CN108734570A - A kind of Risk Forecast Method, storage medium and server - Google Patents
A kind of Risk Forecast Method, storage medium and server Download PDFInfo
- Publication number
- CN108734570A CN108734570A CN201810496195.1A CN201810496195A CN108734570A CN 108734570 A CN108734570 A CN 108734570A CN 201810496195 A CN201810496195 A CN 201810496195A CN 108734570 A CN108734570 A CN 108734570A
- Authority
- CN
- China
- Prior art keywords
- video image
- probability
- expression
- frame
- cheating
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of Risk Forecast Method, storage medium and servers, including：Obtain video image of applicant during face is examined；Video frame in the video image is clustered, determines key frame video image；According to the determining crucial frame video image and micro- expression probability of cheating model, the probability of cheating of the corresponding micro- expression of the crucial frame video image is determined；According to the probability of cheating of the determining corresponding micro- expression of the key frame video image, risk profile is carried out to the loan repayment capacity of the applicant.The present invention is by analyzing micro- expression of applicant during face is examined, assess the probability of cheating of applicant, and risk profile is carried out to the loan repayment capacity of the applicant according to probability of cheating, objective auxiliary judgment is provided for the loan repayment capacity of forecast assessment applicant, to improve the accuracy of risk profile and the efficiency of prediction.
Description
Technical field
The present invention relates to a kind of information monitoring field more particularly to Risk Forecast Method, storage medium and servers.
Background technology
Credit applications people usually requires progress credit face when arranging bank loans and examines, and risk profile personnel are with credit applications
People, which interviews, verifies relevant information.It is usually to have credit applications people to fill in papery credit material that existing credit face, which is examined, pre- by risk
Survey personnel audit the credit material that credit applications people fills in, and by the interview with credit applications people come to credit applications people's future
The loan repayment capacity for repaying this loan is predicted, proposes risk prevention system measure.
In fact, according to the audit experience of papery credit material and risk profile personnel to being repaid in future to credit applications people
The loan repayment capacity of also this loan is predicted, is proposed risk prevention system measure, mainly the sincerity of credit applications people is relied on to fill in
And the experience of risk profile people, lack some objective auxiliary judgments, it is true to easily cause loan repayment capacity forecasting inaccuracy, to influence
It is proposed the accuracy of risk prevention system measure.
It is mainly filled in and wind by the sincerity of credit applications people in conclusion existing in existing risk profile mode
The empirical evaluation of danger prediction people, lacks some objective auxiliary judgments, easily causes loan repayment capacity and predict the not high problem of true property.
Invention content
An embodiment of the present invention provides a kind of Risk Forecast Method, storage medium and servers, to solve existing risk
Exist in prediction mode and mainly filled in and the empirical evaluation of risk profile people by the sincerity of credit applications people, is lacked
Objective auxiliary judgment, easily causes that risk profile accuracy is high, efficiency also not high problem.
The first aspect of the embodiment of the present invention provides a kind of Risk Forecast Method, including：
Obtain video image of applicant during face is examined；
Video frame in the video image is clustered, determines key frame video image；
According to the determining crucial frame video image and micro- expression probability of cheating model, the key frame video figure is determined
As the probability of cheating of corresponding micro- expression；
According to the probability of cheating of the determining corresponding micro- expression of the key frame video image, the refund to the applicant
Ability carries out risk profile.
The second aspect of the embodiment of the present invention provides a kind of server, including memory and processor, the storage
Device is stored with the computer program that can be run on the processor, and the processor is realized such as when executing the computer program
Lower step：
Obtain video image of applicant during face is examined；
Video frame in the video image is clustered, determines key frame video image；
According to the determining crucial frame video image and micro- expression probability of cheating model, the key frame video figure is determined
As the probability of cheating of corresponding micro- expression；
According to the probability of cheating of the determining corresponding micro- expression of the key frame video image, the refund to the applicant
Ability carries out risk profile.
The third aspect of the embodiment of the present invention provides a kind of computer readable storage medium, the computer-readable storage
Media storage has computer program, the computer program to realize following steps when being executed by processor：
Obtain video image of applicant during face is examined；
Video frame in the video image is clustered, determines key frame video image；
According to the determining crucial frame video image and micro- expression probability of cheating model, the key frame video figure is determined
As the probability of cheating of corresponding micro- expression；
According to the probability of cheating of the determining corresponding micro- expression of the key frame video image, the refund to the applicant
Ability carries out risk profile.
It, will be in the video image by obtaining video image of applicant during face is examined in the embodiment of the present invention
Video frame clustered, key frame video image is determined, then according to the determining crucial frame video image and micro- expression
Probability of cheating model determines the probability of cheating of the corresponding micro- expression of the crucial frame video image, finally according to described in determining
The probability of cheating of the corresponding micro- expression of crucial frame video image carries out risk profile, we to the loan repayment capacity of the applicant
Case assesses the probability of cheating of applicant, and general according to fraud by analyzing micro- expression of applicant during face is examined
Rate carries out risk profile to the loan repayment capacity of the applicant, and objective auxiliary is provided for the loan repayment capacity of forecast assessment applicant
Judge, to improve the accuracy of risk profile and the efficiency of prediction.
Description of the drawings
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description be only the present invention some
Embodiment for those of ordinary skill in the art without having to pay creative labor, can also be according to these
Attached drawing obtains other attached drawings.
Fig. 1 is the implementation flow chart of Risk Forecast Method provided in an embodiment of the present invention；
Fig. 2 is the specific implementation flow chart of Risk Forecast Method S103 provided in an embodiment of the present invention；
Fig. 3 is the specific implementation flow chart of Risk Forecast Method A2 provided in an embodiment of the present invention；
Fig. 4 is the specific implementation flow chart of Risk Forecast Method S105 provided in an embodiment of the present invention；
Fig. 5 is the implementation flow chart for the Risk Forecast Method that another embodiment of the present invention provides；
Fig. 6 is the structure diagram of risk profile device provided in an embodiment of the present invention；
Fig. 7 is the structure diagram for the risk profile device that another embodiment of the present invention provides；
Fig. 8 is the schematic diagram of server provided in an embodiment of the present invention.
