CN107623696A

CN107623696A - A kind of user ID authentication method and device based on user behavior feature

Info

Publication number: CN107623696A
Application number: CN201710940479.0A
Authority: CN
Inventors: 阚志刚; 陈彪; 闫布福; 孙俊飞; 方宁; 卢佐华
Original assignee: Beijing Bang Bang Safety Technology Co Ltd
Current assignee: Beijing Bang Bang Safety Technology Co Ltd
Priority date: 2017-09-30
Filing date: 2017-09-30
Publication date: 2018-01-23
Anticipated expiration: 2037-09-30
Also published as: CN107623696B

Abstract

This application discloses a kind of user ID authentication method and device based on user behavior feature, can obtain the quantized value that user to be verified triggers behavioural characteristic when pre-set business operates, and determines the behavioural characteristic mark of the behavioural characteristic；The behavioural characteristic includes one or more of：Gyroscope fluctuation behavioural characteristic, slide behavioural characteristic and click on behavioural characteristic；Identified according to the behavioural characteristic, the quantized value excursion with the corresponding behavioural characteristic of behavioural characteristic mark is obtained in subordinate act feature database；According to the quantized value of the behavioural characteristic and the relation of quantized value excursion got, the legitimacy of the user to be verified is determined.It is different to hold the posture of same terminal and operating habit due to different user, this make it that the quantized value excursion of the behavioural characteristic of the same business operation of different user triggering is also different, and it is not easy to be cracked, imitates, therefore, this method and device can improve the security of subscriber authentication.

Description

A kind of user ID authentication method and device based on user behavior feature

Technical field

The application is related to field of computer technology, more particularly to a kind of subscriber authentication side based on user behavior feature Method and device.

Background technology

With the rapid development of mobile Internet, user carries out the operation of all kinds of " internet+" business by mobile terminal It is very common.For example, user can carry out net purchase by shopping website APP on mobile phone, or user can be with Transferred accounts, paid by the financial APP on mobile phone, etc..

However, the popularization of all kinds of movement " internet+" business, although bringing facility for user, there is also more Security risk.For example, in " internet+finance " business, account and password that validated user often occur are stolen by malicious user Or situation about cracking, after account and the password of validated user are stolen or cracked to malicious user, validated user can be pretended to be to log in legal The account of user, the business operation such as transferred accounts, paid, makes the property of validated user sustain a loss.

In view of the above-mentioned problems, prior art often user perform related service operation when, it is desirable to user input short-message verification Code or other dynamic passwords (answer for the problem of such as presetting), checking is made with the identity to user.

But this mode verified only by short message verification code or other dynamic passwords, because of short message verification code Or other dynamic passwords may be fished by fishing software and taken, and easily cracked by disabled user.It can be seen that existing user to be verified There is larger potential safety hazard in auth method, how to lift the security of user ID authentication method to be verified, be urgently The technical problem of solution.

The content of the invention

The embodiment of the present application provides a kind of user ID authentication method and device based on user behavior feature, to improve The security of subscriber authentication.

In a first aspect, the embodiment of the present application provides a kind of user ID authentication method based on user behavior feature, including：

The quantized value that user to be verified triggers behavioural characteristic when pre-set business operates is obtained, determines the behavioural characteristic Behavioural characteristic identifies；The behavioural characteristic includes one or more of：Gyroscope fluctuation behavioural characteristic, slide behavioural characteristic and Click on behavioural characteristic；

Identified according to the behavioural characteristic, it is special that behavior corresponding with behavioural characteristic mark is obtained in subordinate act feature database The quantized value excursion of sign；Wherein, behavioural characteristic mark is stored with the behavioural characteristic storehouse and the behavior of validated user is special The corresponding relation of the quantized value excursion of sign；

According to the quantized value of the behavioural characteristic and the relation of the quantized value excursion got, determine described to be verified The legitimacy of user.

Second aspect, a kind of behavioural characteristic storehouse method for building up, it is characterised in that methods described includes：

The first set pre-saved is obtained, is included in the first set：During validated user triggering pre-set business operation The quantized value of behavioural characteristic identified with corresponding behavioural characteristic；

Quantized value in the first set is screened, it is special to obtain the user of validated user described in energy accurate characterization The quantized value of sign is added in second set；

According to the quantized value in the second set, the quantized value of behavioural characteristic corresponding to the behavioural characteristic mark is determined Excursion；

The quantized value excursion of the behavioural characteristic mark and the behavioural characteristic is accordingly stored, it is described to obtain Behavioural characteristic storehouse.

The third aspect, the embodiment of the present application also provide a kind of subscriber authentication device based on user behavior feature, institute Stating device includes：

First acquisition module, the quantized value of behavioural characteristic when pre-set business operates is triggered for obtaining user to be verified, Determine the behavioural characteristic mark of the behavioural characteristic；Wherein, the behavioural characteristic includes one or more of：Gyroscope fluctuates Behavioural characteristic, slide behavioural characteristic and click on behavioural characteristic；

Second acquisition module, obtained for being identified according to the behavioural characteristic, in subordinate act feature database special with the behavior The quantized value excursion of behavioural characteristic corresponding to sign mark；Wherein, behavioural characteristic mark is stored with the behavioural characteristic storehouse With the corresponding relation of the quantized value excursion of the behavioural characteristic of validated user；

First determining module, for the quantized value according to the behavioural characteristic and the pass of the quantized value excursion got System, determine the legitimacy of the user to be verified.

Device is established in fourth aspect, a kind of behavioural characteristic storehouse, it is characterised in that including：

3rd acquisition module, for obtaining the first set pre-saved, included in the first set：Validated user touches The quantized value of behavioural characteristic when sending out pre-set business operation identifies with corresponding behavioural characteristic；

Data processing module, the quantized value in the first set is screened, can be closed with obtaining described in accurate characterization The quantized value of the user characteristics of method user is added in second set；

Excursion determining module, for the quantized value in the second set, determine the behavioural characteristic mark The quantized value excursion of corresponding behavioural characteristic；

Feature database establishes module, for accordingly storing the quantized value of the behavioural characteristic mark and the behavioural characteristic Excursion, to obtain the behavioural characteristic storehouse.

Due under same business operation, different user hold the posture of same terminal and operating habit be it is different, This make it that the quantized value excursion of the behavioural characteristic of the same business operation of different user triggering is also different, and is not easy to be broken Solution, imitate.Therefore, above-mentioned at least one technical scheme that the embodiment of the present application uses, it can identify that triggering is default exactly The legitimacy of the user of business operation, improve the security of subscriber authentication.

Brief description of the drawings

Accompanying drawing described herein is used for providing further understanding of the present application, forms the part of the application, this Shen Schematic description and description please is used to explain the application, does not form the improper restriction to the application.In the accompanying drawings：

Fig. 1 is a kind of a kind of tool for user ID authentication method based on user behavior feature that the embodiment of the present application provides The schematic flow sheet of body embodiment；

Fig. 2 is the schematic diagram that user carries out sliding trace caused by slide using left hand and the right hand；

Fig. 3 is a kind of a kind of flow of the embodiment for behavioural characteristic storehouse method for building up that the embodiment of the present application provides Schematic diagram；

Fig. 4 is that a kind of user ID authentication method based on user behavior feature that the embodiment of the present application provides actually should Schematic flow sheet in；

Fig. 5 is that a kind of user ID authentication method based on user behavior feature that the embodiment of the present application provides actually should System structure diagram in；

Fig. 6 is a kind of a kind of tool for subscriber authentication device based on user behavior feature that the embodiment of the present application provides The structural representation of body embodiment；

Fig. 7 is a kind of structure for embodiment that device is established in a kind of behavioural characteristic storehouse that the embodiment of the present application provides Schematic diagram；

Fig. 8 is the structural representation for a kind of electronic equipment that the embodiment of the present application provides.

