CN109766772A - Risk control method, device, computer equipment and storage medium - Google Patents
Risk control method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109766772A CN109766772A CN201811549381.3A CN201811549381A CN109766772A CN 109766772 A CN109766772 A CN 109766772A CN 201811549381 A CN201811549381 A CN 201811549381A CN 109766772 A CN109766772 A CN 109766772A
- Authority
- CN
- China
- Prior art keywords
- air control
- micro
- field
- expression
- result
- 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
- 238000012954 risk control Methods 0.000 title claims abstract description 67
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000012549 training Methods 0.000 claims abstract description 25
- 230000001360 synchronised effect Effects 0.000 claims abstract description 18
- 238000004590 computer program Methods 0.000 claims description 29
- 238000012545 processing Methods 0.000 claims description 16
- 239000000284 extract Substances 0.000 claims description 5
- 230000005540 biological transmission Effects 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 10
- 238000012512 characterization method Methods 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 6
- 238000012795 verification Methods 0.000 description 6
- 238000000605 extraction Methods 0.000 description 5
- 238000010195 expression analysis Methods 0.000 description 4
- 241001269238 Data Species 0.000 description 3
- 235000013399 edible fruits Nutrition 0.000 description 3
- 230000002996 emotional effect Effects 0.000 description 3
- 238000013139 quantization Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000010923 batch production Methods 0.000 description 2
- 238000013506 data mapping Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 230000000877 morphologic effect Effects 0.000 description 2
- 238000011897 real-time detection Methods 0.000 description 2
- 208000019901 Anxiety disease Diseases 0.000 description 1
- 230000036506 anxiety Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000000700 radioactive tracer Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001755 vocal effect Effects 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
This application involves a kind of risk control method, device, computer equipment and storage mediums.The method is related to micro- Expression Recognition technology, comprising: receives the business request information that terminal is sent, issues preset business form corresponding with business request information to terminal；When detecting that business form is in editing mode, the current edit field in business form is determined；Current video data corresponding with current edit field is obtained, synchronous recording obtains when current video data is terminal editing affairs list；Current video data is inputted in preset micro- expression air control model and human face recognition model respectively, obtain micro- expression air control result and face recognition result, micro- expression air control model is obtained by the micro- expression air control data training of history；Field air control is obtained according to micro- expression air control result and face recognition result as a result, fraud degree when the field air control result characterization current edit field of terminal editor.It can be improved the effect of risk control using this method.
Description
Technical field
This application involves field of computer technology, more particularly to a kind of risk control method, device, computer equipment and
Storage medium.
Background technique
With the development of internet technology, there is various application programs, such as the application of social application, online shopping platform, it can
To provide rich and varied service, people's lives are greatly facilitated.Generally, terminal user requests in each application program
When related service services, need to fill in corresponding business form, to provide required user information, operation system again believes user
Breath carries out verification verifying, to carry out business risk control, it is ensured that service security.
However, the user information that current operation system provides terminal user, is carried out by the verification personnel of profession mostly
Verifying is verified under line, the confidence level of Information Authentication is big by verification personnel's personal influence factor, so as to cause business risk control
Effect is limited.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide a kind of risk control that can be improved risk control effect
Method, apparatus, computer equipment and storage medium.
A kind of risk control method, which comprises
The business request information that terminal is sent is received, issues preset business form corresponding with business request information to end
End；
When detecting that business form is in editing mode, the current edit field in business form is determined；
Current video data corresponding with current edit field is obtained, when current video data is terminal editing affairs list
Synchronous recording obtains；
Current video data is inputted in preset micro- expression air control model and human face recognition model respectively, obtains micro- expression
Air control result and face recognition result, micro- expression air control model are obtained by the micro- expression air control data training of history；
Field air control is obtained according to micro- expression air control result and face recognition result as a result, field air control result characterizes terminal
Edit fraud degree when current edit field.
Issuing preset business form corresponding with business request information to terminal in one of the embodiments, includes:
Determine the type of service of business request information；
Preset business form corresponding with type of service is inquired from operation system；
Issuing service list is to terminal.
In one of the embodiments, after determining the current edit field in business form, further includes:
Determine the field type of current edit field；
When field type is non-key field, preset field air control condition is inquired；
When current edit field meets field air control condition, executes and obtain current video corresponding with current edit field
Data；
Otherwise, the current edit field determined in business form is returned.
In one of the embodiments, before obtaining current video data corresponding with current edit field, further includes:
Generate recording request message；
Recording request message is issued to terminal, recording request message is used to indicate terminal and is regarded in editing affairs list
Frequency is recorded；
Receive editor's video data that terminal returns；
Obtaining current video data corresponding with current edit field includes:
Current video data corresponding with current edit field is extracted from editor's video data.
Current video data is inputted to preset micro- expression air control model respectively in one of the embodiments, and face is known
In other model, obtains micro- expression air control result and face recognition result includes:
Extract micro- expressive features data and face recognition features' data respectively from current video data；
Inquire preset micro- expression air control model and human face recognition model；
Micro- expressive features data are inputted in micro- expression air control model, micro- expression air control result is obtained；
Face recognition features' data are inputted in human face recognition model, face recognition result is obtained.
In one of the embodiments, before inquiring preset micro- expression air control model, further includes:
The micro- expression air control data of history are obtained from each operation system, the micro- expression air control data of history include micro- expression data
With air control data corresponding with micro- expression data；
Micro- expressive features parameter is extracted from micro- expression data, and is established between micro- expressive features parameter and air control data
Mapping；
The micro- expressive features parameter of training and air control data, obtain micro- expression air control model.
In one of the embodiments, field air control result include field air control scoring, obtain field air control result it
Afterwards, further includes:
Inquire preset air control threshold value list corresponding with business form；
Field air control scoring is compared with corresponding air control threshold value in air control threshold value list；
According to comparison result, risk identification is added for the corresponding service fields of field air control scoring.
