CN109409049A - The method and apparatus of interactive operation for identification - Google Patents
The method and apparatus of interactive operation for identification Download PDFInfo
- Publication number
- CN109409049A CN109409049A CN201811179742.XA CN201811179742A CN109409049A CN 109409049 A CN109409049 A CN 109409049A CN 201811179742 A CN201811179742 A CN 201811179742A CN 109409049 A CN109409049 A CN 109409049A
- Authority
- CN
- China
- Prior art keywords
- input
- information
- machine
- operating characteristics
- characteristics vector
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 230000002452 interceptive effect Effects 0.000 title claims abstract description 30
- 239000013598 vector Substances 0.000 claims abstract description 103
- 238000012549 training Methods 0.000 claims abstract description 68
- 230000004044 response Effects 0.000 claims abstract description 29
- 238000004590 computer program Methods 0.000 claims abstract description 11
- 230000002123 temporal effect Effects 0.000 claims description 29
- 238000012512 characterization method Methods 0.000 claims description 25
- 238000003825 pressing Methods 0.000 claims description 16
- 230000009471 action Effects 0.000 claims description 12
- 241000699666 Mus <mouse, genus> Species 0.000 description 19
- 230000006870 function Effects 0.000 description 12
- 230000006399 behavior Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 230000006854 communication Effects 0.000 description 8
- 238000004891 communication Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000005291 magnetic effect Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000003066 decision tree Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000000586 desensitisation Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 210000003127 knee Anatomy 0.000 description 1
- 230000002045 lasting effect Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2221/00—Indexing scheme relating to security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F2221/21—Indexing scheme relating to G06F21/00 and subgroups addressing additional information or applications relating to security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F2221/2133—Verifying human interaction, e.g., Captcha
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computer Security & Cryptography (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The embodiment of the present application discloses the method and apparatus of interactive operation for identification.One specific embodiment of this method includes: to request in response to receiving the submission of target list, obtains the input operation information of the target list, wherein the corresponding key of character inputted in the character string that operation information includes input presses moment and release moment；Based on the input operation information, input operating characteristics vector is generated；The input operating characteristics vector is input to the man-machine identification model of training in advance, obtain classification information, wherein, man-machine identification model is used to characterize the corresponding relationship between input operating characteristics vector and classification information, and classification information comes from machine or real user for characterizing input operation.The embodiment realizes the identification to using computer program to interact operation.
Description
Technical field
The invention relates to field of computer technology, and in particular to the method and apparatus of interactive operation for identification.
Background technique
With the rapid development of Internet, the following network security problem is also increasingly prominent.Pass through " robot " journey
The case where sequence is automatically performed website registration on a large scale, logs in and maliciously attempts the illegal operations such as password occurs often.
In order to effectively intercept above-mentioned malicious operation, relevant mode is usually to use verification code technology.Common verifying
Code includes random digit identifying code, character formula identifying code, graphical verification code, image authentication code, question and answer identifying code and behavior formula
Identifying code.
Summary of the invention
The embodiment of the present application proposes the method and apparatus of interactive operation for identification.
In a first aspect, the embodiment of the present application provides a kind of method of interactive operation for identification, this method comprises: response
It is requested in the submission for receiving target list, obtains the input operation information of target list, wherein input operation information includes defeated
The corresponding key of the character in character string entered presses moment and release moment；Based on input operation information, input behaviour is generated
Make feature vector；Operating characteristics vector will be inputted and be input to the man-machine identification model trained in advance, obtain classification information, wherein
Man-machine identification model is used to characterize the corresponding relationship between input operating characteristics vector and classification information, and classification information is for characterizing
Input operation comes from machine or real user.
In some embodiments, input operation information further includes at least one of following: the character in the character string of input
Character types, mouse action information.
In some embodiments, input operating characteristics vector is generated, comprising: based on input operation information, generate key and hold
Input frame switching in continuous time series and target list spends time series；Generate the temporal signatures of key time durations sequence
Switch the temporal signatures for spending time series with input frame；Based on input operation information, statistical information is generated, wherein statistics letter
Breath includes at least one of the following: that the character types of the character in the character string of input belong to the number of preset characters type, sliding
Dynamic item drags number, the information input time of target list；Based on temporal signatures generated and statistical information, input behaviour is generated
Make feature vector.
In some embodiments, the above method further include: based on input operation information, generate at least one of following: adjacent
Key press time sequence is adjacent to release key time series, wherein the adjacent key time is used to characterize the pressing between the moment of adjacent key
Difference, it is adjacent release the key time for characterize adjacent key release the moment between difference.
In some embodiments, man-machine identification model includes machine operation identification model；And will input operating characteristics to
Amount is input to the man-machine identification model of training in advance, obtains classification information, comprising: input operating characteristics vector is input to machine
Identification model is operated, probability of the input operation from machine is obtained, wherein machine operates identification model for characterizing input operation
Corresponding relationship between the probability of feature vector and input operation from machine；In response to determining input operation from the general of machine
Rate is greater than or equal to preset threshold, determines that classification information is information of the characterization input operation from machine；It is inputted in response to determining
It operates the probability from machine and is less than preset threshold, determine that classification information is information of the characterization input operation from real user.
In some embodiments, training obtains machine operation identification model as follows: training sample set is obtained,
Training sample includes sample input operating characteristics vector sum sample markup information corresponding with sample input operating characteristics vector,
In, sample markup information is for characterizing sample input operation from machine or real user；By the training in training sample set
The sample input operating characteristics vector of sample is as input, by sample mark corresponding with the sample of input input operating characteristics vector
Information is infused as desired output, training obtains machine operation identification model.
Second aspect, the embodiment of the present application provide a kind of device of interactive operation for identification, which includes: to obtain
Unit is configured in response to receive the submission request of target list, obtains the input operation information of target list, wherein
The corresponding key of character inputted in the character string that operation information includes input presses moment and release moment；Generation unit,
It is configured to generate input operating characteristics vector based on input operation information；Recognition unit is configured to that operating characteristics will be inputted
Vector is input to the man-machine identification model of training in advance, obtains classification information, wherein man-machine identification model is for characterizing input behaviour
Make the corresponding relationship between feature vector and classification information, classification information is for characterization input operation from machine or true use
Family.
In some embodiments, input operation information further includes at least one of following: the character in the character string of input
Character types, mouse action information.
In some embodiments, generation unit includes: sequence generating module, is configured to based on input operation information, raw
Time series is spent at the input frame switching in key time durations sequence and target list；Temporal signatures generation module is matched
It is set to the temporal signatures for generating key time durations sequence and input frame switching spends the temporal signatures of time series；Statistical information
Generation module is configured to generate statistical information, wherein statistical information includes at least one of the following: based on input operation information
The character types of character in the character string of input belong to the number of preset characters type, and slider bar drags number, object table
Single information input time；Feature vector generation module is configured to generate based on temporal signatures generated and statistical information
Input operating characteristics vector.
In some embodiments, above-mentioned apparatus further include: sequence generating unit is configured to based on input operation information,
It generates at least one of following: adjacent key time series is adjacent to release key time series, wherein the adjacent key time is for characterizing
The difference of adjacent key pressed between the moment, the difference between the adjacent release moment for releasing the key time for characterizing adjacent key
Value.
