CN109063965A - A kind of network payment methods of risk assessment, device and server - Google Patents
A kind of network payment methods of risk assessment, device and server Download PDFInfo
- Publication number
- CN109063965A CN109063965A CN201810714606.XA CN201810714606A CN109063965A CN 109063965 A CN109063965 A CN 109063965A CN 201810714606 A CN201810714606 A CN 201810714606A CN 109063965 A CN109063965 A CN 109063965A
- Authority
- CN
- China
- Prior art keywords
- risk
- payment
- user network
- value
- data
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/382—Payment protocols; Details thereof insuring higher security of transaction
Abstract
This specification embodiment provides a kind of network payment methods of risk assessment, payment risk concentration value is calculated by user network payment behavior data, determines the payment decision-making value curve based on different scores, to assess the risk of user network payment behavior, thus let pass or bother this process of exchange in time so that be optimal balance, the entire effect of bothering object it is smaller.
Description
Technical field
This specification be related to network payment technical field more particularly to a kind of network payment methods of risk assessment, device and
Server.
Background technique
As Internet technology develops, more and more electronic equipments are appeared in the work and life of people, are facilitated
Daily life.These electronic equipments provide convenient and fast service, the especially field of internet payment by internet for user
Scape is more and more, and application is also more widespread.But following, the safety problem of internet payment or network payment is also therewith
It generates.Due to internet self attributes, network payment platform can not completely carry out each network payment transaction detailed
User identity compares, that is, needs to take into account safety of payment and convenient two attributes of payment, thereby how efficiently control payment wind
Danger is just a problem to be solved.
Summary of the invention
In view of the above problems, this specification is proposed to overcome the above problem in order to provide one kind or at least be partially solved
Network payment methods of risk assessment, device and the server of the above problem.
In a first aspect, this specification provides a kind of network payment methods of risk assessment, comprising: obtain user network paying bank
For data, the user network payment behavior data are input in risk probability Function generator；Based on the risk probability function
The payment risk concentration value of device output, assesses the risk of the user network payment behavior.
Second aspect, this specification provide network payment risk assessment device, comprising: acquiring unit, for obtaining user
The user network payment behavior data are input in risk probability Function generator by network payment behavioral data；Risk probability letter
Number device calculates payment risk concentration value, and export the payment risk for inputting the user network payment behavior data
Concentration value；Assessment unit, the payment risk concentration value for being exported based on the risk probability Function generator, assesses the user network
The risk of network payment behavior.
The third aspect, this specification provide a kind of server, including processor and memory: the memory is for storing
The program of any of the above-described the method；The processor is configured to being realized for executing the program stored in the memory
The step of any of the above-described the method.
Fourth aspect, this specification embodiment provide a kind of computer readable storage medium, are stored thereon with computer journey
Sequence, when which is executed by processor the step of realization any of the above-described the method.
This specification said one or multiple technical solutions at least have following one or more technical effects:
In the technical solution for implementing this specification, user network payment behavior data are obtained, by the user network branch
Pay behavioral data be input in risk probability Function generator, based on the risk probability Function generator output payment risk concentration value,
Assess the risk of the user network payment behavior.In this way, risk probability letter can be passed through when user initiates network payment behavior
Number device, based on the risk of this payment behavior of loss probability assessment user, this payment transaction of letting pass in risk range, and
This process of exchange is bothered when beyond risk range in time, further verifies subscriber identity information.
Since exponential distribution feature is presented using relationship between quantization score and risk concentration in the technical solution of this specification
The characteristics of, it carries out exponential function by the way that score and risk concentration will be quantified and is fitted to form risk probability function, and then construct outlet air
Dangerous decision-making value curve (Decision Threshold Curve), for substitute it is original it is ladder-like check threshold value, solve as
What selection bothers object and makes the smaller technical problem of entire effect, so that income/cost ratio rate of strategy is effectively mentioned
It rises, ensure that the acquirement of optimal balance.