A kind of risk control device, described device include:
Service request receiving module issues and business request information pair for receiving the business request information of terminal transmission
Answer preset business form to terminal；
Present field determining module, for determining in business form when detecting that business form is in editing mode
Current edit field；
Field video acquiring module, for obtaining current video data corresponding with current edit field, current video number
Synchronous recording obtains when according to for terminal editing affairs list；
Field video processing module, for current video data to be inputted to preset micro- expression air control model and face respectively
In identification model, micro- expression air control result and face recognition result are obtained, micro- expression air control model is by the micro- expression air control number of history
It is obtained according to training；
Field risk control module, for obtaining field air control knot according to micro- expression air control result and face recognition result
Fruit, field air control result characterize fraud degree when the current edit field of terminal editor.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
Device performs the steps of when executing the computer program
The business request information that terminal is sent is received, issues preset business form corresponding with business request information to end
End；
When detecting that business form is in editing mode, the current edit field in business form is determined；
Current video data corresponding with current edit field is obtained, when current video data is terminal editing affairs list
Synchronous recording obtains；
Current video data is inputted in preset micro- expression air control model and human face recognition model respectively, obtains micro- expression
Air control result and face recognition result, micro- expression air control model are obtained by the micro- expression air control data training of history；
Field air control is obtained according to micro- expression air control result and face recognition result as a result, field air control result characterizes terminal
Edit fraud degree when current edit field.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
It is performed the steps of when row
The business request information that terminal is sent is received, issues preset business form corresponding with business request information to end
End；
When detecting that business form is in editing mode, the current edit field in business form is determined；
Current video data corresponding with current edit field is obtained, when current video data is terminal editing affairs list
Synchronous recording obtains；
Current video data is inputted in preset micro- expression air control model and human face recognition model respectively, obtains micro- expression
Air control result and face recognition result, micro- expression air control model are obtained by the micro- expression air control data training of history；
Field air control is obtained according to micro- expression air control result and face recognition result as a result, field air control result characterizes terminal
Edit fraud degree when current edit field.
Above-mentioned risk control method, device, computer equipment and storage medium, will be corresponding with received business request information
Business form be issued to terminal, and when obtaining current edit field of the terminal in editing affairs list synchronous recording it is current
Current video data is inputted in preset micro- expression air control model and human face recognition model, obtains micro- expression wind by video data
Result and face recognition result are controlled, and according to micro- expression air control result and face recognition result obtains field air control as a result, field
Air control result characterizes fraud degree when the current edit field of terminal editor, can be used for risk control.During risk control,
Risk control is carried out by the video data that synchronous recording when service fields of the terminal in editing affairs list obtains, is not needed
Professional verification personnel carry out information and verify verifying, avoid human factor influence, effectively increase the effect of risk control.
Detailed description of the invention
Fig. 1 is the application scenario diagram of one embodiment risk control method；
Fig. 2 is the flow diagram of one embodiment risk control method；
Fig. 3 is the flow diagram that editor's video data is recorded in one embodiment；
Fig. 4 is the flow diagram of another embodiment risk control method；
Fig. 5 is the structural block diagram of one embodiment risk control device；
Fig. 6 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.
Risk control method provided by the present application can be applied in application environment as shown in Figure 1.Wherein, terminal is set
Standby 102 are communicated with server 104 by network by network.Terminal device 102 sends service request to server 104 and disappears
Breath, business form corresponding with the business request information is issued to terminal device 102 by server 104, and obtains terminal device
The current video data of synchronous recording, current video data is inputted when 102 current edit field in editing affairs list
In preset micro- expression air control model and human face recognition model, micro- expression air control result and face recognition result are obtained, and according to
Micro- expression air control result and face recognition result obtain field air control as a result, field air control result characterization terminal editor works as pre-editing
Fraud degree when field, can be used for risk control.Wherein, terminal device 102 can be, but not limited to be various personal computers,
Laptop, smart phone, tablet computer and portable wearable device, server 104 can with independent server or
Person is the server cluster of multiple server compositions to realize.
In one embodiment, as shown in Fig. 2, providing a kind of risk control method, it is applied in Fig. 1 in this way
It is illustrated for server 104, comprising the following steps:
Step S201: the business request information that terminal is sent is received, preset business corresponding with business request information is issued
List is to terminal.
Service-user sends business request information by terminal to server 104, to request related service service.Server
After 104 receive business request information, corresponding business service is determined, and obtain preset traffic table corresponding with the business service
It is single, user information needed for which is used for capturing service system, such as name, identification card number, region, income, mobile phone
The user informations such as number and academic information.For the different business service that different business systems provide, difference can be correspondingly arranged on
Business form.It include the various users that risk control needs in business form for example, borrowing financial service for financial industry
Information, such as identity information, family information, economic information, job information, academic information and reference information.It obtains asking with business
After seeking the corresponding business form of message, it is issued to terminal, editor is carried out by terminal and is filled in, and will fill in edited business
List is back to server 104, and server 104 can therefrom extract to obtain various user informations.
Step S203: when detecting that business form is in editing mode, the current edit field in business form is determined.
After business form is issued to terminal, whether periodicity or real-time detection business form trigger editor, in business
When list triggering editor, show that the service-user of terminal carries out editor to business form and fills in operation.In the present embodiment, detecting
When being in editing mode to business form, further determine that the current edit field in the business form, current edit field are
In the business form, service fields that the service-user of terminal is being edited.Generally, there is various businesses word in business form
Section needs the service-user of terminal to carry out editor and fills in, and when service fields in editing affairs list, the service fields meeting
It is activated and enters field editing state, and have cursor flashing, to prompt editor position.In specific implementation, detection can be passed through
The position of cursor flashing, so that it is determined that the current edit field in business form.
Step S205: obtaining current video data corresponding with current edit field, and current video data is terminal editor
Synchronous recording obtains when business form.