In some embodiments, man-machine identification model includes machine operation identification model；And recognition unit includes: identification
Module is configured to input operating characteristics vector and is input to machine operation identification model, obtains input operation from machine
Probability, wherein machine operation identification model for characterize input operating characteristics vector and input operate the probability from machine it
Between corresponding relationship；Determining module is configured in response to determine input probability of the operation from machine more than or equal to default
Threshold value determines that classification information is information of the characterization input operation from machine；In response to determining input operation from the general of machine
Rate is less than preset threshold, determines that classification information is information of the characterization input operation from real user.
In some embodiments, training obtains machine operation identification model as follows: training sample set is obtained,
Training sample includes sample input operating characteristics vector sum sample markup information corresponding with sample input operating characteristics vector,
In, sample markup information is for characterizing sample input operation from machine or real user；By the training in training sample set
The sample input operating characteristics vector of sample is as input, by sample mark corresponding with the sample of input input operating characteristics vector
Information is infused as desired output, training obtains machine operation identification model.
The third aspect, the embodiment of the present application provide a kind of server, which includes: one or more processors；
Storage device is stored thereon with one or more programs；When one or more programs are executed by one or more processors, so that
One or more processors realize the method as described in implementation any in first aspect.
Fourth aspect, the embodiment of the present application provide a kind of computer-readable medium, are stored thereon with computer program, should
The method as described in implementation any in first aspect is realized when program is executed by processor.
The method and apparatus of interactive operation for identification provided by the embodiments of the present application, in response to receiving target list
Request is submitted, the input operation information of target list is obtained.Wherein, input operation information includes the word in the character string of input
Accord with corresponding key presses time and release time.Then, the input operation information based on acquisition, generate input operating characteristics to
Amount.Next, the input operating characteristics vector of generation to be input to the man-machine identification model of training in advance, classification information is obtained.
Wherein, man-machine identification model is used to characterize the corresponding relationship between input operating characteristics vector and classification information, and classification information is used
Machine or real user are come from characterization input operation.To realize the knowledge to using computer program to interact operation
Not.
Detailed description of the invention
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, the application's is other
Feature, objects and advantages will become more apparent upon:
Fig. 1 is that one embodiment of the application can be applied to exemplary system architecture figure therein；
Fig. 2 is the flow chart according to one embodiment of the method for the interactive operation for identification of the application；
Fig. 3 is the schematic diagram according to an application scenarios of the method for the interactive operation for identification of the embodiment of the present application；
Fig. 4 is the flow chart according to another embodiment of the method for the interactive operation for identification of the application；
Fig. 5 is the structural schematic diagram according to one embodiment of the device of the interactive operation for identification of the application；
Fig. 6 is adapted for the structural schematic diagram for the computer system for realizing the server of the embodiment of the present application.
Specific embodiment
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that in order to
Convenient for description, part relevant to related invention is illustrated only in attached drawing.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 is shown can be using the method or the dress of interactive operation for identification of the interactive operation for identification of the application
The exemplary architecture 100 set.
As shown in Figure 1, system architecture 100 may include terminal device 101,102,103, network 104 and server 105.
Network 104 between terminal device 101,102,103 and server 105 to provide the medium of communication link.Network 104 can be with
Including various connection types, such as wired, wireless communication link or fiber optic cables etc..
Terminal device 101,102,103 is interacted by network 104 with server 105, to receive or send message etc..Terminal
Various telecommunication customer end applications can be installed in equipment 101,102,103, such as the application of web browser applications, searching class,
Instant messaging tools, mailbox client, social platform software etc..
Terminal device 101,102,103 can be hardware, be also possible to software.When terminal device 101,102,103 is hard
When part, the various electronic equipments of submission form, including but not limited to smart phone, plate are can be with display screen and supported
Computer, E-book reader, pocket computer on knee and desktop computer etc..When terminal device 101,102,103 is soft
When part, it may be mounted in above-mentioned cited electronic equipment.Its may be implemented into multiple softwares or software module (such as
Distributed Services are provided), single software or software module also may be implemented into.It is not specifically limited herein.
Server 105 can be to provide the server of various services, for example, submit table on terminal device 101,102,103
It is single that the background server supported is provided.Background server can be requested in response to receiving the submission of target list, be obtained above-mentioned
The input operation information of target list is simultaneously analyzed and processed, and determines that input operation behavior is from machine or real user.
Optionally, whether background server can also be according to identified as a result, submitting successful result to feed back above-mentioned target list
To terminal device.
It should be noted that the above-mentioned input operation to target list can also carry out on server 105, server
105 can directly acquire the input operation information of local target list collected and be handled, at this point it is possible to which there is no eventually
End equipment 101,102,103.
It should be noted that server can be hardware, it is also possible to software.When server is hardware, may be implemented
At the distributed server cluster that multiple servers form, individual server also may be implemented into.It, can when server is software
To be implemented as multiple softwares or software module (such as providing Distributed Services), single software or software also may be implemented into
Module.It is not specifically limited herein.
It should be noted that provided by the embodiment of the present application for identification the method for interactive operation generally by server
105 execute, and correspondingly, the device of interactive operation is generally positioned in server 105 for identification.
It should be understood that the number of terminal device, network and server in Fig. 1 is only schematical.According to realization need
It wants, can have any number of terminal device, network and server.
With continued reference to Fig. 2, the stream of one embodiment of the method for the interactive operation for identification according to the application is shown
Journey 200.This for identification interactive operation method the following steps are included:
Step 201, it is requested in response to receiving the submission of target list, obtains the input operation information of target list.
In the present embodiment, the executing subject (server 105 as shown in Figure 1) of the method for interactive operation can for identification
To obtain the input operation information of target list.Wherein, above-mentioned target list can be according to actual application demand, refer in advance
Fixed any list.Above-mentioned target list is also possible to the list depending on rule, such as includes user name input frame and close
The list of code input frame.As an example, above-mentioned target list can be the enrollment page of the website XX, it is also possible to energy on the website XX
It enough modifies the pages of Password Operations.Above-mentioned submission request, which can be, is sent to the collected data of above-mentioned target list institute
The various requests of above-mentioned executing subject." submission " of the page is clicked in user, " is stepped on as an example, above-mentioned submission request can be
By terminal used by a user request generated after the buttons such as record " or " registration ".
In the present embodiment, above-mentioned input operation information, which can be, has recorded user to the element in above-mentioned target pages
(for example, text box, textview field, button, scroll bar etc.) carries out the information of various operations.It may include the character sequence of input
The corresponding key of character in column presses moment and release moment.Above-mentioned character can be Arabic numerals, letter, punctuate symbol
Number, oeprator etc., be also possible to the control characters such as backspace, tabulation and carriage return character that ASCII value is 8,9 and 13.It needs
Bright, above-mentioned " the pressing moment and release moment of key " refers to that the electronic equipment for the submission request for generating target list can be adopted
The operation information collected.Therefore, above-mentioned " key " refers not only to the physical button of keyboard, also includes tablet computer, touch-screen mobile phone etc.