Specific implementation mode
In order to make the invention's purpose, features and advantages of the invention more obvious and easy to understand, below in conjunction with the present invention
Attached drawing in embodiment, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that disclosed below
Embodiment be only a part of the embodiment of the present invention, and not all embodiment.Based on the embodiments of the present invention, this field
All other embodiment that those of ordinary skill is obtained without making creative work, belongs to protection of the present invention
Range.
Fig. 1 shows that the implementation process of Risk Forecast Method provided in an embodiment of the present invention, this method flow include step
S101 to S104.The specific implementation principle of each step is as follows：
S101：Obtain video image of applicant during face is examined.
In embodiments of the present invention, during applicant's progress face is examined, Shen during face is examined is shot by camera
The facial expression of the performance asked someone, especially applicant.Therefore, the video image includes the facial expression image of the applicant.
In fact, many expressions of applicant are to flash across namely micro- expression, it is only 1/25~1/5s that micro- expression, which is a kind of duration,
Very quick expression, it be attempted to constrain or hide oneself real feelings when show it is of short duration, be unable to autonomous control
Facial expression.In embodiments of the present invention, due to when applicant answers a problem, being all in most of the time applicant
Poker-faced or some other common expression, and useful information is often only present in micro- expression that those may flash across
In.Therefore the performance video shooting of applicant, analyzes micro- expression of user, avoiding missing can during being examined by opposite
The micro- expression that can occur, improves the accuracy of risk profile.
It further, can be by the process of interviewing due to the problem of applicant may answer during face is examined more than one
In intact video images be divided into multiple video images by the duration of a problem and answer, to the multiple videos split
Image carries out micro- Expression analysis respectively, i.e., the video image during examining face is divided several sons of being grown up by interior perhaps duration and regarded
Frequency image.
S102：Video frame in the video image is clustered, determines key frame video image.
Useful information is often only present in micro- expression that those may flash across, in a video image, such as
Fruit counts the duration that an expression occurs, very big for the influence for analyzing the expression, therefore, by determining in video image
Crucial frame video image rejects redundant frame image, can eliminate influence of the video length to micro- Expression analysis.In the embodiment of the present invention
In, by clustering the video frame in the video image, key frame video image is determined, to avoid regarding to each frame
Frequency image is analyzed, and the efficiency of analysis is improved.
Specifically, in embodiments of the present invention, it is clustered according to the human face expression in video frame.The principle packet of cluster
It includes：Human face expression in video frame images tends to (similarity is higher) similar to each other in some sense；Different human face expressions
It levels off to dissimilar (similarity is relatively low).Wherein, similarity is higher and the relatively low similarity threshold by with setting of similarity into
Row compares, if similarity is not less than in default similarity threshold, then it is assumed that similarity is higher, tends to be similar to each other；If similarity
Less than default similarity threshold, then it is assumed that similarity is relatively low, tends to be dissimilar each other.
As an embodiment of the present invention, as shown in Fig. 2, above-mentioned S102 is specifically included：
A1：The video frame of specified quantity is chosen from the video image as initial cluster center.
A2：Calculate the similarity of the video frame and the initial cluster center in the video image.Specifically, calculating regards
Human face expression and the similarity as the human face expression in the video frame of initial cluster center in frequency frame.
A3：The video frame in the video image is gathered with preset minimum similarity degree according to the similarity of calculating
Class.Specifically, if the similarity calculated is not less than preset minimum similarity degree, by the video frame and the initial cluster center
Cluster.Opposite, if the similarity calculated is less than preset minimum similarity degree, without cluster.Further, by all meters
The video frame that the similarity of calculation is less than preset similarity individually clusters as cluster.
A4：Cluster centre is chosen again from the video frame after cluster, repeats cluster until cluster centre is restrained.Its
In, cluster centre convergence refers to no longer being changed as the video frame images of cluster centre.Specifically, each video frame images are all marked
Having time is stabbed, and whether the timestamp for the video frame images that can be used as cluster centre by judgement changes whether to judge cluster centre
Convergence.If the timestamp as video frame images does not change, then it is assumed that cluster centre has been restrained, if as video frame images when
Between stab change, then it is assumed that cluster centre is also not converged.
A5：The cluster centre that will eventually determine is determined as the crucial frame video image of the video image.
It in embodiments of the present invention, will be superfluous by the way that the video frame cluster in video image is determined crucial frame video image
Remaining video frame is rejected, to improve the efficiency of image analysis.
As an embodiment of the present invention, as shown in figure 3, all including face face action list in each frame video image
Member, therefore, above-mentioned S102 specifically include：
B1：According to the video frame in the video image, face Facial action unit in each frame video image is obtained
Intensity value.
B2：Classified to the video frame picture according to the intensity value of face Facial action unit, and is tied according to classification
Fruit determines crucial frame video image.