Embodiment

To make the purpose, technical scheme and advantage of the application clearer, below in conjunction with the application specific embodiment and Technical scheme is clearly and completely described corresponding accompanying drawing.Obviously, described embodiment is only the application one Section Example, rather than whole embodiments.Based on the embodiment in the application, those of ordinary skill in the art are not doing Go out under the premise of creative work the every other embodiment obtained, belong to the scope of the application protection.

The low technical problem of security, the embodiment of the present application are identified to solve subscriber authentication scheme of the prior art A kind of user ID authentication method and device based on user behavior feature are provided, is described with reference to the drawings separately below.

A kind of user ID authentication method based on user behavior feature first provided below the embodiment of the present application is carried out Introduce.

The executive agent of the user ID authentication method based on user behavior feature that the embodiment of the present application provides can be Server can also be terminal, when executive agent is server, specifically can be perform the embodiment of the present application provide based on The server of the fail-safe software of the user ID authentication method of user behavior feature or the third party provider of plug-in unit or The server of the service provider of " internet+" business service is provided.Described executive agent does not form the limit to the application It is fixed.For convenience of explanation, the embodiment of the present application is mainly introduced so that executive agent is server as an example.

As shown in figure 1, a kind of user ID authentication method based on user behavior feature that the embodiment of the present application provides, can To comprise the following steps：

S101, the quantized value that user to be verified triggers behavioural characteristic when pre-set business operates is obtained, determine the behavior The behavioural characteristic mark of feature；

Wherein, the behavioural characteristic includes one or more of：Gyroscope fluctuation behavioural characteristic, slide behavioural characteristic and Click on behavioural characteristic, etc..

Accordingly, the quantized value of gyroscope fluctuation behavioural characteristic can specifically include：Data are fluctuated according to gyroscope to calculate Obtained magnitude of angular velocity etc..One or more of can specifically be included by sliding the quantized value of behavioural characteristic：The end of sliding trace Put relative to the one or more in the abscissa offset and ordinate offset, sliding distance and sliding speed of starting point, Etc..Clicking on the quantized value of behavioural characteristic can specifically include：Coordinate value corresponding to click location etc..

Behavioural characteristic identifies, it can be understood as is the mark that can distinguish variety classes behavioural characteristic.Also, having When body is realized, the mark of behavioural characteristic according to the attribute of the quantized value of the behavioural characteristic got, can be specifically determined.Wherein, The attribute of the quantized value of behavioural characteristic, such as can be the unit of quantized value, number range of quantized value etc..Specifically, such as Fruit says that the unit of the quantized value got is rad/s, then it is magnitude of angular velocity that can determine the quantized value, and corresponding behavioural characteristic should The feature of behavior is fluctuated for gyroscope, can thus be identified accordingly based upon the attribute of the quantized value prestored with behavioural characteristic Corresponding relation, determine the mark of behavioural characteristic.

Certainly, in actual applications, the mark of behavioural characteristic can also be determined by other means, and aforesaid way is only Citing.

For example, gyroscope fluctuation behavioural characteristic, slip behavioural characteristic and the behavioural characteristic mark for clicking on behavioural characteristic Can be respectively：001st, Serial No. as 002 and 003.

Above-mentioned pre-set business operation, can be that the business that the predetermined any required identity to user is verified is grasped Make, for example, log in be arranged on terminal on APP register, in terminal log in mailbox operation, phase is logged in terminal Operation that the operation of pass website, the screen to terminal are unlocked, etc..

Above-mentioned terminal can be the mobile terminals such as smart mobile phone, tablet personal computer, notebook computer or electric paper book.On also, Gyroscope and touch-screen can be provided with by stating in terminal.

In specific implementation, the application programming interface (Application in the operating system of terminal can be passed through Programming Interface, API) function obtains the quantized value of above-mentioned behavioural characteristic, for example, can pass through MotionEvent functions obtain quantized value --- the magnitude of angular velocity on gyroscope fluctuation behavior.

S102, identify according to the behavioural characteristic, obtain in subordinate act feature database corresponding with behavioural characteristic mark The quantized value excursion of behavioural characteristic；

Wherein, the quantized value that behavioural characteristic mark and the behavioural characteristic of validated user are stored with the behavioural characteristic storehouse becomes Change the corresponding relation of scope.

Exemplarily, above-mentioned corresponding relation can be stored in behavioural characteristic storehouse in the form of following：(behavioural characteristic identifies, The excursion of excursion // quantized value 3 of excursion // quantized value 2 of quantized value 1 // ...), wherein symbol " // " is used for Different quantized values corresponding to same behavior feature are separated.

For example, according to above, if gyroscope fluctuation behavioural characteristic is identified as 001, gyroscope fluctuates behavioural characteristic Quantized value is magnitude of angular velocity, then, above-mentioned corresponding relation can be expressed as：(001,1~2rad/s)；If slide behavioural characteristic Be identified as 002, the quantized value for sliding behavioural characteristic be respectively slip behavior terminal relative to starting point abscissa offset Amount and ordinate offset, sliding distance and sliding speed, then, above-mentioned corresponding relation can be expressed as：(002,2~ 2.5cm//3~3.5cm//3.5~4cm//4~4.5cm/s).

Due in actual applications, validated user may possess multiple different terminals simultaneously, and validated user may be Pre-set business operation is triggered in its any terminal possessed, but the screen size of different terminals and different terminals are used Gyroscope be possible to different；Also, the type of pre-set business operation can also more than one.Therefore, in detail, behavioural characteristic In storehouse, the behavior of terminal iidentification, the type identification of pre-set business operation, behavioural characteristic value mark and validated user can be stored with Corresponding relation between the quantized value excursion of feature, and specifically can be stored by following form：(terminal iidentification, preset industry The type identification of business operation, behavioural characteristic mark, excursion // quantized value 3 of excursion // quantized value 2 of quantized value 1 Excursion // ...).

Further, since validated user is also different using left hand and using the quantized value of behavioural characteristic caused by the right hand , the most it will be evident that as shown in Fig. 2 when behavioural characteristic is slides behavioural characteristic, user uses the sliding trace that left hand is formed For the first circular arc 1 of left opening, the sliding trace that user is formed using the right hand is the second circular arc 2 of right opening.Therefore, in behavior In feature database, the quantization of the behavioural characteristic of the validated user of the left hand for corresponding respectively to validated user and the right hand can also be stored with The corresponding relation of value changes scope.For example, following corresponding relation can be stored with behavioural characteristic storehouse：(left hand or right hand mark, Terminal iidentification, the type identification of pre-set business operation, behavioural characteristic mark, the change of excursion // quantized value 2 of quantized value 1 The excursion of scope // quantized value 3 // ...).

