridge regression parameter of middle selection, processor 501 can specifically execute following steps:
Minimal error is determined from the corresponding error of every group of ridge regression parameter；
The corresponding ridge regression parameter of the minimal error is chosen from the multiple groups ridge regression parameter as target ridge regression Parameter.
It can be seen from the above, the electronic equipment of the embodiment of the present application, obtains the multidimensional characteristic of application, the training being applied is special Collection is closed；Ridge regression model is trained according to the training characteristics set of application, the ridge regression model after being trained；It obtains The multidimensional characteristic of application, the predicted characteristics set being applied；Ridge regression model according to predicted characteristics set and after training, Whether prediction application can clear up；To clear up the application that can be cleared up；The automatic cleaning of application may be implemented in the program, mentions The high operation fluency of electronic equipment, reduces power consumption.
Referring to Figure 7 together, in some embodiments, electronic equipment 500 can also include: display 503, radio frequency electrical Road 504, voicefrequency circuit 505 and power supply 506.Wherein, wherein display 503, radio circuit 504, voicefrequency circuit 505 and Power supply 506 is electrically connected with processor 501 respectively.
The display 503 be displayed for information input by user or be supplied to user information and various figures Shape user interface, these graphical user interface can be made of figure, text, icon, video and any combination thereof.Display 503 may include display panel, in some embodiments, can use liquid crystal display (Liquid Crystal Display, LCD) or the forms such as Organic Light Emitting Diode (Organic Light-Emitting Diode, OLED) match Set display panel.
The radio circuit 504 can be used for transceiving radio frequency signal, with by wireless communication with the network equipment or other electricity Sub- equipment establishes wireless telecommunications, the receiving and transmitting signal between the network equipment or other electronic equipments.
The voicefrequency circuit 505 can be used for providing the audio between user and electronic equipment by loudspeaker, microphone Interface.
The power supply 506 is used to all parts power supply of electronic equipment 500.In some embodiments, power supply 506 Can be logically contiguous by power-supply management system and processor 501, to realize management charging by power-supply management system, put The functions such as electricity and power managed.
Although being not shown in Fig. 7, electronic equipment 500 can also include camera, bluetooth module etc., and details are not described herein.
The embodiment of the present application also provides a kind of storage medium, and the storage medium is stored with computer program, when the meter When calculation machine program is run on computers, so that the computer, which executes in any of the above-described embodiment, applies method for cleaning, than Such as: obtaining the multidimensional characteristic of application, the training characteristics set being applied；According to the training characteristics set of application to ridge regression mould Type is trained, the ridge regression model after being trained；Obtain the multidimensional characteristic of application, the predicted characteristics set being applied； According to the ridge regression model after predicted characteristics set and training, whether prediction application can be cleared up.
In the embodiment of the present application, storage medium can be magnetic disk, CD, read-only memory (Read Only Memory, ROM) or random access memory (Random Access Memory, RAM) etc..
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, there is no the portion being described in detail in some embodiment Point, reference can be made to the related descriptions of other embodiments.
It should be noted that this field common test personnel can be with for the application method for cleaning of the embodiment of the present application Understand all or part of the process using method for cleaning for realizing the embodiment of the present application, is that can be controlled by computer program Relevant hardware is completed, and the computer program can be stored in a computer-readable storage medium, be such as stored in electronics It in the memory of equipment, and is executed by least one processor in the electronic equipment, in the process of implementation may include such as application The process of the embodiment of method for cleaning.Wherein, the storage medium can be magnetic disk, CD, read-only memory, arbitrary access note Recall body etc..
For the application cleaning plant of the embodiment of the present application, each functional module be can integrate in a processing chip In, it is also possible to modules and physically exists alone, can also be integrated in two or more modules in a module.It is above-mentioned Integrated module both can take the form of hardware realization, can also be realized in the form of software function module.It is described integrated If module realized in the form of software function module and when sold or used as an independent product, also can store one In a computer-readable storage medium, the storage medium is for example read-only memory, disk or CD etc..
Above to a kind of application method for cleaning, device, storage medium and electronic equipment provided by the embodiment of the present application into It has gone and has been discussed in detail, specific examples are used herein to illustrate the principle and implementation manner of the present application, the above implementation The explanation of example is merely used to help understand the present processes and its core concept；Meanwhile for those skilled in the art, according to According to the thought of the application, there will be changes in the specific implementation manner and application range, in conclusion the content of the present specification It should not be construed as the limitation to the application.

