Summary of the invention
In view of this, determination method, apparatus, computer equipment and the computer the present invention provides a kind of logging state are depositedStorage media, main purpose are to solve the problems, such as that the logging state of current single-mode is easy to cause user account security risk.
According to the present invention on one side, a kind of determination method of logging state is provided, this method comprises:
Multiple groups characteristic when sample of users enters using account every time is obtained, carries sample in the characteristicUser enters every time applies the corresponding logging state label of account, and the multiple groups characteristic is included at least to be entered from sample of usersTransaction data, browsing data and the configuration data extracted in historical operating data when using account；
The multiple groups characteristic is input in deep learning model as training data and is trained, building logs in shapeState identification model, characteristic and user when record has user to enter using account in the logging state identification model enterUsing the mapping relations between the corresponding logging state of account；
When user enters using account, multiple groups characteristic when user is entered using account is input to the loginState recognition model determines that user enters using the corresponding logging state of account.
Further, the deep learning model is convolutional neural networks, and the convolutional neural networks include multilayered structure,Described be input to the multiple groups characteristic in deep learning model as training data is trained, and building logging state is knownOther model includes:
The feature that the multiple groups characteristic is extracted by the convolutional layer of the deep learning model obtains user's entrance and answersThe characteristic parameter of each logging state is corresponded to account；
The user is entered by the pond layer of the deep learning model and corresponds to each logging state using accountCharacteristic parameter carries out dimension-reduction treatment, and user enters the feature ginseng that each logging state is corresponded to using account after obtaining dimension-reduction treatmentNumber；
User enters using account correspondence after summarizing the dimension-reduction treatment by the full articulamentum of the deep learning modelThe characteristic parameter of each logging state obtains weight of characteristic when user enters using account in each logging stateValue；
Characteristic when being entered according to the user using account by the classification layer of the deep learning model is eachThe characteristic that weighted value in a logging state generates when user enters using account enters corresponding using account with userMapping relations between logging state construct logging state identification model.
Further, the multiple groups characteristic obtained when sample of users enters using account every time includes:
Historical operating data when calling sample of users to enter using account by preset interface；
Historical operating data when being entered according to the user using account extracts sample of users and enters every time using accountWhen multiple groups characteristic.
Further, described after the multiple groups characteristic when the acquisition sample of users enters using account every timeMethod further include:
Entered every time using the session object created after account by parsing user, determines that user enters every time using accountCorresponding logging state.
Further, described to be entered every time using the session object created after account by parsing user, determine that user is everyIt is secondary to include: into using the corresponding logging state of account
Entered every time using the session object created after account by parsing user, extracts and stored in the session objectLogin configurations information；
Determine that user enters every time using the corresponding logging state of account according to the login configurations information.
Record has user is pre-set to enter using the corresponding logging state of account in the login configurations information, describedLogging state include keep logging state and verifying logging state, it is described according to the login configurations information determine user every time intoEnter and includes: using the corresponding logging state of account
When record user is pre-set in the login configurations information enters using logging state is kept after account, reallyDetermine user to enter every time using the corresponding logging state of account to be holding logging state；
When record user is pre-set in the login configurations information enters using logging state is verified after account, reallyDetermine user to enter every time using the corresponding logging state of account to be verifying logging state.
Further, in the multiple groups characteristic when user enters using account, when user is entered using accountAccording to the logging state identification model is input to, determine that user enters using after the corresponding logging state of account, the methodFurther include:
If the multiple groups characteristic when user enters using account sends variation, pass through the multiple groups feature after changingData are input to the logging state identification model, and adjustment user enters using the corresponding logging state of account.
Further, in the multiple groups characteristic when user enters using account, when user is entered using accountAccording to the logging state identification model is input to, determine that user enters using after the corresponding logging state of account, the methodFurther include:
Entered according to the user using the corresponding logging state of account, determines that user is again introduced into the login using accountMode is logged in using account.
