CN109697666A - Method for prewarning risk, device, computer equipment and storage medium - Google Patents
Method for prewarning risk, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109697666A CN109697666A CN201811546615.9A CN201811546615A CN109697666A CN 109697666 A CN109697666 A CN 109697666A CN 201811546615 A CN201811546615 A CN 201811546615A CN 109697666 A CN109697666 A CN 109697666A
- Authority
- CN
- China
- Prior art keywords
- video
- answer
- expression
- target
- micro
- 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 43
- 230000014509 gene expression Effects 0.000 claims abstract description 117
- 238000013507 mapping Methods 0.000 claims abstract description 30
- 230000011218 segmentation Effects 0.000 claims abstract description 27
- 230000001815 facial effect Effects 0.000 claims description 32
- 238000004590 computer program Methods 0.000 claims description 26
- 235000011464 Pachycereus pringlei Nutrition 0.000 claims description 22
- 240000006939 Pachycereus weberi Species 0.000 claims description 22
- 235000011466 Pachycereus weberi Nutrition 0.000 claims description 22
- 238000012790 confirmation Methods 0.000 claims description 12
- 208000003164 Diplopia Diseases 0.000 claims description 8
- 238000010195 expression analysis Methods 0.000 claims description 8
- 238000001514 detection method Methods 0.000 claims description 7
- 238000010586 diagram Methods 0.000 description 5
- 238000012549 training Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000012550 audit Methods 0.000 description 2
- 238000005266 casting Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 210000001097 facial muscle Anatomy 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- 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
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/174—Facial expression recognition
Abstract
This application involves field of biological recognition, in particular to a kind of method for prewarning risk, device, computer equipment and storage medium.The described method includes: receiving default problem, and acquires target corresponding with default problem and reply video；It identifies that target replies the answer keyword in video, and target is replied into video segmentation by replying keyword；It obtains and presets mapping relations, the target after being segmented according to the identification of default mapping relations replies video and obtains replying the corresponding micro- expression of answer of keyword, and obtains the corresponding probability of cheating of target answer video according to micro- expression is replied；When probability of cheating is greater than preset value, Risk-warning signal is exported.It can judge that it provides the authenticity of information according to micro- expression of the user when filing an application using this method, improve the accuracy of auditing result.
Description
Technical field
This application involves field of computer technology, more particularly to a kind of method for prewarning risk, device, computer equipment and
Storage medium.
Background technique
In recent years, the development of society, the level of consumption of people are also gradually increased therewith, and more and more consumers can select
Loan product, to alleviate consumption pressure or carry out other investments, bank and other financial mechanism is also proposed the finance such as debt-credit class therewith
Product.
However in a large number of users application financial product, business personnel needs to be performed in accordance with record list and document audit, so
And business personnel is difficult to tell whether application user is high risk user, and when the application to user is audited, accuracy
It is lower.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide a kind of risk that can be improved auditing result accuracy
Method for early warning, device, computer equipment and storage medium.
A kind of method for prewarning risk, which comprises
Default problem is received, and acquires target answer video corresponding with the default problem；
It identifies that the target replies the answer keyword in video, and is replied the target by the answer keyword
Video segmentation；
Default mapping relations are obtained, video is replied according to the target after the default mapping relations identification segmentation and is obtained
The answer keyword is corresponding to reply micro- expression, and replies micro- expression according to described and obtain the target to reply video corresponding
Probability of cheating；
When the probability of cheating is greater than preset value, Risk-warning signal is exported.
Acquisition target answer video corresponding with the default problem in one of the embodiments, comprising:
Acquisition the first answer video corresponding with the default problem, and the acquisition according to the default problem detection
First, which replies video, whether there is error message；
When detecting the error message, the first answer video is stored in predeterminated position；
Instruction is rerecorded in reception, and rerecords instruction acquisition facial image according to described；
The facial image corresponding first, which is searched, in the predeterminated position replies video；
Acquisition replies video with the default problem corresponding second；
Spliced the first answer video and the second answer video to obtain the target answer video.
In one of the embodiments, it is described according to it is described reply micro- expression and obtain the target reply that video is corresponding to take advantage of
Cheat probability, comprising:
Obtain the corresponding micro- expression of standard of the answer keyword；
Calculate the difference between the micro- expression of the answer and the micro- expression of the standard；
The target, which is calculated, according to the difference replies the corresponding probability of cheating of video.
In one of the embodiments, the method also includes:
It obtains micro- expression cardon group expression corresponding with the micro- expression cardon group and determines result；
The variation track of face characteristic is extracted from micro- expression cardon group；
The variation track and the expression are determined that result establishes the default mapping relations.
In one of the embodiments, after the answer keyword in the identification target answer video, further includes:
When identifying numeric item corresponding with the answer keyword, then voice corresponding with the numeric item is obtained simultaneously
Output；
When receiving the voice corresponding confirmation instruction, save the answer keyword and with the answer keyword
Corresponding numeric item.
In one of the embodiments, it is described according to it is described reply micro- expression and obtain the target reply that video is corresponding to take advantage of
After swindleness probability, further includes:
When the probability of cheating is less than or equal to preset value, the facial image replied in video is obtained；
By facial image storage corresponding with the probability of cheating.