S103, quantized value and the relation of the quantized value excursion got according to the behavioural characteristic, it is determined that described The legitimacy of user to be verified.

Specifically, step S103 can include：When the quantized value of the behavioural characteristic falls into the quantized value change got When changing scope, or, when the quantized value and the absolute value of the difference of the quantized value excursion got of the behavioural characteristic are small When five preset values, the user to be verified is defined as validated user.Wherein, the 5th preset value can be artificial as needed Setting.

In more detail, step S103 can specifically include：When each quantized value of each behavioural characteristic of acquisition falls When entering in the quantized value excursion of corresponding behavioural characteristic, or, quantized value and acquisition when each behavioural characteristic of acquisition To the absolute value of difference of quantized value excursion be respectively less than corresponding five preset value when, the user to be verified is determined For validated user；Otherwise, the user to be verified is defined as disabled user.

Alternatively, in another embodiment, due in addition to the verification mode that the embodiment of the present application provides, generally going back Ensure also to match using the username and password of account, could finally be verified, therefore, step S103 can specifically be wrapped Include：When the quantized value of the behavioural characteristic falls into the quantized value excursion got, and the user of the user to be verified Name and password authentification by the user to be verified by being defined as validated user.Or step S103 can specifically include：When When the absolute value of the difference of the quantized value of the behavioural characteristic and the quantized value excursion got is less than five preset values, and The username and password of the user to be verified is verified, and the user to be verified is defined as into validated user.

Further, when it is that validated user is legal that obtained the result, which is the user to be verified, can subsequently ring Above-mentioned pre-set business operation and should be performed；When it is disabled user that obtained the result, which is the user to be verified, then do not ring The pre-set business is answered to operate.Assuming that the pre-set business operation is register, when obtained the result is described to be tested When card user is illegal, then interface of logging off, or ejection login failure interface etc., to prevent the data of pairing method user And property safety causes damage.

Due under same business operation, different user hold the posture of same terminal and operating habit be it is different, This cause different user triggered in same terminal the behavioural characteristic of same business operation quantized value excursion it is also different, and And it is not easy to be imitated, cracks.Therefore, a kind of user based on user behavior feature that the embodiment shown in the application Fig. 1 provides Auth method, the legitimacy of the user of triggering pre-set business operation can be identified exactly, user identity is improved and tests The security of card.

Further, it is to be appreciated that when corresponding to the type of behavioural characteristic and/or the behavioural characteristic of each type obtained When the type of quantized value is more, the user ID authentication method based on user behavior feature of the embodiment of the present application offer cracks Difficulty is bigger, and the result drawn is more accurate, can more improve the security of user identity identification.

Further, when operating different terminals using different hand due to validated user as previously described, obtained different behaviors The quantized value excursion of behavioural characteristic corresponding to signature identification is different, therefore, alternatively, in a kind of specific embodiment party In formula：

Before step S102, a kind of subscriber authentication side based on user behavior feature of the embodiment of the present application offer Method can also include：

Step 1, determine that user to be verified triggers following one or more parameters when pre-set business operates：It is described to be verified It is the identifying of terminal used in user, the mark of the hand of the user to be verified (being used to distinguish left hand or the right hand), described pre- If the type identification of business operation；

Wherein, the mark of user terminal can be the model of terminal.

Step 2, judge in the behavioural characteristic storehouse to whether there is and one or more of parameters and behavior spy The quantized value excursion of the corresponding behavioural characteristic of sign mark；If it is, perform step S102；Otherwise, directly by described in User to be verified is defined as disabled user.

Also, corresponding, step S102 can specifically include：It is special according to one or more of parameters and the behavior Sign is identified, and it is special that behavior corresponding with one or more of parameters and behavioural characteristic mark is obtained in subordinate act feature database The quantized value excursion of sign；Wherein, the mark of hand, terminal iidentification, pre-set business operation are stored with the behavioural characteristic storehouse Type identification, behavioural characteristic mark and validated user behavioural characteristic quantized value excursion corresponding relation.

It can be seen that the embodiment of the present application, except the quantized value according to the behavioural characteristic and the quantization value changes model got Outside the relation enclosed, the identifying of used terminal when pre-set business operates, user to be verified are also triggered by user to be verified Mark of hand etc., the legitimacy of user to be verified is judged from multiple dimensions, therefore, the security of authentication is higher.For example, such as In fruit behavioural characteristic storehouse, only the corresponding validated user that stores triggers pre-set business by the right hand in the terminal that terminal iidentification is X Corresponding relation during operation, sliding behavior 002 and quantized value excursion, then pass through left hand when getting user to be verified When triggering pre-set business operation in the terminal that terminal iidentification is X, the user to be verified is clearly illegal, can be directly true The fixed user to be verified is illegal.

As shown in figure 3, the embodiment of the present application additionally provides a kind of behavioural characteristic storehouse method for building up, it is to be understood that should Behavioural characteristic storehouse method for building up can also be referenced to a kind of user based on user behavior feature of the embodiment of the present application offer In auth method.Behavior feature database method for building up can include (it is also understood that before above-mentioned steps S102, A kind of user ID authentication method based on user behavior feature that the embodiment of the present application provides can also include)：

S301, the first set pre-saved is obtained, included in the first set：Validated user triggering pre-set business behaviour The quantized value of behavioural characteristic when making identifies with corresponding behavioural characteristic；

In step s 103, behavior of the validated user when triggering pre-set business operation in default terminal can specifically be obtained The first set that the quantized value of feature is formed.

Validated user, can be the corresponding owner or lawful owner using account of the pre-set business operation, wherein, For example can be Alipay account, Net silver account, etc. using account.

In actual applications, validated user can trigger pre-set business operation with continuous several times, to obtain above-mentioned first set, Pre-set business operation can also be discontinuously triggered, to obtain above-mentioned first set.Specifically can be by nearly one week of validated user The quantized value of caused behavioural characteristic value or the nearly internal trigger in month of validated user are pre- when triggering pre-set business operation If the quantized value of caused behavioural characteristic value during business operation, it can also be that validated user is nearly M times (M can be more than or equal to 10) The quantized value of caused behavioural characteristic value, the application are not limited this when triggering pre-set business operation.

S302, the quantized value in the first set is screened, to obtain validated user described in energy accurate characterization The quantized value of user characteristics is added in second set；

Specifically, step S302 can include：The irregular data in first set is removed using preset algorithm, to obtain Obtain the quantized value of the user characteristics of validated user can be added in second set described in accurate characterization.So-called irregular data, can With the difference larger quantization value being not understood as in first set with benchmark quantized value.

Above-mentioned preset algorithm can be the filtering algorithm based on mean algorithm or the filtering algorithm based on radiation area algorithm, etc. Deng.Wherein, the filtering algorithm based on mean algorithm, can specifically refer to remove in first set, with first set respectively quantifying The algorithm of the average value larger quantization value of value.Filtering algorithm based on radiation area, it can specifically refer to, first according to first The basic distribution of part quantized value structure quantized value in set, then remove in first set not within the scope of this The algorithm of quantized value.