According to the present invention on the other hand, a kind of determining device of logging state is provided, described device includes:
Acquiring unit, for obtaining multiple groups characteristic when sample of users enters using account every time, the characteristicIt carries sample of users in enter every time using the corresponding logging state label of account, the multiple groups characteristic includes at leastTransaction data, browsing data and the configuration data extracted in historical operating data when entering from sample of users using account；
Construction unit is instructed for the multiple groups characteristic to be input in deep learning model as training dataPractice, constructs logging state identification model, feature when record has user to enter using account in the logging state identification modelData and user enter using the mapping relations between the corresponding logging state of account；
Determination unit, for the multiple groups characteristic when user enters using account, when user is entered using accountIt is input to the logging state identification model, determines that user enters using the corresponding logging state of account.
Further, the deep learning model is convolutional neural networks, and the convolutional neural networks include multilayered structure,The construction unit includes:
Extraction module, for extracting the feature of the multiple groups characteristic by the convolutional layer of the deep learning model,It obtains user and enters the characteristic parameter for corresponding to each logging state using account；
Dimensionality reduction module enters the user for the pond layer by the deep learning model corresponding each using accountThe characteristic parameter of a logging state carries out dimension-reduction treatment, obtains user after dimension-reduction treatment and enter to correspond to each login shape using accountThe characteristic parameter of state；
Summarizing module enters for user after summarizing the dimension-reduction treatment by the full articulamentum of the deep learning modelThe characteristic parameter that each logging state is corresponded to using account obtains characteristic when user enters using account in each loginWeighted value in state；
Module is constructed, when for being entered according to the user using account by the classification layer of the deep learning modelCharacteristic of the characteristic when the weighted value generation user in each logging state enters using account enters with user answersWith the mapping relations between the corresponding logging state of account, logging state identification model is constructed.
Further, the acquiring unit includes:
Calling module, historical operating data when for calling sample of users to enter using account by preset interface；
It is every to extract sample of users for extraction module, historical operating data when for being entered according to the user using accountThe secondary multiple groups characteristic entered when applying account.
Further, described device further include:
Resolution unit, after the multiple groups characteristic when the acquisition sample of users enters using account every time,Determine that user enters every time using the corresponding logging state of account.
Further, the resolution unit includes:
Parsing module extracts the meeting for entering every time using the session object created after account by parsing userThe login configurations information stored in words object；
Determining module, for determining that user enters every time using the corresponding login shape of account according to the login configurations informationState.
Further, record has user is pre-set to enter using the corresponding login of account in the login configurations informationState, the logging state include keeping logging state and verifying logging state, the determining module, specifically for stepping on when describedWhen recording that record user in configuration information is pre-set to enter using logging state is kept after account, determines that user enters every time and answerIt is to keep logging state with the corresponding logging state of account；
The determining module is specifically also used to enter application when record user is pre-set in the login configurations informationWhen verifying logging state after account, determining that user enters every time using the corresponding logging state of account is verifying logging state.
Further, described device further include:
Adjustment unit, for, when user enters using account, multiple groups when user is entered using account to be special describedSign data are input to the logging state identification model, determine that user enters using after the corresponding logging state of account, if instituteIt states multiple groups characteristic when user enters using account and sends variation, by the way that the multiple groups characteristic after variation is input to instituteLogging state identification model is stated, adjustment user enters using the corresponding logging state of account.
Further, described device further include:
Unit is logged in, for, when user enters using account, multiple groups when user is entered using account to be special describedSign data are input to the logging state identification model, determine that user enters using after the corresponding logging state of account, according toThe user enters using the corresponding logging state of account, determines that user is again introduced into the login mode using account, to applicationAccount is logged in.
Another aspect according to the present invention provides a kind of computer equipment, including memory and processor, the storageDevice is stored with computer program, and the processor realizes the step of the determination method of logging state when executing the computer programSuddenly.
Another aspect according to the present invention provides a kind of computer storage medium, is stored thereon with computer program, instituteThe step of stating the determination method that logging state is realized when computer program is executed by processor.