A kind of Risk-warning device, described device include:
Video acquisition module for receiving default problem, and acquires target answer video corresponding with the default problem；
Video segmentation module, the target replies the answer keyword in video for identification, and is closed by the answer
The target is replied video segmentation by keyword；
Micro- Expression analysis module, for obtaining default mapping relations, after the default mapping relations identification segmentation
The target replies video and obtains the corresponding micro- expression of answer of the answer keyword, and obtains institute according to the micro- expression of answer
It states target and replies the corresponding probability of cheating of video；
Risk judgment module, for exporting Risk-warning signal when the probability of cheating is greater than preset value.
Micro- Expression analysis module includes: in one of the embodiments,
First acquisition unit replies video with the default problem corresponding first for acquiring, and according to described default
First of acquisition described in problem detection, which replies video, whether there is error message；
Erroneous memory cell, for the first answer video being stored in default when detecting the error message
Position；
Start unit is rerecorded, rerecords instruction for receiving, and rerecord instruction acquisition facial image according to described；
Video matching unit replies video for searching the facial image corresponding first in the predeterminated position；
Second acquisition unit replies video with the default problem corresponding second for acquiring；
Video-splicing unit, it is described for being spliced to obtain the first answer video and the second answer video
Target replies video.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
The step of device realizes any of the above-described the method when executing the computer program.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
The step of method described in any of the above embodiments is realized when row.
Above-mentioned method for prewarning risk, device, computer equipment and storage medium, technical staff acquire application according to terminal
The user of financial product identifies according to speech recognition apparatus according to the answer video of default problem typing and replies answering in video
Returning to customs keyword will reply video segmentation, and according to micro- expression in trained each section of video of micro- Expression Recognition rule analysis
Reasonability, to judge whether this application user is high risk user, and the request for product proposed to user is audited；By upper
Method is stated, judges that it provides the authenticity of information according to micro- expression of the user when filing an application, improves the standard of auditing result
True property.
Detailed description of the invention
Fig. 1 is the application scenario diagram of one embodiment risk method for early warning；
Fig. 2 is the flow diagram of one embodiment risk method for early warning；
Fig. 3 is the flow diagram of step S202 in one embodiment；
Fig. 4 is the structural block diagram of one embodiment risk prior-warning device；
Fig. 5 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
Method for prewarning risk provided by the present application can be applied in application environment as shown in Figure 1.Wherein, terminal 102
It is communicated by network with server 104.Terminal 102 obtains the corresponding default problem of a certain product from server 104, then
Video is replied by the target corresponding with default problem that the video capture device of terminal 102 acquires user's input, identifies this mesh
After mark replies the answer keyword in video, video is replied to target and carries out piecewise analysis, corresponding micro- expression is obtained, judges it
Probability of cheating, when probability of cheating is higher, then terminal 102 makes prompting to technical staff.Wherein, terminal 102 can with but it is unlimited
Then various personal computers, laptop, smart phone, tablet computer and portable wearable device, server 104 can
To be realized with the independent server either server cluster that forms of multiple servers.
In one embodiment, as shown in Fig. 2, providing a kind of method for prewarning risk, it is applied in Fig. 1 in this way
It is illustrated for terminal 102, comprising the following steps:
S202 receives default problem, and acquires target corresponding with default problem and reply video.
Wherein, default problem be for making user correspond to answer according to this question answering, and record reply video foundation；
It can be the problem of technical staff or micro- expression researcher are arranged according to the key message in the product audited to needs, example
Such as be directed to financial product, then preset problem can for application identity information, whether credit record excellent, family relationship etc..
Target replies the video that the user that video is application purchase product records according to default problem, may include user's
Face information and user make the voice messaging of answer according to default problem.
Specifically, user apply product when, the available default problem for this product set of staff to
Apply for that user, user answer before capture apparatus according to the problem of presetting, capture apparatus acquisition user makes the video of answer
Video is replied as target.
S204, identification target replies the answer keyword in video, and will answer target diplopia frequency division by replying keyword
Section.
Wherein, replying keyword is for replying the keyword that video is segmented to target, for example, for financial credit
Class product can be identity information, proprietary information, contact information, guarantee information etc. keyword.
Specifically, terminal replies in video from collected target and identifies answer keyword in the voice of user, by this
Target replies video and is divided into several segments, then to carrying out correspondence analysis in each section of video.
Optionally, technical staff can be by the speech recognition modeling pair that obtains to a large amount of voice and semantic sample training
Target reply video in voice identified, when recognize for the first time there is a certain keyword when, then target is replied into video
Subsequent one section is used as this to reply the corresponding video-frequency band of keyword, until next answer keyword occurs.In addition in video
In recording process, the default problem that user Xu answers can be broadcasted by the voice-output device of terminal, should include in this default problem
The answer keyword that need to be identified, by the method, terminal, which need to only identify the terminal speech of setting, replies keyword, without locating
The a variety of accents and pronunciation habit for managing user, the step for can more accurately and rapidly completing.
S206 obtains default mapping relations, replies video according to the target after the identification segmentation of default mapping relations and is answered
Returning to customs keyword is corresponding to reply micro- expression, and obtains the corresponding probability of cheating of target answer video according to micro- expression is replied.
