CN109684800A - Method, apparatus, equipment and the computer storage medium of In vivo detection - Google Patents
Method, apparatus, equipment and the computer storage medium of In vivo detection Download PDFInfo
- Publication number
- CN109684800A CN109684800A CN201811053358.5A CN201811053358A CN109684800A CN 109684800 A CN109684800 A CN 109684800A CN 201811053358 A CN201811053358 A CN 201811053358A CN 109684800 A CN109684800 A CN 109684800A
- Authority
- CN
- China
- Prior art keywords
- user
- detection
- movement
- vivo detection
- information
- 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.)
- Withdrawn
Links
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
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/40—Spoof detection, e.g. liveness detection
- G06V40/45—Detection of the body part being alive
Abstract
The invention discloses a kind of methods of In vivo detection, it include: in the business handling request for receiving terminal transmission, movement to be detected is generated at random according to the request and wait corresponding prompt information of answering a question, and the prompt information is sent to the terminal, when receiving the action message and problem reply message of the terminal feedback, judge whether the action message and problem reply message are all satisfied detection and pass through condition, when the action message and problem reply message, which are all satisfied the detection, passes through condition, business handling operation is carried out.The invention also discloses a kind of living body detection device, In vivo detection equipment and computer storage mediums.The present invention is by issuing the movement to be detected generated at random to user and wait corresponding prompt information of answering a question, the significant increase random performance of In vivo detection in a manner of movement to be detected and combined type In vivo detection to be answered a question, the ability for making In vivo detection have better defensive attack.
Description
Technical field
The present invention relates to field of computer technology more particularly to a kind of biopsy method, living body detection device, living body inspections
Measurement equipment and computer storage medium.
Background technique
Recently as the development of face recognition technology, based on the face identification system of video image processing in authorization identifying
Field is widely used.During face identification system application, especially closely related with client's property
In financial transaction application, the attack of malice, such as the illegal face picture for collecting user are highly prone to attack recognition of face system
System.In order to resist the attack of such malice, detect whether that the biopsy method for being true man and system are given birth to therewith.
In existing biopsy method and system, merely by client issued to user select at random it is dynamic
Make to cause to be easy to be cracked with the increase of attack frequency since its random performance is bad to carry out In vivo detection, to subsequent
Financial transaction brings very big risk.
Above content is only used to facilitate the understanding of the technical scheme, and is not represented and is recognized that above content is existing skill
Art.
Summary of the invention
The main purpose of the present invention is to provide a kind of method of In vivo detection, living body detection device, In vivo detection equipment
And computer storage medium, it is intended to solve in the prior art merely by issuing the movement selected at random to user in client
In vivo detection is carried out, causes since its random performance is bad to be easy the technical issues of being cracked with the increase of attack frequency.
To achieve the above object, the present invention provides a kind of method of In vivo detection, and the method for the In vivo detection includes such as
Lower step:
In the business handling request for receiving terminal transmission, prompt information is generated according to the request is random, and by institute
It states prompt information and is sent to the terminal, the prompt information includes movement to be detected and believes wait corresponding prompt of answering a question
Breath；
When receiving the action message and problem reply message of the terminal feedback, the action message and problem are judged
Whether reply message, which is all satisfied detection, passes through condition, wherein the detection is special by the movement that condition includes the action message
It seeks peace the motion characteristic matching and described problem reply message and the answer to be answered a question of the movement to be detected
Match；
When the action message and problem reply message, which are all satisfied the detection, passes through condition, business handling behaviour is carried out
Make.
Preferably, described when the action message for receiving the user feedback and problem reply message, judge described dynamic
Make information and whether problem reply message is all satisfied the step of detection passes through condition and includes:
When the action message and problem reply message for receiving the user feedback within a preset time, judge described dynamic
Make information and whether problem reply message meets detection and pass through condition.
Preferably, described the step of generating the corresponding prompt information of movement to be detected at random according to the request, includes:
User identifier is obtained from the request, and corresponding user information is obtained according to the user identifier, wherein institute
Stating user information includes age of user and health status；
Corresponding set of actions is determined according to the user information；
It selects movement to be detected at random from the corresponding set of actions and generates that the band detection operation is corresponding to be mentioned
Show information.
Preferably, described random the step of generating prompt information to be answered a question, includes:
User identifier is obtained from the request, and corresponding user information is obtained according to the user identifier, wherein institute
State the risk class that user information includes user；
Corresponding problem set is determined according to the user information；
It is selected at random from the corresponding problem set described wait corresponding mention of answering a question wait answer a question and generate
Show information.
Preferably, described when the action message for receiving the user feedback and problem reply message, judge described dynamic
Make information and whether problem reply message is all satisfied the step of detection passes through condition and includes:
Shape of mouth and audio-frequency information in described problem reply message with it is described corresponding preset wait answer a question
When Shape of mouth and audio-frequency information match, described problem reply message and the answer matches to be answered a question are determined.