Further, degree of risk is combined with payment amount, in addition to solving cost absorbing and benefit in decision in the face of risk process
Equalization point select permeability outside, also set up to carry out decision in the face of risk selection between the payment transaction of different risks, the different amount of money
One succinct standard effective, easy to carry out, especially risk control is when setting only once bothers chance, using this explanation
The technical solution of book, in the case where more efficiently control payment risk, so that it is smaller to bother object entire effect.
Detailed description of the invention
By reading the following detailed description of the preferred embodiment, various other advantages and benefits are common for this field
Technical staff will become clear.The drawings are only for the purpose of illustrating a preferred embodiment, and is not considered as to this explanation
The limitation of book.And throughout the drawings, the same reference numbers will be used to refer to the same parts.In the accompanying drawings:
Fig. 1 is the schematic diagram of an application scenarios example of the scheme of this specification；
Fig. 2 is the flow chart of one of this specification first embodiment network payment methods of risk assessment；
Fig. 3 is the schematic diagram of one of this specification second embodiment network payment risk assessment device；
Fig. 4 is a kind of example of the server using network payment risk assessment in this specification 3rd embodiment.
Specific embodiment
This specification technical solution is described in detail below by attached drawing and specific embodiment, it should be understood that this theory
Specific features in bright book embodiment and embodiment are the detailed description to this specification technical solution, rather than to this theory
The restriction of bright book technical solution, in the absence of conflict, technical characteristic in this specification embodiment and embodiment can be with
It is combined with each other.
The terms "and/or", only a kind of incidence relation for describing affiliated partner, indicates that there may be three kinds of passes
System, for example, A and/or B, can indicate: individualism A exists simultaneously A and B, these three situations of individualism B.In addition, herein
Middle character "/" typicallys represent the relationship that forward-backward correlation object is a kind of "or".
Embodiment
Referring to FIG. 1, the application scenarios schematic diagram of one embodiment that the technical solution of this specification is related to.In user side
One or more users can use terminal 10 and communicated with the server 20 of network side, user utilizes the branch in terminal 10
It pays client 30 and realizes payment behavior, generate payment behavior data, which includes realizing the APP of business based on internet
Or website etc., it transaction interface is provided and payment behavior data are supplied to network side for user handles, and the clothes of network side
Business device 20 can use output payment risk concentration value in the risk probability Function generator for being input to payment behavior data and setting,
To carry out network payment risk assessment.
How the amount of money under different scores is selected to check threshold value by quantitative mode rather than expertise, commonly
The selection of air control decision-making value be difficult to obtain between cost absorbing and benefit optimal balance, limited risk bothered be output to it is most desirable
Place is gone, in this regard, this specification embodiment proposes that a kind of network payment methods of risk assessment and its device are applied to network payment
Intelligent air control control, by will quantify score and risk concentration progress exponential function be fitted to form risk probability function, in turn
Decision in the face of risk threshold curve is constructed, risk is assessed and ensures that selection bothers object and makes entire effect smaller, effectively promotion plan
Income/cost slightly guarantees optimal balance, limited risk is bothered and is supplied to the most desirable place than interest rate.
Risk probability Function generator is by model training, determines risk concentration to sample scorable marker to coordinate system and to mark
Note point does curve matching and is arranged.
Referring to FIG. 2, this specification first embodiment provides a kind of network payment methods of risk assessment, the network payment wind
Dangerous appraisal procedure includes the following steps:
S101: user network payment behavior data are obtained, it is general that the user network payment behavior data are input to risk
In rate Function generator.
Specifically for example, network payment behavior occurs for client one or more user, payment behavior data are generated, are being serviced
Device one end is the payment risk for reducing user and occurring, and obtains these payment behavior data, is input in risk probability Function generator.
S102: the payment risk concentration value based on risk probability Function generator output assesses the user network payment
The risk of behavior.