Soft keyboard on screen.Correspondingly, " the pressing moment and release moment of key " also may include that finger passes through touch screen to soft keyboard
On " key " at the time of pressed and discharge operation.It should also be noted that, the character string of above-mentioned input refers to passing through
The character that key generates.Above-mentioned character can be different with the character inserted in list.As an example, the word inserted in list
Symbol can be " Zhang San ".But the character in the character string of input corresponding can be " zhangsan ".As another example, it uses
Family key in list character string be " H1 ", after be changed to " Hi ".So, user can successively be grasped as follows sequentially in time
Make: pressing shift key, press " H " key, release " H " key, release shift key, press " 1 " key, release " 1 " key, press backspace
Key, presses " I " key, release " I " key at release backspace key.Correspondingly, above-mentioned input operation information may include above-mentioned each operation
At the time of corresponding.
In some optional implementations of the present embodiment, above-mentioned input operation information can also include the character of input
Character types in sequence.Above-mentioned character types may include number, letter, punctuation mark.Above-mentioned character types can also wrap
Include the control character type for only generating keystroke information without generating character visible information.For example, press shift key, Alt key,
The character types of character caused by function key, cursor movement key and spcial character key (such as Insert key and Delete key).
In practice, the character in character string that can usually key in user carries out desensitization process.It is alternatively possible to by above-mentioned character
Corresponding character types are converted into, to guarantee the safety of the inputted information of user.With continued reference to above-mentioned character string by
" H1 " is changed to the example of " Hi ", and above-mentioned input operation information can also include " control key, letter, number, control key, letter ".
In some optional implementations of this implementation, above-mentioned input operation information can also include that mouse action is believed
Breath.Above-mentioned mouse action information can refer to record by mouse or touch screen input to realize the operation and operation to Form Element
The information of the time of generation.The rollover elements of list are operated as an example, above-mentioned mouse action information can be record
The information of the number of (for example, roll mouse pulley).Above-mentioned mouse action information can be have recorded to text box, textview field,
The information of the time of the clicking operation of password box or button.Above-mentioned mouse action information can also be that having recorded cursor hovers over table
The information of the time on button in list.It should be noted that since mobile terminal browser can support touch event, gesture thing
Part, therefore Form Element is operated by modes such as mouse or touch screens and is had no for the record of operation information point
Not.
In the present embodiment, above-mentioned executing subject is requested in response to receiving the submission of target list, can be by various
Mode obtains the input operation information of target list.As an example, user can directly be clicked by above-mentioned executing subject
The operation of " registration " button.Generated keystroke message can recorde when user is by character string key entry target list holds above-mentioned
In the operating system (for example, Windows) of row main body.That is, above-mentioned executing subject can directly acquire target list
Input operation information.As another example, firstly, user can be clicked " login " by used terminal electronic device
The operation of button.Above-mentioned terminal electronic device for example can be and the laptop of above-mentioned executing subject communication connection or touching
Screen mobile phone.Then, above-mentioned terminal electronic device can directly obtain the input operation information of target list by KeyEvent.It connects
Get off, above-mentioned executing subject can obtain the input operation letter of above-mentioned target list from the terminal electronic device of above-mentioned communication connection
Breath.
It should be noted that obtaining pressing the moment and discharging the moment and pass through operation for key above by KeyEvent
System record keystroke message is the well-known technique studied and applied extensively at present, and details are not described herein.
Step 202, based on input operation information, input operating characteristics vector is generated.
In the present embodiment, above-mentioned executing subject can be based on the input operation information obtained from step 201, by various
Mode generates input operating characteristics vector.Wherein, above-mentioned input operating characteristics vector may include the above-mentioned target user's of characterization
Input the various information of operation.Continuing for the corresponding key of character is pressed when as an example, may include user inputs character sequence
Time.As another example, it may include user inputs character sequence to press the average duration of each key, adjacent press twice
Maximum time interval of key etc..
Specifically, input operating characteristics vector can be expressed asWherein, T indicate key from
Press the duration of release.Subscript n indicates that the key pressed is n-th of key.T1Expression presses the 1st key from pressing release
Duration.T2Expression presses the 2nd key from the duration pressed to release.TnN-th of key holding from pressing release is pressed in expression
The continuous time.TnIt can pass throughTo determine.Wherein, TupIndicate the release moment of key.TdownIndicate pressing for key
Moment.The release moment of n-th of key is pressed in expression.Indicate that presses n-th of key presses the moment.TMeanIndicate T1To TnThis n
The average value of numerical value.Indicate T1To TnThe variance of this n numerical value.
In the present embodiment, above-mentioned executing subject can be first from the character string for extracting input in input operation information
The corresponding key of character press the moment and release the moment.It is then possible to when determining lasting from pressing release of each key
Between.Later, the average value and variance of above-mentioned key time durations sequence can be determined.Finally, above-mentioned executing subject can will be upper
State each key time durations, above-mentioned average value and variance composition input operating characteristics vector.
In some optional implementations of the present embodiment, above-mentioned executing subject can be raw based on input operation information
Time series is spent at the input frame switching in key time durations sequence and target list.Wherein, key time durations can be with
The method of the duration of the corresponding key of character is pressed according to above-mentioned generation to determine.Input frame switching spends the time that can pass through
Mouse action information determines.Thus, it is possible to generate key time durations sequence and input frame switching cost time series.
Next, the temporal signatures and above-mentioned input frame of above-mentioned key time durations sequence can be generated in above-mentioned executing subject
Switching spends the temporal signatures of time series.Wherein, the temporal signatures of above-mentioned sequence can include but is not limited to following at least one
: maximum value, minimum value, average value, variance, the difference of maxima and minima, 10 quantiles, 50 quantiles, 90 quantiles, peak
Degree, the degree of bias.Then, above-mentioned executing subject can generate statistical information according to above-mentioned input operation information.Wherein, statistical information
Can include but is not limited at least one of following: the character types of the character in the character string of input belong to preset characters type
Number, slider bar drag number, the information input time of target list.Optionally, preset characters type can be numeric class
Type or control character type.The number that the character types of character in the character string of input belong to preset characters type can lead to
It crosses to count the data of KeyEvent record and be obtained.Optionally, slider bar dragging number can by mouse event or
Touch event and obtain.Optionally, the information input time of target list can leave the last one on list by mouse
Difference between at the time of text box and at the time of mouse clicks the 1st text box determines.
Finally, above-mentioned executing subject can by temporal signatures generated and statistical information composition input operating characteristics to
Amount.Optionally, the arrangement of elements mode inputted in operating characteristics vector is unrestricted.But in all input operating characteristics vectors
Arrangement of elements mode needs unanimously.For example, input operating characteristics vector can be [temporal signatures of key time durations sequence,
Input frame switching spend time series temporal signatures, statistical information], input operating characteristics vector be also possible to [statistical information,
Input frame switching spends the temporal signatures of time series, the temporal signatures of key time durations sequence].