Preferably, the method for the In vivo detection further include:
Whether real-time monitoring user has abnormal network behavior；
When monitoring that user has abnormal network behavior, the user is identified as illegal user；
Count the number in the illegal user by In vivo detection；
When the number by In vivo detection is greater than preset threshold, determine that be detected act is in the In vivo detection
Easily crack movement to be detected；
When the movement to be detected is easily cracks movement to be detected, described to be detected will act from deliberate action database
Middle deletion, wherein the deliberate action database for generating movement to be detected at random.
Preferably, described when the action message and problem reply message are all satisfied the detection and pass through condition, it carries out
After the step of business handling operates further include:
Real-time statistics send movement to be detected and wait answer a question to the frequency of terminal；
When the frequency is more than preset threshold, increase random seed generating mode, wherein the increased random seed
Generating mode for generating movement to be detected and wait answer a question at random.
In addition, to achieve the above object, the present invention also provides the living body detection device, which includes:
Random detection item generation module, when for being requested in the business handling for receiving terminal transmission, according to the request
It is random to generate prompt information, and the prompt information is sent to the terminal, the prompt information include movement to be detected and
Wait corresponding prompt information of answering a question；
Judgment module, for when receiving the action message and problem reply message of terminal feedback, described in judgement
Whether action message and problem reply message, which are all satisfied detection, passes through condition, wherein the detection includes described dynamic by condition
Make video motion characteristic and the movement to be detected motion characteristic matching and described problem reply message and it is described wait return
The answer matches of question and answer topic；
Business module, for when the action message and problem reply message are all satisfied the detection and pass through condition, into
Row business handling operation.
In addition, to achieve the above object, the present invention also provides the In vivo detection equipment, which includes: memory, place
It manages device and is stored in the In vivo detection control program that can be run on the memory and on the processor, the In vivo detection
The step of control program realizes biopsy method as described above when being executed by the processor.
In addition, to achieve the above object, the present invention also proposes a kind of computer storage medium, which is characterized in that the meter
In vivo detection control program is stored on calculation machine storage medium, the In vivo detection control program is realized such as when being executed by processor
Above the step of biopsy method.
Method, apparatus, equipment and the computer storage medium for a kind of In vivo detection that the embodiment of the present invention proposes, by giving
User issues the movement to be detected generated at random and wait corresponding prompt information of answering a question, when user feedback action message and
Problem reply message is all satisfied the service request that user is just handled when detection passes through condition, with movement to be detected and wait answer a question
The combined type In vivo detection mode significant increase random performance of In vivo detection, so that In vivo detection is had better defensive attack
Ability.
Detailed description of the invention
Fig. 1 is the apparatus structure schematic diagram for the hardware running environment that the embodiment of the present invention is related to；
Fig. 2 is the flow diagram of biopsy method first embodiment of the present invention；
Fig. 3 is the flow diagram of biopsy method second embodiment of the present invention；
Fig. 4 is the flow diagram of biopsy method 3rd embodiment of the present invention；
Fig. 5 is the flow diagram of biopsy method fourth embodiment of the present invention；
Fig. 6 is the functional block diagram of one embodiment of living body detection device of the present invention.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
As shown in Figure 1, Fig. 1 is the terminal structure schematic diagram for the hardware running environment that the embodiment of the present invention is related to.
As shown in Figure 1, the server that Fig. 1 is the hardware running environment that the embodiment of the present invention is related to (is called at event
Manage equipment, wherein event handling equipment can be to be made of individual event processing apparatus, is also possible to by other devices and thing
Part processing unit combines to be formed) structural schematic diagram.
Server of the embodiment of the present invention refers to a management resource and provides the computer of service for user, is generally divided into file
Server, database server and apps server.The computer or computer system for running the above software are also referred to as
Server.For common PC (personal computer) personal computer, server is in stability, safety, property
Energy etc. requires higher；As shown in Figure 1, the server may include: processor 1001, such as central processing unit
(Central Processing Unit, CPU), network interface 1004, user interface 1003, memory 1005, communication bus
1002, hardware such as chipset, disk system, network etc..Wherein, communication bus 1002 is for realizing the connection between these components
Communication.User interface 1003 may include display screen (Display), input unit such as keyboard (Keyboard), optional user
Interface 1003 can also include standard wireline interface and wireless interface.Network interface 1004 optionally may include having for standard
Line interface, wireless interface (such as Wireless Fidelity WIreless-FIdelity, WIFI interface).Memory 1005 can be high speed with
Machine accesses memory (random access memory, RAM), is also possible to stable memory (non-volatile
), such as magnetic disk storage memory.Memory 1005 optionally can also be the storage dress independently of aforementioned processor 1001
It sets.
Optionally, server can also include camera, RF (Radio Frequency, radio frequency) circuit, sensor, sound
Frequency circuit, WiFi module；Input unit, than display screen, touch screen；Network interface can be blue in blanking wireless interface in addition to WiFi
Tooth, probe, 3G/4G/5G (digital representation of front be cellular mobile communication networks algebra.Which exactly indicate to be generation
Network.English alphabet G indicates generation) internet base station equipment etc..It will be understood by those skilled in the art that showing in Fig. 1
Server architecture out does not constitute the restriction to server, may include than illustrating more or fewer components, or combination
Certain components or different component layouts.