After determining the current edit field in business form, current video data corresponding with current edit field is obtained,
The current video data by terminal editing affairs list synchronous recording obtain.In the present embodiment, used in the business of terminal
When the editing affairs list of family, real-time perfoming video record specifically can carry out video record by dedicated video camera, can also lead to
It crosses the included front camera of terminal and carries out video record, obtain editor's recorded video.From editor's recorded video, Ke Yiti
Current video data of the service-user of terminal when editing current edit field is taken, current video data has recorded service-user
The morphological datas such as expression, expression, movement when editor fills in the service fields.By the morphological data, micro- table can be carried out
Mutual affection analysis, recognition of face processing etc. realize business risk control to carry out anti-fraud judgement and authentication.
Step S207: current video data being inputted respectively in preset micro- expression air control model and human face recognition model,
Micro- expression air control result and face recognition result are obtained, micro- expression air control model is obtained by the micro- expression air control data training of history.
After obtaining current video data corresponding with current edit field, it is inputted to preset micro- expression air control mould respectively
In type and human face recognition model, micro- expression air control result and face recognition result are obtained.Wherein, micro- expression air control model is by history
Micro- expression air control data training obtains；Human face recognition model can be obtained by the training of various human face datas.
Specifically, micro- expression air control model can identify in current video data, micro- expression of service-user, such as glad,
Fear, indignation, detest, surprised and contempt etc., and micro- expression of service-user being analyzed, obtain service-user editor should
The quantization degree of each emotional state when current edit field, such as positive, tranquil and anxiety, it is finally comprehensive to export micro- expression air control
As a result.Micro- expression air control result can be used for instead cheating reference, to judge whether service-user has fraud, to realize wind
Danger control.In addition, human face recognition model can carry out recognition of face to the service-user in current video data, to use business
The identity at family is verified, and is judged whether to operate in person, is further ensured that risk control effect.
Step S209: field air control is obtained according to micro- expression air control result and face recognition result as a result, field air control knot
Fruit characterizes fraud degree when the current edit field of terminal editor.
After obtaining micro- expression air control result and face recognition result, both can directly integrate obtain field air control as a result,
It can also be weighted processing according to actual business air control demand and obtain field air control as a result, field air control result characterizes end
Fraud degree when current edit field is edited at end, can carry out business risk control by each field air control result in business form
System.Specifically, available preset air control weight coefficient, air control weight coefficient are set according to practical business air control demand
It sets, for being weighted processing to micro- expression air control result and face recognition result, to embody micro- Expression analysis and recognition of face
Significance level.
After obtaining air control weight coefficient, in conjunction with micro- expression air control result and face recognition result, field air control is calculated
As a result, field air control result reflects fraud degree of the service-user of terminal when editing current edit field, it can be to business
The risk control of user refers to.For example, if can be scored according to the field air control when field air control result is that field air control is scored
Numerical values recited carry out risk judgment, if field air control score it is higher, then corresponding risk is higher, shows that service-user is being edited
There may be fraud when deserving pre-editing field, the risk control to business is realized with this.Further, it is also possible to integrated service
The corresponding field air control result of each service fields in list obtains list air control as a result, such as will be to business word each in business form
The field air control result of section is counted, to realize the risk control in business form level.
In above-mentioned risk control method, business form corresponding with received business request information is issued to terminal, and
The current video data of synchronous recording when obtaining current edit field of the terminal in editing affairs list, by current video data
It inputs in preset micro- expression air control model and human face recognition model, obtains micro- expression air control result and face recognition result, and
Field air control is obtained according to micro- expression air control result and face recognition result as a result, field air control result characterization terminal editor is current
Fraud degree when edit field, can be used for risk control.During risk control, through terminal in editing affairs list
Service fields when the obtained video data of synchronous recording carry out risk control, do not need professional verification personnel and carry out information verification
Verifying avoids human factor influence, effectively increases the effect of risk control.
In one embodiment, it issues preset business form corresponding with business request information to terminal and comprises determining that industry
The type of service of business request message；Preset business form corresponding with type of service is inquired from operation system；Issuing service table
Singly to terminal.
In the present embodiment, the business request information that terminal is sent is for requesting corresponding business service, and different business
Service, operation system need to acquire different user informations, i.e., operation system is by different business list to obtain required use
Family information.
Specifically, after receiving the business request information that terminal is sent, the type of service of business request information is determined, and from
Preset business form corresponding with type of service is inquired in operation system.In specific application, it can be inquired from operation system
Preset business form database, and according to the type of service of business request information, the acquisition pair from the business form database
The business form answered.Business form is for acquiring user information comprising each service fields according to the practical need of type of service
It asks and is configured.For example, may include identity information, contact method, family information, job information, income information and reference letter
Breath etc..After obtaining business form corresponding with business request information, it is issued to terminal, editor is carried out by terminal and is filled in, and will
Business form after filling in is back to server 104.
In one embodiment, after determining the current edit field in business form, further includes: pre-editing is worked as in determination
The field type of field；When field type is non-key field, preset field air control condition is inquired；When current edit field
When meeting field air control condition, executes and obtain current video data corresponding with current edit field；Otherwise, the business of determination is returned
Current edit field in list.
For various businesses list, the service fields quantity being related to is different according to the difference of type of service, and business
The importance of each service fields is also different in list.For the critical field in business form, such as it is closely related with business service
Service fields, it can be ensured that carry out risk control；And for the non-key field in business form, it selective can carry out
Risk control such as carries out burying a little at random, randomly selects carry out risk control, can ensure the same of risk control effect with this
When, effectively improve the treatment effeciency of risk control.
Specifically, it can further determine that after determining the current edit field in business form and deserve pre-editing field
Field type, and corresponding risk control processing is carried out according to field type.In the present embodiment, current edit field is determined
Field type, such as identity type, job category, academic type and economic type.The field class of pre-editing field is deserved in judgement
Whether type is critical field, if non-key field, inquires preset field air control condition.Wherein, field air control condition can be with
For the air control decimation rule for non-key field, such as can be to extract, randomly select by odd number of the number of service fields
Deng.After obtaining field air control condition, judge whether current edit field meets field air control condition, if satisfied, then current to this
Edit field carries out subsequent risk control processing, that is, executes and obtain current video data corresponding with current edit field.If
Current edit field is unsatisfactory for field air control condition, then does not return and determine to the progress risk control processing of pre-editing field is deserved
Current edit field in business form redefines the current edit field in editing mode.