Specifically, it is the objective facial expression for portraying applicant, using one group of Coding and description expression, each coding is known as one
The facial expression of a motor unit (ActionUnit), people indicates that foundation is acted with a series of actions unit (ActionUnit)
Element number mapping table, each motor unit are indicated with a prespecified number.For example, a surprised expression includes eyebrow
Hair inside raises up, outside eyebrow raises up, upper eyelid raises up, lower jaw opens, according to motor unit number mapping table it is found that these are dynamic
It is 1,2,6 and 18 respectively to make corresponding motor unit number.This group of Coding and description surprised expression.Motor unit identification can be with
The face action of objective description people can also be used to the corresponding emotional state of analysis expression.When the intensity value of motor unit is not small
When preset strength threshold value, motor unit standard is just thought.Specifically, a facial expression includes several motor units, when
In several motor units, when the intensity value of specified motor unit is all not less than preset strength threshold value, assert this several
Motor unit corresponds to this expression.Wherein, the intensity value of motor unit can be embodied by the movable amplitude of face organ, for example,
The difference of amplitude and the predetermined amplitude threshold value opened by lower jaw judges the intensity value of the motor unit.Further, same
May include more than one motor unit in one facial expression, for example, in a surprised expression, by judging eyebrow respectively
A series of amplitudes of face organs such as inside raises up, outside eyebrow raises up, upper eyelid raises up, lower jaw is opened with it is corresponding preset
The difference of amplitude threshold, to determine the intensity value of each motor unit.It is determined according to the sum of intensity value of each motor unit
The intensity value of this group of motor unit, to determine the corresponding human face expression of this group of motor unit.
In embodiments of the present invention, face Facial action unit of the difference of intensity value within the scope of preset difference value is corresponding
Human face expression is also very much like, therefore, is classified to the video frame picture according to the intensity value of face Facial action unit,
And determine crucial frame video image according to classification results, reject the video frame of redundancy.
Further, it according to the intensity of face Facial action unit in each frame picture, is regarded to all in video image
Frequency frame is clustered, and randomly selecting setting quantity video frame, (such as 7 cluster centres, just selection 7 regard as initial cluster center
Frequency frame image), and according to the preset strength threshold value of the motor unit obtained in advance by statistical result, filter out key frame figure
Piece.For example, for a video frame images, wherein the intensity value of specified Facial action unit is all not less than preset strength threshold value,
And the difference of the intensity value of the intensity value and cluster centre of the Facial action unit of the video frame images is poor not less than preset strength
Value, just thinks that this pictures is crucial frame video image.
S103：According to the determining crucial frame video image and micro- expression probability of cheating model, the key frame is determined
The probability of cheating of the corresponding micro- expression of video image.
In embodiments of the present invention, micro- expression probability of cheating model is for obtaining to the crucial frame video image
In micro- expression probability of cheating, micro- expression probability of cheating model be in advance it is trained, it is micro- to this that machine learning can be used
Expression probability of cheating model is trained.
As an embodiment of the present invention, Fig. 4 shows that Risk Forecast Method training provided in an embodiment of the present invention is micro-
The specific implementation flow of expression probability of cheating model, details are as follows：
C1：The Sample video of setting quantity label is obtained, the label includes fraud and non-fraud.Since sample regards
Frequency posts the label of fraud or non-fraud, and therefore, each video frame images in Sample video are all posted to be regarded with the sample
Frequently identical label.
C2：Extract the sample key frame images in each Sample video, the label of the sample key frame images and institute
The label of the Sample video of category is identical.
C3：The sample key frame images of extraction are trained SVM classifier as training sample, training is completed
SVM classifier is determined as micro- expression probability of cheating model.Wherein, SVM (Support VectorMachine) classifier is to support
Vector machine is a kind of common method of discrimination.A learning model for having supervision in machine learning field, commonly used into
Row pattern-recognition, classification and regression analysis.
Specifically, the sample key frame images that each Sample video is extracted according to K-means clustering algorithms, determine sample
The intensity of motor unit in key frame images is trained SVM classifier using sample key frame images as training sample,
Wherein, data point is a sample key frame images, the intensity value characterized by Facial action unit, and label is fraud or non-takes advantage of
Swindleness, the optimized parameter of SVM classifier is determined by repetition training, to generate micro- expression probability of cheating model.
In embodiments of the present invention, sample key frame images are trained using SVM classifier, generate micro- expression fraud
Probabilistic model, then the determining crucial frame video image is input to micro- expression probability of cheating model, determine the pass
The probability of cheating of the corresponding micro- expression of key frame video image.
Illustratively, a hyperplane is trained with SVM classifier, it is one that human face expression motor unit, which is characterized in space,
It is a, the motor unit intensity value of human face expression in a pictures is inputted, that is, inputs a point, judges the point to SVM classifier
Hyperplane distance, the distance input to sigmoid functions is obtained into probability value, sigmoid function representations are：X indicates the point of motor unit representative to the distance of the SVM hyperplane trained.If probability value is more than 50%,
Then judge that the key frame images judge the key frame images not cheat for fraud if probability value is not more than 50%.
In embodiments of the present invention, can be obtained by often inputting in a video image to micro- expression probability of cheating model by one
Probability value.If the probability of cheating of crucial frame video image is more than predetermined probabilities threshold value, judge in the crucial frame video image
Micro- expression be fraud expression, if the probability of cheating of the video image be not more than predetermined probabilities threshold value, judge the key
Micro- expression in frame video image is non-fraud expression.In general, predetermined probabilities threshold value is set as 50%.
For the same applicant, there may be more than one video images during face is examined.For the same video figure
Picture, it may be determined that more than one crucial frame video image.Multiple crucial frame video images of video image are sequentially input to micro-
Acquisition probability value is distinguished in expression probability of cheating model, then this multiple key frame picture probability value is averaged, it is described average
Value is determined as the probability of cheating of the video image.And then judge to be somebody's turn to do according to the probability of cheating and the comparison result of predetermined probabilities threshold value
Whether video image cheats.
S104：According to the probability of cheating of the determining corresponding micro- expression of the key frame video image, to the applicant
Loan repayment capacity carry out risk profile.
It in embodiments of the present invention, can be true according to the probability of cheating of the corresponding micro- expression of the key frame video image
Determine the sincere reliability of applicant, the reliability of sincere reliability and probability of cheating is inversely proportional, and probability of cheating is higher, sincere reliable
Degree is lower, and sincere reliability is also inversely proportional with refund risk, and sincere reliability is lower, and refund risk is higher.