Specifically for example, risk probability Function generator calculates these user network payment behavior data, obtain corresponding each
The payment risk concentration value of payment behavior data, and one or more user network paying banks are assessed based on payment risk concentration value
For risk.
Assessment risk is specifically for example: can be stood a loss value, be counted based on the payment risk concentration value and preset maximum
Calculation obtains the payment decision-making value curve based on different scores；It is corresponding one or more by the payment decision-making value curve acquisition
The risk threshold value of user network payment behavior data；Compare the risk threshold value in corresponding user network payment behavior data
Payment amount assesses the risk of one or more user network payment behaviors, for example, if payment amount is described greater than corresponding
Risk threshold value then assesses the user network payment behavior, and there are risks, or if the payment amount be less than or equal to it is corresponding
The risk threshold value then assesses the user network payment behavior, and there is no risks, further, to the use evaluated there are risk
Family network payment behavior, output prompt, verifies user identity.
Specifically for example, risk probability Function generator is that the pre- history payment risk transaction data progress model training that first passes through obtains
?.Such as: history payment risk transaction data is obtained, history payment risk transaction data includes black sample data and Fei Hei sample
Data, such as: the transaction data of occurrence risk is labeled as black sample data, non-occurrence risk transaction data labeled as non-black
Sample data, based on black sample data and Fei Hei sample data training payment risk quantitative model；Quantify mould based on payment risk
Type, curve matching go out an exponential function, are set as function used in risk probability Function generator.Wherein, training parameter includes payment
One or more of equipment, payment environment, transaction relationship, payment behavior.
Another example is: going out an exponential function based on payment risk quantitative model curve matching, it is set as risk probability function
Function used in device, comprising: it is given a mark based on payment risk quantitative model to each black sample data and Fei Hei sample data, point
A sample score value is not obtained；Coordinate system is established, by each sample award indicators to x-axis, marking corresponding y-axis is this score value of various kinds
Under black concentration of specimens ratio value, i.e. risk concentration of the quantization strategy under the sample score value；Label in coordinate system is clicked through
Row curve matching obtains an exponential function, is set as the risk probability Function generator.Wherein, black concentration of specimens ratio value is
Black sample data volume/(black sample data volume+non-black sample data volume).
Below with reference to Fig. 2, the present embodiment is further illustrated.Network payment methods of risk assessment is mainly used in network payment
The server end of platform, it is of course also possible to be applied to client.For example, application scenarios with reference to Fig. 1 this specification show
In example, multiple users pay online, after payment behavior data are assessed by risk probability Function generator, it is determined whether right
To user pay carry out air control interference/air control bother, including such as identification check or authentication identification (such as short message, face,
KBA verification etc.), payment failure, account limit power etc..
Further, in the present embodiment, above-mentioned steps S101, user is in the client with network payment function by sweeping
When code, the modes such as transfer accounts initiate network payment behavior request, user network payment behavior data are transmitted to network branch by client
Pay the server of platform.
Accordingly, wind is input to after server receives the user network payment behavior data in above-mentioned steps S102
Marking calculating is carried out to payment behavior data in dangerous probability function device.On this basis, server also will use one or more
The network payment behavioral data of risk probability Function generator while parallel processing mass users evaluates the wind of each user's payment
Danger.
Further, presetting maximum in the server can stand a loss value, by the default maximum can stand a loss value divided by
The payment risk concentration value of risk probability Function generator output, obtains the payment decision-making value curve based on different scores.
Such as it is current there are two user network payment behavior A (100 yuan) and B (10000 yuan), payment platform is needed to two
Payment carry out risk assessment, to two pay expection maximum can stand a loss value be 80 yuan.The risk score of payment behavior A is
8.2 points, the risk score of payment behavior B is 5.3 points.It is 50%, B by the risk concentration value that risk probability Function generator calculates A
Risk concentration value be 10%.