Wherein, default mapping relations are for judging that target replies the foundation of the micro- expression occurred in video；Technical staff
Default mapping relations can be trained according to situation of change of a large amount of human face datas when making different micro- expressions, such as work as end
When a series of certain variation occur in the face that end recognizes the face in video, then it can determine whether that this face has made glad or doubt
Micro- expression.
Replying micro- expression is that the target after replying the corresponding segmentation of keyword replies micro- expression that user makes in video,
It may include the micro- expression result of happy, interested, doubt etc..
Specifically, terminal replies each section in video according to target after trained default mapping relations identification segmentation
Then micro- expression judges that whether rationally this micro- expression occurs in this section, if unreasonable, the promise breaking possibility of this user is more
Greatly, that is, judge the probability of cheating of user, terminal replies video to the target after each section of segmentation according to the method and analyzes, obtains
The corresponding probability of cheating of video is replied to entire target.
Optionally, technical staff can be changed by the face to a large amount of faces and facial muscle movement carries out research and training
It can identify micro- Expression Recognition model of micro- expression of the human face action in video out, terminal is by the answer video input after segmentation
In micro- Expression Recognition model, that is, it can determine whether the corresponding micro- expression of the facial action of user in video.
S208 exports Risk-warning signal when probability of cheating is greater than preset value.
Wherein, preset value is can be specially for judging whether the probability of cheating of this user meets the threshold value of application condition
Family breaks a contract according to history records and analyzes a specific value of setting.
Risk-warning signal is the alarm signal that the purchase condition of product is not met for reminding business personnel this user, can
To be the message shown on a terminal screen or mail, the mobile phone or computer of business personnel can also be sent to by terminal
On equal intelligent terminals.
Optionally, terminal, can be by this target after replying entire target video analysis and obtaining its corresponding probability of cheating
Answer video and its result of probability of cheating analysis are sent to server and are stored, a part as user's application record.
The auditor on backstage can check the request for product that user lifts according to this video, guarantee the accuracy of audit.
Above-mentioned method for prewarning risk, technical staff acquire the user for applying for financial product according to default problem according to terminal
The answer video of typing identifies the answer keyword replied in video according to speech recognition apparatus, will reply video segmentation, and
According to the reasonability of micro- expression in trained each section of video of micro- Expression Recognition rule analysis, to judge that this application user is
No is high risk user, and the request for product proposed to user is audited；Through the above method, according to user when filing an application
Micro- expression judge its provide information authenticity, improve the accuracy of auditing result.
In one embodiment, the acquisition mesh corresponding with default problem in the step S202 in above-mentioned method for prewarning risk
Mark replies video, may comprise steps of:
S302 acquires corresponding with default problem first and replies video, and answers according to the first of the acquisition of default problem detection
Diplopia frequency whether there is error message.
Wherein, the first answer video is a part that target replies video, may include the face information and use of user
The voice messaging of answer is made according to the default problem of a part in family.
Error message is the information whether normally recorded for detecting the first answer video, and terminal is adopted by capture apparatus
When collecting target answer video, needs while whether detector shooting state degree is normal, whether the shooting that target replies video is complete,
Whether user answers all default problems etc. information, if shooting state is abnormal, target answer video is imperfect, user
Not answering all default problems etc. all can be used as error message.
Specifically, terminal replies video for the part acquired as first, terminal exists when acquiring target answer video
While acquisition, also to detect the target acquired and reply video with the presence or absence of error message.
First answer video is stored in predeterminated position when detecting error message by S304.
Wherein, predeterminated position is the position that video is replied for storing the target acquired；It can be in terminal one to set
The file set is also possible to server or other positions in order not to the space of occupied terminal.
Specifically, when terminal detects that acquired first replies in video there are when error message in step s 302,
The part acquired is then stored in predeterminated position, avoids loss of data, there is no can continue after above-mentioned error message after terminal
It acquires target and replies video.
Instruction is rerecorded in S306, reception, and according to rerecording instruction acquisition facial image.
Wherein, rerecording instruction is the instruction for acquiring the video of user of existing acquisition and recording again, can be business people
Instruction of the member to terminal input.
Facial image is user in the acquisition visual field of terminal, and the photo or video of the face of application user are acquired by terminal
Deng.
Specifically, when terminal receives when rerecording instruction of technical staff's input, the capture apparatus for first passing through terminal is acquired
The image of face in visible range is indexed as its query video.
S308 searches facial image corresponding first in predeterminated position and replies video.
Specifically, the time can be used as index in the video that terminal stores in predeterminated position, can also use user
Identity information is index, such as the facial image of user；When terminal needs to carry out video record to the user for having record again,
After terminal collects the facial image of this user by capture apparatus, i.e., this use is searched as identity index by facial image
First recorded before family replies video.
S310 acquires corresponding with default problem second and replies video.
Specifically, when terminal by step S308 after predeterminated position finds corresponding first and replies video, can be the
The position of one answer video error continues to record the second answer video, for example, if the first answer video is in a certain default problem
Recording in malfunction, then terminal can continue to record this default problem and its part later.