Alternatively, temporal information caused by the quantized value of behavioural characteristic is also included in the first set, a kind of specific In embodiment, step S302 can specifically include：

Step 1, the quantized value in the first set, determine benchmark quantized value；

Wherein, benchmark quantized value includes earliest quantized value of caused time or the first set in the first set In each quantized value average value；

Step 2, each quantized value is calculated in the first set relative to the relative value of the benchmark quantized value；Wherein, institute State difference or ratio of the relative value for each quantized value relative to the benchmark quantized value；

Step 3, choose the quantized value for meeting the first preparatory condition in the first set, using as can accurate characterization it is legal The quantized value of the user characteristics of user is added in second set；Wherein, first preparatory condition includes：The relative value is less than The duration away from current time is less than preset duration at the time of first preset value and/or quantized value produce.

First preset value can be rule of thumb manually set, and it is to be appreciated that difference and corresponding to ratio One preset value can be different.The quantized value (magnitude of angular velocity) that behavior is fluctuated using the quantized value that is stored in first set as gyroscope is For example, the span of the first preset value corresponding to above-mentioned difference can be between 2~3rad/s, the corresponding to above-mentioned ratio The span of one preset value can be between 0.9~1.1.

Above-mentioned preset duration can also be manually set, such as can be one week, one month, etc..Above-mentioned current time tool At the time of body can be that user triggers step S101.

It can be appreciated that this embodiment can screen out the irregular data in first set well, it is follow-up The checking for carrying out user identity is laid a good foundation.

Alternatively, temporal information caused by the quantized value of behavioural characteristic is also included in the first set, has in another kind In body embodiment, step S302 can specifically include：

Step 1, according to the sequencing of time caused by quantized value the quantized value in the first set is ranked up；

Step 2, by first quantized value in the first set after sequence, be defined as benchmark quantized value；

Step 3, circulation perform given step, until the quantized value in the first set after having traveled through sequence；It is described Given step includes：

Sub-step 1, calculate relative value of the current quantisation value relative to benchmark quantized value；The relative value is current quantisation value Relative to the difference or ratio of benchmark quantized value；

Sub-step 2, the current quantisation value that the relative value is less than the second preset value is chosen, to be used as energy accurate characterization The quantized value of the user characteristics of validated user is added in second set；

After the current quantisation value of selection is added in the second set, when currently being preserved in the second set The quantity of quantized value when being more than or equal to predetermined number, the given step also includes：

Sub-step 3, redefine the benchmark quantized value；Wherein, redefining the benchmark quantized value includes, by described in The average value of currently stored each quantized value in second set, as the benchmark quantized value after redefining.

It can not be accurately reflected it is also understood that another embodiment also can be screened out preferably in first set The irregular data of validated user operating habit, have laid a good foundation, contribute to for the follow-up checking for carrying out user identity Improve the security of subscriber authentication.

It should be noted that in actual applications, screening is carried out to the quantized value in first set and obtains second set Mode can be not limited to above two, and other modes for screening out irregular quantized value are also applied for the embodiment of the present application.

S303, the quantized value in the second set, determine behavioural characteristic corresponding to the behavioural characteristic mark Quantized value excursion；

In a kind of embodiment, step S303 can specifically include：According to quantized value in the second set Maximum and minimum value, determine the first number range；By first number range, it is corresponding to be defined as the behavioural characteristic mark Behavioural characteristic quantized value excursion.

In another embodiment, step S303 can specifically include：Build the quantized value in second set Normal distribution model, it is determined that the quantized value of the center section of the normal distribution model is distributed in, and according to the center section The maximum and minimum value of quantized value determine second value scope；By the second value scope, it is defined as the behavioural characteristic The quantized value excursion of behavioural characteristic corresponding to mark.

S304, the quantized value excursion for accordingly storing the behavioural characteristic mark and the behavioural characteristic, with To the behavioural characteristic storehouse.

, therefore, can be according to being actually needed further, since validated user may possess multiple different terminals simultaneously, pin The one or more terminals possessed validated user perform above-mentioned steps S301 to S304 respectively, so that in behavioural characteristic storehouse, deposit Contain the above-mentioned corresponding relation for different terminals.And/or according to being actually needed, left hand and the right hand point for validated user Not Zhi Hang above-mentioned steps S301 to S304 so that in behavioural characteristic storehouse, be stored with the left hand for being directed to user respectively and the right hand Above-mentioned corresponding relation.

It is conceivable that the behavioural characteristic established according to a kind of the embodiment of the present application offer behavioural characteristic storehouse method for building up Storehouse, the situation of change of the quantized value of behavioural characteristic of the validated user when triggering pre-set business operation can be reflected exactly, be It is follow-up to identify the corresponding relation with the quantized value of behavioural characteristic to user's according to the behavioural characteristic stored in behavior feature database Identity carries out checking and had laid a good foundation, and is favorably improved the security of subscriber authentication.

With reference to practical application scene a kind of user identity based on user behavior feature is provided to the embodiment of the present application Verification method illustrates.

Fig. 4 and Fig. 5 are refer to, Fig. 4 is a kind of user identity based on user behavior feature that the embodiment of the present application provides The schematic flow sheet of verification method in actual applications.Fig. 5 is that one kind that the embodiment of the present application provides is based on user behavior feature User ID authentication method system structure diagram in actual applications.As shown in Figure 4 and Figure 5, in actual applications, it is real Three equipment can be included by applying the system of this method, and these three equipment are respectively：Corresponding to terminal 3, server 4 and pre-set business Server 5.

In order to make it easy to understand, needing to illustrate in advance, in Fig. 4, diamond represents data, and rectangle frame represents and performs step Suddenly.Specifically as shown in figure 4, this method may include steps of：

S401, user's operation：It can be specifically the slip that user to be verified makes triggering pre-set business operation in terminal 3 Operation such as operation and/or click, etc.；

S402, behavior are collected：It can be specifically the type that terminal 3 determines the pre-set business operation that user to be verified is triggered Mark, and the behavioural characteristic obtained when user to be verified triggers pre-set business operation identifies and the quantized value A of behavioural characteristic, and The mark of terminal 3；

S403, terminal 3 will include the type identification of identified pre-set business operation, behavioural characteristic identifies, behavior is special The quantized value of sign and the first information of the mark of terminal 3 are sent to server 4；

Server 4 can be understood as being to provide the service of the software of the method for identifying ID or the provider of plug-in unit Device.

S404 and S405, data preparation and statistics：Server 4 is arranged and counted to the first information, is therefrom extracted The effectively letter of mark of type identification, behavioural characteristic mark, the quantized value of behavioural characteristic and terminal 3 that pre-set business operates etc. first Breath；

S406, data analysis：Server 4 is according to the mark of terminal 3, the type identification and behavioural characteristic of pre-set business operation Mark, in subordinate act feature database, obtain and the identifying of terminal 3, the type identification and behavioural characteristic mark of pre-set business operation The quantized value excursion of the behavioural characteristic of validated user corresponding to knowledge；And the quantized value according to each behavioural characteristic and corresponding amount Change the matching relationship of value changes scope, draw the result B.