As an embodiment of the present invention, Fig. 5 shows Risk Forecast Method step provided in an embodiment of the present invention
The specific implementation flow of S104, details are as follows：
D1：The probability of cheating of the corresponding micro- expression of the key frame video image is compared with default risk probability threshold value
Compared with.
D2：If the probability of cheating of the corresponding micro- expression of the key frame video image is not less than the default risk probability threshold
Value then predicts that the refund risk of the applicant exceeds default risk range.
D3：If the probability of cheating of the corresponding micro- expression of the key frame video image is less than the default risk probability threshold
Value then predicts the refund risk of the applicant within default risk range.
Specifically, critical point is used as by the default risk probability threshold value, predicts that the refund risk of the applicant is
It is no to exceed default risk range.Further, calculate the difference of the probability of cheating and the default risk probability threshold value with it is pre-
If risk difference, the grade of the refund risk of the applicant is judged according to the difference grade table of comparisons pre-established.
Optionally, as an embodiment of the present invention, the step S104 further includes：
D4：If predicting, the refund risk of the applicant exceeds default risk range, proposes and risk prevention system measure.
Specifically, if predicting, the refund risk of the applicant exceeds default risk range, transfers and is audited according to history
The matched measure of refund risk in the measure library that information is established with the applicant, suggestion is provided for auditor.
It, will be in the video image by obtaining video image of applicant during face is examined in the embodiment of the present invention
Video frame clustered, clustered according to the similarity of human face expression in video frame, determine key frame video image, or
Person is clustered according to the intensity value of face Facial action unit in video frame, key frame video image is determined, then according to really
The fixed crucial frame video image and micro- expression probability of cheating model determine the corresponding micro- expression of the crucial frame video image
Probability of cheating, finally according to the probability of cheating of the corresponding micro- expression of the determining crucial frame video image, to the application
The loan repayment capacity of people carries out risk profile, and this programme is assessed by analyzing micro- expression of applicant during face is examined
The probability of cheating of applicant judges the sincerity of the applicant according to the comparison result of probability of cheating and default risk probability threshold value
Reliability, and risk profile is carried out to the loan repayment capacity of the applicant according to sincere reliability, it is forecast assessment applicant's
Loan repayment capacity provides objective auxiliary judgment, to improve the accuracy of risk profile and the efficiency of prediction.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process
Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit
It is fixed.
Corresponding to the Risk Forecast Method described in foregoing embodiments, Fig. 6 shows that risk provided by the embodiments of the present application is pre-
The structure diagram for surveying device illustrates only and the relevant part of the embodiment of the present application for convenience of description.
With reference to Fig. 6, which includes：Video image acquisition module 61, key images determining module 62, fraud
Probability determination module 63, risk profile module 64, wherein：
Video image acquisition module 61, for obtaining video image of applicant during face is examined；
Key images determining module 62 determines that key frame regards for clustering the video frame in the video image
Frequency image；
Probability of cheating determining module 63, for according to the determining crucial frame video image and micro- expression probability of cheating mould
Type determines the probability of cheating of the corresponding micro- expression of the crucial frame video image；
Risk profile module 64, it is general for the fraud according to the determining corresponding micro- expression of the key frame video image
Rate carries out risk profile to the loan repayment capacity of the applicant.
Optionally, the key images determining module 62 includes：
Center determination sub-module, for choosing the video frame of specified quantity from the video image as in initial clustering
The heart；
Similarity calculation submodule, the phase for calculating the video frame in the video image and the initial cluster center
Like degree；
Cluster submodule, for according to the similarity of calculating and preset minimum similarity degree by regarding in the video image
Frequency frame is clustered；
The cluster submodule is additionally operable to choose cluster centre again from the video frame after cluster, repeats to cluster
Until cluster centre is restrained；
First image determination sub-module, the cluster centre for will eventually determine are determined as the key frame of the video image
Video image.
Optionally, the key images determining module 62 includes：
Intensity value determination unit, for according to the video frame in the video image, obtaining people in each frame video image
The intensity value of face Facial action unit；
Second image determination sub-module, for according to the intensity value of face Facial action unit to the video frame picture into
Row classification, and determine crucial frame video image according to classification results.
Optionally, the risk profile module 64 includes：
Probability comparison sub-module is used for the probability of cheating of the corresponding micro- expression of the key frame video image and default wind
Dangerous probability threshold value is compared；
First prediction submodule, if the probability of cheating for the corresponding micro- expression of the key frame video image is not less than institute
Default risk probability threshold value is stated, then predicts that the refund risk of the applicant exceeds default risk range；
Second prediction submodule, if the probability of cheating for the corresponding micro- expression of the key frame video image is less than described
Default risk probability threshold value then predicts the refund risk of the applicant within default risk range.
Optionally, as shown in fig. 7, the risk profile device further includes：
Sample video acquisition module 71, the Sample video for obtaining setting quantity label, the label include taking advantage of
Swindleness and non-fraud；
Key images abstraction module 72, for extracting the sample key frame images in each Sample video, the sample
The label of key frame images is identical as the label of affiliated Sample video；
Classification based training module 73, the sample key frame images for that will extract carry out SVM classifier as training sample
The SVM classifier that training is completed is determined as micro- expression probability of cheating model by training.
It, will be in the video image by obtaining video image of applicant during face is examined in the embodiment of the present invention
Video frame clustered, key frame video image is determined, then according to the determining crucial frame video image and micro- expression
Probability of cheating model determines the probability of cheating of the corresponding micro- expression of the crucial frame video image, finally according to described in determining
The probability of cheating of the corresponding micro- expression of crucial frame video image carries out risk profile, we to the loan repayment capacity of the applicant
Case assesses the probability of cheating of applicant, and general according to fraud by analyzing micro- expression of applicant during face is examined
Rate carries out risk profile to the loan repayment capacity of the applicant, and objective auxiliary is provided for the loan repayment capacity of forecast assessment applicant
Judge, to improve the accuracy of risk profile and the efficiency of prediction.