S312 is spliced the first answer video and the second answer video to obtain target answer video.
Specifically, after the completion of second replies video record, then first can be replied the part and the before video error
Two answer videos are spliced, and are obtained complete and faultless target and are replied video.
In above-described embodiment, it is automatically stored by the way that the target of error is replied the part that video has acquired, and terminal
Stored first can be obtained automatically according to the facial image for rerecording instruction and user and reply video, and continued automatic after recording
Splicing, the collection process for making target reply video are more flexible.
In one embodiment, target is obtained according to the micro- expression of answer in the step S206 in above-mentioned method for prewarning risk
The corresponding probability of cheating of video is replied, may include: to obtain to reply the corresponding micro- expression of standard of keyword；It calculates and replies micro- expression
Difference between the micro- expression of standard；Target, which is calculated, according to difference replies the corresponding probability of cheating of video.
Wherein, the micro- expression of standard is micro- table that user can normally make during the corresponding answer of a certain answer keyword
Feelings, type can not be unique, such as when answering policy information, should be micro- expression such as self-confident, happy.
Specifically, after target is replied video segmentation by terminal, acquiring technology personnel are according to user in a large amount of history applications
The micro- expression of standard that can normally occur in the corresponding video-frequency band of each answer keyword that fraud information obtains, and calculate standard
The target that micro- expression and this user record replies the micro- expression of answer occurred in the video end of this answer keyword in video, that is, works as
Reply between micro- expression and the micro- expression of standard that difference is bigger, then prove this target reply video probability of cheating it is bigger, technology people
Member can specify that relationship between this difference and probability of cheating, and terminal can calculate that difference is corresponding to take advantage of according to the relationship of regulation
Cheat probability.
In above-described embodiment, technical staff is closed according to each answer that the fraud information of user in a large amount of history applications obtains
The micro- expression of standard that can normally occur in the corresponding video-frequency band of keyword, it is micro- that terminal replies the answer occurred in video according to target
Difference between expression and the micro- expression of standard obtains this target and replies the corresponding probability of cheating of video.
In one embodiment, above-mentioned method for prewarning risk can also include: and obtain micro- expression cardon group to move with micro- expression
The corresponding expression of figure group determines result；The variation track of face characteristic is extracted from micro- expression cardon group；By variation track and table
Feelings determine that result establishes default mapping relations.
Wherein, micro- expression cardon group is the corresponding micro- expression of situation of change for judging the face in the video of input
Sample cardon；It may include the corresponding video-frequency band of several micro- expressions or cardon group.
Face characteristic is several changed characteristic points of face in micro- expression cardon group for identification, may include five
The distance between official, face, face several major muscles etc. characteristic point, the index as the variation of observation face.
Specifically, terminal needs to obtain and make for several micro- expression cardon groups of training in the default mapping relations of training
For training sample, terminal extracts the face characteristic in micro- expression cardon group, records this face characteristic when making a certain micro- expression
Variation track, train can be determined according to the variation track of face characteristic its corresponding micro- expression default mapping close
System.
In above-described embodiment, provide for determining that target replies the default mapping pass for micro- expression that user makes in video
The generating mode of system.
In one embodiment, the step S204 identification target in above-mentioned Risk-warning replies the answer keyword in video
It later, can also include: then to obtain voice corresponding with numeric item simultaneously when identifying numeric item corresponding with keyword is replied
Output；When receiving voice corresponding confirmation instruction, saves and reply keyword and numeric item corresponding with keyword is replied.
Wherein, numeric item is that the number or character string for replying and providing in video, example are recorded according to default problem in user
The account number of such as user, phone, identification card number, guarantor contact method.
Confirmation instruction is the instruction for the recognition result confirmation that user says terminal according to user numeric item, can be end
After holding the numeric item that will identify that carry out voice broadcast, if user judges that casting content is correct, to the confirmation of terminal input
Instruction.
Specifically, when terminal record reply video when, the answer content of user can be identified simultaneously, when recognizing
The answer content of user is the numeric item progress voice broadcast that then terminal provides user after the numeric item of key message, user
If judgement casting content is correct, the confirmation instruction inputted to terminal counts this after terminal receives the confirmation instruction of user
Word item is corresponding with keyword is replied to be saved.
In above-described embodiment, the numeric item that terminal provides user speech is further confirmed that and is stored.
In one embodiment, the step S204 in above-mentioned Risk-warning obtains target answer video according to micro- expression is replied
After corresponding probability of cheating, further includes: when probability of cheating is less than or equal to preset value, obtain the face figure replied in video
Picture；By facial image storage corresponding with probability of cheating.
Specifically, when terminal determines the corresponding probability of cheating of target answer video of user less than or equal to preset value, i.e.,
Determine that user meets the condition for buying this product, terminal is obtained target and replied by built-in or connection face recognition device
The facial image of user in video, a part of the identity information as this user, and by the information of user, facial image,
Probability of cheating correspondence is stored in user database.
In above-described embodiment, the judgement of face and probability of cheating for determining the user of probability of cheating in safe range
As a result corresponding storage can be used as the considerations of user applies for other Related products later factor as user record.