As shown in Figure 1, the computer software product, which is stored in a storage medium, (storage medium: is called computer storage
Medium, computer media, readable medium, readable storage medium storing program for executing, computer readable storage medium are directly medium etc., such as
RAM, magnetic disk, CD) in, including some instructions are used so that a terminal device (can be mobile phone, computer, server, sky
Adjust device or the network equipment etc.) method described in each embodiment of the present invention is executed, as a kind of depositing for computer storage medium
It may include operating system, network communication module, Subscriber Interface Module SIM and computer program in reservoir 1005.
In server shown in Fig. 1, network interface 1004 be mainly used for connect background data base, with background data base into
Row data communication；User interface 1003 is mainly used for connection client, and (client, is called user terminal or terminal, and the present invention is implemented
Example terminal can be also possible to mobile terminal, details are not described herein with fixed terminal), data communication is carried out with client；And it handles
Device 1001 can be used for calling the computer program stored in memory 1005, and execute the thing that following embodiment of the present invention provides
Step in part processing method.
Referring to Fig. 2, first embodiment of the invention provides a kind of method of In vivo detection, which comprises
Step S10 generates prompt letter according to the request is random in the business handling request for receiving terminal transmission
Breath, and the prompt information is sent to the terminal, the prompt information includes movement to be detected and correspondence to be answered a question
Prompt information.
Server is responsible for receiving and handling the business handling request of user, and generates In vivo detection request according to request, i.e.,
Movement to be detected and prompt information to be answered a question are generated at random according to request, expect that user makes instead according to prompt information
Feedback judges user when the feedback received is correct for legitimate user, is user's transacting business.Wherein, prompt information is to be detected
The problem of movement and wait corresponding prompt information of answering a question, movement and answer that specific effect should feed back for prompt user.
Such as prompt information can be such text information: please upload the right hand and draw the video of circle movement, and answer a question: " this year
Which country Football World Championship held at? ", prompt information can also be the audio of the text information, or with small animated video
Mode be shown.
Server establish and service action database and issue database, and can according to preset random algorithm and with
Machine generates the random number in specified range, wherein can generate random seed according to system clock.
Server generates the process of movement to be detected at random from action database are as follows: will be to be detected in action database
Number consecutively is acted, the random number in preset random algorithm generation Serial Number Range is run, according to the taking-up pair of the random number of generation
The movement to be detected that should be numbered.
Server generates process to be answered a question at random from issue database are as follows: by issue database wait answer
Problem number consecutively runs the random number in preset random algorithm generation Serial Number Range, according to the taking-up pair of the random number of generation
Should number wait answer a question.
It can be sent out to further increase generation movement to be detected and randomness to be answered a question, server with real-time statistics
It send movement to be detected and wait answer a question to the frequency of terminal, when the frequency counted on is more than preset threshold, increases with machine
Sub- generating mode, wherein increased random seed generating mode for generating movement to be detected and wait answer a question at random.It can increase
The random seed generating mode added includes being generated, being generated according to Network statistical information or according to business according to software process information
Information generation etc..
Step S20, the action message of terminal feedback and when problem reply message judge that the action message and problem reply
Whether information, which is all satisfied detection, passes through condition, wherein it is described detection by condition include the action message motion characteristic with
The motion characteristic matching of the movement to be detected and described problem reply message and the answer matches to be answered a question.
The problem of action message type of terminal feedback includes picture and video, feedback reply message type include text,
Audio and video.Server can judge the motion characteristic of action message received and to be detected by human action identification technology
Whether the motion characteristic of movement matches, wherein human action identification technology mainly has Statistics-Based Method and based on template
Method is these two types of.
By taking terminal feedback is action video as an example, when using such as hidden Markov model of the method based on probability statistics
It when method, is primarily based on action video image zooming-out and goes out characteristic vector sequence, model parameter instruction is then carried out by learning algorithm
Practice, identification classification finally is carried out to characteristic vector sequence to be identified.By taking movement to be identified is hand-written 26 English alphabets as an example
Illustrate the realization process for identifying human action using hidden markov model approach: first training sample being modeled, will be built
Modulus estimates the parameter of model according to input hidden Markov model, wherein training sample includes each hand-written English alphabet pair
The multiple groups training sample data answered；Then Hand Gesture Segmentation, gesture tracking and gesture feature are carried out based on the image sequence received
Extraction, wherein Hand Gesture Segmentation refers to gesture by features such as the shapes, color, movement of gesture from the background area of image
In extract, gesture tracking be using gesture motion continuity according to this frame image segmentation go out gesture estimate next frame figure
The position of gesture and state as in, gesture feature are extracted as extracting the effective gesture feature that can most represent every class gesture feature, can
The effective gesture feature extracted includes shape, profile or the track of gesture；The feature that will finally be extracted by gesture feature
Sequence vector calculates the preset gesture motion in hidden Markov model as in observation sequence input hidden Markov model
Whether the probability that the observation sequence is generated under disaggregated model belongs to this according to the corresponding feature vector of probabilistic determination this observation sequence
Gesture motion disaggregated model, to realize the gesture identification to the image sequence received.