Fig. 8 is the schematic diagram for the server that one embodiment of the invention provides.As shown in figure 8, the server 8 of the embodiment wraps
It includes：Processor 80, memory 81 and it is stored in the computer that can be run in the memory 81 and on the processor 80
Program 82, such as risk profile program.The processor 80 realizes that above-mentioned each risk is pre- when executing the computer program 82
The step in embodiment of the method, such as step 101 shown in FIG. 1 are surveyed to 104.Alternatively, the processor 80 executes the calculating
The function of each module/unit in above-mentioned each device embodiment, such as the work(of module 61 to 64 shown in Fig. 6 are realized when machine program 82
Energy.
Illustratively, the computer program 82 can be divided into one or more module/units, it is one or
Multiple module/units are stored in the memory 81, and are executed by the processor 80, to complete the present invention.Described one
A or multiple module/units can be the series of computation machine program instruction section that can complete specific function, which is used for
Implementation procedure of the computer program 82 in the server 8 is described.
The server 8 can be the computing devices such as desktop PC, notebook, palm PC and cloud server.
The server may include, but be not limited only to, processor 80, memory 81.It will be understood by those skilled in the art that Fig. 8 is only
It is the example of server 8, does not constitute the restriction to server 8, may include than illustrating more or fewer components or group
Close certain components or different components, for example, the server can also include input-output equipment, network access equipment,
Bus etc..
The processor 80 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), application-specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor can also be any conventional processor
Deng.
The memory 81 can be the internal storage unit of the server 8, such as the hard disk or memory of server 8.
The memory 81 can also be that the plug-in type that is equipped on the External memory equipment of the server 8, such as the server 8 is hard
Disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card, flash card
(Flash Card) etc..Further, the memory 81 can also both include the internal storage unit of the server 8 or wrap
Include External memory equipment.The memory 81 is used to store other programs needed for the computer program and the server
And data.The memory 81 can be also used for temporarily storing the data that has exported or will export.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, it can also
It is that each unit physically exists alone, it can also be during two or more units be integrated in one unit.Above-mentioned integrated list
The form that hardware had both may be used in member is realized, can also be realized in the form of SFU software functional unit.
If the integrated module/unit be realized in the form of SFU software functional unit and as independent product sale or
In use, can be stored in a computer read/write memory medium.Based on this understanding, the present invention realizes above-mentioned implementation
All or part of flow in example method, can also instruct relevant hardware to complete, the meter by computer program
Calculation machine program can be stored in a computer readable storage medium, the computer program when being executed by processor, it can be achieved that on
The step of stating each embodiment of the method.Wherein, the computer program includes computer program code, the computer program generation
Code can be source code form, object identification code form, executable file or certain intermediate forms etc..The computer-readable medium
May include：Any entity or device, recording medium, USB flash disk, mobile hard disk, magnetic of the computer program code can be carried
Dish, CD, computer storage, read-only memory (ROM, Read-Only Memory), random access memory (RAM,
Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium etc..It should be noted that described
The content that computer-readable medium includes can carry out increasing appropriate according to legislation in jurisdiction and the requirement of patent practice
Subtract, such as in certain jurisdictions, according to legislation and patent practice, computer-readable medium does not include electric carrier signal and electricity
Believe signal.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations；Although with reference to aforementioned reality
Applying example, invention is explained in detail, it will be understood by those of ordinary skill in the art that：It still can be to aforementioned each
Technical solution recorded in embodiment is modified or equivalent replacement of some of the technical features；And these are changed
Or replace, the spirit and scope for various embodiments of the present invention technical solution that it does not separate the essence of the corresponding technical solution should all
It is included within protection scope of the present invention.
Claims (10)
1. a kind of Risk Forecast Method, which is characterized in that including：
Obtain video image of applicant during face is examined；
Video frame in the video image is clustered, determines key frame video image；
According to the determining crucial frame video image and micro- expression probability of cheating model, the crucial frame video image pair is determined
The probability of cheating for the micro- expression answered；
According to the probability of cheating of the determining corresponding micro- expression of the key frame video image, to the loan repayment capacity of the applicant
Carry out risk profile.
2. according to the method described in claim 1, it is characterized in that, the video frame by the video image is gathered
The step of class, determining key frame video image, including：
The video frame of specified quantity is chosen from the video image as initial cluster center；
Calculate the similarity of the video frame and the initial cluster center in the video image；
The video frame in the video image is clustered with preset minimum similarity degree according to the similarity of calculating；
Cluster centre is chosen again from the video frame after cluster, repeats cluster until cluster centre is restrained；
The cluster centre that will eventually determine is determined as the crucial frame video image of the video image.
3. according to the method described in claim 1, it is characterized in that, the video frame by the video image is gathered
The step of class, determining key frame video image, including：
According to the video frame in the video image, the intensity value of face Facial action unit in each frame video image is obtained；
Classified to the video frame picture according to the intensity value of face Facial action unit, and is determined and closed according to classification results
Key frame video image.
4. according to the method described in claim 1, it is characterized in that, it is described according to the determining crucial frame video image with
Micro- expression probability of cheating model, before the step of determining the probability of cheating of the corresponding micro- expression of the crucial frame video image, packet
It includes：
The Sample video of setting quantity label is obtained, the label includes fraud and non-fraud；
Extract the sample key frame images in each Sample video, the label of the sample key frame images and affiliated sample
The label of video is identical；
The sample key frame images of extraction are trained SVM classifier as training sample, the svm classifier that training is completed
Device is determined as micro- expression probability of cheating model.
5. method according to any one of claims 1 to 4, which is characterized in that described to be regarded according to the determining key frame
The step of probability of cheating of the corresponding micro- expression of frequency image, progress risk profile, including：
The probability of cheating of the corresponding micro- expression of the key frame video image is compared with default risk probability threshold value；
If the probability of cheating of the corresponding micro- expression of the key frame video image is not less than the default risk probability threshold value, in advance
The refund risk for surveying the applicant exceeds default risk range；
If the probability of cheating of the corresponding micro- expression of the key frame video image is less than the default risk probability threshold value, predict
The refund risk of the applicant is within default risk range.
6. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, feature to exist
In the step of realization Risk Forecast Method as described in any one of claim 1 to 5 when the computer program is executed by processor
Suddenly.
7. a kind of server, including memory, processor and it is stored in the memory and can transports on the processor
Capable computer program, which is characterized in that the processor realizes following steps when executing the computer program：
Obtain video image of applicant during face is examined；
Video frame in the video image is clustered, determines key frame video image；
According to the determining crucial frame video image and micro- expression probability of cheating model, the crucial frame video image pair is determined
The probability of cheating for the micro- expression answered；
According to the probability of cheating of the determining corresponding micro- expression of the key frame video image, to the loan repayment capacity of the applicant
Carry out risk profile.
8. server as claimed in claim 7, which is characterized in that the video frame by the video image is gathered
The step of class, determining key frame video image, including：
The video frame of specified quantity is chosen from the video image as initial cluster center；
Calculate the similarity of the video frame and the initial cluster center in the video image；
The video frame in the video image is clustered with preset minimum similarity degree according to the similarity of calculating；
Cluster centre is chosen again from the video frame after cluster, repeats cluster until cluster centre is restrained；
The cluster centre that will eventually determine is determined as the crucial frame video image of the video image.
9. server as claimed in claim 7, which is characterized in that the video frame by the video image is gathered
The step of class, determining key frame video image, including：
According to the video frame in the video image, the intensity value of face Facial action unit in each frame video image is obtained；
Classified to the video frame picture according to the intensity value of face Facial action unit, and is determined and closed according to classification results
Key frame video image.
10. such as claim 7 to 9 any one of them server, which is characterized in that the processor executes the computer journey
Following steps are also realized when sequence：
The probability of cheating according to the determining corresponding micro- expression of the key frame video image carries out the step of risk profile
Suddenly, including：
The probability of cheating of the corresponding micro- expression of the key frame video image is compared with default risk probability threshold value；
If the probability of cheating of the corresponding micro- expression of the key frame video image is not less than the default risk probability threshold value, in advance
The refund risk for surveying the applicant exceeds default risk range；
If the probability of cheating of the corresponding micro- expression of the key frame video image is less than the default risk probability threshold value, predict
The refund risk of the applicant is within default risk range.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810496195.1A CN108734570A (en) | 2018-05-22 | 2018-05-22 | A kind of Risk Forecast Method, storage medium and server |
| PCT/CN2018/101579 WO2019223139A1 (en) | 2018-05-22 | 2018-08-21 | Risk prediction method and device, storage medium, and server |
| TW108102852A TWI731297B (en) | 2018-05-22 | 2019-01-25 | Risk prediction method and apparatus, storage medium, and server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810496195.1A CN108734570A (en) | 2018-05-22 | 2018-05-22 | A kind of Risk Forecast Method, storage medium and server |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108734570A true CN108734570A (en) | 2018-11-02 |
Family
ID=63937780
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810496195.1A Withdrawn CN108734570A (en) | 2018-05-22 | 2018-05-22 | A kind of Risk Forecast Method, storage medium and server |
Country Status (3)
| Country | Link |
|---|---|
| CN (1) | CN108734570A (en) |
| TW (1) | TWI731297B (en) |
| WO (1) | WO2019223139A1 (en) |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109584050A (en) * | 2018-12-14 | 2019-04-05 | 深圳壹账通智能科技有限公司 | Consumer's risk degree analyzing method and device based on micro- Expression Recognition |
| CN109711297A (en) * | 2018-12-14 | 2019-05-03 | 深圳壹账通智能科技有限公司 | Risk Identification Method, device, computer equipment and storage medium based on facial picture |
| CN109729383A (en) * | 2019-01-04 | 2019-05-07 | 深圳壹账通智能科技有限公司 | Double record video quality detection methods, device, computer equipment and storage medium |
| CN109766772A (en) * | 2018-12-18 | 2019-05-17 | 深圳壹账通智能科技有限公司 | Risk control method, device, computer equipment and storage medium |
| CN109800703A (en) * | 2019-01-17 | 2019-05-24 | 深圳壹账通智能科技有限公司 | Risk checking method, device, computer equipment and storage medium based on micro- expression |
| CN109816518A (en) * | 2019-01-04 | 2019-05-28 | 深圳壹账通智能科技有限公司 | Face core result acquisition methods, device, computer equipment and readable storage medium storing program for executing |
| CN109829359A (en) * | 2018-12-15 | 2019-05-31 | 深圳壹账通智能科技有限公司 | Monitoring method, device, computer equipment and the storage medium in unmanned shop |
| CN109858411A (en) * | 2019-01-18 | 2019-06-07 | 深圳壹账通智能科技有限公司 | Case trial method, apparatus and computer equipment based on artificial intelligence |
| CN109919001A (en) * | 2019-01-23 | 2019-06-21 | 深圳壹账通智能科技有限公司 | Customer service monitoring method, device, device and storage medium based on emotion recognition |