Thus obtain A risk threshold value be 80 divided by 50% be 160, B risk threshold value be 80 divided by 10% be 800.Than
Compared with risk threshold value and corresponding payment amount, the payment amount 100 of A is less than risk threshold value 160, then assesses the user network branch
Risk is not present in the behavior of paying, and does not need output prompt, completes payment transaction, and the payment amount 10000 of B is greater than corresponding risk
Threshold value 800, then assessing the user network payment behavior, there are risks, then need to bother output prompt, carry out identity to user
It veritifies.
Further, the risk probability Function generator is that the pre- history payment risk transaction data progress model training that first passes through obtains
, for example obtain history payment risk transaction data, the transaction data of occurrence risk labeled as black sample data (such as
Positive label), non-occurrence risk transaction data labeled as non-black sample data (such as Unlabel is marked), it is based on institute
Black sample data and Fei Hei sample data training payment risk quantitative model (such as exponential Function Model) are stated, the payment is based on
Risk quantification model gives a mark to each black sample data and Fei Hei sample data, the marking for example: as one payment, 8
It gives a mark respectively in a module/parameter, identity 0.5 is divided, and behavior 0.5 divides, and equipment 1 is divided, and environment 0.9 divides, conflict 0.8 point, relationship-
2.0 points, scene 0.7 is divided, and FTG0 points, whole score is 2.4 points；A sample score value is respectively obtained as a result, (such as output Score
Score value)；Coordinate system is established, by each sample award indicators to x-axis, marks corresponding y-axis dense for the black sample under this score value of various kinds
Ratio value is spent, the black concentration of specimens ratio value is black sample data volume/(black sample data volume+non-black sample data volume), i.e.,
As risk concentration of the quantization strategy under the sample score value；It carries out curve fitting to the mark point in the coordinate system, such as
By statistical tool (such as: Python) to mark point curve matching, an exponential function is obtained, the risk probability is set as
Function generator.
Further, it is possible to which online give a mark to payment behavior, the risk for calculating its quantization point by risk probability Function generator is dense
Preset maximum can be stood a loss value divided by the risk concentration value, obtain the payment based on different scores by angle value as the aforementioned
Decision-making value curve (decision threshold curve) finally determines wind compared with the payment amount of actual delivery behavior
Danger, it is determined whether by pay or export bother verify payment behavior user identity.
Further, described based on the black sample data and Fei Hei sample data training payment risk quantitative model, into one
Step include: training parameter include one or more of payment devices, payment environment, transaction relationship, payment behavior or its
His dimensional parameter, this specification is without limitation.
Referring to figure 2., this specification second embodiment additionally provides a kind of network payment risk assessment device, comprising:
Acquiring unit 201, it is for obtaining user network payment behavior data, the user network payment behavior data are defeated
Enter into risk probability Function generator 202；
Risk probability Function generator 202 calculates payment risk concentration for inputting the user network payment behavior data
Value, and export the payment risk concentration value；
Assessment unit 203, the payment risk concentration value for being exported based on the risk probability Function generator, assesses the use
The risk of family network payment behavior.
Specifically, in the present embodiment, network payment risk assessment device can be set in the server, also can be set
In terminal device, such as mobile phone, ipad, tablet computer, laptop equipment, it can also be the equipment such as desktop computer, certainly
It can also be other electronic equipments, here, this specification is with no restrictions.Network payment risk assessment device carries out network payment wind
The method nearly assessed is described in detail in aforementioned first embodiment, here, this embodiment is not repeated.
As a kind of optional embodiment, the risk probability Function generator 202 further comprises,
Payment risk concentration value computing unit obtains pair for calculating the user network payment behavior data
Answer the payment risk concentration value of each payment behavior data.