When using the method based on template, trains first and establish human action feature templates library, it then will be based on dynamic
The motion characteristic to be identified extracted as video image is matched with template, is known by calculating similarity between the two
It does not move work.
Server takes different methods to judge to receive according to the difference of the type of answer content to be answered a question
Problem replies and whether answer to be answered a question matches.When the answer type wait answer a question is numerical value, will directly receive
The problem of reply and answer to be answered a question be compared；It, will when the answer type wait answer a question is single word
The synonym of the problem of receiving answer and answer to be answered a question and answer is compared；When answer to be answered a question is language
When sentence, need to judge using semantic analysis technology that the problem of receiving replies and whether answer to be answered a question matches, specifically
Are as follows: it is primarily based on dictionary and statistical language model and is segmented and carried out part-of-speech tagging to answer character string the problem of receiving, then
Core word is estimated and extracted based on weight of the training pattern to obtained word, finally by will compare wait answer a question
Core word, other words and term weighing, word order and degree of correlation that answer and problem reply etc. come decision problem reply and
Whether answer to be answered a question matches.
Further, when problem reply message is video information, Shape of mouth can be first extracted from video information
And audio-frequency information, when determine Shape of mouth and audio-frequency information with wait corresponding preset Shape of mouth and the audio letter of answering a question
When breath matching, decision problem reply message and answer matches to be answered a question.Specifically, the shape of the mouth as one speaks shape sequence that will be extracted
The feature of column and preset shape of the mouth as one speaks shape sequence feature carry out similarity calculation, by the audio frequency characteristics extracted and preset sound
Frequency feature also carries out similarity calculation, and matching is determined when two similarities are above corresponding preset threshold.Such method is excellent
Choosing is applied to work as the answer type answered a question to be single word scene.
Further, when the information answered a question is video and answer type is sentence, in addition to using speech recognition
Technology and semantic analysis technology judge that the problem of extracting from the audio-frequency information of video replies and answer to be answered a question is
No matching can also extract Shape of mouth and audio-frequency information comprising temporal information, using audio lip sync technology from video
Judge that the shape of the mouth as one speaks changes with time whether to change with audio-frequency information synchronous.It, can be only in audio for the considerations of simplifying processing
Change and choose some sampled points in the duration, judges whether the shape of the mouth as one speaks is continuing according to Shape of mouth acquired in sampling point moment
Change, thinks to have reached audio lip sync if lasting variation again, which is effective.
Step S30 carries out business when the action message and problem reply message, which are all satisfied the detection, passes through condition
Handle operation.
When server determine the action message of user feedback and problem reply message all meets detect pass through condition when, can be with
Determine that the user is authentic and valid user, rather than attack user or fictitious users, next the user can be requested
Business handled.
Further, in order to avoid illegal user or fictitious users carry out brokenly the In vivo detection request that server issues
Solution can limit when the action message and problem for receiving the user feedback within a preset time reply, just execute judgement
The action video and problem reply whether meet movement of the detection by condition.Specifically, server can be sent out to user
When In vivo detection being sent to request, starts a timer and set timer generation interruption when timing reaches preset time, in
It by the status indication of the user is time-out in disconnected service routine.If server receives the movement of user feedback within a preset time
When information and problem reply, the state for viewing user at this time is not a time out state, then to the action message of user feedback and asks
Topic replies and carries out judgement processing, while discarding the corresponding timer of the user；If server is just received having crossed preset time
The action message and problem reply message of user feedback, the state for viewing user at this time is timeout mode, then not anti-to user
Action message and the problem answer of feedback carry out judgement processing.
In the present embodiment, by issuing the movement to be detected generated at random to user and wait corresponding prompt of answering a question
Information, when the action message of user feedback and problem reply message are all satisfied when detection passes through condition, just the business of processing user is asked
It asks, due to movement to be detected and wait answer a question is generated by random algorithm, improve the random degree of In vivo detection, make
In vivo detection is more difficult to be attacked and cracked.
Further, referring to Fig. 3, second embodiment of the invention provides a kind of side of In vivo detection based on first embodiment
Method, the present embodiment include: in step S10
Step S40 obtains user identifier from the request, and obtains corresponding user according to the user identifier and believe
Breath, wherein the user information includes age of user and health status.
The user identifier obtained from request can be user name, Customs Assigned Number or user identity card number.According to acquisition
User identifier executes inquiry operation in User Information Database and obtains user information.Wherein, user information include age of user and
Health status, such as user Zhang the age 42 years old, are in a good state of health or user Lu, the age 65 years old, health status compared with
Difference, there is diabetes, and finger movement is bad.