| CN110197295A (en) * | 2019-04-23 | 2019-09-03 | 深圳壹账通智能科技有限公司 | Prediction financial product buy in risk method and relevant apparatus |
| 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 |
| CN110222554A (en) * | 2019-04-16 | 2019-09-10 | 深圳壹账通智能科技有限公司 | Cheat recognition methods, device, electronic equipment and storage medium |
| CN110503563A (en) * | 2019-07-05 | 2019-11-26 | 中国平安人寿保险股份有限公司 | Risk control method and system |
| CN111080874A (en) * | 2019-12-31 | 2020-04-28 | 中国银行股份有限公司 | Face image-based vault safety door control method and device |
| CN111667359A (en) * | 2020-06-19 | 2020-09-15 | 上海印闪网络科技有限公司 | Information auditing method based on real-time video |
| CN111768286A (en) * | 2020-05-14 | 2020-10-13 | 北京旷视科技有限公司 | Risk prediction method, device, equipment and storage medium |
| CN111860554A (en) * | 2019-04-28 | 2020-10-30 | 杭州海康威视数字技术股份有限公司 | Risk monitoring method and device, storage medium and electronic equipment |
| CN112001785A (en) * | 2020-07-21 | 2020-11-27 | 小花网络科技(深圳)有限公司 | Network credit fraud identification method and system based on image identification |
| 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 |
| CN113283978A (en) * | 2021-05-06 | 2021-08-20 | 北京思图场景数据科技服务有限公司 | Financial risk assessment method based on biological basis, behavior characteristics and business characteristics |
| CN116884149A (en) * | 2023-07-20 | 2023-10-13 | 中国工商银行股份有限公司 | Methods, devices, electronic equipment and media for multimodal information analysis |
| CN117132391A (en) * | 2023-10-16 | 2023-11-28 | 杭银消费金融股份有限公司 | Human-computer interaction-based trust approval method and system |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111325185B (en) * | 2020-03-20 | 2023-06-23 | 上海看看智能科技有限公司 | Face fraud prevention method and system |
| CN111582757B (en) * | 2020-05-20 | 2024-04-30 | 深圳前海微众银行股份有限公司 | Method, device, equipment and computer readable storage medium for analyzing fraud risk |
| CN112215700B (en) * | 2020-10-13 | 2024-10-22 | 中国银行股份有限公司 | Credit surface examination method and device |
| CN112348318B (en) * | 2020-10-19 | 2024-04-23 | 深圳前海微众银行股份有限公司 | Training and application method and device of supply chain risk prediction model |
| CN112381036B (en) * | 2020-11-26 | 2024-10-15 | 厦门大学 | Micro-expression and macro-expression fragment identification method applied to criminal investigation |
| CN113657440A (en) * | 2021-07-08 | 2021-11-16 | 同盾科技有限公司 | Rejection sample inference method and device based on user feature clustering |
| CN114219630A (en) * | 2021-12-21 | 2022-03-22 | 中国农业银行股份有限公司 | Service risk prediction method, device, equipment and medium |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8311294B2 (en) * | 2009-09-08 | 2012-11-13 | Facedouble, Inc. | Image classification and information retrieval over wireless digital networks and the internet |
| CN103258204B (en) * | 2012-02-21 | 2016-12-14 | 中国科学院心理研究所 | A kind of automatic micro-expression recognition method based on Gabor and EOH feature |
| CN103065122A (en) * | 2012-12-21 | 2013-04-24 | 西北工业大学 | Facial expression recognition method based on facial motion unit combination features |
| CN105893920B (en) * | 2015-01-26 | 2019-12-27 | 阿里巴巴集团控股有限公司 | Face living body detection method and device |
| CN107292218A (en) * | 2016-04-01 | 2017-10-24 | 中兴通讯股份有限公司 | A kind of expression recognition method and device |
| CN105913046A (en) * | 2016-05-06 | 2016-08-31 | 姜振宇 | Micro-expression identification device and method |
| CN106529453A (en) * | 2016-10-28 | 2017-03-22 | 深圳市唯特视科技有限公司 | Reinforcement patch and multi-tag learning combination-based expression lie test method |
| CN107704834B (en) * | 2017-10-13 | 2021-03-30 | 深圳壹账通智能科技有限公司 | Micro-surface examination assisting method, device and storage medium |
-
2018
- 2018-05-22 CN CN201810496195.1A patent/CN108734570A/en not_active Withdrawn
- 2018-08-21 WO PCT/CN2018/101579 patent/WO2019223139A1/en active Application Filing
-
2019
- 2019-01-25 TW TW108102852A patent/TWI731297B/en not_active IP Right Cessation
Cited By (32)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109711297A (en) * | 2018-12-14 | 2019-05-03 | 深圳壹账通智能科技有限公司 | Risk Identification Method, device, computer equipment and storage medium based on facial picture |
| CN109584050A (en) * | 2018-12-14 | 2019-04-05 | 深圳壹账通智能科技有限公司 | Consumer's risk degree analyzing method and device based on micro- Expression Recognition |
| CN109829359A (en) * | 2018-12-15 | 2019-05-31 | 深圳壹账通智能科技有限公司 | Monitoring method, device, computer equipment and the storage medium in unmanned shop |
| CN109766772A (en) * | 2018-12-18 | 2019-05-17 | 深圳壹账通智能科技有限公司 | Risk control method, device, computer equipment and storage medium |
| CN109816518A (en) * | 2019-01-04 | 2019-05-28 | 深圳壹账通智能科技有限公司 | Face core result acquisition methods, device, computer equipment and readable storage medium storing program for executing |
| WO2020140665A1 (en) * | 2019-01-04 | 2020-07-09 | 深圳壹账通智能科技有限公司 | Method and apparatus for quality detection of double-recorded video, and computer device and storage medium |
| CN109729383A (en) * | 2019-01-04 | 2019-05-07 | 深圳壹账通智能科技有限公司 | Double record video quality detection methods, device, computer equipment and storage medium |
| CN109729383B (en) * | 2019-01-04 | 2021-11-02 | 深圳壹账通智能科技有限公司 | Double-recording video quality detection method and device, computer equipment and storage medium |
| CN109800703A (en) * | 2019-01-17 | 2019-05-24 | 深圳壹账通智能科技有限公司 | Risk checking method, device, computer equipment and storage medium based on micro- expression |
| CN109858411A (en) * | 2019-01-18 | 2019-06-07 | 深圳壹账通智能科技有限公司 | Case trial method, apparatus and computer equipment based on artificial intelligence |
| CN109919001A (en) * | 2019-01-23 | 2019-06-21 | 深圳壹账通智能科技有限公司 | Customer service monitoring method, device, device and storage medium based on emotion recognition |