S407, server 4 are sent the result B drawn as the second information to server 5 corresponding to pre-set business；

Wherein, pre-set business can be business corresponding to the operation of above-mentioned pre-set business.For example, pre-set business operation can To be logged on the business operation of Net silver, corresponding pre-set business can be ebanking services.So server corresponding to pre-set business, It then can be understood as providing the server of the provider of ebanking services.

S408, data preparation：Server 5 corresponding to pre-set business is carried out to the data content in the second information for receiving Arrange, determine the second effective information；

Wherein, the second effective information, can be the result.

S409, data are won：Server 5 corresponding to pre-set business is won out above-mentioned second from the second information and effectively believed Breath；

Server 5 corresponding to S410, pre-set business determines whether user to be verified is legal according to the second effective information, and According to result is determined, step S411 is performed；

5 pairs of server corresponding to S411, pre-set business determines that result is shown.

Such a specific application scenarios of Net silver are logged in for example with user to be verified, step S411 can specifically be wrapped Include：Server 5 corresponding to pre-set business determines that result is shown in Net silver login interface on pair, also, when determination result is When user to be verified is illegal, prompt message as " login failure " can be shown；When it is determined that result is closed for user to be verified During method, login interface can be skipped and switch to Net silver operation interface.For example, Net silver operation interface can be query interface, Transfer accounts interface, payment interface etc..

Exemplarily given in Fig. 5 content performed by terminal 3, server 4 and server 5 corresponding to pre-set business and Mutual interactive relation, substantially process is similar with the process shown in Fig. 4 for it, carries out brief description below.

In Figure 5, user to be verified interacts triggering pre-set business operation with terminal 3；Terminal 3 triggers according to user to be verified Pre-set business operation carry out behavioural characteristic the data such as quantized value collection, and the data being collected into are sent to server 4. After server 4 receives data, arranged, counted, and quantized value and the behavioural characteristic storehouse that the behavioural characteristic after counting will be arranged The corresponding quantization value changes scope of middle storage is matched, and draws the result, and the result drawn is sent to default Server 5 corresponding to business；Meanwhile server 4 is sending the result to server 5 corresponding to pre-set business, also needs Cache management is carried out to the result；Further, since server 4 need it is corresponding with terminal 3 and pre-set business by network Server 5 carries out data transmission, and therefore, network management is also carried out in server 4.Server 5 docks corresponding to pre-set business The result received carries out data and wins and show.

Corresponding to above method embodiment, the embodiment of the present application additionally provides a kind of user's body based on user behavior feature Part checking device, is illustrated below in conjunction with the accompanying drawings.

As indicated with 6, a kind of subscriber authentication device based on user behavior feature that the embodiment of the present application provides, can be with Including：First acquisition module 601, the second acquisition module 602 and the first determining module 603.

First acquisition module 601, the quantization of behavioural characteristic when pre-set business operates is triggered for obtaining user to be verified Value, determine the behavioural characteristic mark of the behavioural characteristic；

Second acquisition module 602, for being identified according to the behavioural characteristic, obtained and the behavior in subordinate act feature database The quantized value excursion of behavioural characteristic corresponding to signature identification；

Wherein, the quantized value that behavioural characteristic mark and the behavioural characteristic of validated user are stored with the behavioural characteristic storehouse becomes Change the corresponding relation of scope；

First determining module 603, for the quantized value according to the behavioural characteristic and the quantized value excursion got Relation, determine the legitimacy of the user to be verified.

Above-mentioned first determining module 603, specifically it can be used for when the quantized value of the behavioural characteristic falls into the amount got When changing value changes scope, or, when the behavioural characteristic quantized value and the difference of quantized value excursion that gets it is exhausted When being less than five preset values to value, the user to be verified is defined as validated user.Wherein, the 5th preset value can be according to need It is manually set.

In more detail, above-mentioned first determining module 603, specifically can be used for when obtain each behavioural characteristic it is each When quantized value is each fallen within the quantized value excursion of corresponding behavioural characteristic, or, when the amount of each behavioural characteristic of acquisition , will be described to be tested when change value is respectively less than corresponding five preset value with the absolute value of the difference of the quantized value excursion got Card user is defined as validated user；Otherwise, the user to be verified is defined as disabled user.

Alternatively, in another embodiment, due in addition to the verification mode that the embodiment of the present application provides, generally going back Ensure also to match using the username and password of account, could finally be verified, therefore, above-mentioned first determining module 603, Specifically it can be used for when the quantized value of the behavioural characteristic falls into the quantized value excursion got, and the use to be verified The username and password at family is verified, and the user to be verified is defined as into validated user.Or above-mentioned first determining module 603, it specifically can be used for the absolute value when the quantized value of the behavioural characteristic and the difference of the quantized value excursion got During less than five preset values, and the username and password of the user to be verified is verified, and the user to be verified is determined For validated user.

Due under same business operation, different user hold the posture of same terminal and operating habit be it is different, This cause different user triggered in same terminal the behavioural characteristic of same business operation quantized value excursion it is also different, and And it is not easy to be imitated, cracks.Therefore, a kind of user based on user behavior feature that the embodiment shown in the application Fig. 6 provides Authentication means, the legitimacy of the user to be verified of triggering pre-set business operation can be identified exactly, improves user The security of authentication.

Further, it is to be appreciated that when corresponding to the type of behavioural characteristic and/or the behavioural characteristic of each type obtained When the type of quantized value is more, the subscriber authentication device based on user behavior feature of the embodiment of the present application offer cracks Difficulty is bigger, and the result drawn is more accurate, can more improve the security of user identity identification.

Further, when operating different terminals using different hand due to validated user as previously described, obtained different behaviors The quantized value excursion of behavioural characteristic corresponding to signature identification is different, therefore, alternatively, in a kind of specific embodiment party In formula, a kind of subscriber authentication device based on user behavior feature that the embodiment of the present application provides can also include：

Second determining module, for being identified according to the behavioural characteristic, obtained and the behavior in subordinate act feature database Before the quantized value excursion of behavioural characteristic corresponding to signature identification, determine when user to be verified triggers pre-set business operation with Next or multiple parameters：The identifying of terminal used in the user to be verified, the mark of the hand of the user to be verified (are used In distinguishing left hand or the right hand), the type identification of pre-set business operation；

Judge module, for judging to whether there is and one or more of parameters, Yi Jisuo in the behavioural characteristic storehouse State the quantized value excursion of behavioural characteristic corresponding to behavioural characteristic mark；If it is, the second acquisition module 602 of triggering；Otherwise, The user to be verified is directly defined as disabled user.

Also, corresponding, now the second acquisition module 602, specifically can be used for according to one or more of parameters with Obtain and the behavioural characteristic identifies, in subordinate act feature database and identified with one or more of parameters and the behavioural characteristic The quantized value excursion of corresponding behavioural characteristic；Wherein, be stored with the behavioural characteristic storehouse mark of hand, terminal iidentification, The type identification of pre-set business operation, behavioural characteristic identify and the correspondence of the quantized value excursion of the behavioural characteristic of validated user Relation.