As an example, user inputs to the 1st text box, mouse is at the time of leaving the 1st text box
T1', user is T at the time of clicking the 2nd text box using mouse1", then it is defeated between the 1st input frame and the 2nd input frame
Enter frame switching and spends time Δ T1=T1”-T1'.Similarly, the input frame between the 2nd input frame and the 3rd input frame switches flower
Time-consuming Δ T2=T2”-T2', wherein T2' and T2" it is respectively at the time of mouse leaves the 2nd text box and user uses mouse
At the time of clicking the 3rd text box.If only there are three text boxes in above-mentioned target list, then, input frame switching spends the time
Sequence can be { Δ T1,ΔT2}.Above-mentioned key time durations sequence can be { T1,T2,T3,T4,T5,T6,T7,T8, wherein T1
To T8It can be respectively intended to indicate the key time durations of the corresponding key of 8 characters in the character string of input.Input frame is cut
It changes and spends the temporal signatures of time series that can be expressed as Δ T1With Δ T2Average value Δ Tmean.Key time durations sequence
Temporal signatures can be expressed as T1To T8The variance of this 8 numerical valueStatistical information can be expressed as in the character string of input
The character types of character belong to the number n of preset characters type and the information input time t of target list.So, generation
Inputting operating characteristics vector can be
In some optional implementations of the present embodiment, based on input operation information, above-mentioned executing subject can be with
It generates at least one of following: adjacent key time series is adjacent to release key time series, wherein the adjacent key time is for characterizing
The difference of adjacent key pressed between the moment, the difference between the adjacent release moment for releasing the key time for characterizing adjacent key
Value.As an example, the character string of user's input is " you ".Above-mentioned adjacent key time series can be by pressing pressing for " o " key
It the lower moment and presses the difference for pressing the moment of " y " key and presses the difference for pressing the moment pressed the moment and press " o " key of " u " key
Composition.Correspondingly, above-mentioned adjacent key time series of releasing can be by pressing the release moment after " o " key and pressing releasing after " y " key
It puts the difference at moment and presses the release moment after " u " key and press the difference at the release moment after " o " key and form.
Step 203, operating characteristics vector will be inputted and is input to the man-machine identification model trained in advance, obtain classification information.
In the present embodiment, above-mentioned executing subject can input the input operating characteristics vector generated by step 202
To the man-machine identification model of training in advance, classification information is obtained.Wherein, man-machine identification model for characterize input operating characteristics to
Corresponding relationship between amount and classification information, classification information come from machine or real user for characterizing input operation.Classification letter
Breath can be various forms of information, such as: number, letter, symbol etc..As an example, can indicate input behaviour with " A "
Make to come from machine, indicates input operation from real user with " a ".
It should be noted that as an example, man-machine identification model can be technical staff based on to a large amount of input operation
The statistics of feature vector and classification information and pre-establish, be stored with it is multiple input operating characteristics vectors and classification information pairs
The mapping table that should be related to.It is also possible to technical staff to preset and stored to above-mentioned based on the statistics to mass data
It is in execution, to input operating characteristics vector in one or more numerical value carry out numerical value calculate with obtain for characterize classification letter
The calculation formula of the calculated result of breath.The key inputted in operating characteristics vector is continued for example, above-mentioned calculation formula can be
The average value of time is multiplied with the variance of key time durations, then is compared with obtained product with a preset threshold,
Finally obtain classification information.Above-mentioned preset threshold can be technical staff according to a large amount of data statistics pre-set number
Value.If result of product is greater than or equal to preset threshold, classification information can be letter of the characterization input operation from real user
Breath.If result of product is less than preset threshold, classification information can be information of the characterization input operation from machine.
Further, in some optional implementations of the present embodiment, under the application scenarios of website registration, service
Device is after obtaining above-mentioned classification information, it can obtains whether aforesaid operations information comes from machine according to category information, and holds
The corresponding subsequent operation of row.For example, can refuse if server obtains characterizing above-mentioned classification information of the input operation from machine
This time registration request.Further, server can also send the information of characterization registration failure to terminal device 301.If service
Device obtains characterizing above-mentioned classification information of the input operation from real user, can be in the case where meeting other registration conditions
Pass through this registration request.Further, server can also send the information that characterization succeeds in registration to terminal device.
With continued reference to the application scenarios that Fig. 3, Fig. 3 are according to the method for the interactive operation for identification of the embodiment of the present application
One schematic diagram.In the application scenarios 300 of Fig. 3, terminal device 301 sends the request 302 of submission form to server 303.
Server 303 obtains the input operation information 304 of above-mentioned list in response to receiving above-mentioned request.Wherein, operation information is inputted
It can be and press and discharge when inputting user name " XX ", mailbox " * * *@* * " and password " * * * * * * " on keyboard with touch screen accordingly
At the time of the key of character.Next, generating input operating characteristics vector 305 based on input operation information 304.Then, server
303 are input to above-mentioned input operating characteristics vector 305 the man-machine identification model of training in advance.Finally, server 303 obtains table
Levy above-mentioned classification information 306 of the input operation from machine or real user.Optionally, if server 303 obtain characterizing it is above-mentioned
Classification information of the input operation from machine, can refuse this registration request.Further, server 303 can also be to end
End equipment 301 sends the information of characterization registration failure.Optionally, if server 303 obtains characterizing above-mentioned input operation from true
The classification information of real user can pass through this registration request in the case where meeting other registration conditions.Further, it takes
Business device 303 can also send the information that characterization succeeds in registration to terminal device 301.
The method provided by the above embodiment of the application is requested in response to receiving the submission of target list first, is obtained
The input operation information of target list；Then, it is based on above-mentioned input operation information, generates input operating characteristics vector；Finally, will
Above-mentioned input operating characteristics vector is input to the man-machine identification model of training in advance, obtains for characterizing input operation from machine
Or the classification information of real user.So as to realize and carried out to computer program according to the input operation information of submission form
The identification of interactive operation, so avoid using computer program carry out extensive website registration, login and malice attempt it is close
The illegal operations such as code.
With further reference to Fig. 4, it illustrates the processes 400 of another embodiment of the method for interactive operation for identification.
The process 400 of the method for interactive operation for identification, comprising the following steps:
Step 401, it is requested in response to receiving the submission of target list, obtains the input operation information of target list.
Step 402, based on input operation information, input operating characteristics vector is generated.
Above-mentioned steps 401, step 402 are consistent with step 201, the step 202 in previous embodiment respectively, above with respect to step
Rapid 201, the description of step 202 is also applied for step 401, step 402, and details are not described herein again.
Step 403, input operating characteristics vector is input to machine operation identification model, obtains input operation from machine
Probability.
In the present embodiment, machine operation identification model can be CART (Classification and regression
Tree, Taxonomy and distribution), it is also possible to SVM (Support Vector Machine, support vector machines).As an example, can
With by following steps training obtain: obtain training sample set, training sample include sample input operating characteristics vector sum with
Sample inputs the corresponding sample markup information of operating characteristics vector；The sample of training sample in training sample set is inputted into behaviour
Make feature vector and is used as input, sample markup information corresponding with the sample of input input operating characteristics vector is defeated as it is expected
Out, training obtains machine operation identification model.Specifically includes the following steps:
The first step obtains initial machine and operates identification model.Initial machine operation identification model can be various classifiers.
For example, correspond to machine operation identification model be CART, initial machine operation identification model can be RF (Random forest,
Random forest), Boosted Trees (boosted tree) etc..