It should be understood that although each step in the flow chart of Fig. 2 to Fig. 3 is successively shown according to the instruction of arrow,
But these steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly state otherwise herein, these
There is no stringent sequences to limit for the execution of step, these steps can execute in other order.Moreover, Fig. 2 is into Fig. 3
At least part step may include that perhaps these sub-steps of multiple stages or stage are not necessarily same to multiple sub-steps
One moment executed completion, but can execute at different times, and the execution in these sub-steps or stage sequence is also not necessarily
Be successively carry out, but can at least part of the sub-step or stage of other steps or other steps in turn or
Alternately execute.
In one embodiment, as shown in figure 4, providing a kind of Risk-warning device, comprising: video acquisition module 100,
Video segmentation module 200, micro- Expression analysis module 300 and risk judgment module 400, in which:
Video acquisition module 100 for receiving default problem, and acquires target corresponding with default problem and replies video.
Video segmentation module 200, target replies the answer keyword in video for identification, and will by replying keyword
Target replies video segmentation.
Micro- Expression analysis module 300, for obtaining default mapping relations, according to the mesh after the identification segmentation of default mapping relations
It marks answer video to obtain replying the corresponding micro- expression of answer of keyword, and target answer video is obtained according to the micro- expression of answer and is corresponded to
Probability of cheating.
Risk judgment module 400, for exporting Risk-warning signal when probability of cheating is greater than preset value.
In one embodiment, micro- Expression analysis module 300 in above-mentioned Risk-warning device may include:
First acquisition unit replies video for acquiring corresponding with default problem first, and according to default problem detection
The first of acquisition, which replies video, whether there is error message.
Erroneous memory cell, for when detecting error message, the first answer video to be stored in predeterminated position.
Start unit is rerecorded, rerecords instruction for receiving, and according to rerecording instruction acquisition facial image.
Video matching unit replies video for searching facial image corresponding first in predeterminated position.
Second acquisition unit replies video for acquiring corresponding with default problem second.
Video-splicing unit, for being spliced the first answer video and the second answer video to obtain target answer view
Frequently.
In one embodiment, micro- Expression analysis module 300 in above-mentioned Risk-warning device may include:
The micro- expression acquiring unit of standard replies the corresponding micro- expression of standard of keyword for obtaining.
Difference computational unit, for calculating the difference replied between micro- expression and the micro- expression of standard.
Probability of cheating computing unit replies the corresponding probability of cheating of video for calculating target according to difference.
In one embodiment, above-mentioned Risk-warning device can also include:
Expression determination module determines result for obtaining micro- expression cardon group expression corresponding with micro- expression cardon group.
Characteristic locus extraction module, for extracting the variation track of face characteristic from micro- expression cardon group.
Relationship establishes module, for variation track and expression to be determined that result establishes default mapping relations.
In one embodiment, above-mentioned Risk-warning device can also include:
Numeric item identification module, for when identifying with the corresponding numeric item of keyword is replied, then obtaining and numeric item
Corresponding voice simultaneously exports.
Numeric item confirmation module, for when receiving voice corresponding confirmation instruction, save reply keyword and with answer
The corresponding numeric item of returning to customs keyword.
In one embodiment, above-mentioned Risk-warning device can also include:
Safety application processing module, for obtaining the face replied in video when probability of cheating is less than or equal to preset value
Image.
Generation module is recorded, is used for facial image storage corresponding with probability of cheating.
Specific about Risk-warning device limits the restriction that may refer to above for method for prewarning risk, herein not
It repeats again.Modules in above-mentioned Risk-warning device can be realized fully or partially through software, hardware and combinations thereof.On
Stating each module can be embedded in the form of hardware or independently of in the processor in computer equipment, can also store in a software form
In memory in computer equipment, the corresponding operation of the above modules is executed in order to which processor calls.
In one embodiment, a kind of computer equipment is provided, which can be terminal, internal structure
Figure can be as shown in Figure 5.The computer equipment includes processor, the memory, network interface, display connected by system bus
Screen and input unit.Wherein, the processor of the computer equipment is for providing calculating and control ability.The computer equipment is deposited
Reservoir includes non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system and computer journey
Sequence.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The network interface of machine equipment is used to communicate with external terminal by network connection.When the computer program is executed by processor with
Realize a kind of method for prewarning risk.The display screen of the computer equipment can be liquid crystal display or electric ink display screen,
The input unit of the computer equipment can be the touch layer covered on display screen, be also possible to be arranged on computer equipment shell
Key, trace ball or Trackpad, can also be external keyboard, Trackpad or mouse etc..
It will be understood by those skilled in the art that structure shown in Fig. 5, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, which is stored with
Computer program, which performs the steps of reception default problem when executing computer program, and acquires and default problem
Corresponding target replies video；It identifies that target replies the answer keyword in video, and is replied target by replying keyword
Video segmentation；Default mapping relations are obtained, obtains replying according to the target answer video after the identification segmentation of default mapping relations and close
Keyword is corresponding to reply micro- expression, and obtains the corresponding probability of cheating of target answer video according to micro- expression is replied；When fraud is general
When rate is greater than preset value, Risk-warning signal is exported.