The assessment unit 203 further comprises:
Threshold curve computing unit, for that can be stood a loss based on the payment risk concentration value and preset maximum
Value, is calculated the payment decision-making value curve based on different scores；
Risk threshold value determination unit is paid for corresponding to the user network by the payment decision-making value curve acquisition
The risk threshold value of behavioral data；
Comparing unit, for the risk threshold value and the payment amount in corresponding user network payment behavior data；
It wherein, can also include default loss value cell in assessment unit 203, for corresponding to different payment risk concentration
Value, default maximum can stand a loss value；Further, the default maximum value that can stand a loss is defeated divided by risk probability Function generator
Payment risk concentration value out obtains the payment decision-making value curve based on different scores.
The assessment unit 203 is further used for, can unit based on the comparison comparison result, assess it is one or
The risk of multiple user network payment behaviors.
The comparing unit further comprises:
Risk judgment unit assesses the use if being greater than the corresponding risk threshold value for the payment amount
There are risks for family network payment behavior；Or it if the payment amount is less than or equal to the corresponding risk threshold value, assesses
Risk is not present in the user network payment behavior.
The risk probability Function generator 202 is that the pre- history payment risk transaction data that first passes through carries out model training acquisition.
The risk probability Function generator 202 further comprises:
Model training unit, for obtaining history payment risk transaction data, history payment risk transaction data includes black
Sample data and Fei Hei sample data, such as: the transaction data of occurrence risk is labeled as black sample data, non-occurrence risk
Transaction data is labeled as non-black sample data, quantifies mould based on the black sample data and Fei Hei sample data training payment risk
Type；
Iunction for curve unit, for being based on the payment risk quantitative model, curve matching goes out an exponential function,
Setting unit, for setting function used in the risk probability Function generator for the exponential function.
The risk probability Function generator 202 further comprises:
Sample score value unit, for being based on the payment risk quantitative model to each black sample data and Fei Hei sample number
According to giving a mark, a sample score value is respectively obtained；
Coordinate system unit, for by each sample award indicators to x-axis, it to be black under this score value of various kinds for marking corresponding y-axis
The risk concentration of concentration of specimens ratio value, i.e. quantization strategy under the sample score value；
The iunction for curve unit is further used for carrying out curve fitting to the mark point in the coordinate system, obtain
To the exponential function.
The black concentration of specimens ratio value is black sample data volume/(black sample data volume+non-black sample data volume).
It is described that payment risk quantitative model is trained based on the black sample data and Fei Hei sample data, further comprise:
Training parameter includes one or more of payment devices, payment environment, transaction relationship, payment behavior.
Optionally, the assessment unit 203 further comprises:
Unit is bothered, to the user network payment behavior evaluated there are risk, output prompt carries out core to user identity
It looks into.
Risk assessment is carried out specifically to one or more user's payment behavior data for example, currently there are two user network branch
Behavior A (100 yuan) and B (10000 yuan) are paid, payment platform needs to utilize the network payment risk assessment device pair in the present embodiment
Current there are two user network payment behavior A (100 yuan) and (10000 yuan) progress risk assessment of B, wherein pays to two
It is expected that maximum can stand a loss, value is 80 yuan.The risk score of payment behavior A is 8.2 points, and the risk score of payment behavior B is
5.3 point.Calculating the risk concentration value that the risk concentration value of A is 50%, B by risk probability Function generator is 10%.
Thus obtain A risk threshold value be 80 divided by 50% be 160, B risk threshold value be 80 divided by 10% be 800.Than
Compared with risk threshold value and corresponding payment amount, the payment amount 100 of A is less than risk threshold value 160, then assesses the user network branch
Risk is not present in the behavior of paying, and does not need output prompt, completes payment transaction, and the payment amount 10000 of B is greater than corresponding risk
Threshold value 800, then assessing the user network payment behavior, there are risks, then need to bother output prompt, carry out identity to user
It veritifies.