By above-mentioned technical proposal, the present invention provides a kind of determination method and device of logging state, by collecting sampleMultiple groups characteristic when user enters using account every time is input in deep learning model as training data to be trained,Logging state identification model is constructed, when user enters using account, identifies that user enters by logging state identification model and answersWith the corresponding logging state of account, and then the logging state that user is obtained using identification after login, it is user-friendly.With it is existingHave in technology and compared using the logging state of single-mode come the method for carrying out account information login, the present invention is by using loginState recognition model identifies that user enters the logging state using account, can be accustomed to determination based on the login of user and be suitable forUsing the logging state of account, and judge automatically allow user be directly entered user login validation is still allowed using account after enter answerWith account, reduce unnecessary register during user's logon account, it is convenient for the user to operate, while reducing user's accountThe security risk at family.
Specific embodiment
Exemplary embodiments of the present disclosure are described in more detail below with reference to accompanying drawings.Although showing the disclosure in attached drawingExemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth hereIt is limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosureIt is fully disclosed to those skilled in the art.
The embodiment of the invention provides a kind of determination methods of logging state, can be accustomed to determining based on the login of user suitableIt is convenient for the user to operate for the logging state of application account, while the security risk of user account is reduced, as shown in Figure 1, shouldMethod includes:
101, multiple groups characteristic when sample of users enters using account every time is obtained.
Wherein, multiple groups characteristic when sample of users enters using account every time is included at least to enter from sample of users and be answeredTransaction data, browsing data and the configuration data extracted in historical operating data when with account, for example, when user logs inBetween, operation place, device type, account whether can trade, consumer's risk ability to bear, identity information, account assets amount etc.Characteristic can all be registered specifically when user first enters using account by personally identifiable information, for example, accountTitle, telephone number, gender etc., and the operation of application account can be configured, sequence, login side for example, payment is withholddFormula, logging state setting etc..
It is understood that user is during login account information, for not for the ease of the login of account informationWith application account, the logging state of account information can be all set, can in order to according to the logging state of the account information of settingTo realize quick registration, for example, for the application account wind for being related to financial category, risk is higher in use, in order to guarantee accountThe logging state for keeping logging in will not be usually arranged, for being related to the account and account of social category in the safety at family after loginIt is higher that service is related to risk when transaction authentication in use, since user's frequency of use is higher, is usually arranged after loginThe logging state logged in is kept, but is related to that safety verification can be arranged when transaction, is existed for the application service account of shopping classRisk is higher when transaction authentication involved in use process, and holding logging state usually also can be set after login.
102, the multiple groups characteristic is input in deep learning model as training data and is trained, building is stepped onRecord state recognition model.
Wherein, characteristic when record has user to enter using account in logging state identification model enters with user answersWith the mapping relations between the corresponding logging state of account, since deep learning model has mapping relations between training dataEffect, by constructing logging state identification model, characteristic when logging into different user using account, by stepping onThe characteristic phase that the obtained mapping relations of record state recognition model training are available when logging into user using accountCorresponding logging state.
Enter every time using the corresponding logging state label of account due to carrying sample of users in characteristic, for example,Logging state label can be arranged two kinds, keep logging in and verifying logs in, more logging state labels can also be set certainly,Specifically, the application account of the characteristic not changed and the transaction of non-amount of money involved can be set to keep stepping onRecord can be set to verifying login for the application account of characteristic or the amount of money involved transaction to change, can be withWhether the change range setting for characteristic switches logging state etc., here without limiting, thus according to sample of usersEnter every time and multiple groups characteristic is trained using account corresponding logging state label.
For the embodiment of the present invention, deep learning model can be convolutional neural networks model here, can specifically pass throughThe network knot of multiple groups characteristic building logging state identification model when repetition training sample of users enters using account every timeStructure, which can be trained the data of input, and provide correct Input output Relationship, be equivalent to user intoEnter to apply characteristic and user when account to enter using the mapping relations between the corresponding logging state of account.
The structure of specific convolutional neural networks model can pass through convolutional layer, full articulamentum, pond layer and classification layer knotStructure realizes that convolutional layer here is equivalent to the hidden layer of convolutional neural networks, can be multilayered structure, for extracting deeper timeUser enter the characteristic parameter that each logging state is corresponded to using account；In convolutional neural networks model, in order to reduce ginsengNumber lowers and calculates, usually the interval insertion pond layer in continuous convolution layer；Here full articulamentum is similar to convolutional layer, convolutionThe neuron of layer is connected with upper one layer of output regional area, and of course for reducing, output feature vector is excessive, can be set twoFull articulamentum integrates the characteristic of training output after training data is by the training of several convolutional layers.