Second step obtains training sample set.Each training sample in training sample set may include sample input
Operating characteristics vector sum sample markup information.Wherein, sample markup information can be used for characterizing sample input operation from machine
Probability.In practice, sample input operating characteristics vector can be obtained in several ways.For example, can choose will utilize meter
The operation information that calculation machine program carries out website registration carries out the processing such as abovementioned steps 202, and it is corresponding to obtain aforesaid operations information
Sample input operating characteristics vector, and by its sample markup information be set as characterization machine operation information.For another example, it can incite somebody to action
The operation information that real user carries out website registration carries out the processing such as abovementioned steps 202, and it is corresponding to obtain aforesaid operations information
Sample inputs operating characteristics vector, and sets its sample markup information to the information of characterization real user operation.Markup information
It can be the information of diversified forms.As an example, 1 can be set by markup information of the input operation from machine, will input
Markup information of the operation from real user is set as 0.For numerical value closer to 1, above-mentioned probability of the input operation from machine is bigger.
Sample in training sample in training sample set is inputted operation using the method for machine learning by third step
Input of the feature vector as initial machine operation identification model, by sample corresponding with the sample of input input operating characteristics vector
This markup information is used as desired output, and training obtains above-mentioned machine operation identification model.
Specifically, the executing subject of above-mentioned training step can input the sample of the training sample in training sample set
Operating characteristics vector inputs initial machine and operates identification model, obtains probability of the input operation from machine of the training sample.
It is then possible to calculate the sample of obtained probability and the training sample of the input operation from machine using preset loss function
Difference degree between this markup information.Next, can use the complexity of regularization term computation model.Later, based on
The complexity of resulting difference degree and model, the structural parameters of adjustment initial machine operation identification model are calculated, and are being met in advance
If training termination condition in the case where, terminate training.Finally, the initial machine operation identification model that training obtains is determined as
Machine operates identification model.
It should be noted that above-mentioned loss function can use logarithm loss function, above-mentioned regularization term can use L2
Norm.Above-mentioned preset trained termination condition can include but is not limited at least one of following: the training time is more than preset duration；
Frequency of training is more than preset times；Resulting difference degree is calculated less than preset discrepancy threshold；Accuracy rate on test set reaches
To preset accuracy rate threshold value；Coverage rate on test set reaches preset coverage rate threshold value.
It should also be noted that, the sample mark based on probability and the training sample of the input operation from machine generated
The difference degree between information is infused, the structural parameters of adjustment initial machine operation identification model in various manners can be adopted.For example,
It can be calculated using XGBoost algorithm or GBDT (Gradient Boosting Decision Tree, gradient promote decision tree)
Method come adjust initial machine operation identification model structural parameters.
It is worth noting that, the executing subject of above-mentioned training step can be with the execution of the method for interactive operation for identification
Main body is same or different.If identical, the executing subject of above-mentioned training step can obtain machine operation identification in training
The structural information of trained machine operation identification model and parameter value are stored in local after model.If it is different, then above-mentioned
Trained machine can be operated identification model after training obtains machine operation identification model by the executing subject of training step
Structural information and parameter value be sent to interactive operation for identification method executing subject.
In the present embodiment, input operating characteristics vector can be input to and train by the above process by above-mentioned executing subject
Obtained machine operation identification model, obtains probability of the input operation from machine.
Step 404, in response to determining that inputting probability of the operation from machine is greater than or equal to preset threshold, determines that classification is believed
Breath is information of the characterization input operation from machine.
Step 405, in response to determining that inputting probability of the operation from machine is less than preset threshold, determines that classification information is table
Information of the sign input operation from real user.
In the present embodiment, above-mentioned in response to determining that inputting probability of the operation from machine is greater than or equal to preset threshold
Executing subject can determine that classification information is information of the characterization input operation from machine.In response to determining that input operation comes from machine
The probability of device is less than preset threshold, and above-mentioned executing subject can determine that classification information is characterization input operation from real user
Information.Wherein, above-mentioned preset threshold can be determined by technical staff according to actual conditions and experience.
Figure 4, it is seen that compared with the corresponding embodiment of Fig. 2, interactive operation for identification in the present embodiment
The process 400 of method, which has been refined, is input to the man-machine identification model trained in advance for input operating characteristics vector, obtains classification letter
The step of breath.The method that the scheme of the present embodiment description can use machine learning as a result, generates man-machine identification model, thus rich
The rich generation method of man-machine identification model.
With further reference to Fig. 5, as the realization to method shown in above-mentioned each figure, this application provides interaction behaviour for identification
One embodiment of the device of work, the Installation practice is corresponding with embodiment of the method shown in Fig. 2, which can specifically answer
For in various electronic equipments.
As shown in figure 5, the device 500 of interactive operation for identification provided in this embodiment includes acquiring unit 501, generates
Unit 502 and recognition unit 503.Wherein, acquiring unit 501 are configured in response to receive the submission request of target list,
Obtain the input operation information of target list.Wherein, input operation information includes that the character in the character string of input is corresponding
Key presses moment and release moment.Generation unit 502 is configured to generate input operating characteristics based on input operation information
Vector.Recognition unit 503 is configured to input the man-machine identification model that operating characteristics vector is input to training in advance, obtains
Classification information.Wherein, man-machine identification model is used to characterize the corresponding relationship between input operating characteristics vector and classification information, class
Other information comes from machine or real user for characterizing input operation.
In the present embodiment, in the device 500 of interactive operation for identification: acquiring unit 501, generation unit 502 and knowledge
The specific processing of other unit 503 and its brought technical effect can be respectively with reference to step 201, the steps in Fig. 2 corresponding embodiment
Rapid 202 and step 203 related description, details are not described herein.
In some optional implementations of the present embodiment, above-mentioned input operation information can also include following at least one
: the character types of the character in the character string of input, mouse action information.
In some optional implementations of the present embodiment, above-mentioned generation unit 502 may include sequence generating module
(not shown), temporal signatures generation module (not shown), statistical information generation module (not shown) and feature
Vector generation module (not shown).Wherein, sequence generating module is configured to generate key based on input operation information
Input frame switching in duration time sequence and target list spends time series.Temporal signatures generation module is configured to give birth to
The temporal signatures of time series are spent at temporal signatures and the input frame switching of key time durations sequence.Statistical information generates mould
Block is configured to generate statistical information based on input operation information.Wherein, statistical information includes at least one of the following: input
The character types of character in character string belong to the number of preset characters type, and slider bar drags number, the letter of target list
Cease input time.Feature vector generation module is configured to generate input behaviour based on temporal signatures generated and statistical information
Make feature vector.
In some optional implementations of the present embodiment, above-mentioned apparatus 500 can also include sequence generating unit (figure
In be not shown), be configured to generate at least one of following based on input operation information: adjacent key time series, it is adjacent to release key
Time series.Wherein, the adjacent key time is used to characterize the difference of adjacent key pressed between the moment, adjacent to release key time use
Difference between the release moment of characterization adjacent key.
In some optional implementations of the present embodiment, above-mentioned man-machine identification model may include machine operation identification
Model.Above-mentioned recognition unit 503 may include identification module (not shown) and determining module (not shown).Wherein,
Identification module is configured to input operating characteristics vector and is input to machine operation identification model, obtains input operation from machine
The probability of device.Wherein, machine operation identification model is for characterizing input operating characteristics vector with input operation from the general of machine
Corresponding relationship between rate.Determining module is configured in response to determine that probability of the input operation from machine is greater than or equal to
Preset threshold determines that classification information is information of the characterization input operation from machine；In response to determining that input operation comes from machine
Probability be less than preset threshold, determine classification information be characterization input operate the information from real user.