It should be noted that in order to make the health information in user information be easy to subsequent classification map processing, it can
To be collected and typing based on preset template.The content of default template can be classified as the overall assessment of health status, disease
Title, illness duration, disease sites etc..Wherein, for each classification, it is selective to provide corresponding list, such as health
The overall assessment of situation, corresponding list content include " good, general, poor ", such as disease name, corresponding
List content is listed according to the major disease or common chronic disease of national regulation, such as " hypertension, heart disease, diabetes,
Rheumatoid " etc. such as disease sites, corresponding list content include " head, neck, shoulder, hand, leg, eye,
Oral area " etc..
Step S50 determines corresponding set of actions according to the user information.
Age and health status in user information reflect the unsuitable actuating range of user, such as young and health
User in order does not have unsuitable movement, but older and poor health status user is just only suitable for more
Simple movement, such as eye have the movement of disease be not suitable for " under blink three ", and hand has unsuitable " the hand-written letter of disease
The movement of A " has the cardiopathic movement etc. for being not suitable for " under fast hop five ".
It, can will be in database in order to accurately determine the actuating range i.e. set of actions that is suitble to of user according to user information
Complexity and execution of the everything according to movement required by speed movement is classified, such as be divided into it is more difficult,
Medium, simple three grades or more grades.It is that user obtains comprehensive score, root according to the age of user and health status
The movement grade that user is suitble to is determined according to comprehensive score.Such as regulation: first of age of user less than or equal to 30 years old is scored at
0.6, the age is greater than 30 years old first being scored at for 0.3, age and greater than 60 years old first be scored at 0.1 less than or equal to 60 years old；User
Health status is that good second to be scored at 0.4, health status be that general second to be scored at 0.2, health status be poor
Second is scored at 0.1, and the comprehensive score that the first score is added with the second score is the dynamic of 0.7 point or more the more difficult grade of corresponding selection
Make, comprehensive score be 0.7 assign to the movement of 0.4 point of corresponding selection Middle grade, comprehensive score is 0.4 point of corresponding selection below
The movement of simple grade.
For the set of actions of every level-one after classification, movement is finely divided according to related human body, such as
It can be categorized further, as: hand motion, headwork, leg action, eye motion, oral area movement, multiple location interoperation etc.,
Each classification corresponds to the unsuitable classification of motion of disease sites institute according to systematic name, such as hand motion this kind is unsuitable
Disease sites are the set of actions of hand.
Step S60 selects movement to be detected at random from the corresponding set of actions and generates the band detection operation
Corresponding prompt information.
In the present embodiment, it by the way that set of actions to be classified according to difficulty, and according to the age information of user and is good for
Health condition information selects the set of actions of corresponding grade, avoids causing user that cannot pass through work because inappropriate movement is issued
Physical examination is surveyed, and success rate of the user by In vivo detection is improved, and promotes user experience.
Further, referring to Fig. 4, third embodiment of the invention provides a kind of side of In vivo detection based on first embodiment
Method, the present embodiment include: in step S10
Step S70 obtains user identifier from the request, and obtains corresponding user according to the user identifier and believe
Breath, wherein the user information includes the risk class of user.
The user identifier obtained from request can be user name, Customs Assigned Number or user identity card number.According to acquisition
User identifier executes inquiry operation in User Information Database and obtains user information.Wherein, user information includes the risk of user
Class information, such as can be high risk, three medium risk, low-risk risk class.
It should be noted that depending on service application scene of the setting rule of the risk class of user belonging to it.Example
Such as if it is the application scenarios of insurance business, the wind to user can be recorded according to user's payment of insurance money record, settlement of insurance claim
Dangerous grade is assessed and is set, and if it is the application scenarios of credit card business, can be recorded according to the refund of user, consumption is remembered
Record, cash withdrawal record the setting assessed.So when obtaining the risk class of user, it is also necessary to be requested according to user
The application scenarios type of business goes to obtain its corresponding risk class.
Step S80 determines corresponding problem set according to the user information.
The risk class information of user and authentication grade needed for user are closely related, i.e. consumer's risk higher grade, need
Certification that will be more advanced also needs more high-grade problem certification for the problems in In vivo detection authentication mode
Mode.First problem set can classify according to the type of problem and carry out class letter, example for various classification problems
Such as it is divided into common-sense problem, personal information class problem, passing Transaction Information class problem, wherein be by common-sense problem identification
Simple grade, be general grade by personal information class problem identification, by passing Transaction Information class problem identification be more difficult grade, and
Simple hierarchical problem is corresponded into low risk level user, general hierarchical problem is corresponded to medium risk user, will be more difficult etc.
Grade problem corresponds to high risk user.
Step S90 is selected described wait answer a question wait answer a question and generate at random from the corresponding problem set
Corresponding prompt information.
It in the present embodiment, by the way that problem set to be classified according to difficulty, and is it according to the risk class of user
It determines corresponding problem set, generates problem at random from problem set and issued by In vivo detection request, further improved
The certification effect of In vivo detection.