In addition, showing the important journey for deserving pre-editing field if the field type of current edit field is critical field
Degree is high, needs to carry out risk control, then is directly entered the step of obtaining current video data corresponding with current edit field, with
Carry out subsequent risk control processing.
In one embodiment, as shown in figure 3, before obtaining current video data corresponding with current edit field,
Further include the steps that editing video data records:
Step S301: recording request message is generated.
In the present embodiment, after determining the current edit field in business form, obtains and deserve pre-editing in terminal editor
The current video data of corresponding recording when field, current video data can be extracted from editor's video data of recording
It arrives.Specifically, server 104 generates recording request message, which is used to indicate recording arrangement and carries out video record
System, recording arrangement can be the video camera of vocational window fixed setting, or the included front camera of terminal.Specific
In, the recording request message can be generated after receiving business request information, and by the recording request message and business
List is sent to terminal simultaneously.It can also generate recording request when detecting that the business form issued is in editing mode and disappear
Breath.
Step S303: recording request message is issued to terminal, recording request message is used to indicate terminal in editing affairs table
Video record is carried out when single.
Recording request message is issued to terminal, so that terminal carries out video record in editing affairs list.This implementation
In example, recording request message is issued to terminal, by terminal according to the message initiated front camera of the recording request, and in editor's industry
It is engaged in carrying out video record when list.
Step S305: editor's video data that terminal returns is received.
Terminal is recorded after obtaining editor's video data according to recording request message when collecting business form, will edit video counts
According to server 104 is back to, server 104 receives editor's video data, and therefrom extracts corresponding with current edit field
Current video data.
In the present embodiment, shape is edited in the business request information for receiving terminal transmission or detecting that business form is in
When state, generates and issue recording request message to terminal, terminal is made to carry out video record in editing affairs list, it can be real-time
The service-user of acquisition terminal corresponding shape information in editing affairs list, and utilize the shape information for risk control
System, improves the effect of risk control.
Further, obtaining current video data corresponding with current edit field includes: to mention from editor's video data
Take current video data corresponding with current edit field.
After terminal carries out video record according to recording request message, editor's video data is obtained.In determining business form
Current edit field after, current video number corresponding with current edit field can be extracted directly from editor's video data
According to.Specifically, it can be in editor's moment value when editing mode according to current edit field, inquired from editor's video data
Time shaft position corresponding with editor's moment value obtains current video number corresponding with current edit field to therefrom extract
According to.
In one embodiment, current video data is inputted to preset micro- expression air control model and recognition of face mould respectively
In type, obtains micro- expression air control result and face recognition result includes: to extract micro- expressive features respectively from current video data
Data and face recognition features' data；Inquire preset micro- expression air control model and human face recognition model；By micro- expressive features number
According to inputting in micro- expression air control model, micro- expression air control result is obtained；Face recognition features' data are inputted into human face recognition model
In, obtain face recognition result.
In the present embodiment, current video data is being inputted to preset micro- expression air control model and human face recognition model respectively
In, when carrying out micro- Expression analysis and recognition of face analysis respectively, current video data can be pre-processed, be removed useless superfluous
Remaining information carries out corresponding micro- Expression analysis and recognition of face point by micro- expressive features data and face recognition features' data
Analysis.
Specifically, micro- expressive features data and face recognition features' data are extracted respectively from current video data.Wherein,
Micro- expressive features data are related to micro- expression of service-user, are used for micro- Expression analysis；Face recognition features' data and business are used
The facial characteristics at family is related, analyzes for recognition of face.Preset micro- expression air control model and human face recognition model are inquired again, it is micro-
Expression air control model is obtained by the micro- expression air control data training of history；Human face recognition model can be trained by various human face datas
It arrives.
Micro- expressive features data are inputted in micro- expression air control model, obtain micro- expression air control as a result, micro- expression air control knot
Fruit reflects the intensity of the service-user of the terminal various emotional states when editor deserves pre-editing field, such as actively, it is tranquil and
Tensity.Generally, it is expressed compared to truth, in fraud or fraud, the various emotional states of service-user are had
Institute is different, and whether have fraud, to realize risk control if can analyze service-user according to micro- expression air control result.Separately
On the one hand, face recognition features' data are inputted in human face recognition model, obtains face recognition result, face recognition result reflection
The authentication of service-user is as a result, can be further improved risk control effect in conjunction with the face recognition result.
In one embodiment, before inquiring preset micro- expression air control model, further includes: obtained from each operation system
The micro- expression air control data of history are taken, the micro- expression air control data of history include micro- expression data and air control corresponding with micro- expression data
Data；Micro- expressive features parameter is extracted from micro- expression data, and establishes reflecting between micro- expressive features parameter and air control data
It penetrates；The micro- expressive features parameter of training and air control data, obtain micro- expression air control model.
Micro- expression air control model can be based on artificial neural network algorithm, be obtained by the training micro- expression air control data of history
It arrives.Specifically, the micro- expression air control data of history are first obtained from each operation system, the micro- expression air control data of the history include micro- table
Feelings data and air control data corresponding with micro- expression data.For example, micro- expression data can be each service-user in editing affairs
Shape information in list when each service fields, air control data can be the confidence level of each service fields after subsequent authentication.From
Micro- expressive features parameter is extracted in micro- expression data, to pre-process to micro- expression data, removes redundancy garbage, and build
Stand the mapping between micro- expressive features parameter and air control data.Each micro- expressive features parameter and air control data are established mapping to close
System, obtains micro- expression air control mould by the micro- expressive features parameter of training and air control data collectively as model training data set
Type, micro- expression air control model can export corresponding micro- expression air control according to the current video data of input as a result, as exported
Micro- expression air control scoring.