In some optional implementations of the present embodiment, above-mentioned machine operation identification model can be as follows
Training obtains: obtaining training sample set, training sample includes that sample input operating characteristics vector sum and sample input operation are special
Levy the corresponding sample markup information of vector.Wherein, sample markup information is used to characterize sample input operation and comes from machine or true
User.Using the sample of the training sample in training sample set input operating characteristics vector as input, by the sample with input
The corresponding sample markup information of operating characteristics vector is inputted as desired output, training obtains machine operation identification model.
The device provided by the above embodiment of the application, by acquiring unit 501 in response to receiving mentioning for target list
Request is handed over, the input operation information of target list is obtained.Then, generation unit 502 is based on input operation information, generates input behaviour
Make feature vector.Finally, recognition unit 503 is input to the man-machine identification model trained in advance for operating characteristics vector is inputted, obtain
To classification information.To realize input operation information according to submission form, to using computer program to interact operation
Identification.
Below with reference to Fig. 6, it illustrates the computer systems 600 for the server for being suitable for being used to realize the embodiment of the present application
Structural schematic diagram.Server shown in Fig. 6 is only an example, should not function and use scope band to the embodiment of the present application
Carry out any restrictions.
As shown in fig. 6, computer system 600 includes central processing unit (CPU) 601, it can be read-only according to being stored in
Program in memory (ROM) 602 or be loaded into the program in random access storage device (RAM) 603 from storage section 608 and
Execute various movements appropriate and processing.In RAM 603, also it is stored with system 600 and operates required various programs and data.
CPU 601, ROM 602 and RAM 603 are connected with each other by bus 604.Input/output (I/O) interface 605 is also connected to always
Line 604.
I/O interface 605 is connected to lower component: the importation 606 including keyboard, mouse etc.；It is penetrated including such as cathode
The output par, c 607 of spool (CRT), liquid crystal display (LCD) etc.；Storage section 608 including hard disk etc.；And including such as
The communications portion 609 of the network interface card of LAN card, modem etc..Communications portion 609 is held via the network of such as internet
Row communication process.Driver 610 is also connected to I/O interface 605 as needed.Detachable media 611, such as disk, CD, magnetic
CD, semiconductor memory etc. are mounted on as needed on driver 610, in order to from the computer program read thereon
It is mounted into storage section 608 as needed.
Particularly, in accordance with an embodiment of the present disclosure, it may be implemented as computer above with reference to the process of flow chart description
Software program.For example, embodiment of the disclosure includes a kind of computer program product comprising be carried on computer-readable medium
On computer program, which includes the program code for method shown in execution flow chart.In such reality
It applies in example, which can be downloaded and installed from network by communications portion 609, and/or from detachable media
611 are mounted.When the computer program is executed by central processing unit (CPU) 601, limited in execution the present processes
Above-mentioned function.
It should be noted that the computer-readable medium of the application can be computer-readable signal media or computer
Readable storage medium storing program for executing either the two any combination.Computer readable storage medium for example can be --- but it is unlimited
In system, device or the device of --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, or any above combination.It calculates
The more specific example of machine readable storage medium storing program for executing can include but is not limited to: have the electrical connection, portable of one or more conducting wires
Formula computer disk, hard disk, random access storage device (RAM), read-only memory (ROM), erasable programmable read only memory
(EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory device or
The above-mentioned any appropriate combination of person.In this application, computer readable storage medium can be it is any include or storage program
Tangible medium, which can be commanded execution system, device or device use or in connection.And in this Shen
Please in, computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
In carry computer-readable program code.The data-signal of this propagation can take various forms, including but not limited to
Electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be computer-readable
Any computer-readable medium other than storage medium, the computer-readable medium can send, propagate or transmit for by
Instruction execution system, device or device use or program in connection.The journey for including on computer-readable medium
Sequence code can transmit with any suitable medium, including but not limited to: wireless, electric wire, optical cable, RF etc. are above-mentioned
Any appropriate combination.
The calculating of the operation for executing the application can be write with one or more programming languages or combinations thereof
Machine program code, described program design language include object-oriented programming language-such as Java, Smalltalk, C+
+, it further include conventional procedural programming language-such as " C " language or similar programming language.Program code can
Fully to execute, partly execute on the user computer on the user computer, be executed as an independent software package,
Part executes on the remote computer or executes on a remote computer or server completely on the user computer for part.
In situations involving remote computers, remote computer can pass through the network of any kind --- including local area network (LAN)
Or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as utilize Internet service
Provider is connected by internet).
Flow chart and block diagram in attached drawing are illustrated according to the system of the various embodiments of the application, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of the module, program segment or code include one or more use
The executable instruction of the logic function as defined in realizing.It should also be noted that in some implementations as replacements, being marked in box
The function of note can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are actually
It can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it to infuse
Meaning, the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart can be with holding
The dedicated hardware based system of functions or operations as defined in row is realized, or can use specialized hardware and computer instruction
Combination realize.
Being described in unit involved in the embodiment of the present application can be realized by way of software, can also be by hard
The mode of part is realized.Described unit also can be set in the processor, for example, can be described as: a kind of processor, packet
Include acquiring unit, generation unit, recognition unit.Wherein, the title of these units is not constituted under certain conditions to the unit
The restriction of itself, for example, generation unit is also described as " based on input operation information, generating input operating characteristics vector
Unit ".
As on the other hand, present invention also provides a kind of computer-readable medium, which be can be
Included in server described in above-described embodiment；It is also possible to individualism, and without in the supplying server.It is above-mentioned
Computer-readable medium carries one or more program, when said one or multiple programs are executed by the server,
So that the server: the submission in response to receiving target list is requested, and the input operation information of target list is obtained, wherein
The corresponding key of character inputted in the character string that operation information includes input presses moment and release moment；It is grasped based on input
Make information, generates input operating characteristics vector；Operating characteristics vector will be inputted and be input to the man-machine identification model trained in advance, obtained
To classification information, wherein man-machine identification model is used to characterize the corresponding relationship between input operating characteristics vector and classification information,
Classification information comes from machine or real user for characterizing input operation.
Above description is only the preferred embodiment of the application and the explanation to institute's application technology principle.Those skilled in the art
Member is it should be appreciated that invention scope involved in the application, however it is not limited to technology made of the specific combination of above-mentioned technical characteristic
Scheme, while should also cover in the case where not departing from foregoing invention design, it is carried out by above-mentioned technical characteristic or its equivalent feature
Any combination and the other technical solutions formed.Such as features described above has similar function with (but being not limited to) disclosed herein
Can technical characteristic replaced mutually and the technical solution that is formed.
Claims (14)
1. a kind of method of interactive operation for identification, comprising:
Submission in response to receiving target list is requested, and obtains the input operation information of the target list, wherein described defeated
Enter the corresponding key of character in the character string that operation information includes input presses moment and release moment；
Based on the input operation information, input operating characteristics vector is generated；
The input operating characteristics vector is input to the man-machine identification model of training in advance, obtains classification information, wherein described
Man-machine identification model is used to characterize the corresponding relationship between input operating characteristics vector and classification information, and the classification information is used for
Characterization input operation comes from machine or real user.