It can be seen that the embodiment of the present application, except the quantized value according to the behavioural characteristic and the quantization value changes model got Outside the relation enclosed, the mark of used terminal, mark of hand of user etc. when pre-set business operates also are triggered by user, from Multiple dimensions judge the legitimacy of user, and therefore, the security of authentication is higher.It is if only right for example, in behavioural characteristic storehouse Validated user should be stored when pre-set business operates, slip behavior 002 is being triggered by the right hand in the terminal that terminal iidentification is X With the corresponding relation of corresponding quantized value excursion, then when getting user to be verified by left hand be X in terminal iidentification Terminal on trigger pre-set business operation when, it is clear that be illegal, can directly determine that the user to be verified is illegal.

As shown in fig. 7, the embodiment of the present application, which additionally provides a kind of behavioural characteristic storehouse, establishes device, it is to be understood that should Device is established in behavioural characteristic storehouse can also be referenced to a kind of user based on user behavior feature of the embodiment of the present application offer In authentication means.Behavior feature database, which establishes device, can be included (it is also understood that the one of the embodiment of the present application offer Subscriber authentication device of the kind based on user behavior feature can also include)：3rd acquisition module 701, data processing module 702nd, excursion determining module 703 and feature database establish module 704.

3rd acquisition module 701, for obtaining the first set pre-saved, included in the first set：Legal use The quantized value of behavioural characteristic during family triggering pre-set business operation identifies with corresponding behavioural characteristic；

Data processing module 702, for being screened to the quantized value in the first set, to obtain energy accurate characterization The quantized value of the user characteristics of the validated user is added in second set；

Specifically, data processing module 702, specifically can be used for removing not advising in first set using preset algorithm Then data, the quantized value of the user characteristics of validated user it can be added to obtaining described in accurate characterization in second set.It is so-called not Regular data, it can be understood as be the difference larger quantization value with benchmark quantized value in first set.

Alternatively, temporal information caused by the quantized value of behavioural characteristic is also included in the first set, a kind of specific In embodiment, the data processing module 702, it can include：

First reference value determination sub-module, for the quantized value in the first set, determine benchmark quantized value；Institute Stating benchmark quantized value includes each quantized value in earliest quantized value of caused time in the first set or the first set Average value；

First calculating sub module, for calculating in the first set each quantized value relative to the phase of the benchmark quantized value To value；Wherein, the relative value is difference or ratio of each quantized value relative to the benchmark quantized value；

First data decimation submodule, meet the quantized value of the first preparatory condition in the first set for choosing, with Quantized value as the user characteristics of energy accurate characterization validated user is added in second set；Wherein, first preparatory condition Including：When the duration away from current time is less than default at the time of the relative value is less than the first preset value and/or quantized value generation It is long.

Alternatively, temporal information caused by the quantized value of behavioural characteristic is also included in the first set, has in another kind In body embodiment, the data processing module 702, it can specifically include：

Sorting sub-module, for the sequencing according to the time caused by quantized value to the quantized value in the first set It is ranked up；

Second a reference value determination sub-module, for by first quantized value in the first set after sequence, it is determined that On the basis of quantized value；

Submodule is triggered, for circulating the second calculating sub module of triggering, the second data decimation submodule and a reference value renewal Submodule, the quantized value in the first set after having traveled through sequence：

Second calculating sub module, for calculating relative value of the current quantisation value relative to benchmark quantized value；The phase To being worth difference or ratio for current quantisation value relative to benchmark quantized value；

The second data decimation submodule, the current quantisation of the second preset value is less than for choosing the relative value Value, added using the quantized value of the user characteristics as energy accurate characterization validated user in second set；

The a reference value updates submodule, for being added by the current quantisation value of selection in the second set Afterwards, when the quantity of the quantized value currently preserved in the second set is more than or equal to predetermined number, the base is redefined Quasi- quantized value；Wherein, redefining the benchmark quantized value includes, by each quantized value currently stored in the second set Average value, as the benchmark quantized value after redefining.

It can not be accurately reflected it is also understood that another embodiment also can be screened out preferably in first set The irregular data of validated user operating habit, have laid a good foundation, contribute to for the follow-up checking for carrying out user identity Improve the accuracy of subscriber authentication.

Excursion determining module 703, for the quantized value in the second set, determine the behavioural characteristic mark The quantized value excursion of behavioural characteristic corresponding to knowledge；

In a kind of embodiment, the excursion determining module 703, specifically it can be used for according to described second The maximum and minimum value of quantized value, determine the first number range in set；By first number range, it is defined as the row It is characterized the quantized value excursion of behavioural characteristic corresponding to mark.

In another embodiment, the excursion determining module 703, it specifically can be used for the collection of structure second The normal distribution model of quantized value in conjunction, it is determined that the quantized value of the center section of the normal distribution model is distributed in, and root Second value scope is determined according to the maximum and minimum value of the quantized value of the center section；By the second value scope, it is determined that For the quantized value excursion of behavioural characteristic corresponding to behavioural characteristic mark.

Feature database establishes module 704, for accordingly storing the amount of the behavioural characteristic mark and the behavioural characteristic Change value changes scope, to obtain the behavioural characteristic storehouse.

, therefore, can be according to being actually needed further, since validated user may possess multiple different terminals simultaneously, pin The one or more terminals possessed validated user trigger above-mentioned module 701 to 704 respectively, so that in behavioural characteristic storehouse, storage There is the above-mentioned corresponding relation for different terminals.And/or according to being actually needed, left hand and right hand difference for validated user Above-mentioned module 701 to 704 is triggered, so that in behavioural characteristic storehouse, is stored with the above-mentioned of the left hand for being directed to user respectively and the right hand Corresponding relation.

It is conceivable that providing a kind of behavioural characteristic storehouse according to the embodiment of the present application establishes the behavioural characteristic that device is established Storehouse, the situation of change of the quantized value of behavioural characteristic of the validated user when triggering pre-set business operation can be reflected exactly, be It is follow-up to identify the corresponding relation with the quantized value of behavioural characteristic to user's according to the behavioural characteristic stored in behavior feature database Identity carries out checking and had laid a good foundation, and is favorably improved the security of subscriber authentication.

Fig. 8 shows the structural representation for a kind of electronic equipment for being the embodiment of the present application offer.Fig. 8 is refer to, hard Part aspect, the electronic equipment include processor, alternatively also include internal bus, network interface, memory.Wherein, memory Internal memory, such as high-speed random access memory (Random-Access Memory, RAM) may be included, it is also possible to also including non- Volatile memory (non-volatile memory), for example, at least 1 magnetic disk storage etc..Certainly, the electronic equipment may be used also The hardware required for other business can be included.

Processor, network interface and memory can be connected with each other by internal bus, and the internal bus can be ISA (Industry Standard Architecture, industry standard architecture) bus, PCI (Peripheral Component Interconnect, Peripheral Component Interconnect standard) bus or EISA (Extended Industry Standard Architecture, EISA) bus etc..The bus can be divided into address bus, data/address bus, control always Line etc..For ease of representing, only represented in Fig. 8 with a four-headed arrow, it is not intended that an only bus or a type of Bus.

Memory, for depositing program.Specifically, program can include program code, and described program code includes calculating Machine operational order.Memory can include internal memory and nonvolatile memory, and provide instruction and data to processor.