This specification 3rd embodiment additionally provides a kind of server, including memory 402, processor 401 and is stored in
On memory 402 and the computer program that can run on processor 401, the processor 401 are realized when executing described program
The step of network payment methods of risk assessment described previously.For ease of description, it illustrates only related to this specification embodiment
Part, it is disclosed by specific technical details, please refer to this specification embodiment method part.The server, can be including
The server apparatus that various electronic equipments are formed, PC computer, network Cloud Server or even mobile phone, tablet computer, PDA
(Personal Digital Assistant, personal digital assistant), POS (Point of Sales, point-of-sale terminal), vehicle mounted electric
The server capability being arranged on any electronic equipment such as brain, desktop computer.
Specifically, the server composed structure frame relevant to the technical solution of this specification embodiment offer shown in Fig. 4
Figure, it will include one represented by processor 401 or more that bus 400, which may include the bus and bridge of any number of interconnection,
The various circuits for the memory that a processor and memory 402 represent link together.Bus 400 can also such as will be set periphery
Various other circuits of standby, voltage-stablizer and management circuit or the like link together, and these are all it is known in the art,
Therefore, it will not be further described herein.Bus interface 403 bus 400 and receiver and/or transmitter 404 it
Between interface is provided, receiver and/or transmitter 404 can be separately independent receiver or transmitter and be also possible to the same member
Part such as transceiver, provides the unit for communicating over a transmission medium with various other devices.Processor 401 is responsible for management bus
400 and common processing, and memory 402 can be used for the used data when executing operation of storage processor 401.
Based on this understanding, this specification realizes all or part of the process in the method for above-mentioned first embodiment,
Relevant hardware can be instructed to complete by computer program, it is computer-readable that the computer program can be stored in one
In storage medium, the computer program is when being executed by processor, it can be achieved that the step of above-mentioned each embodiment of the method.Wherein,
The computer program includes computer program code, and the computer program code can be source code form, object identification code
Form, executable file or certain intermediate forms etc..The computer-readable medium may include: that can carry the computer
Any entity or device of program code, medium, USB flash disk, mobile hard disk, magnetic disk, CD, computer storage, read-only memory
(ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, electricity
Believe signal and software distribution medium etc..It should be noted that the content that the computer-readable medium includes can be according to department
Make laws in method administrative area and the requirement of patent practice carry out increase and decrease appropriate, such as in certain jurisdictions, according to legislation and
Patent practice, computer-readable medium do not include electric carrier signal and telecommunication signal.
Although the preferred embodiment of this specification has been described, once a person skilled in the art knows basic wounds
The property made concept, then additional changes and modifications may be made to these embodiments.So the following claims are intended to be interpreted as includes
Preferred embodiment and all change and modification for falling into this specification range.
Obviously, those skilled in the art can carry out various modification and variations without departing from this specification to this specification
Spirit and scope.In this way, if these modifications and variations of this specification belong to this specification claim and its equivalent skill
Within the scope of art, then this specification is also intended to include these modifications and variations.
Claims (18)
1. a kind of network payment methods of risk assessment, comprising:
User network payment behavior data are obtained, the user network payment behavior data are input to risk probability Function generator
In；
Based on the payment risk concentration value of risk probability Function generator output, the wind of the user network payment behavior is assessed
Danger.
2. the method as described in claim 1, the payment risk concentration value based on risk probability Function generator output, are commented
Estimate the risk of the user network payment behavior, comprising:
According to the risk probability Function generator, the user network payment behavior data are calculated, counterpart expenditure row is obtained
For the payment risk concentration value of data；
The risk of the user network payment behavior is assessed based on the payment risk concentration value.
3. method according to claim 2, described to assess the user network paying bank based on the payment risk concentration value
For risk, comprising:
It can be stood a loss value based on the payment risk concentration value and preset maximum, the branch based on different scores is calculated
Pay decision-making value curve；
The risk threshold value of the user network payment behavior data is corresponded to by the payment decision-making value curve acquisition；
Compare the risk threshold value and the payment amount in corresponding user network payment behavior data, assesses the user network branch
The risk for the behavior of paying.