2. according to the method described in claim 1, wherein, the input operation information further includes at least one of following: described defeated
The character types of the character in character string entered, mouse action information.
3. according to the method described in claim 2, wherein, the generation inputs operating characteristics vector, comprising:
Based on the input operation information, the input frame generated in key time durations sequence and the target list switches cost
Time series；
The temporal signatures and input frame switching that generate the key time durations sequence spend the temporal signatures of time series；
Based on the input operation information, statistical information is generated, wherein the statistical information includes at least one of the following: described
The character types of character in the character string of input belong to the number of preset characters type, and slider bar drags number, the mesh
Mark the information input time of list；
Based on temporal signatures generated and the statistical information, input operating characteristics vector is generated.
4. according to the method described in claim 1, wherein, the method also includes:
Based on the input operation information, generate at least one of following: adjacent key time series, it is adjacent to release key time series,
Wherein, the adjacent key time is used to characterize the difference of adjacent key pressed between the moment, adjacent to release the key time for characterizing phase
Difference between the release moment of adjacent key.
5. method described in one of -4 according to claim 1, wherein the man-machine identification model includes machine operation identification mould
Type；And
The input operating characteristics vector is input to the man-machine identification model of training in advance, obtains classification information, comprising:
The input operating characteristics vector is input to the machine operation identification model, obtains input operation from the general of machine
Rate, wherein the machine operation identification model is for characterizing the probability of input operating characteristics vector and input operation from machine
Between corresponding relationship；
It is greater than or equal to preset threshold in response to the determination probability of the input operation from machine, determines that the classification information is
Information of the characterization input operation from machine；
It is less than preset threshold in response to the determination probability of the input operation from machine, it is defeated to characterize to determine the classification information
Enter information of the operation from real user.
6. according to the method described in claim 5, wherein, training obtains the machine operation identification model as follows:
Training sample set is obtained, training sample includes that sample input operating characteristics vector sum and sample input operating characteristics vector
Corresponding sample markup information, wherein sample markup information is for characterizing sample input operation from machine or real user；
Using the sample of the training sample in training sample set input operating characteristics vector as input, by the sample with input
For the corresponding sample markup information of this input operating characteristics vector as desired output, training obtains the machine operation identification mould
Type.
7. a kind of device of interactive operation for identification, comprising:
Acquiring unit is configured in response to receive the submission request of target list, obtains the input behaviour of the target list
Make information, wherein the input operation information includes pressing the moment and releasing for the corresponding key of character in the character string of input
Put the moment；
Generation unit is configured to generate input operating characteristics vector based on the input operation information；
Recognition unit is configured to for the input operating characteristics vector being input to the man-machine identification model of training in advance, obtains
Classification information, wherein the man-machine identification model is used to characterize the corresponding pass between input operating characteristics vector and classification information
System, the classification information come from machine or real user for characterizing input operation.
8. device according to claim 7, wherein the input operation information further includes at least one of following: described defeated
The character types of the character in character string entered, mouse action information.
9. device according to claim 8, wherein the generation unit includes:
Sequence generating module is configured to generate key time durations sequence and the target based on the input operation information
Input frame switching in list spends time series；
Temporal signatures generation module, the temporal signatures and the input frame for being configured to generate the key time durations sequence are cut
Change the temporal signatures for spending time series；
Statistical information generation module is configured to generate statistical information, wherein the statistics based on the input operation information
Information includes at least one of the following: that the character types of the character in the character string of the input belong to the number of preset characters type
Mesh, slider bar drag number, the information input time of the target list；
Feature vector generation module is configured to generate input operation based on temporal signatures generated and the statistical information
Feature vector.
10. device according to claim 7, wherein described device further include:
Sequence generating unit is configured to generate at least one of following: adjacent key time sequence based on the input operation information
Column are adjacent to release key time series, wherein the adjacent key time is used to characterize the difference of adjacent key pressed between the moment, phase
Neighbour releases the difference between release moment of the key time for characterizing adjacent key.
11. the device according to one of claim 7-10, wherein the man-machine identification model includes machine operation identification mould
Type；And the recognition unit includes:
Identification module is configured to for the input operating characteristics vector being input to the machine operation identification model, obtains defeated
Enter probability of the operation from machine, wherein the machine operation identification model is for characterizing input operating characteristics vector and input
Operate the corresponding relationship between the probability from machine；
Determining module is configured in response to determine that the probability of the input operation from machine is greater than or equal to preset threshold,
Determine that the classification information is information of the characterization input operation from machine；In response to the determination input operation from machine
Probability is less than preset threshold, determines that the classification information is information of the characterization input operation from real user.
12. device according to claim 11, wherein machine operation identification model is trained as follows
It arrives:
Training sample set is obtained, training sample includes that sample input operating characteristics vector sum and sample input operating characteristics vector
Corresponding sample markup information, wherein sample markup information is for characterizing sample input operation from machine or real user；
Using the sample of the training sample in training sample set input operating characteristics vector as input, by the sample with input
For the corresponding sample markup information of this input operating characteristics vector as desired output, training obtains the machine operation identification mould
Type.
13. a kind of server, comprising:
One or more processors；
Storage device is stored thereon with one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
Now such as method as claimed in any one of claims 1 to 6.