Further, referring to Fig. 5, fourth embodiment of the invention provides a kind of side of In vivo detection based on first embodiment
Method, the present embodiment are further comprising the steps of:
Whether step S100, real-time monitoring user have abnormal network behavior.
In order to further ensure the certification effect of In vivo detection, it is also necessary to whether there is abnormal net by real-time detection user
Network behavior identifies potential loophole in In vivo detection.It specifically, can be based on time record, the User IP logged in user
Whether the real-time analysis of the range record and requested type of service record of location is a large amount of doubtful illegal to judge to have in the short time
User attacks to server implementation, is also based on the login time record of user, input password errors number record, is asked
The real-time analysis for the type of service record asked is to determine whether there is doubtful illegal user being intended to steal the information of user or pretend to be
User carries out unusual business application.
The user is identified as illegal user when monitoring that user has abnormal network behavior by step S110.
Step S120 counts the number in the illegal user by In vivo detection.
Whenever identifying illegal user, judge whether the illegal user has passed through In vivo detection, if the illegal user passes through
In vivo detection, the number in illegal user by In vivo detection accumulated once.
Step S130, when the number by In vivo detection be greater than preset threshold when, determine in the In vivo detection to
Detection operation is easily to crack movement to be detected.
When the illegal user identified is not over In vivo detection, illustrates that In vivo detection has played and identify fictitious users
Effect, which is effective；When the illegal user identified has passed through In vivo detection, illustrate the In vivo detection one
Determine in degree that there are potential loopholes, that is, be easy the attack by fictitious users and crack, especially as a large amount of illegal user
When all having passed through In vivo detection, it can more determine that the In vivo detection haves the defects that easily to be cracked really, so when above-mentioned illegal
When being greater than preset threshold by the number of In vivo detection in user, it is fragile for can sentencing the movement to be detected in the In vivo detection
Solve movement to be detected.
Step S140, when it is described it is to be detected movement for easily crack movement to be detected when, will it is described it is to be detected movement from preset
It is deleted in action database, wherein the deliberate action database for generating movement to be detected at random.
In the present embodiment, abnormal network behavior whether identifies illegal user by real-time monitoring user, when non-
In method user by In vivo detection number be more than preset threshold when by corresponding action identification to be detected be easily crack movement and from
It is deleted in action database, avoids issuing the prompt information for easily cracking movement by In vivo detection request, lead to illegal user
Again by In vivo detection, to improve the certification effect of In vivo detection.
In addition, the embodiment of the present invention also proposes that a kind of living body detection device, the living body detection device include: referring to Fig. 6
Random detection item generation module 10, for being asked according to described in the business handling request for receiving terminal transmission
It asks random and generates prompt information, and the prompt information is sent to the terminal, the prompt information includes movement to be detected
With wait corresponding prompt information of answering a question；
Judgment module 20, for judging institute when receiving the action message and problem reply message of the terminal feedback
It states action message and whether problem reply message is all satisfied detection and passes through condition, wherein the detection includes described by condition
The motion characteristic of action video and the motion characteristic of the movement to be detected matching and described problem reply message and it is described to
The answer matches answered a question；
Business module 30, for when the action message and problem reply message are all satisfied the detection and pass through condition,
Carry out business handling operation.
Optionally, the judgment module 20 can be also used for receiving the movement of the user feedback within a preset time
When information and problem reply message, judge whether the action message and problem reply message meet detection and pass through condition.
Optionally, the random detection item generation module 10 includes:
Acquiring unit obtains corresponding use for obtaining user identifier from the request, and according to the user identifier
Family information, wherein the user information includes age of user and health status；
Determination unit, for determining corresponding set of actions according to the user information；
Random detection item generation unit, for selecting movement to be detected at random from the corresponding set of actions and generating
The corresponding prompt information of the band detection operation.
Optionally, the random detection item generation module 10 includes:
Acquiring unit obtains corresponding use for obtaining user identifier from the request, and according to the user identifier
Family information, wherein the user information includes the risk class of user；
Determination unit, for determining corresponding problem set according to the user information；
Random detection item generation unit, for being selected at random from the corresponding problem set wait answer a question and generate
It is described wait corresponding prompt information of answering a question.
Optionally, judgment module 20 includes:
Audio lip sync judging unit, in described problem reply message Shape of mouth and audio-frequency information with it is described
When corresponding to preset Shape of mouth and audio-frequency information matching wait answer a question, described problem reply message is determined and described wait return
The answer matches of question and answer topic.
Optionally, the living body detection device further include:
Whether detection module has abnormal network behavior for real-time monitoring user；
Illegal user's module is identified, for when monitoring that user has abnormal network behavior, the user to be identified as
Illegal user；
Statistical module, for counting the number in the illegal user by In vivo detection；
Movement determination module easily is cracked, for determining institute when the number by In vivo detection is greater than preset threshold
State to be detected in In vivo detection act easily to crack movement to be detected；
Action database processing module, for when the movement to be detected is easily cracks movement to be detected, will it is described to
Detection operation is deleted from deliberate action database, wherein the deliberate action database for generating movement to be detected at random.