In one embodiment, processor executes the acquisition target corresponding with default problem realized when computer program and answers
Diplopia frequency, comprising: acquisition corresponding with default problem first replies video, and replies according to the first of the acquisition of default problem detection
Video whether there is error message；When detecting error message, the first answer video is stored in predeterminated position；Reception is rerecorded
Instruction, and according to rerecording instruction acquisition facial image；Facial image corresponding first, which is searched, in predeterminated position replies video；Acquisition
Corresponding with default problem second replies video；Spliced the first answer video and the second answer video to obtain target answer
Video.
In one embodiment, that realizes when processor execution computer program obtains target answer according to the micro- expression of answer
The corresponding probability of cheating of video, comprising: obtain and reply the corresponding micro- expression of standard of keyword；It calculates the micro- expression of answer and standard is micro-
Difference between expression；Target, which is calculated, according to difference replies the corresponding probability of cheating of video.
In one embodiment, it is dynamic that acquisition micro- expression can also be performed the steps of when processor executes computer program
Figure group expression corresponding with micro- expression cardon group determines result；The variation track of face characteristic is extracted from micro- expression cardon group；
Variation track and expression are determined that result establishes default mapping relations.
In one embodiment, the answer that processor executes that the identification target realized when computer program replies in video is closed
After keyword, further includes: when identifying numeric item corresponding with keyword is replied, then obtain voice corresponding with numeric item simultaneously
Output；When receiving voice corresponding confirmation instruction, saves and reply keyword and numeric item corresponding with keyword is replied.
In one embodiment, that realizes when processor execution computer program obtains target answer according to the micro- expression of answer
After the corresponding probability of cheating of video, further includes: when probability of cheating is less than or equal to preset value, obtain the face replied in video
Image；By facial image storage corresponding with probability of cheating.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program performs the steps of reception default problem when being executed by processor, and acquires target corresponding with default problem and reply
Video；It identifies that target replies the answer keyword in video, and target is replied into video segmentation by replying keyword；It obtains pre-
If mapping relations, it is micro- that the corresponding answer of answer keyword is obtained according to the target answer video after the identification segmentation of default mapping relations
Expression, and the corresponding probability of cheating of target answer video is obtained according to micro- expression is replied；It is defeated when probability of cheating is greater than preset value
Risk pre-warning signal out.
In one embodiment, the acquisition realized when computer program is executed by processor target corresponding with default problem
Reply video, comprising: acquisition corresponding with default problem first replies video, and answers according to the first of the acquisition of default problem detection
Diplopia frequency whether there is error message；When detecting error message, the first answer video is stored in predeterminated position；Receive weight
Record instruction, and according to rerecording instruction acquisition facial image；Facial image corresponding first, which is searched, in predeterminated position replies video；It adopts
Collect corresponding with default problem second and replies video；Spliced the first answer video and the second answer video to obtain target and be answered
Diplopia frequency.
In one embodiment, that realizes when computer program is executed by processor answers according to replying micro- expression and obtain target
The corresponding probability of cheating of diplopia frequency, comprising: obtain and reply the corresponding micro- expression of standard of keyword；It calculates and replies micro- expression and standard
Difference between micro- expression；Target, which is calculated, according to difference replies the corresponding probability of cheating of video.
In one embodiment, it can also be performed the steps of when computer program is executed by processor and obtain micro- expression
Cardon group expression corresponding with micro- expression cardon group determines result；The variation rail of face characteristic is extracted from micro- expression cardon group
Mark；Variation track and expression are determined that result establishes default mapping relations.
In one embodiment, the identification target realized when computer program is executed by processor replies the answer in video
After keyword, further includes: when identifying numeric item corresponding with keyword is replied, then obtain voice corresponding with numeric item
And it exports；When receiving voice corresponding confirmation instruction, saves and reply keyword and numeric item corresponding with keyword is replied.
In one embodiment, that realizes when computer program is executed by processor answers according to replying micro- expression and obtain target
After the corresponding probability of cheating of diplopia frequency, further includes: when probability of cheating is less than or equal to preset value, obtain the people replied in video
Face image；By facial image storage corresponding with probability of cheating.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
Above embodiments only express the several embodiments of the application, and the description thereof is more specific and detailed, but can not
Therefore it is construed as limiting the scope of the patent.It should be pointed out that for those of ordinary skill in the art,
Under the premise of not departing from the application design, various modifications and improvements can be made, these belong to the protection scope of the application.
Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of method for prewarning risk, which comprises
Default problem is received, and acquires target answer video corresponding with the default problem；
It identifies that the target replies the answer keyword in video, and the target is replied by video by the answer keyword
Segmentation；
Default mapping relations are obtained, are obtained according to the target answer video after the default mapping relations identification segmentation described
The corresponding micro- expression of answer of keyword is replied, and the target is obtained according to the micro- expression of answer and replies the corresponding fraud of video
Probability；
When the probability of cheating is greater than preset value, Risk-warning signal is exported.
2. the method according to claim 1, wherein acquisition target answer corresponding with the default problem
Video, comprising:
Acquisition replies video, and first of the acquisition according to the default problem detection with the default problem corresponding first
Replying video whether there is error message；
When detecting the error message, the first answer video is stored in predeterminated position；
Instruction is rerecorded in reception, and rerecords instruction acquisition facial image according to described；
The facial image corresponding first, which is searched, in the predeterminated position replies video；
Acquisition replies video with the default problem corresponding second；
Spliced the first answer video and the second answer video to obtain the target answer video.