Processor read from nonvolatile memory corresponding to computer program into internal memory then run, in logical layer Network covering property characterization apparatus is formed on face.Processor, the program that memory is deposited is performed, and it is following specifically for performing Operation：

The subscriber authentication device based on user behavior feature disclosed in the above-mentioned embodiment illustrated in fig. 8 such as the application performs Method can apply in processor, or realized by processor.Processor is probably a kind of IC chip, has letter Number disposal ability.In implementation process, each step of the above method can pass through the integration logic electricity of the hardware in processor The instruction of road or software form is completed.Above-mentioned processor can be general processor, including central processing unit (Central Processing Unit, CPU), network processing unit (Network Processor, NP) etc.；It can also be Digital Signal Processing Device (Digital Signal Processor, DSP), application specific integrated circuit (Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-Programmable Gate Array, FPGA) or other can Programmed logic device, discrete gate or transistor logic, discrete hardware components.It can realize or perform the application implementation Disclosed each method, step and logic diagram in example.General processor can be that microprocessor or the processor can also It is any conventional processor etc..The step of method with reference to disclosed in the embodiment of the present application, can be embodied directly in hardware decoding Computing device is completed, or performs completion with the hardware in decoding processor and software module combination.Software module can position In random access memory, flash memory, read-only storage, programmable read only memory or electrically erasable programmable memory, register Deng in the ripe storage medium in this area.The storage medium is located at memory, and processor reads the information in memory, with reference to it Hardware completes the step of above method.

The embodiment of the present application also proposed a kind of computer-readable recording medium, the computer-readable recording medium storage one Individual or multiple programs, one or more programs include instruction, and the instruction is held when the electronic equipment for being included multiple application programs During row, the electronic equipment can be made to perform the subscriber authentication device based on user behavior feature in embodiment illustrated in fig. 8 and held Capable method, and specifically for performing：

It should be understood by those skilled in the art that, embodiments herein can be provided as method, system or computer program Product.Therefore, the application can use the reality in terms of complete hardware embodiment, complete software embodiment or combination software and hardware Apply the form of example.Moreover, the application can use the computer for wherein including computer usable program code in one or more The computer program production that usable storage medium is implemented on (including but is not limited to magnetic disk storage, CD-ROM, optical memory etc.) The form of product.

The application is with reference to the flow according to the method for the embodiment of the present application, equipment (system) and computer program product Figure and/or block diagram describe.It should be understood that can be by every first-class in computer program instructions implementation process figure and/or block diagram Journey and/or the flow in square frame and flow chart and/or block diagram and/or the combination of square frame.These computer programs can be provided The processors of all-purpose computer, special-purpose computer, Embedded Processor or other programmable data processing devices is instructed to produce A raw machine so that produced by the instruction of computer or the computing device of other programmable data processing devices for real The device for the function of being specified in present one flow of flow chart or one square frame of multiple flows and/or block diagram or multiple square frames.

These computer program instructions, which may be alternatively stored in, can guide computer or other programmable data processing devices with spy Determine in the computer-readable memory that mode works so that the instruction being stored in the computer-readable memory, which produces, to be included referring to Make the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one square frame of block diagram or The function of being specified in multiple square frames.

These computer program instructions can be also loaded into computer or other programmable data processing devices so that counted Series of operation steps is performed on calculation machine or other programmable devices to produce computer implemented processing, so as in computer or The instruction performed on other programmable devices is provided for realizing in one flow of flow chart or multiple flows and/or block diagram one The step of function of being specified in individual square frame or multiple square frames.

It should be noted that each embodiment in the application is described by the way of related, between each embodiment Identical similar part is mutually referring to what each embodiment stressed is the difference with other embodiment.Especially Its, for device embodiment, because it is substantially similar to embodiment of the method, so description is fairly simple, related part Illustrate referring to the part of embodiment of the method.

It should also be noted that, term " comprising ", "comprising" or its any other variant are intended to nonexcludability Comprising so that process, method, commodity or equipment including a series of elements not only include those key elements, but also wrapping Include the other element being not expressly set out, or also include for this process, method, commodity or equipment intrinsic want Element.In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that including key element Other identical element in process, method, commodity or equipment also be present.

Embodiments herein is these are only, is not limited to the application.To those skilled in the art, The application can have various modifications and variations.All any modifications made within spirit herein and principle, equivalent substitution, Improve etc., it should be included within the scope of claims hereof.

Claims

1. a kind of user ID authentication method based on user behavior feature, it is characterised in that methods described includes：

The first set pre-saved is obtained, is included in the first set：Row during validated user triggering pre-set business operation The quantized value being characterized identifies with corresponding behavioural characteristic；

According to the quantized value in the first set, benchmark quantized value is determined；The benchmark quantized value includes the first set In in earliest quantized value of caused time or the first set each quantized value average value；

Each quantized value is calculated in the first set relative to the relative value of the benchmark quantized value；Wherein, the relative value is Each quantized value relative to the benchmark quantized value difference or ratio；

The quantized value for meeting the first preparatory condition in the first set is chosen, using the user as energy accurate characterization validated user The quantized value of feature is added in second set；Wherein, first preparatory condition includes：The relative value is less than the first preset value And/or the duration away from current time is less than preset duration at the time of quantized value generation；

According to the quantized value in the second set, the quantization value changes of behavioural characteristic corresponding to the behavioural characteristic mark are determined Scope；

The quantized value excursion of the behavioural characteristic mark and the behavioural characteristic is accordingly stored, to obtain behavioural characteristic Storehouse；

The quantized value that user to be verified triggers behavioural characteristic when pre-set business operates is obtained, determines the behavior of the behavioural characteristic Signature identification；The behavioural characteristic includes one or more of：Gyroscope fluctuation behavioural characteristic, slide behavioural characteristic and click Behavioural characteristic；

Identify according to the behavioural characteristic, obtained and the corresponding behavioural characteristic of behavioural characteristic mark in subordinate act feature database Quantized value excursion；Wherein, behavioural characteristic mark and the behavioural characteristic of validated user are stored with the behavioural characteristic storehouse The corresponding relation of quantized value excursion；

According to the quantized value of the behavioural characteristic and the relation of the quantized value excursion got, the user to be verified is determined Legitimacy.

2. a kind of user ID authentication method based on user behavior feature, it is characterised in that methods described includes：

The quantized value in the first set is ranked up according to the sequencing of time caused by quantized value；

By first quantized value in the first set after sequence, it is defined as benchmark quantized value；

Circulation performs given step, until the quantized value in the first set after having traveled through sequence；The given step bag Include：Calculate relative value of the current quantisation value relative to benchmark quantized value；The relative value is current quantisation value relative to datum quantity The difference or ratio of change value；The current quantisation value that the relative value is less than the second preset value is chosen, to be used as the accurate table of energy The quantized value for levying the user characteristics of validated user is added in second set；The current quantisation value of selection is being added described the After in two set, when the quantity of the quantized value currently preserved in the second set is more than or equal to the first predetermined number, institute Stating given step also includes：Redefine the benchmark quantized value；Wherein, redefining the benchmark quantized value includes, by institute The border for the touch area that each quantized value currently stored in second set limits is stated, is quantified as the benchmark after redefining Value；

3. a kind of user ID authentication method based on user behavior feature, it is characterised in that methods described includes：

4. according to the method for claim 3, it is characterised in that the process of establishing in the behavioural characteristic storehouse includes：

Quantized value in the first set is screened, to obtain the user characteristics of validated user described in energy accurate characterization Quantized value is added in second set；

The quantized value excursion of the behavioural characteristic mark and the behavioural characteristic is accordingly stored, to obtain the behavior Feature database.