Optionally, the living body detection device further include:
Statistical module sends movement to be detected for real-time statistics and wait answer a question to the frequency of terminal；
Random algorithm module, for increasing random seed generating mode when the frequency is more than preset threshold, wherein
The increased random seed generating mode for generating movement to be detected and wait answer a question at random.
The present invention also provides a kind of In vivo detection equipment, which includes: memory, processor and is stored in
On the memory and the In vivo detection control program that can run on the processor, In vivo detection control program is by institute
State the step of realizing the biopsy method when processor executes.
In addition, the embodiment of the present invention also proposes a kind of computer storage medium, it is stored in the computer storage medium
In vivo detection controls program, and the In vivo detection control program realizes the step of the biopsy method when being executed by processor
Suddenly.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, method, article or the system that include a series of elements not only include those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or system institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to do
There is also other identical elements in the process, method of element, article or system.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in one as described above
In storage medium (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that terminal device (it can be mobile phone,
Computer, server, air conditioner or network equipment etc.) execute method described in each embodiment of the present invention.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of method of In vivo detection, which is characterized in that the method for the In vivo detection the following steps are included:
In the business handling request for receiving terminal transmission, prompt information is generated according to the request is random, and mention described
Show that information is sent to the terminal, the prompt information includes to be detected acts and wait corresponding prompt information of answering a question；
When receiving the action message and problem reply message of the terminal feedback, judge that the action message and problem reply
Whether information, which is all satisfied detection, passes through condition, wherein it is described detection by condition include the action message motion characteristic with
The motion characteristic matching of the movement to be detected and described problem reply message and the answer matches to be answered a question；
When the action message and problem reply message, which are all satisfied the detection, passes through condition, business handling operation is carried out.
2. the method for In vivo detection as described in claim 1, which is characterized in that described to receive the dynamic of the user feedback
When making information and problem reply message, judge whether the action message and problem reply message are all satisfied detection and pass through condition
Step includes:
When the action message and problem reply message for receiving the user feedback within a preset time, the movement letter is judged
Whether breath and problem reply message, which meet detection, passes through condition.
3. the method for In vivo detection as described in claim 1, which is characterized in that it is described according to it is described request generate at random it is to be checked
Survey act corresponding prompt information the step of include:
User identifier is obtained from the request, and corresponding user information is obtained according to the user identifier, wherein the use
Family information includes age of user and health status；
Corresponding set of actions is determined according to the user information；
It selects movement to be detected at random from the corresponding set of actions and generates the corresponding prompt letter of the band detection operation
Breath.
4. the method for In vivo detection as described in claim 1, which is characterized in that described random to generate prompt to be answered a question
The step of information includes:
User identifier is obtained from the request, and corresponding user information is obtained according to the user identifier, wherein the use
Family information includes the risk class of user；
Corresponding problem set is determined according to the user information；
It is selected at random from the corresponding problem set described wait corresponding prompt letter of answering a question wait answer a question and generate
Breath.
5. the method for In vivo detection as described in claim 1, which is characterized in that described to receive the dynamic of the user feedback
When making information and problem reply message, judge whether the action message and problem reply message are all satisfied detection and pass through condition
Step includes:
Shape of mouth and audio-frequency information in described problem reply message are with described wait the corresponding preset shape of the mouth as one speaks of answering a question
When information and audio-frequency information match, described problem reply message and the answer matches to be answered a question are determined.
6. the method for In vivo detection as described in claim 1, which is characterized in that the method for the In vivo detection further include:
Whether real-time monitoring user has abnormal network behavior；
When monitoring that user has abnormal network behavior, the user is identified as illegal user；
Count the number in the illegal user by In vivo detection；
When the number by In vivo detection is greater than preset threshold, determine that be detected act is fragile in the In vivo detection
Solve movement to be detected；
When the movement to be detected is easily cracks movement to be detected, the movement to be detected is deleted from deliberate action database
It removes, wherein the deliberate action database for generating movement to be detected at random.
7. such as the method for In vivo detection as claimed in any one of claims 1 to 6, which is characterized in that described to work as the action message
With problem reply message be all satisfied it is described detection pass through condition when, carry out business handling operation the step of after further include:
Real-time statistics send movement to be detected and wait answer a question to the frequency of terminal；
When the frequency is more than preset threshold, increase random seed generating mode, wherein the increased random seed generates
Mode for generating movement to be detected and wait answer a question at random.
8. a kind of living body detection device, which is characterized in that the living body detection device includes:
Random detection item generation module, for being requested at random according to described in the business handling request for receiving terminal transmission
Prompt information is generated, and the prompt information is sent to the terminal, the prompt information includes to be detected acts and wait return
Question and answer inscribes corresponding prompt information；
Judgment module, for judging the movement when receiving the action message and problem reply message of the terminal feedback
Whether information and problem reply message, which are all satisfied detection, passes through condition, wherein the detection includes that the movement is believed by condition
It the motion characteristic of breath and the matching of the motion characteristic of the movement to be detected and described problem reply message and described is asked wait answer
The answer matches of topic；
Business module, for carrying out industry when the action message and problem reply message are all satisfied the detection and pass through condition
Operation is handled in business.