3. the method according to claim 1, wherein it is described according to it is described reply micro- expression and obtain the target answer
The corresponding probability of cheating of diplopia frequency, comprising:
Obtain the corresponding micro- expression of standard of the answer keyword；
Calculate the difference between the micro- expression of the answer and the micro- expression of the standard；
The target, which is calculated, according to the difference replies the corresponding probability of cheating of video.
4. the method according to claim 1, wherein the method also includes:
It obtains micro- expression cardon group expression corresponding with the micro- expression cardon group and determines result；
The variation track of face characteristic is extracted from micro- expression cardon group；
The variation track and the expression are determined that result establishes the default mapping relations.
5. the method according to claim 1, which is characterized in that the identification target replies video
In answer keyword after, further includes:
When identifying numeric item corresponding with the answer keyword, then corresponding with numeric item voice and defeated is obtained
Out；
When receiving the voice corresponding confirmation instruction, the answer keyword and corresponding with the answer keyword is saved
Numeric item.
6. the method according to claim 1, which is characterized in that described to be obtained according to the micro- expression of answer
After replying the corresponding probability of cheating of video to the target, further includes:
When the probability of cheating is less than or equal to preset value, the facial image replied in video is obtained；
By facial image storage corresponding with the probability of cheating.
7. a kind of Risk-warning device, which is characterized in that described device includes:
Video acquisition module for receiving default problem, and acquires target answer video corresponding with the default problem；
Video segmentation module, the target replies the answer keyword in video for identification, and passes through the answer keyword
The target is replied into video segmentation；
Micro- Expression analysis module, for obtaining default mapping relations, according to after the default mapping relations identification segmentation
Target replies video and obtains the corresponding micro- expression of answer of the answer keyword, and obtains the mesh according to the micro- expression of answer
Mark replies the corresponding probability of cheating of video；
Risk judgment module, for exporting Risk-warning signal when the probability of cheating is greater than preset value.
8. device according to claim 7, which is characterized in that micro- Expression analysis module includes:
First acquisition unit replies video with the default problem corresponding first for acquiring, and according to the default problem
It detects the first of the acquisition and replies video with the presence or absence of error message；
Erroneous memory cell, for when detecting the error message, the first answer video to be stored in predeterminated position；
Start unit is rerecorded, rerecords instruction for receiving, and rerecord instruction acquisition facial image according to described；
Video matching unit replies video for searching the facial image corresponding first in the predeterminated position；
Second acquisition unit replies video with the default problem corresponding second for acquiring；
Video-splicing unit, for being spliced the first answer video and the second answer video to obtain the target
Reply video.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 6 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 6 is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811546615.9A CN109697666A (en) | 2018-12-18 | 2018-12-18 | Method for prewarning risk, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811546615.9A CN109697666A (en) | 2018-12-18 | 2018-12-18 | Method for prewarning risk, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109697666A true CN109697666A (en) | 2019-04-30 |
Family
ID=66232678
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811546615.9A Pending CN109697666A (en) | 2018-12-18 | 2018-12-18 | Method for prewarning risk, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109697666A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110223158A (en) * | 2019-05-21 | 2019-09-10 | 平安银行股份有限公司 | A kind of recognition methods of risk subscribers, device, storage medium and server |
| CN110321789A (en) * | 2019-05-21 | 2019-10-11 | 平安普惠企业管理有限公司 | Method and relevant device based on living things feature recognition interview fraud |
| CN110458018A (en) * | 2019-07-05 | 2019-11-15 | 深圳壹账通智能科技有限公司 | A kind of test method, device and computer readable storage medium |
| CN112232827A (en) * | 2020-10-29 | 2021-01-15 | 支付宝(杭州)信息技术有限公司 | Fraud identification method and device and electronic equipment |
| CN112541411A (en) * | 2020-11-30 | 2021-03-23 | 中国工商银行股份有限公司 | Online video anti-fraud identification method and device |
| CN113221712A (en) * | 2021-05-06 | 2021-08-06 | 新疆爱华盈通信息技术有限公司 | Method, device and equipment for detecting risks by recognizing gestures of people |
| CN113780993A (en) * | 2021-09-09 | 2021-12-10 | 平安科技（深圳）有限公司 | Data processing method, device, equipment and readable storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106792121A (en) * | 2017-02-09 | 2017-05-31 | 广东小天才科技有限公司 | A kind of about class method based on teacher, system and user equipment |
| WO2017108850A1 (en) * | 2015-12-21 | 2017-06-29 | Koninklijke Philips N.V. | System and method for effectuating presentation of content based on complexity of content segments therein |