103, when user enters using account, multiple groups characteristic when user is entered using account is input to describedLogging state identification model determines that user enters using the corresponding logging state of account.
For the embodiment of the present invention, by determining that user enters using the corresponding logging state of account, user is without voluntarilyJudge logging state, application account higher for risk class can be set to verifying logging state, step on by safety verificationAccount is applied in record, and application account lower for risk class can be set to keep logging state, verify without userIt can log in using account, it is user-friendly.
The embodiment of the present invention provides a kind of determination method of logging state, is entered every time by collecting sample of users using accountMultiple groups characteristic when family is input in deep learning model as training data to be trained, and building logging state identifies mouldType identifies that user enters using the corresponding login shape of account by logging state identification model when user enters using accountState, and then the logging state that user is obtained using identification after login, it is user-friendly.With in the prior art use single mouldThe logging state of formula is compared come the method for carrying out account information login, and the present invention is identified by using logging state identification modelUser enters the logging state using account, can determine the login shape being suitable for using account based on the login habit of userState, and judge automatically allow user be directly entered user login validation is still allowed using account after enter using account, reduce useUnnecessary register, convenient for the user to operate during the logon account of family, while reducing the security risk of user account.
The embodiment of the invention provides the determination methods of another logging state, can be accustomed to determining based on the login of userIt is convenient for the user to operate suitable for the logging state of application account, while the security risk of user account is reduced, as shown in Fig. 2,The described method includes:
201, historical operating data when calling sample of users to enter using account by preset interface.
Wherein, historical operating data when sample of users enters using account may include but be not limited to sample of users friendshipEasy data, browsing data, configuration data etc..Historical operation number when calling sample of users to enter using account by preset interfaceIt logs according to available using the operation data after account.
202, historical operating data when being entered according to the user using account extracts sample of users and enters application every timeMultiple groups characteristic when account.
For the embodiment of the present invention, after user's registration application account, for ease of operation, for application account characteristic allCharacteristic when can be arranged for entering using account, this feature data are equivalent to the behaviour of history when user enters using accountMake data, for example, safety verification can usually be arranged in login and transaction for the network service of financial category is related to, such as logs inLong logging state is usually arranged for the network service of social category is related in account password, trading password etc. after login, transactionWhen safety verification is set, for the network service of shopping class, safety verification usually will not be set when logging in, setting peace when transactionIt is complete to verify, user can be extracted in historical operating data when further entering from user using account to be entered every time using accountWhen multiple groups characteristic.
203, entered every time using the session object created after account by parsing user, determine that user enters application every timeThe corresponding logging state of account.
For the embodiment of the present invention, user can create session object after each enter using account, if user thinksLogging state is kept, then user, which is in, keeps logging state, and will not log off request, can be directly entered using account next timeFamily, and can have the information of user in session object at this time, whereas if user is not desired to continue to keep logging state, then useFamily is in verifying logging state, and can log off request, enters next time after applying account and needs logon account again, and at this timeThere is no the information of user in session object, can be with here by judging whether to record the information of user in session objectDetermine that user enters every time using the corresponding logging state of account.
The session object specifically created after being entered every time using account by parsing user determines that user enters every time and answersDuring the corresponding logging state of account, it can be entered every time by parsing user using the session object created after account,Login configurations information is stored in the session object, record has user is pre-set to enter using account in the login configurations informationThe corresponding logging state in family such as keeps logging state and verifying logging state, further true according to the login configurations information of extractionDetermining user, entrance is answered using the corresponding logging state of account when recording the pre-set entrance of user in login configurations information every timeWhen with keeping logging state after account, determining that user enters every time using the corresponding logging state of account is holding logging state；When recording that user is pre-set to be entered using logging state is verified after account in login configurations information, determine user every time intoEntering using the corresponding logging state of account is verifying logging state.
204, the multiple groups characteristic is input in deep learning model as training data and is trained, building is stepped onRecord state recognition model.