Claims (12)

1. a kind of apply method for cleaning characterized by comprising
The multidimensional characteristic for obtaining application, obtains the training characteristics set of the application；
Ridge regression model is trained according to the training characteristics set of the application, the ridge regression model after being trained；Tool Body includes: the error judgment function for establishing the ridge regression model；According to the training characteristics set and the error judgment letter Number obtains the target ridge regression parameter of the ridge regression model, and the target ridge regression parameter includes ridge parameter and regression parameter； According to the ridge regression model after the target ridge regression parameter and the ridge regression model training；
The multidimensional characteristic for obtaining the application obtains the predicted characteristics set of the application；
According to the ridge regression model after the predicted characteristics set and the training, predict whether the application can clear up.
2. applying method for cleaning as described in claim 1, which is characterized in that according to the training characteristics set and the error Discriminant function obtains the target ridge regression parameter of the ridge regression model, comprising:
Multiple groups ridge regression parameter is obtained according to the error judgment function, the ridge regression parameter includes: ridge parameter and recurrence ginseng Number；
According to the training characteristics set, the ridge regression parameter and the error judgment function, obtains and join in the ridge regression Several lower training characteristics set obtain the corresponding error of every group of ridge regression parameter for the error of the ridge regression model；
According to the corresponding error of every group of ridge regression parameter, corresponding target ridge regression ginseng is chosen from the multiple groups ridge regression parameter Number.
3. applying method for cleaning as claimed in claim 2, which is characterized in that obtain multiple groups ridge according to the error judgment function Regression parameter, comprising:
Corresponding regression parameter, which is obtained, according to the error judgment function obtains function；
Function is obtained according to multiple default ridge parameters and the regression parameter, obtains the corresponding recurrence ginseng of each default ridge parameter Number, obtains multiple groups ridge regression parameter.
4. applying method for cleaning as claimed in claim 2, which is characterized in that returned according to the training characteristics set, the ridge Return parameter and the error judgment function, obtains under the ridge regression parameter training characteristics set for the ridge regression The error of model, comprising:
The training characteristics set is divided into multiple sub- training characteristics set；
According to the sub- training characteristics set, the ridge regression parameter and the error judgment function, obtains and returned in the ridge Return the son training set under parameter that it is corresponding described to obtain every sub- training characteristics set for the sub- error of ridge regression model Sub- error；
According to the corresponding sub- error of every sub- training characteristics set, the training characteristics set under the ridge regression parameter is obtained For the error of the ridge regression model.
5. applying method for cleaning as claimed in claim 4, which is characterized in that according to the corresponding son of every sub- training characteristics set Error obtains error of the training characteristics set for the ridge regression model under the ridge regression parameter, comprising:
According to the corresponding sub- error of every sub- training characteristics set, the mean error of sub- training characteristics set is obtained；
According to the mean error obtain under the ridge regression parameter training characteristics set for the ridge regression model Error.
6. applying method for cleaning as claimed in claim 2, which is characterized in that according to the corresponding error of every group of ridge regression parameter, Corresponding target ridge regression parameter is chosen from the multiple groups ridge regression parameter, comprising:
Minimal error is determined from the corresponding error of every group of ridge regression parameter；
The corresponding ridge regression parameter of the minimal error is chosen from the multiple groups ridge regression parameter as target ridge regression parameter.
7. a kind of apply cleaning plant characterized by comprising
Training characteristics acquiring unit obtains the training characteristics set of the application for obtaining the multidimensional characteristic of application；
Training unit, for being trained according to the training characteristics set of the application to ridge regression model, after being trained Ridge regression model；
Predicted characteristics acquiring unit obtains the predicted characteristics set of the application for obtaining the multidimensional characteristic of the application；
Predicting unit, for predicting the application according to the ridge regression model after the predicted characteristics set and the training Whether can clear up；
Wherein, the training unit, comprising:
Subelement is established, for establishing the error judgment function of the ridge regression model；
Parameter obtains subelement, for obtaining the ridge regression mould according to the training characteristics set and the error judgment function The target ridge regression parameter of type, the target ridge regression parameter includes ridge parameter and regression parameter；
Training subelement, for according to the ridge regression mould after the target ridge regression parameter and the ridge regression model training Type.
8. cleaning plant the use as claimed in claim 7, which is characterized in that the parameter obtains subelement, is used for:
Multiple groups ridge regression parameter is obtained according to the error judgment function, the ridge regression parameter includes: ridge parameter and recurrence ginseng Number；
According to the training characteristics set, the ridge regression parameter and the error judgment function, obtains and join in the ridge regression Several lower training characteristics set obtain the corresponding error of every group of ridge regression parameter for the error of the ridge regression model；
According to the corresponding error of every group of ridge regression parameter, corresponding target ridge regression ginseng is chosen from the multiple groups ridge regression parameter Number.
9. applying cleaning plant as claimed in claim 8, which is characterized in that the parameter obtains subelement, is specifically used for:
Corresponding regression parameter, which is obtained, according to the error judgment function obtains function；
Function is obtained according to multiple default ridge parameters and the regression parameter, obtains the corresponding recurrence ginseng of each default ridge parameter Number, obtains multiple groups ridge regression parameter.
10. applying cleaning plant as claimed in claim 8, which is characterized in that the parameter obtains subelement, is specifically used for:
The training characteristics set is divided into multiple sub- training characteristics set；
According to the sub- training characteristics set, the ridge regression parameter and the error judgment function, obtains and returned in the ridge Return the son training set under parameter that it is corresponding described to obtain every sub- training characteristics set for the sub- error of ridge regression model Sub- error；
According to the corresponding sub- error of every sub- training characteristics set, the training characteristics set under the ridge regression parameter is obtained For the error of the ridge regression model.
11. a kind of storage medium, is stored thereon with computer program, which is characterized in that when the computer program is in computer When upper operation, so that the computer, which is executed, applies method for cleaning as claimed in any one of claims 1 to 6.
12. a kind of electronic equipment, including processor and memory, the memory have computer program, which is characterized in that described Processor applies method for cleaning as claimed in any one of claims 1 to 6 by calling the computer program, for executing.
CN201711050187.6A 2017-10-31 2017-10-31 Using method for cleaning, device, storage medium and electronic equipment Active CN107807730B (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201711050187.6A CN107807730B (en) 2017-10-31 2017-10-31 Using method for cleaning, device, storage medium and electronic equipment
PCT/CN2018/110632 WO2019085754A1 (en) 2017-10-31 2018-10-17 Application cleaning method and apparatus, and storage medium and electronic device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711050187.6A CN107807730B (en) 2017-10-31 2017-10-31 Using method for cleaning, device, storage medium and electronic equipment