5. according to the method for claim 4, it is characterised in that also include the quantized value of behavioural characteristic in the first set Caused temporal information；

The quantized value in the first set screens, special to obtain the user of validated user described in energy accurate characterization The quantized value of sign is added in second set, including：

The quantized value for meeting the first preparatory condition in the first set is chosen, using the user as energy accurate characterization validated user The quantized value of feature is added in second set；Wherein, first preparatory condition includes：The relative value is less than the first preset value And/or the duration away from current time is less than preset duration at the time of quantized value generation.

6. according to the method for claim 4, it is characterised in that also include the quantized value of behavioural characteristic in the first set Caused temporal information；

Circulation performs given step, until the quantized value in the first set after having traveled through sequence；The given step bag Include：

Calculate relative value of the current quantisation value relative to benchmark quantized value；The relative value is current quantisation value relative to datum quantity The difference or ratio of change value；

The current quantisation value that the relative value is less than the second preset value is chosen, using the use as energy accurate characterization validated user The quantized value of family feature is added in second set；

After the current quantisation value of selection is added in the second set, when the amount currently preserved in the second set When the quantity of change value is more than or equal to the first predetermined number, the given step also includes：Redefine the benchmark quantized value； Wherein, redefining the benchmark quantized value includes, the touch that each quantized value currently stored in the second set is limited The border in region, as the benchmark quantized value after redefining.

7. according to the method described in claim any one of 4-6, it is characterised in that the quantization in the second set Value, the quantized value excursion of behavioural characteristic corresponding to the behavioural characteristic mark is determined, including：

According to the maximum and minimum value of quantized value in the second set, the first number range is determined；By first numerical value Scope, it is defined as the quantized value excursion of behavioural characteristic corresponding to the behavioural characteristic mark.

8. according to the method for claim 1, it is characterised in that

The quantized value of the gyroscope fluctuation behavioural characteristic includes：The magnitude of angular velocity being calculated according to gyroscope fluctuation data；

The quantized value for sliding behavioural characteristic includes：The terminal of sliding trace is relative to the abscissa offset of starting point and vertical One or more in coordinate offset amount, sliding distance and sliding speed；

The quantized value for clicking on behavioural characteristic includes：Coordinate value corresponding to click location.

9. according to the method for claim 1, it is characterised in that according to the quantized value of the behavioural characteristic and the amount got Change the relation of value changes scope, determine the legitimacy of the user to be verified, including：

When the quantized value of the behavioural characteristic falls into the quantized value excursion got, or, when the behavioural characteristic When the absolute value of the difference of quantized value and the quantized value excursion got is less than five preset values, by the user to be verified It is defined as validated user.

10. a kind of behavioural characteristic storehouse method for building up, it is characterised in that methods described includes：

11. a kind of subscriber authentication device based on user behavior feature, it is characterised in that described device includes：

3rd acquisition module, for obtaining the first set pre-saved, included in the first set：Validated user triggering is pre- If the quantized value of behavioural characteristic during business operation identifies with corresponding behavioural characteristic；

First reference value determination sub-module, for the quantized value in the first set, determine benchmark quantized value；The base Quasi- quantized value includes in the first set the flat of each quantized value in earliest quantized value of caused time or the first set Average；

First calculating sub module, for calculating in the first set each quantized value relative to the relative of the benchmark quantized value Value；Wherein, the relative value is difference or ratio of each quantized value relative to the benchmark quantized value；

First data decimation submodule, meet the quantized value of the first preparatory condition in the first set for choosing, using as The quantized value of the user characteristics of energy accurate characterization validated user is added in second set；Wherein, first preparatory condition includes： The duration away from current time is less than preset duration at the time of the relative value is less than the first preset value and/or quantized value generation；

Excursion determining module, for the quantized value in the second set, determine that the behavioural characteristic mark is corresponding Behavioural characteristic quantized value excursion；

Feature database establishes module, for accordingly storing the quantization value changes of the behavioural characteristic mark and the behavioural characteristic Scope, to obtain behavioural characteristic storehouse；

First acquisition module, the quantized value of behavioural characteristic when pre-set business operates is triggered for obtaining user to be verified, it is determined that The behavioural characteristic mark of the behavioural characteristic；The behavioural characteristic includes one or more of：Gyroscope fluctuation behavioural characteristic, Slide behavioural characteristic and click on behavioural characteristic；

Second acquisition module, for being identified according to the behavioural characteristic, obtained and the behavioural characteristic mark in subordinate act feature database The quantized value excursion of behavioural characteristic corresponding to knowledge；Wherein, behavioural characteristic mark is stored with the behavioural characteristic storehouse and is closed The corresponding relation of the quantized value excursion of the behavioural characteristic of method user；

First determining module, for the quantized value according to the behavioural characteristic and the relation of quantized value excursion got, Determine the legitimacy of the user to be verified.

12. a kind of subscriber authentication device based on user behavior feature, it is characterised in that described device includes：

Sorting sub-module, the quantized value in the first set is carried out for the sequencing according to the time caused by quantized value Sequence；

Second a reference value determination sub-module, for by first quantized value in the first set after sequence, being defined as base Quasi- quantized value；

Submodule is triggered, for circulating the second calculating sub module of triggering, the second data decimation submodule and a reference value renewal submodule Block, the quantized value in the first set after having traveled through sequence：

Second calculating sub module, for calculating relative value of the current quantisation value relative to benchmark quantized value；The relative value Difference or ratio for current quantisation value relative to benchmark quantized value；

The second data decimation submodule, the current quantisation value of the second preset value is less than for choosing the relative value, Added using the quantized value of the user characteristics as energy accurate characterization validated user in second set；

The a reference value updates submodule, for being more than or equal to when the quantity of the quantized value currently preserved in the second set During predetermined number, the benchmark quantized value is redefined；Wherein, redefining the benchmark quantized value includes, by described second The average value of currently stored each quantized value in set, as the benchmark quantized value after redefining；

Feature database establishes module, for accordingly storing the quantization value changes of the behavioural characteristic mark and the behavioural characteristic Scope, obtain behavioural characteristic storehouse；

13. a kind of subscriber authentication device based on user behavior feature, it is characterised in that described device includes：

First acquisition module, the quantized value of behavioural characteristic when pre-set business operates is triggered for obtaining user to be verified, it is determined that The behavioural characteristic mark of the behavioural characteristic；Wherein, the behavioural characteristic includes one or more of：Gyroscope fluctuates behavior Feature, slide behavioural characteristic and click on behavioural characteristic；

14. device is established in a kind of behavioural characteristic storehouse, it is characterised in that including：

Data processing module, the quantized value in the first set is screened, to obtain legal use described in energy accurate characterization The quantized value of the user characteristics at family is added in second set；

Feature database establishes module, for accordingly storing the quantization value changes of the behavioural characteristic mark and the behavioural characteristic Scope, to obtain the behavioural characteristic storehouse.