Specifically multiple groups characteristic is input to as training data be trained in deep learning model during,One group of characteristic when family enters using account every time can be mixed the sample with as a N-dimensional vector, each characteristic tableA numerical value being shown as in N-dimensional vector, and by the way that characteristic is normalized after so that each characteristicDistribution is [- 1,1], and the characteristic not set for user is expressed as numerical value 0, to obtain the training number of reference formatAccording to.
Specific convolutional neural networks include multilayered structure, can extract multiple groups by the convolutional layer of convolutional neural networks modelThe feature of characteristic obtains user and enters the characteristic parameter for corresponding to each logging state using account；Pass through convolutional Neural netThe pond layer of network model, which enters user, carries out dimension-reduction treatment using the characteristic parameter that account corresponds to each logging state, is droppedUser enters the characteristic parameter that each logging state is corresponded to using account after dimension processing；Pass through connecting entirely for convolutional neural networks modelIt meets user after layer summarizes dimension-reduction treatment and enters the characteristic parameter for corresponding to each logging state using account, obtain user and enter applicationWeighted value of the characteristic in each logging state when account；By the classification layer of convolutional neural networks model according to userCharacteristic when into using account generates feature when user enters using account in the weighted value in each logging stateData and user enter using the mapping relations between the corresponding logging state of account, construct logging state identification model.
For example, convolutional neural networks include 13 convolutional layers, each convolutional layer is can be set in 3 full articulamentums hereConvolution kernel number is respectively 64,64,128,128,256,256,512,512,512,512,512,512, and the 2nd convolutional layerBetween the 3rd convolutional layer, between the 4th convolutional layer and the 5th convolutional layer, between the 6th convolutional layer and the 7th convolutional layer,Between 8th convolutional layer and the 9th convolutional layer, between the 10th convolutional layer and the 11st convolutional layer, the 13rd convolutional layer and the 1stBetween a full articulamentum, it is all connected with 1 pond layer, and above-mentioned 13 convolutional layers and 3 full articulamentums use nonlinear activationFunction is handled, specifically can basis here to the number of plies of above-mentioned convolutional layer, full articulamentum and pond layer without limitingActual conditions are chosen, similarly, for activation primitive selected in every layer also without limiting.When input user every time intoEnter to apply multiple groups characteristic when account, the characteristic and user when output user enters using account enter using accountMapping relations between corresponding logging state are equivalent to characteristic when user enters using account in each logging stateOn classification results.
205, when user enters using account, multiple groups characteristic when user is entered using account is input to describedLogging state identification model determines that user enters using the corresponding logging state of account.
For the embodiment of the present invention, entered by the user that logging state identification model identifies corresponding using accountLogging state be that the logging state that the characteristic of account tentatively to judge suitable user is entered according to user, so as to userIt can be judged automatically when logging on and be directly entered using account or enter by safety verification using account, user is facilitated to graspMake.
If multiple groups characteristic when 206, the user enters using account sends variation, pass through the multiple groups after changingCharacteristic is input to the logging state identification model, and adjustment user enters using the corresponding logging state of account.
It is understood that characteristic when user enters using account every time be it is constantly changed, withCharacteristic when family enters using account every time changes, if characteristic when user enters using account generates changeChange, can also be changed by constructing the logging state that logging state identification model identifies.
For example, the login place that user enters every time in characteristic when applying account shows that user logs in placeChange, the user identified enters using the corresponding logging state change of account or user every time into when applying accountPersonal information change, can all make the obtained user of identification enter using the corresponding logging state change of account.
207, entered according to the user using the corresponding logging state of account, determine that user is again introduced into using accountLogin mode is logged in using account.
For the embodiment of the present invention, if user enters using the corresponding logging state of account to keep logging state, thatWhen user is again introduced into using account, it may not need and log in again, be directly entered using account, if user enters using accountThe corresponding logging state in family is verifying logging state, then needing to log in again when user is again introduced into using account.
Further, the specific implementation as Fig. 1 the method, the embodiment of the invention provides a kind of logging states reallyDevice is determined, as shown in figure 3, described device includes: acquiring unit 31, construction unit 32, determination unit 33.