Publications (2)

Publication Number Publication Date
CN107807730A CN107807730A (en) 2018-03-16
CN107807730B true CN107807730B (en) 2019-12-03

Family

ID=61583133

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711050187.6A Active CN107807730B (en) 2017-10-31 2017-10-31 Using method for cleaning, device, storage medium and electronic equipment

Country Status (2)

Country Link
CN (1) CN107807730B (en)
WO (1) WO2019085754A1 (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107807730B (en) * 2017-10-31 2019-12-03 Oppo广东移动通信有限公司 Using method for cleaning, 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
CN111797859A (en) * 2019-04-09 2020-10-20 Oppo广东移动通信有限公司 Feature processing method, feature processing device, storage medium and electronic equipment
CN113705107B (en) * 2021-09-01 2023-09-08 桂林电子科技大学 Power consumption analysis method based on mean value ridge regression

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101763503A (en) * 2009-12-30 2010-06-30 中国科学院计算技术研究所 Face recognition method of attitude robust
CN104159294A (en) * 2014-08-01 2014-11-19 西南科技大学 Cloud positioning platform based on Bluetooth 4.0 technology
CN104899474A (en) * 2015-06-09 2015-09-09 大连三生科技发展有限公司 Method and system for rectifying MB-seq methylation level based on ridge regression
CN106709295A (en) * 2016-12-08 2017-05-24 湖南文理学院 Intelligent terminal program permission control method based on finger screen-touching information analysis