4. method as claimed in claim 3, the risk threshold value in corresponding user network payment behavior data
Payment amount, assess the risk of the user network payment behavior, comprising:
If the payment amount is greater than the corresponding risk threshold value, assessing the user network payment behavior, there are wind
Danger；Or
If the payment amount is less than or equal to the corresponding risk threshold value, the user network payment behavior is assessed not
There are risks.
5. the method as described in claim 1, comprising: the risk probability Function generator first passes through history payment risk number of deals in advance
According to progress model training acquisition, comprising:
History payment risk transaction data is obtained, the history payment risk transaction data includes black sample data and Fei Hei sample
Data, based on the black sample data and Fei Hei sample data training payment risk quantitative model；
Based on the payment risk quantitative model, curve matching goes out an exponential function, is set as the risk probability Function generator
Function used.
6. method as claimed in claim 5, described to be based on the payment risk quantitative model, curve matching goes out an index letter
Number, is set as function used in the risk probability Function generator, comprising:
It is given a mark based on the payment risk quantitative model to each black sample data and Fei Hei sample data, respectively obtains one
A sample score value；
Coordinate system is established, by each sample award indicators to x-axis, marking corresponding y-axis is the black concentration of specimens under this score value of various kinds
Ratio value；
It carries out curve fitting to the mark point in the coordinate system, obtains an exponential function, be set as the risk probability letter
Number device.
7. method as claimed in claim 5, during the training payment risk quantitative model, setting training parameter is branch
Dispensing apparatus parameter, payment environment parameter, transaction relationship parameter, one or more combinations in payment behavior parameter.
8. the method as described in claim 1, which is characterized in that the assessment user network payment behavior risk it
Afterwards, further includes:
To the user network payment behavior evaluated there are risk, user identity is verified in output prompt.
9. a kind of network payment risk assessment device, comprising:
The user network payment behavior data are input to wind for obtaining user network payment behavior data by acquiring unit
In dangerous probability function device；
Risk probability Function generator calculates payment risk concentration value, and defeated for inputting the user network payment behavior data
The payment risk concentration value out；
Assessment unit, the payment risk concentration value for being exported based on the risk probability Function generator, assesses the user network
The risk of payment behavior.
10. device as claimed in claim 9, the risk probability Function generator further comprise,
Payment risk concentration value computing unit obtains corresponding branch for calculating the user network payment behavior data
Pay the payment risk concentration value of behavioral data.
11. device as claimed in claim 10, the assessment unit, further comprise:
Threshold curve computing unit is counted for that can be stood a loss value based on the payment risk concentration value and preset maximum
Calculation obtains the payment decision-making value curve based on different scores；
Risk threshold value determination unit, for corresponding to the user network payment behavior by the payment decision-making value curve acquisition
The risk threshold value of data；
Comparing unit, for the risk threshold value and the payment amount in corresponding user network payment behavior data；
The assessment unit is further used for, based on the comparison the comparison result of unit, assesses the user network paying bank
For risk.
12. device as claimed in claim 11, the comparing unit, further comprise:
Risk judgment unit assesses the user network if being greater than the corresponding risk threshold value for the payment amount
There are risks for network payment behavior；Or if the payment amount be less than or equal to the corresponding risk threshold value, assessment described in
Risk is not present in user network payment behavior.
13. device as claimed in claim 9, the risk probability Function generator first pass through in advance history payment risk transaction data into
Row model training obtains, comprising:
Model training unit, for obtaining history payment risk transaction data, the history payment risk transaction data includes black
Sample data and Fei Hei sample data, based on the black sample data and Fei Hei sample data training payment risk quantitative model；
Iunction for curve unit, for being based on the payment risk quantitative model, curve matching goes out an exponential function；
Setting unit, for setting function used in the risk probability Function generator for the exponential function.