Acquiring unit 31 can be used for obtaining multiple groups characteristic when sample of users enters using account every time, describedIt carries sample of users in characteristic to enter using the corresponding logging state label of account every time, the multiple groups characteristic is extremelyIt less include the transaction data extracted in historical operating data when entering from sample of users using account, browsing data and configurationData；
Construction unit 32 can be used for being input in deep learning model using the multiple groups characteristic as training dataIt is trained, logging state identification model is constructed, when record has user to enter using account in the logging state identification modelCharacteristic and user enter using the mapping relations between the corresponding logging state of account；
Determination unit 33, the multiple groups that can be used for when user enters using account, when user is entered using account are specialSign data are input to the logging state identification model, determine that user enters using the corresponding logging state of account.
The determining device of a kind of logging state provided by the invention, when being entered every time using account by collecting sample of usersMultiple groups characteristic be input in deep learning model and be trained as training data, construct logging state identification model,When user enters using account, identify that user enters using the corresponding logging state of account by logging state identification model,And then the logging state that user is obtained using identification after login, it is user-friendly.With in the prior art use single-modeLogging state compared come the method for carrying out account information login, the present invention identifies use by using logging state identification modelFamily enters the logging state using account, can determine the logging state being suitable for using account based on the login habit of user,And judge automatically allow user be directly entered user login validation is still allowed using account after enter using account, reduce user and step onUnnecessary register during record account, it is convenient for the user to operate, while reducing the security risk of user account.
The further explanation of determining device as logging state shown in Fig. 3, Fig. 4 are another according to embodiments of the present inventionThe structural schematic diagram of the determining device of kind logging state, as shown in figure 4, described device further include:
Resolution unit 34 can be used for the multiple groups characteristic when the acquisition sample of users enters using account every timeLater, determine that user enters every time using the corresponding logging state of account；
Adjustment unit 35 can be used for described when user enters using account, when user is entered using accountMultiple groups characteristic is input to the logging state identification model, determine user enter using the corresponding logging state of account itAfterwards, if the multiple groups characteristic when user enters using account sends variation, pass through the multiple groups characteristic after changingIt is input to the logging state identification model, adjustment user enters using the corresponding logging state of account；
Unit 36 is logged in, can be used for described when user enters using account, when user is entered using accountMultiple groups characteristic is input to the logging state identification model, determine user enter using the corresponding logging state of account itAfterwards, entered according to the user using the corresponding logging state of account, determine that user is again introduced into the login mode using account,It is logged in using account.
Further, the deep learning model is convolutional neural networks, and the convolutional neural networks include multilayered structure,The construction unit 32 includes:
Extraction module 321, for extracting the spy of the multiple groups characteristic by the convolutional layer of the deep learning modelSign, obtains user and enters the characteristic parameter for corresponding to each logging state using account；
Dimensionality reduction module 322, for being entered the user using account pair by the pond layer of the deep learning modelIt answers the characteristic parameter of each logging state to carry out dimension-reduction treatment, obtains user after dimension-reduction treatment and enter to correspond to each step on using accountThe characteristic parameter of record state；
Summarizing module 323, after can be used for summarizing the dimension-reduction treatment by the full articulamentum of the deep learning modelUser enters the characteristic parameter that each logging state is corresponded to using account, obtains characteristic when user enters using account and existsWeighted value in each logging state；
Module 324 is constructed, can be used for entering application according to the user by the classification layer of the deep learning modelCharacteristic when account generates the characteristic and use when user enters using account in the weighted value in each logging stateFamily enters using the mapping relations between the corresponding logging state of account, constructs logging state identification model.
Further, the acquiring unit 31 includes:
Calling module 311 can be used for historical operation when calling sample of users to enter using account by preset interfaceData；
Extraction module 312 can be used for historical operating data when entering according to the user using account, extract sampleMultiple groups characteristic when user enters using account every time.
Further, the resolution unit 34 includes:
Parsing module 341 can be used for entering every time by parsing user using the session object created after account, extractThe login configurations information stored in the session object；
It is corresponding using account to can be used for determining that user enters every time according to the login configurations information for determining module 342Logging state.