9. a kind of In vivo detection equipment, which is characterized in that the In vivo detection equipment includes: memory, processor and is stored in
On the memory and the In vivo detection processing routine that can run on the processor, the living body inspection processing routine are described
The step of biopsy method as described in any one of claims 1 to 7 is realized when processor executes.
10. a kind of computer storage medium, which is characterized in that be stored with In vivo detection processing journey in the computer storage medium
Sequence realizes the In vivo detection as described in any one of claims 1 to 7 when the In vivo detection processing routine is executed by processor
The step of method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811053358.5A CN109684800A (en) | 2018-09-07 | 2018-09-07 | Method, apparatus, equipment and the computer storage medium of In vivo detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811053358.5A CN109684800A (en) | 2018-09-07 | 2018-09-07 | Method, apparatus, equipment and the computer storage medium of In vivo detection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109684800A true CN109684800A (en) | 2019-04-26 |
Family
ID=66185198
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811053358.5A Withdrawn CN109684800A (en) | 2018-09-07 | 2018-09-07 | Method, apparatus, equipment and the computer storage medium of In vivo detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109684800A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111046804A (en) * | 2019-12-13 | 2020-04-21 | 北京旷视科技有限公司 | Living body detection method, living body detection device, electronic equipment and readable storage medium |
| CN111126214A (en) * | 2019-12-13 | 2020-05-08 | 北京旷视科技有限公司 | Living body detection method and apparatus, computer device, and computer-readable storage medium |
| WO2021000415A1 (en) * | 2019-07-03 | 2021-01-07 | 平安科技（深圳）有限公司 | Method and device for live user detection, computer device, and storage medium |
| CN113033404A (en) * | 2021-03-26 | 2021-06-25 | 平安银行股份有限公司 | Face attack event detection method, device, equipment and storage medium |
-
2018
- 2018-09-07 CN CN201811053358.5A patent/CN109684800A/en not_active Withdrawn
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021000415A1 (en) * | 2019-07-03 | 2021-01-07 | 平安科技（深圳）有限公司 | Method and device for live user detection, computer device, and storage medium |
| CN111046804A (en) * | 2019-12-13 | 2020-04-21 | 北京旷视科技有限公司 | Living body detection method, living body detection device, electronic equipment and readable storage medium |
| CN111126214A (en) * | 2019-12-13 | 2020-05-08 | 北京旷视科技有限公司 | Living body detection method and apparatus, computer device, and computer-readable storage medium |
| CN113033404A (en) * | 2021-03-26 | 2021-06-25 | 平安银行股份有限公司 | Face attack event detection method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9298912B2 (en) | System and method for distinguishing human swipe input sequence behavior and using a confidence value on a score to detect fraudsters | |
| WO2017071126A1 (en) | Touch-screen user key-press behavior pattern construction and analysis system and identity recognition method thereof | |
| Li et al. | Unobservable re-authentication for smartphones. | |
| CN106803168B (en) | Abnormal transfer detection method and device | |
| CN109684800A (en) | Method, apparatus, equipment and the computer storage medium of In vivo detection | |
| Ryu et al. | Continuous multimodal biometric authentication schemes: a systematic review | |
| CN104408341B (en) | Smart phone user identity identifying method based on gyroscope behavioural characteristic | |
| CN108717663B (en) | Facial tag fraud judging method, device, equipment and medium based on micro expression | |
| US20180012003A1 (en) | Pointing device biometrics continuous user authentication | |
| CN104135365B (en) | Method, server and the client that access request is verified | |
| CN108229130A (en) | A kind of verification method and device | |
| CN103258157B (en) | A kind of online handwriting authentication method based on finger information and system | |
| CN106572049A (en) | Identity verifying apparatus and method | |
| CN105844206A (en) | Identity authentication method and identity authentication device | |
| CN109918892A (en) | Verification code generation method, device and storage medium, computer equipment | |
| CN111652087B (en) | Car inspection method, device, electronic equipment and storage medium | |
| CN109413023A (en) | The training of machine recognition model and machine identification method, device, electronic equipment | |
| Weng et al. | Towards understanding the security of modern image captchas and underground captcha-solving services | |
| CN109600336A (en) | Store equipment, identifying code application method and device | |
| US10997609B1 (en) | Biometric based user identity verification | |
| CN109194689A (en) | Abnormal behaviour recognition methods, device, server and storage medium | |
| CN106570367B (en) | Method for identifying ID and device based on keyboard operation | |
| WO2022142903A1 (en) | Identity recognition method and apparatus, electronic device, and related product | |
| CN109871673A (en) | Based on the lasting identity identifying method and system in different context environmentals | |
| CN110675252A (en) | Risk assessment method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190426 |
|
| WW01 | Invention patent application withdrawn after publication |