14. a kind of computer-readable medium, is stored thereon with computer program, wherein the realization when program is executed by processor
Such as method as claimed in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811179742.XA CN109409049A (en) | 2018-10-10 | 2018-10-10 | The method and apparatus of interactive operation for identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811179742.XA CN109409049A (en) | 2018-10-10 | 2018-10-10 | The method and apparatus of interactive operation for identification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109409049A true CN109409049A (en) | 2019-03-01 |
Family
ID=65467510
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811179742.XA Pending CN109409049A (en) | 2018-10-10 | 2018-10-10 | The method and apparatus of interactive operation for identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109409049A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109582854A (en) * | 2018-12-28 | 2019-04-05 | 百度在线网络技术（北京）有限公司 | Method and apparatus for generating information |
| CN109977641A (en) * | 2019-03-25 | 2019-07-05 | 山东浪潮云信息技术有限公司 | A kind of authentication processing method and system of Behavior-based control analysis |
| CN110288995A (en) * | 2019-07-19 | 2019-09-27 | 出门问问(苏州)信息科技有限公司 | Exchange method, device, storage medium and electronic equipment based on speech recognition |
| CN110519228A (en) * | 2019-07-22 | 2019-11-29 | 中国科学院信息工程研究所 | A kind of black recognition methods and system for producing malice cloud robot under scene |
| CN111210271A (en) * | 2020-01-03 | 2020-05-29 | 北京字节跳动网络技术有限公司 | Method and device for identifying form cheating, electronic equipment and storage medium |
| CN111666968A (en) * | 2020-04-21 | 2020-09-15 | 北京奇艺世纪科技有限公司 | Man-machine recognition method and device, electronic equipment and computer readable storage medium |
| CN112149705A (en) * | 2019-06-28 | 2020-12-29 | 京东数字科技控股有限公司 | Method and system for training classification model, computer equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101478401A (en) * | 2009-01-21 | 2009-07-08 | 东北大学 | Authentication method and system based on key stroke characteristic recognition |
| CN104318138A (en) * | 2014-09-30 | 2015-01-28 | 杭州同盾科技有限公司 | Method and device for verifying identity of user |
| CN105989268A (en) * | 2015-03-02 | 2016-10-05 | 苏宁云商集团股份有限公司 | Safety access method and system for human-computer identification |
| US9514293B1 (en) * | 2012-03-20 | 2016-12-06 | United Services Automobile Association | Behavioral profiling method and system to authenticate a user |
| CN107977555A (en) * | 2017-11-10 | 2018-05-01 | 传神语联网网络科技股份有限公司 | It is a kind of to judge that identification object is the method for the mankind or machine |
| CN108491714A (en) * | 2018-04-09 | 2018-09-04 | 众安信息技术服务有限公司 | The man-machine recognition methods of identifying code |
-
2018
- 2018-10-10 CN CN201811179742.XA patent/CN109409049A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101478401A (en) * | 2009-01-21 | 2009-07-08 | 东北大学 | Authentication method and system based on key stroke characteristic recognition |
| US9514293B1 (en) * | 2012-03-20 | 2016-12-06 | United Services Automobile Association | Behavioral profiling method and system to authenticate a user |
| CN104318138A (en) * | 2014-09-30 | 2015-01-28 | 杭州同盾科技有限公司 | Method and device for verifying identity of user |
| CN105989268A (en) * | 2015-03-02 | 2016-10-05 | 苏宁云商集团股份有限公司 | Safety access method and system for human-computer identification |
| CN107977555A (en) * | 2017-11-10 | 2018-05-01 | 传神语联网网络科技股份有限公司 | It is a kind of to judge that identification object is the method for the mankind or machine |
| CN108491714A (en) * | 2018-04-09 | 2018-09-04 | 众安信息技术服务有限公司 | The man-machine recognition methods of identifying code |
Non-Patent Citations (2)
| Title |
|---|
| 董学雄: "基于击键特征的用户身份识别算法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 魏梓丞: "面向身份伪冒的主机异常行为检测", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109582854A (en) * | 2018-12-28 | 2019-04-05 | 百度在线网络技术（北京）有限公司 | Method and apparatus for generating information |
| CN109582854B (en) * | 2018-12-28 | 2022-05-03 | 百度在线网络技术（北京）有限公司 | Method and apparatus for generating information |
| CN109977641A (en) * | 2019-03-25 | 2019-07-05 | 山东浪潮云信息技术有限公司 | A kind of authentication processing method and system of Behavior-based control analysis |
| CN112149705A (en) * | 2019-06-28 | 2020-12-29 | 京东数字科技控股有限公司 | Method and system for training classification model, computer equipment and storage medium |
| CN110288995A (en) * | 2019-07-19 | 2019-09-27 | 出门问问(苏州)信息科技有限公司 | Exchange method, device, storage medium and electronic equipment based on speech recognition |
| CN110288995B (en) * | 2019-07-19 | 2021-07-16 | 出门问问(苏州)信息科技有限公司 | Interaction method and device based on voice recognition, storage medium and electronic equipment |
| CN110519228A (en) * | 2019-07-22 | 2019-11-29 | 中国科学院信息工程研究所 | A kind of black recognition methods and system for producing malice cloud robot under scene |
| CN110519228B (en) * | 2019-07-22 | 2020-12-04 | 中国科学院信息工程研究所 | Method and system for identifying malicious cloud robot in black-production scene |
| CN111210271A (en) * | 2020-01-03 | 2020-05-29 | 北京字节跳动网络技术有限公司 | Method and device for identifying form cheating, electronic equipment and storage medium |
| CN111210271B (en) * | 2020-01-03 | 2023-10-17 | 北京字节跳动网络技术有限公司 | Method, device, electronic equipment and storage medium for identifying form cheating |
| CN111666968A (en) * | 2020-04-21 | 2020-09-15 | 北京奇艺世纪科技有限公司 | Man-machine recognition method and device, electronic equipment and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109409049A (en) | The method and apparatus of interactive operation for identification | |
| US11877152B2 (en) | Method, device, and system of differentiating between a cyber-attacker and a legitimate user | |
| US10262324B2 (en) | System, device, and method of differentiating among users based on user-specific page navigation sequence | |
| Antal et al. | Information revealed from scrolling interactions on mobile devices | |
| US10069891B2 (en) | Channel accessible single function micro service data collection process for light analytics | |
| US20160063484A1 (en) | Augmented reality card activation | |
| Alpar | Frequency spectrograms for biometric keystroke authentication using neural network based classifier | |
| CN106845999A (en) | Risk subscribers recognition methods, device and server | |
| CN108595628A (en) | Method and apparatus for pushed information | |
| CN109857908A (en) | Method and apparatus for matching video | |
| CN104660688B (en) | A kind of method and apparatus obtaining log-on message | |
| CN109325213A (en) | Method and apparatus for labeled data | |
| CN108064385A (en) | Compare extracted user name and the user data stored | |
| CN109299477A (en) | Method and apparatus for generating text header | |
| CN109933217A (en) | Method and apparatus for pushing sentence | |
| Maiorana et al. | Mobile keystroke dynamics for biometric recognition: An overview | |
| Samet et al. | TouchMetric: a machine learning based continuous authentication feature testing mobile application | |
| US11687641B1 (en) | Graphical event-based password system | |
| CN108182180B (en) | Method and apparatus for generating information | |
| CN110110693A (en) | The method and apparatus of face character for identification | |
| US11669604B2 (en) | Methods and systems for authenticating a user | |
| CN107835305A (en) | Data inputting method and device for the terminal device with screen | |
| US20170091859A1 (en) | System for real-time data structuring and storage | |
| US20220414193A1 (en) | Systems and methods for secure adaptive illustrations | |
| CN113779198A (en) | Electronic business card generating method, device, equipment and medium based on artificial intelligence |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: Room 221, 2nd floor, Block C, 18 Kechuang 11th Street, Daxing Economic and Technological Development Zone, Beijing, 100176 Applicant after: JINGDONG DIGITAL TECHNOLOGY HOLDINGS Co.,Ltd. Address before: Room 221, 2nd floor, Block C, 18 Kechuang 11th Street, Daxing Economic and Technological Development Zone, Beijing, 100176 Applicant before: BEIJING JINGDONG FINANCIAL TECHNOLOGY HOLDING Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: Room 221, 2nd floor, Block C, 18 Kechuang 11th Street, Daxing Economic and Technological Development Zone, Beijing, 100176 Applicant after: Jingdong Technology Holding Co.,Ltd. Address before: Room 221, 2nd floor, Block C, 18 Kechuang 11th Street, Daxing Economic and Technological Development Zone, Beijing, 100176 Applicant before: Jingdong Digital Technology Holding Co.,Ltd. Address after: Room 221, 2nd floor, Block C, 18 Kechuang 11th Street, Daxing Economic and Technological Development Zone, Beijing, 100176 Applicant after: Jingdong Digital Technology Holding Co.,Ltd. Address before: Room 221, 2nd floor, Block C, 18 Kechuang 11th Street, Daxing Economic and Technological Development Zone, Beijing, 100176 Applicant before: JINGDONG DIGITAL TECHNOLOGY HOLDINGS Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190301 |