In one embodiment, field air control result includes field air control scoring, after obtaining field air control result, also
It include: inquiry preset air control threshold value list corresponding with business form；Field air control scoring is corresponding with air control threshold value list
Air control threshold value be compared；According to comparison result, risk identification is added for the corresponding service fields of field air control scoring.
In the present embodiment, it such as can be the five-grade marking system, percentage that field air control result, which includes the field air control scoring that quantization shows,
The numerical value of system.After obtaining field air control result, corresponding air control mark can be added for each service fields, is examined so as to subsequent
The reference of batch process.
Specifically, preset air control threshold value list corresponding with business form is inquired.Wherein, air control threshold value list includes business
The air control threshold value of each service fields in list then shows the service fields when field air control is scored above the air control threshold value
Risk is high, with a low credibility.In specific application, air control threshold value can also be arranged with stepping, be such as set as high, neutralize low third gear.
After obtaining air control threshold value list, the field air control scoring air control threshold value corresponding with the service fields of each service fields is compared
Compared with, and be that service fields add corresponding risk identification according to comparison result.Comparison result and risk identification can be according to reality
Business demand carries out personal settings.For example, for the service fields of high risk, high risk mark can be added, and by the industry
Business field mark is red；For the service fields of risk, risk mark is added, and service fields are subjected to mark orange；For low wind
The service fields of danger, addition low-risk mark.
In one embodiment, as shown in figure 4, providing a kind of risk control method, comprising:
Step S401: the business request information that terminal is sent is received；
Step S402: the type of service of business request information is determined；
Step S403: preset business form corresponding with type of service is inquired from operation system；
Step S404: issuing service list to terminal.
The business request information that terminal is sent is for requesting corresponding business service, and different business services, business system
System needs to acquire different user informations, i.e., operation system is by different business list to obtain required user information.Service
Device 104 determines the type of service of business request information, and from operation system after receiving the business request information that terminal is sent
Inquire preset business form corresponding with type of service.After obtaining business form corresponding with business request information, it is issued to
Terminal carries out editor by terminal and fills in, and the business form after will fill in is back to server 104.
Step S405: when detecting that business form is in editing mode, the current edit field in business form is determined；
Step S406: the field type of current edit field is determined；
Step S407: judging whether field type is critical field, if so, executing step S410；Otherwise, step is executed
S408；
Step S408: preset field air control condition is inquired；
Step S409: judging whether current edit field meets field air control condition, if so, executing step step S410；
Otherwise, step S405 is executed；
Step S410: current video data corresponding with current edit field is obtained.
After business form is issued to terminal, whether real-time detection business form triggers editor, triggers in business form
When editor, show that the service-user of terminal carries out editor to business form and fills in operation.In the present embodiment, traffic table is being detected
When list is in editing mode, the current edit field in the business form is further determined that.
For various businesses list, the service fields quantity being related to is different according to the difference of type of service, and business
The importance of each service fields is also different in list.For the critical field in business form, such as it is closely related with business service
Service fields, it can be ensured that carry out risk control；And for the non-key field in business form, it selective can carry out
Risk control such as carries out burying a little at random, randomly selects carry out risk control, can ensure the same of risk control effect with this
When, effectively improve the treatment effeciency of risk control.
Step S411: current video data being inputted respectively in preset micro- expression air control model and human face recognition model,
Obtain micro- expression air control result and face recognition result；
Step S412: according to micro- expression air control result, face recognition result and preset air control weight coefficient, field is obtained
Air control result.
The acquisition step of micro- expression air control result and face recognition result include: extracted respectively from current video data it is micro-
Expressive features data and face recognition features' data；Inquire preset micro- expression air control model and human face recognition model；By micro- table
Feelings characteristic inputs in micro- expression air control model, obtains micro- expression air control result；Face recognition features' data are inputted into face
In identification model, face recognition result is obtained.
In the present embodiment, after obtaining micro- expression air control result and face recognition result, according to actual business air control demand
It is weighted processing and obtains field air control result.The service-user that field air control result reflects terminal is editing current edit word
Fraud degree when section, can refer to the risk control of service-user.
Step S413: field air control result includes field air control scoring, inquires preset air control threshold corresponding with business form
It is worth list；
Step S414: field air control scoring is compared with corresponding air control threshold value in air control threshold value list；
Step S415: according to comparison result, risk identification is added for the corresponding service fields of field air control scoring.
In the present embodiment, it such as can be the five-grade marking system, percentage that field air control result, which includes the field air control scoring that quantization shows,
The numerical value of system.After obtaining field air control result, corresponding air control mark can be added for each service fields, is examined so as to subsequent
The reference of batch process.
It should be understood that although each step in the flow chart of Fig. 2-4 is successively shown according to the instruction of arrow,
These steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, these steps can execute in other order.Moreover, at least one in Fig. 2-4
Part steps may include that perhaps these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, the execution sequence in these sub-steps or stage is also not necessarily successively
It carries out, but can be at least part of the sub-step or stage of other steps or other steps in turn or alternately
It executes.
In one embodiment, as shown in figure 5, providing a kind of risk control device, comprising: service request receiving module
501, present field determining module 503, field video acquiring module 505, field video processing module 507 and field risk control
Module 509, in which:
Service request receiving module 501 issues and business request information for receiving the business request information of terminal transmission
Preset business form is corresponded to terminal；
Present field determining module 503, for determining in business form when detecting that business form is in editing mode
Current edit field；
Field video acquiring module 505, for obtaining current video data corresponding with current edit field, current video
Synchronous recording obtains when data are terminal editing affairs list；
Field video processing module 507, for current video data is inputted respectively preset micro- expression air control model and
In human face recognition model, micro- expression air control result and face recognition result are obtained, micro- expression air control model is by the micro- expression wind of history
Monitor database is got；
Field risk control module 509, for obtaining field air control according to micro- expression air control result and face recognition result
As a result, fraud degree when field air control result characterization current edit field of terminal editor.
In one embodiment, service request receiving module 501 includes type of service determination unit, business form cargo tracer
Member and business form issuance unit, in which: type of service determination unit, for determining the type of service of business request information；Industry
Business list query unit, for inquiring preset business form corresponding with type of service from operation system；Business form issues
Unit, for issuing service list to terminal.