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103902266A (en) * 2012-12-26 2014-07-02 中兴通讯股份有限公司 Method and device for cleaning application running in background
CN104298549B (en) * 2014-09-30 2018-03-30 北京金山安全软件有限公司 Method and device for cleaning application programs in mobile terminal and mobile terminal
US9910481B2 (en) * 2015-02-13 2018-03-06 Intel Corporation Performing power management in a multicore processor
CN104866069A (en) * 2015-06-12 2015-08-26 广东小天才科技有限公司 Method and device for automatically clearing background application programs
CN107133094B (en) * 2017-06-05 2021-11-02 努比亚技术有限公司 Application management method, mobile terminal and computer readable storage medium
CN107807730B (en) * 2017-10-31 2019-12-03 Oppo广东移动通信有限公司 Using method for cleaning, device, storage medium and electronic equipment

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101763503A (en) * 2009-12-30 2010-06-30 中国科学院计算技术研究所 Face recognition method of attitude robust
CN104159294A (en) * 2014-08-01 2014-11-19 西南科技大学 Cloud positioning platform based on Bluetooth 4.0 technology
CN104899474A (en) * 2015-06-09 2015-09-09 大连三生科技发展有限公司 Method and system for rectifying MB-seq methylation level based on ridge regression
CN106709295A (en) * 2016-12-08 2017-05-24 湖南文理学院 Intelligent terminal program permission control method based on finger screen-touching information analysis

Also Published As

Publication number Publication date
CN107807730A (en) 2018-03-16
WO2019085754A1 (en) 2019-05-09

Similar Documents

Publication Publication Date Title
CN107807730B (en) Using method for cleaning, device, storage medium and electronic equipment
CN108337358B (en) Application cleaning method and device, storage medium and electronic equipment
CN107678799B (en) Application program management-control method, device, storage medium and electronic equipment
CN107678845A (en) Application program management-control method, device, storage medium and electronic equipment
CN107704070B (en) Application cleaning method and device, storage medium and electronic equipment
CN109948633A (en) User gender prediction method, apparatus, storage medium and electronic equipment
CN108090497A (en) Video classification methods, device, storage medium and electronic equipment
CN104951340A (en) Information processing method and device
CN107870810B (en) Application cleaning method and device, storage medium and electronic equipment
CN108108455A (en) Method for pushing, device, storage medium and the electronic equipment of destination
CN107943534A (en) Method for closing, device, storage medium and the electronic equipment of background application
CN107704289A (en) Using method for cleaning, device, storage medium and electronic equipment
CN107894827A (en) Using method for cleaning, device, storage medium and electronic equipment
CN107291539A (en) Cluster program scheduler method based on resource significance level
CN107678531A (en) Using method for cleaning, device, storage medium and electronic equipment
CN107943582A (en) Characteristic processing method, apparatus, storage medium and electronic equipment
CN107748697B (en) Application closing method and device, storage medium and electronic equipment
CN110533459A (en) A kind of terminal replacement probability prediction technique and device based on gradient boosting algorithm
CN107643925A (en) Background application method for cleaning, device, storage medium and electronic equipment
CN107943571A (en) Background application management-control method, device, storage medium and electronic equipment
CN109961075A (en) User gender prediction method, apparatus, medium and electronic equipment
CN104360934A (en) Mobile terminal and processing method for notification of application program of mobile terminal
CN107797832A (en) Using method for cleaning, device, storage medium and electronic equipment
CN104346201B (en) Method, device and terminal for acquiring system resource consumed by application program
CN107943537A (en) Using method for cleaning, 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: Changan town in Guangdong province Dongguan 523860 usha Beach Road No. 18

Applicant after: OPPO Guangdong Mobile Communications Co., Ltd.

Address before: Changan town in Guangdong province Dongguan 523860 usha Beach Road No. 18

Applicant before: Guangdong Opel Mobile Communications Co., Ltd.

GR01 Patent grant
GR01 Patent grant