Further, record has user is pre-set to enter using the corresponding login of account in the login configurations informationState, the logging state include keeping logging state and verifying logging state,
The determining module 342, specifically can be used for the record user in the login configurations information it is pre-set intoWhen entering using logging state is kept after account, determining that user enters every time using the corresponding logging state of account is to keep logging in shapeState；
The determining module 342 specifically can be also used for when record user is pre-set in the login configurations informationWhen verifying logging state after into application account, determines that user enters every time and logged in using the corresponding logging state of account for verifyingState.
It should be noted that its of each functional unit involved by a kind of determining device of logging state provided in this embodimentHe accordingly describes, can be with reference to the corresponding description in Fig. 1 and Fig. 2, and details are not described herein.
It is deposited thereon based on above-mentioned method as depicted in figs. 1 and 2 correspondingly, the present embodiment additionally provides a kind of storage mediumComputer program is contained, which realizes the determination side of above-mentioned logging state as depicted in figs. 1 and 2 when being executed by processorMethod.
Based on this understanding, the technical solution of the application can be embodied in the form of software products, which producesProduct can store in a non-volatile memory medium (can be CD-ROM, USB flash disk, mobile hard disk etc.), including some instructionsWith so that computer equipment (can be personal computer, server or the network equipment an etc.) execution the application is eachMethod described in implement scene.
Based on above-mentioned method as shown in Figure 1 and Figure 2 and Fig. 3, virtual bench embodiment shown in Fig. 4, in order to realizeAbove-mentioned purpose, the embodiment of the present application also provides a kind of computer equipments, are specifically as follows personal computer, server, networkEquipment etc., the entity device include storage medium and processor；Storage medium, for storing computer program；Processor is used forComputer program is executed to realize the determination method of above-mentioned logging state as depicted in figs. 1 and 2.
Optionally, which can also include user interface, network interface, camera, radio frequency (RadioFrequency, RF) circuit, sensor, voicefrequency circuit, WI-FI module etc..User interface may include display screen(Display), input unit such as keyboard (Keyboard) etc., optional user interface can also connect including USB interface, card readerMouthful etc..Network interface optionally may include standard wireline interface and wireless interface (such as blue tooth interface, WI-FI interface).
It will be understood by those skilled in the art that the entity device structure of the determining device of logging state provided in this embodimentThe restriction to the entity device is not constituted, may include more or fewer components, perhaps combines certain components or differenceComponent layout.
It can also include operating system, network communication module in storage medium.Operating system is that the above-mentioned computer of management is setThe program of standby hardware and software resource, supports the operation of message handling program and other softwares and/or program.Network communication mouldBlock leads to for realizing the communication between each component in storage medium inside, and between other hardware and softwares in the entity deviceLetter.
Through the above description of the embodiments, those skilled in the art can be understood that the application can borrowIt helps software that the mode of necessary general hardware platform is added to realize, hardware realization can also be passed through.Pass through the skill of application the applicationArt scheme, compared with currently available technology, the present invention identifies that user enters using account by using logging state identification modelThe logging state at family can determine the logging state being suitable for using account based on the login habit of user, and judge automatically and allowUser is directly entered user login validation is still allowed using account after enter using account, during reducing user's logon accountUnnecessary register, it is convenient for the user to operate, while reducing the security risk of user account.
It will be appreciated by those skilled in the art that the accompanying drawings are only schematic diagrams of a preferred implementation scenario, module in attached drawing orProcess is not necessarily implemented necessary to the application.It will be appreciated by those skilled in the art that the mould in device in implement sceneBlock can according to implement scene describe be distributed in the device of implement scene, can also carry out corresponding change be located at be different fromIn one or more devices of this implement scene.The module of above-mentioned implement scene can be merged into a module, can also be into oneStep splits into multiple submodule.
Above-mentioned the application serial number is for illustration only, does not represent the superiority and inferiority of implement scene.Disclosed above is only the applicationSeveral specific implementation scenes, still, the application is not limited to this, and the changes that any person skilled in the art can think of is allThe protection scope of the application should be fallen into.