| CN110222554A (en) * | 2019-04-16 | 2019-09-10 | 深圳壹账通智能科技有限公司 | Cheat recognition methods, device, electronic equipment and storage medium |
| WO2020211388A1 (en) * | 2019-04-16 | 2020-10-22 | 深圳壹账通智能科技有限公司 | Behavior prediction method and device employing prediction model, apparatus, and storage medium |
| CN110197295A (en) * | 2019-04-23 | 2019-09-03 | 深圳壹账通智能科技有限公司 | Prediction financial product buy in risk method and relevant apparatus |
| CN111860554B (en) * | 2019-04-28 | 2023-06-30 | 杭州海康威视数字技术股份有限公司 | Risk monitoring method and device, storage medium and electronic equipment |
| CN111860554A (en) * | 2019-04-28 | 2020-10-30 | 杭州海康威视数字技术股份有限公司 | Risk monitoring method and device, storage medium and electronic equipment |
| 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 |
| 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 |
| CN110503563B (en) * | 2019-07-05 | 2023-07-21 | 中国平安人寿保险股份有限公司 | Risk control method and system |
| CN110503563A (en) * | 2019-07-05 | 2019-11-26 | 中国平安人寿保险股份有限公司 | Risk control method and system |
| CN111080874A (en) * | 2019-12-31 | 2020-04-28 | 中国银行股份有限公司 | Face image-based vault safety door control method and device |
| CN111080874B (en) * | 2019-12-31 | 2022-06-03 | 中国银行股份有限公司 | Face image-based vault safety door control method and device |
| CN111768286A (en) * | 2020-05-14 | 2020-10-13 | 北京旷视科技有限公司 | Risk prediction method, device, equipment and storage medium |
| CN111768286B (en) * | 2020-05-14 | 2024-02-20 | 北京旷视科技有限公司 | Risk prediction methods, devices, equipment and storage media |
| CN111667359A (en) * | 2020-06-19 | 2020-09-15 | 上海印闪网络科技有限公司 | Information auditing method based on real-time video |
| CN112001785A (en) * | 2020-07-21 | 2020-11-27 | 小花网络科技(深圳)有限公司 | Network credit fraud identification method and system based on image identification |
| 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 |
| CN113283978A (en) * | 2021-05-06 | 2021-08-20 | 北京思图场景数据科技服务有限公司 | Financial risk assessment method based on biological basis, behavior characteristics and business characteristics |
| CN113283978B (en) * | 2021-05-06 | 2024-05-10 | 北京思图场景数据科技服务有限公司 | Financial risk assessment method based on biological basis, behavioral characteristics and business characteristics |
| CN116884149A (en) * | 2023-07-20 | 2023-10-13 | 中国工商银行股份有限公司 | Methods, devices, electronic equipment and media for multimodal information analysis |
| CN117132391A (en) * | 2023-10-16 | 2023-11-28 | 杭银消费金融股份有限公司 | Human-computer interaction-based trust approval method and system |
| CN117132391B (en) * | 2023-10-16 | 2024-07-30 | 杭银消费金融股份有限公司 | Human-computer interaction-based trust approval method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| TW202004637A (en) | 2020-01-16 |
| WO2019223139A1 (en) | 2019-11-28 |
| TWI731297B (en) | 2021-06-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108734570A (en) | A kind of Risk Forecast Method, storage medium and server | |
| Xiao et al. | Ensemble classification based on supervised clustering for credit scoring | |
| CN110378786B (en) | Model training method, default transmission risk identification method, device and storage medium | |
| CN110888857A (en) | Data label generation method, device, terminal and medium based on neural network | |
| CN113516511B (en) | A financial product purchase prediction method, device and electronic equipment | |
| Polamarasetti et al. | Evaluating Machine Learning Models Efficiency with Performance Metrics for Customer Churn Forecast in Finance Markets | |
| CN117038055B (en) | Pain assessment method, system, device and medium based on multi-expert model | |
| CN119167281A (en) | A method and system for analyzing abnormal behavior of examinees in a computer-based examination | |
| Eddy et al. | Credit scoring models: Techniques and issues | |
| CN117575595A (en) | Payment risk identification method, device, computer equipment and storage medium | |
| Sembina | Building a scoring model using the adaboost ensemble model | |
| CN110399818A (en) | A kind of method and apparatus of risk profile | |
| CN115455408B (en) | Network space deduction and security assessment method and device | |
| CN112116441B (en) | Training method, classification method, device and equipment for financial risk classification model | |
| CN117011662A (en) | Training method, training device, training equipment, training medium and training program product for face recognition network | |
| Li et al. | A study on customer churn of commercial banks based on learning from label proportions | |
| CN115705412A (en) | Object identification method and device, computing equipment and storage medium | |
| Nazari et al. | Evaluating the effectiveness of data mining techniques in credit scoring of bank customers using mathematical models: a case study of individual borrowers of Refah Kargaran Bank in Zanjan Province, Iran | |
| Dai | Research on Detecting Credit Card Fraud Through Machine Learning Methods | |
| CN114005550A (en) | Behavior monitoring method, device and equipment based on remote inquiry | |
| Pavlović | Challenges in application of machine learning in insurance industry | |
| HK1257308A1 (en) | Risk prediction method and apparatus, storage medium, and server | |
| CN116258579B (en) | Training method of user credit scoring model and user credit scoring method | |
| Shoaeinaeini et al. | Building Reliable Loan Approval Systems: Leveraging Feature Engineering and Machine Learning | |
| CN114841478A (en) | A method, device, device and readable storage medium for obtaining credit information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 1257308 Country of ref document: HK |
|
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20181102 |
|
| WW01 | Invention patent application withdrawn after publication |