It in one embodiment, further include that field type determining module, air control condition query module, video data jump mould
Block and field determine jump module, in which: field type determining module, for determining the field type of current edit field；Wind
Condition query module is controlled, for inquiring preset field air control condition when field type is non-key field；Video data is jumped
Revolving die block, it is corresponding with current edit field current for when current edit field meets field air control condition, executing acquisition
Video data；Field determines jump module, for otherwise, returning to the current edit field determined in business form.
It in one embodiment, further include that recording request generation module, recording request issue module and editor's video reception
Module, field video acquiring module 505 include field video extraction unit, in which: recording request generation module, for generating record
Request message processed；Recording request issues module, and for issuing recording request message to terminal, recording request message is used to indicate end
End carries out video record in editing affairs list；Video reception module is edited, for receiving editor's video counts of terminal return
According to；Field video extraction unit, for extracting current video data corresponding with current edit field from editor's video data.
In one embodiment, field video processing module 507 include characteristic extraction unit, pattern query unit,
Micro- expression air control unit and face recognition module, in which: characteristic extraction unit, for being mentioned respectively from current video data
Take micro- expressive features data and face recognition features' data；Pattern query unit, for inquiring preset micro- expression air control model
And human face recognition model；Micro- expression air control unit obtains micro- for inputting micro- expressive features data in micro- expression air control model
Expression air control result；Face recognition module obtains face knowledge for inputting face recognition features' data in human face recognition model
Other result.
It in one embodiment, further include that historical data obtains module, training set obtains module and model training module,
In: historical data obtains module, for obtaining the micro- expression air control data of history, the micro- expression air control number of history from each operation system
According to including micro- expression data and air control data corresponding with micro- expression data；Training set obtains module, is used for from micro- expression data
It is middle to extract micro- expressive features parameter, and establish the mapping between micro- expressive features parameter and air control data；Model training module is used
In the micro- expressive features parameter of training and air control data, micro- expression air control model is obtained.
In one embodiment, field air control result includes field air control scoring, further includes air control list enquiry module, wind
Control comparison module and risk identification processing module, in which: air control list enquiry module, it is corresponding with business form default for inquiring
Air control threshold value list；Air control comparison module is used for field air control scoring and corresponding air control threshold value in air control threshold value list
It is compared；Risk identification processing module, for adding wind for the corresponding service fields of field air control scoring according to comparison result
Danger mark.
Specific about risk control device limits the restriction that may refer to above for risk control method, herein not
It repeats again.Modules in above-mentioned risk control 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 server, internal junction
Composition can be as shown in Figure 6.The computer equipment includes processor, memory and the network interface connected by system bus.
Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory of the computer equipment includes non-easy
The property lost storage medium, built-in storage.The non-volatile memory medium is stored with operating system and computer program.The built-in storage
Operation for operating system and computer program in non-volatile memory medium provides environment.The network of the computer equipment connects
Mouth with external terminal by network connection for being communicated.To realize a kind of risk control when the computer program is executed by processor
Method processed.
It will be understood by those skilled in the art that structure shown in Fig. 6, 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, the processor perform the steps of when executing computer program
The business request information that terminal is sent is received, issues preset business form corresponding with business request information to end
End；
When detecting that business form is in editing mode, the current edit field in business form is determined；
Current video data corresponding with current edit field is obtained, when current video data is terminal editing affairs list
Synchronous recording obtains；
Current video data is inputted in preset micro- expression air control model and human face recognition model respectively, obtains micro- expression
Air control result and face recognition result, micro- expression air control model are obtained by the micro- expression air control data training of history；
Field air control is obtained according to micro- expression air control result and face recognition result as a result, field air control result characterizes terminal
Edit fraud degree when current edit field.
In one embodiment, determining business request information is also performed the steps of when processor executes computer program
Type of service；Preset business form corresponding with type of service is inquired from operation system；Issuing service list is to terminal.
In one embodiment, it is also performed the steps of when processor executes computer program and determines current edit field
Field type；When field type is non-key field, preset field air control condition is inquired；When current edit field meets
When field air control condition, executes and obtain current video data corresponding with current edit field；Otherwise, it returns and determines business form
In current edit field.
In one embodiment, it is also performed the steps of when processor executes computer program and generates recording request message；
Recording request message is issued to terminal, recording request message is used to indicate terminal and carries out video record in editing affairs list；
Receive editor's video data that terminal returns；Current video number corresponding with current edit field is extracted from editor's video data
According to.
In one embodiment, it is also performed the steps of from current video data when processor executes computer program
Micro- expressive features data and face recognition features' data are extracted respectively；Inquire preset micro- expression air control model and recognition of face mould
Type；Micro- expressive features data are inputted in micro- expression air control model, micro- expression air control result is obtained；By face recognition features' data
It inputs in human face recognition model, obtains face recognition result.
In one embodiment, it also performs the steps of when processor executes computer program and is obtained from each operation system
The micro- expression air control data of history are taken, the micro- expression air control data of history include micro- expression data and air control corresponding with micro- expression data
Data；Micro- expressive features parameter is extracted from micro- expression data, and establishes reflecting between micro- expressive features parameter and air control data
It penetrates；The micro- expressive features parameter of training and air control data, obtain micro- expression air control model.
In one embodiment, field air control result includes field air control scoring, and processor is gone back when executing computer program
Perform the steps of inquiry preset air control threshold value list corresponding with business form；By field air control scoring and air control threshold value table
Corresponding air control threshold value is compared in list；According to comparison result, risk is added for the corresponding service fields of field air control scoring
Mark.
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 when being executed by processor
The business request information that terminal is sent is received, issues preset business form corresponding with business request information to end
End；
When detecting that business form is in editing mode, the current edit field in business form is determined；
Current video data corresponding with current edit field is obtained, when current video data is terminal editing affairs list
Synchronous recording obtains；
Current video data is inputted in preset micro- expression air control model and human face recognition model respectively, obtains micro- expression
Air control result and face recognition result, micro- expression air control model are obtained by the micro- expression air control data training of history；
Field air control is obtained according to micro- expression air control result and face recognition result as a result, field air control result characterizes terminal
Edit fraud degree when current edit field.