| CN106951856A (en) * | 2017-03-16 | 2017-07-14 | 腾讯科技（深圳）有限公司 | Bag extracting method of expressing one's feelings and device |
| US20170308909A1 (en) * | 2016-04-20 | 2017-10-26 | OA Labs LLC | Systems and methods for sensor data analysis through machine learning |
| CN107704834A (en) * | 2017-10-13 | 2018-02-16 | 上海壹账通金融科技有限公司 | Householder method, device and storage medium are examined in micro- expression face |
| CN108717663A (en) * | 2018-05-18 | 2018-10-30 | 深圳壹账通智能科技有限公司 | Face label fraud judgment method, device, equipment and medium based on micro- expression |
-
2018
- 2018-12-18 CN CN201811546615.9A patent/CN109697666A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017108850A1 (en) * | 2015-12-21 | 2017-06-29 | Koninklijke Philips N.V. | System and method for effectuating presentation of content based on complexity of content segments therein |
| US20170308909A1 (en) * | 2016-04-20 | 2017-10-26 | OA Labs LLC | Systems and methods for sensor data analysis through machine learning |
| CN106792121A (en) * | 2017-02-09 | 2017-05-31 | 广东小天才科技有限公司 | A kind of about class method based on teacher, system and user equipment |
| CN106951856A (en) * | 2017-03-16 | 2017-07-14 | 腾讯科技（深圳）有限公司 | Bag extracting method of expressing one's feelings and device |
| CN107704834A (en) * | 2017-10-13 | 2018-02-16 | 上海壹账通金融科技有限公司 | Householder method, device and storage medium are examined in micro- expression face |
| CN108717663A (en) * | 2018-05-18 | 2018-10-30 | 深圳壹账通智能科技有限公司 | Face label fraud judgment method, device, equipment and medium based on micro- expression |
Non-Patent Citations (1)
| Title |
|---|
| 彭欣;: "基于视频信息分割分类索引方法的初步研究", 新闻世界, no. 12, 31 December 2013 (2013-12-31) * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110223158A (en) * | 2019-05-21 | 2019-09-10 | 平安银行股份有限公司 | A kind of recognition methods of risk subscribers, device, storage medium and server |
| CN110321789A (en) * | 2019-05-21 | 2019-10-11 | 平安普惠企业管理有限公司 | Method and relevant device based on living things feature recognition interview fraud |
| CN110223158B (en) * | 2019-05-21 | 2023-08-18 | 平安银行股份有限公司 | Risk user identification method and device, storage medium and server |
| CN110458018A (en) * | 2019-07-05 | 2019-11-15 | 深圳壹账通智能科技有限公司 | A kind of test method, device and computer readable storage medium |
| CN112232827A (en) * | 2020-10-29 | 2021-01-15 | 支付宝(杭州)信息技术有限公司 | Fraud identification method and device and electronic equipment |
| CN112541411A (en) * | 2020-11-30 | 2021-03-23 | 中国工商银行股份有限公司 | Online video anti-fraud identification method and device |
| CN113221712A (en) * | 2021-05-06 | 2021-08-06 | 新疆爱华盈通信息技术有限公司 | Method, device and equipment for detecting risks by recognizing gestures of people |
| CN113780993A (en) * | 2021-09-09 | 2021-12-10 | 平安科技（深圳）有限公司 | Data processing method, device, equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109697666A (en) | Method for prewarning risk, device, computer equipment and storage medium | |
| CN109729383A (en) | Double record video quality detection methods, device, computer equipment and storage medium | |
| CN110020009B (en) | Online question and answer method, device and system | |
| CN110619568A (en) | Risk assessment report generation method, device, equipment and storage medium | |
| CN109767787B (en) | Emotion recognition method, device and readable storage medium | |
| CN110378228A (en) | Video data handling procedure, device, computer equipment and storage medium are examined in face | |
| CN109902285B (en) | Corpus classification method, corpus classification device, computer equipment and storage medium | |
| CN112468659B (en) | Quality evaluation method, device, equipment and storage medium applied to telephone customer service | |
| CN115828112B (en) | Fault event response method and device, electronic equipment and storage medium | |
| CN111192153B (en) | Crowd relation network construction method, device, computer equipment and storage medium | |
| CN109816141A (en) | Product data prediction technique, device, computer equipment based on data analysis | |
| CN109766772A (en) | Risk control method, device, computer equipment and storage medium | |
| CN113568934B (en) | Data query method and device, electronic equipment and storage medium | |
| CN115034886A (en) | Default risk prediction method and device | |
| CN114358014A (en) | Work order intelligent diagnosis method, device, equipment and medium based on natural language | |
| CN112818868A (en) | Behavior sequence characteristic data-based violation user identification method and device | |
| CN112330442A (en) | Modeling method and device based on ultra-long behavior sequence, terminal and storage medium | |
| CN115982388A (en) | Case quality control map establishing method, case document quality testing method, case quality control map establishing equipment and storage medium | |
| CN113132523B (en) | Call detection model training method and call detection method | |
| CN112084408B (en) | List data screening method, device, computer equipment and storage medium | |
| CN114625960A (en) | On-line evaluation method and device, electronic equipment and storage medium | |
| CN113255361B (en) | Automatic voice content detection method, device, equipment and storage medium | |
| CN117556225B (en) | Pedestrian credit data risk management system | |
| CN114866818B (en) | Video recommendation method, device, computer equipment and storage medium | |
| CN117217807B (en) | Bad asset estimation method based on multi-mode high-dimensional characteristics |
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 |