In one embodiment, determining service request is also performed the steps of when computer program is executed by processor to disappear
The type of service of breath；Preset business form corresponding with type of service is inquired from operation system；Issuing service list is to terminal.
In one embodiment, it is also performed the steps of when computer program is executed by processor and determines current edit word
The field type of section；When field type is non-key field, preset field air control condition is inquired；When current edit field is full
When sufficient field air control condition, executes and obtain current video data corresponding with current edit field；Otherwise, it returns and determines traffic table
Current edit field in list.
In one embodiment, generation recording request is also performed the steps of when computer program is executed by processor to disappear
Breath；Recording request message is issued to terminal, recording request message is used to indicate terminal and carries out video record in editing affairs list
System；Receive editor's video data that terminal returns；Extraction is corresponding with current edit field from editor's video data works as forward sight
Frequency evidence.
In one embodiment, it also performs the steps of when computer program is executed by processor from current video data
It is middle to extract micro- expressive features data and face recognition features' data respectively；Inquire preset micro- expression air control model and recognition of face
Model；Micro- expressive features data are inputted in micro- expression air control model, micro- expression air control result is obtained；By face recognition features' number
According in input human face recognition model, face recognition result is obtained.
In one embodiment, it is also performed the steps of from each operation system when computer program is executed by processor
The micro- expression air control data of history are obtained, the micro- expression air control data of history include micro- expression data and wind corresponding with micro- expression data
Control data；Micro- expressive features parameter is extracted from micro- expression data, and is established between micro- expressive features parameter and air control data
Mapping；The micro- expressive features parameter of training and air control data, obtain micro- expression air control model.
In one embodiment, field air control result includes field air control scoring, when computer program is executed by processor
Also perform the steps of inquiry preset air control threshold value list corresponding with business form；By field air control scoring and air control threshold value
Corresponding air control threshold value is compared in list；According to comparison result, wind is added for the corresponding service fields of field air control scoring
Danger mark.
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.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of risk control method, which comprises
The business request information that terminal is sent is received, issues preset business form corresponding with the business request information to described
Terminal；
When detecting that the business form is in editing mode, the current edit field in the business form is determined；
Current video data corresponding with the current edit field is obtained, the current video data is the terminal editor institute
Synchronous recording obtains when stating business form；
The current video data is inputted respectively in preset micro- expression air control model and human face recognition model, micro- expression is obtained
Air control result and face recognition result, micro- expression air control model are obtained by the micro- expression air control data training of history；
Field air control is obtained according to micro- expression air control result and the face recognition result as a result, the field air control result
Characterize fraud degree when current edit field described in the terminal editor.
2. the method according to claim 1, wherein it is described issue it is corresponding with the business request information preset
Business form to the terminal includes:
Determine the type of service of the business request information；
Preset business form corresponding with the type of service is inquired from operation system；
The business form is issued to the terminal.
3. the method according to claim 1, wherein the current edit word in the determination business form
After section, further includes:
Determine the field type of the current edit field；
When the field type is non-key field, preset field air control condition is inquired；
When the current edit field meets the field air control condition, the acquisition and the current edit field pair are executed
The current video data answered；
Otherwise, the current edit field in the determination business form is returned.
4. the method according to claim 1, wherein obtaining work as corresponding with the current edit field described
Before preceding video data, further includes:
Generate recording request message；
The recording request message is issued to the terminal, the recording request message is used to indicate the terminal described in the editor
Video record is carried out when business form；
Receive editor's video data that the terminal returns；
Acquisition current video data corresponding with the current edit field includes:
Current video data corresponding with the current edit field is extracted from editor's video data.
5. the method according to claim 1, wherein it is described the current video data is inputted respectively it is preset
In micro- expression air control model and human face recognition model, obtains micro- expression air control result and face recognition result includes:
Extract micro- expressive features data and face recognition features' data respectively from the current video data；
Inquire preset micro- expression air control model and human face recognition model；
Micro- expressive features data are inputted in micro- expression air control model, micro- expression air control result is obtained；
Face recognition features' data are inputted in the human face recognition model, face recognition result is obtained.
6. according to the method described in claim 5, it is characterized in that, before the preset micro- expression air control model of the inquiry,
Further include:
The micro- expression air control data of the history are obtained from each operation system, the micro- expression air control data of history include micro- expression
Data and air control data corresponding with the micro- expression data；
Micro- expressive features parameter is extracted from micro- expression data, and establishes micro- expressive features parameter and the air control number
Mapping between；
Training micro- expressive features parameter and the air control data, obtain micro- expression air control model.
7. according to claim 1 to method described in 6 any one, which is characterized in that the field air control result includes field
Air control scoring, it is described obtain field air control result after, further includes:
Inquire preset air control threshold value list corresponding with the business form；
The field air control is scored and is compared with corresponding air control threshold value in the air control threshold value list；
According to comparison result, risk identification is added for the corresponding service fields of field air control scoring.
8. a kind of risk control device, which is characterized in that described device includes:
Service request receiving module issues and the business request information pair for receiving the business request information of terminal transmission
Answer preset business form to the terminal；
Present field determining module, for determining the business form when detecting that the business form is in editing mode
In current edit field；
Field video acquiring module, it is described to work as forward sight for obtaining current video data corresponding with the current edit field
Frequency is obtained according to synchronous recording when being business form described in the terminal editor；
Field video processing module, for the current video data to be inputted preset micro- expression air control model and face respectively
In identification model, micro- expression air control result and face recognition result are obtained, micro- expression air control model is by the micro- expression wind of history
Monitor database is got；
Field risk control module, for obtaining field air control according to micro- expression air control result and the face recognition result
As a result, the fraud degree when field air control result characterizes current edit field described in the terminal editor.
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 7 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 7 is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811549381.3A CN109766772A (en) | 2018-12-18 | 2018-12-18 | Risk control method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811549381.3A CN109766772A (en) | 2018-12-18 | 2018-12-18 | Risk control method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109766772A true CN109766772A (en) | 2019-05-17 |
Family
ID=66451506
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811549381.3A Pending CN109766772A (en) | 2018-12-18 | 2018-12-18 | Risk control method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109766772A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110909622A (en) * | 2019-10-31 | 2020-03-24 | 中国科学院深圳先进技术研究院 | Micro-expression recognition financial wind control method and system |
| CN110930155A (en) * | 2019-10-17 | 2020-03-27 | 平安科技（深圳）有限公司 | Risk management and control method and device, computer device and storage medium |
| CN111861495A (en) * | 2020-08-06 | 2020-10-30 | 中国银行股份有限公司 | Transfer processing method and device |
| CN111861240A (en) * | 2020-07-27 | 2020-10-30 | 深圳前海微众银行股份有限公司 | Suspicious user identification method, device, equipment and readable storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107016608A (en) * | 2017-03-30 | 2017-08-04 | 广东微模式软件股份有限公司 | The long-range account-opening method and system of a kind of identity-based Information Authentication |
| CN107862598A (en) * | 2017-09-30 | 2018-03-30 | 平安普惠企业管理有限公司 | Long-range the interview measures and procedures for the examination and approval, server and readable storage medium storing program for executing |
| 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 |
| CN108734570A (en) * | 2018-05-22 | 2018-11-02 | 深圳壹账通智能科技有限公司 | A kind of Risk Forecast Method, storage medium and server |
| CN108765131A (en) * | 2018-05-18 | 2018-11-06 | 深圳壹账通智能科技有限公司 | Credit authorization method, apparatus, terminal and readable storage medium storing program for executing based on micro- expression |
| CN108876133A (en) * | 2018-06-07 | 2018-11-23 | 中国平安人寿保险股份有限公司 | Risk assessment processing method, device, server and medium based on business information |
-
2018
- 2018-12-18 CN CN201811549381.3A patent/CN109766772A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107016608A (en) * | 2017-03-30 | 2017-08-04 | 广东微模式软件股份有限公司 | The long-range account-opening method and system of a kind of identity-based Information Authentication |
| CN107862598A (en) * | 2017-09-30 | 2018-03-30 | 平安普惠企业管理有限公司 | Long-range the interview measures and procedures for the examination and approval, server and readable storage medium storing program for executing |
| 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 |
| CN108765131A (en) * | 2018-05-18 | 2018-11-06 | 深圳壹账通智能科技有限公司 | Credit authorization method, apparatus, terminal and readable storage medium storing program for executing based on micro- expression |
| CN108734570A (en) * | 2018-05-22 | 2018-11-02 | 深圳壹账通智能科技有限公司 | A kind of Risk Forecast Method, storage medium and server |
| CN108876133A (en) * | 2018-06-07 | 2018-11-23 | 中国平安人寿保险股份有限公司 | Risk assessment processing method, device, server and medium based on business information |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110930155A (en) * | 2019-10-17 | 2020-03-27 | 平安科技（深圳）有限公司 | Risk management and control method and device, computer device and storage medium |
| CN110930155B (en) * | 2019-10-17 | 2023-09-08 | 平安科技（深圳）有限公司 | Risk management and control method, risk management and control device, computer device and storage medium |
| CN110909622A (en) * | 2019-10-31 | 2020-03-24 | 中国科学院深圳先进技术研究院 | Micro-expression recognition financial wind control method and system |
| CN111861240A (en) * | 2020-07-27 | 2020-10-30 | 深圳前海微众银行股份有限公司 | Suspicious user identification method, device, equipment and readable storage medium |
| CN111861495A (en) * | 2020-08-06 | 2020-10-30 | 中国银行股份有限公司 | Transfer processing method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109766772A (en) | Risk control method, device, computer equipment and storage medium | |
| CN109815803B (en) | Face examination risk control method and device, computer equipment and storage medium | |
| CN109034069B (en) | Method and apparatus for generating information | |
| CN109766755B (en) | Face recognition method and related product | |
| CN111428448B (en) | Text generation method, device, computer equipment and readable storage medium | |
| CN109509087A (en) | Intelligentized loan checking method, device, equipment and medium | |
| CN109816200A (en) | Task method for pushing, device, computer equipment and storage medium | |
| CN112329816A (en) | Data classification method and device, electronic equipment and readable storage medium | |
| CN108920640A (en) | Context acquisition methods and equipment based on interactive voice | |
| CN109815489A (en) | Collection information generating method, device, computer equipment and storage medium | |
| CN109697666A (en) | Method for prewarning risk, device, computer equipment and storage medium | |
| CN109509088A (en) | Loan checking method, device, equipment and medium based on micro- Expression Recognition | |
| CN109389028A (en) | Face identification method, device, equipment and storage medium based on motion analysis | |
| CN112241667A (en) | Image detection method, device, equipment and storage medium | |
| CN112634017A (en) | Remote card opening activation method and device, electronic equipment and computer storage medium | |
| CN110689443A (en) | Insurance data processing method and device, storage medium and server | |
| CN112287068A (en) | Artificial intelligence-based inquiry dialogue data processing method and device | |
| CN110675252A (en) | Risk assessment method and device, electronic equipment and storage medium | |
| CN113077821A (en) | Audio quality detection method and device, electronic equipment and storage medium | |
| CN110909889B (en) | Training set generation and model training method and device based on feature distribution | |
| CN109785114A (en) | Credit data methods of exhibiting, device, equipment and medium for audit of providing a loan | |
| CN112686744A (en) | Method and device for monitoring external access service, electronic equipment and storage medium | |
| CN114245204B (en) | Video surface signing method and device based on artificial intelligence, electronic equipment and medium | |
| CN110459296A (en) | Information-pushing method and Related product | |
| CN113642462A (en) | Driving behavior assessment method and device, terminal 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 |