14. device as claimed in claim 13, the risk probability Function generator further comprises:
Sample score value unit, for based on the payment risk quantitative model to each black sample data and Fei Hei sample data into
Row marking, respectively obtains a sample score value；
Coordinate system unit, for by each sample award indicators to x-axis, marking corresponding y-axis to be the black sample under this score value of various kinds
Concentration ratio value；
The iunction for curve unit is further used for carrying out curve fitting to the mark point in the coordinate system, obtains institute
State exponential function.
15. method as claimed in claim 14, training payment risk quantitative model, further comprise: setting training parameter is
Payment devices parameter, payment environment parameter, transaction relationship parameter, one or more combinations in payment behavior parameter.
16. method as claimed in claim 9, the assessment unit further comprises:
Unit is bothered, to the user network payment behavior evaluated there are risk, user identity is verified in output prompt.
17. a kind of server, including processor and memory:
The memory is used to store the program that perform claim requires any one of 1 to 8 the method；
The processor is configured to for executing the program stored in the memory.
18. a kind of computer readable storage medium, is stored with computer program, which is characterized in that the program is held by processor
The step of any one of claim 1 to 8 the method is realized when row.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810714606.XA CN109063965A (en) | 2018-06-29 | 2018-06-29 | A kind of network payment methods of risk assessment, device and server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810714606.XA CN109063965A (en) | 2018-06-29 | 2018-06-29 | A kind of network payment methods of risk assessment, device and server |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109063965A true CN109063965A (en) | 2018-12-21 |
Family
ID=64818893
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810714606.XA Pending CN109063965A (en) | 2018-06-29 | 2018-06-29 | A kind of network payment methods of risk assessment, device and server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109063965A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109794066A (en) * | 2018-12-28 | 2019-05-24 | 广州卓动信息科技有限公司 | Game payment means of defence, equipment, medium and system based on big data |
| CN110675252A (en) * | 2019-09-29 | 2020-01-10 | 北京市商汤科技开发有限公司 | Risk assessment method and device, electronic equipment and storage medium |
| WO2020135242A1 (en) * | 2018-12-25 | 2020-07-02 | 瞬联软件科技（北京）有限公司 | Method and system for displaying security risk value of online payment by color |
| CN113516480A (en) * | 2021-08-19 | 2021-10-19 | 支付宝(杭州)信息技术有限公司 | Payment risk identification method, device and equipment |
| CN113516480B (en) * | 2021-08-19 | 2024-04-26 | 支付宝(杭州)信息技术有限公司 | Payment risk identification method, device and equipment |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101976419A (en) * | 2010-10-19 | 2011-02-16 | 中国工商银行股份有限公司 | Processing method and system for risk monitoring and controlling of transaction data |
| CN102117459A (en) * | 2010-01-06 | 2011-07-06 | 阿里巴巴集团控股有限公司 | Risk control system and method |
| CN102722814A (en) * | 2012-06-01 | 2012-10-10 | 汪德嘉 | Self-adaption controllable management system for cheat risk of online transaction |
| US20160104163A1 (en) * | 2014-10-14 | 2016-04-14 | Jpmorgan Chase Bank, N.A. | ldentifying Potentially Risky Transactions |
| CN105550876A (en) * | 2015-10-30 | 2016-05-04 | 东莞酷派软件技术有限公司 | Mobile payment monitoring method and system and intelligent terminal |
| CN105590055A (en) * | 2014-10-23 | 2016-05-18 | 阿里巴巴集团控股有限公司 | Method and apparatus for identifying trustworthy user behavior in network interaction system |
| CN105719033A (en) * | 2014-12-02 | 2016-06-29 | 阿里巴巴集团控股有限公司 | Method and device for identifying risk in object |
| WO2018035373A1 (en) * | 2016-08-17 | 2018-02-22 | Fair Isaac Corporation | Customer transaction behavioral archetype analytics for cnp merchant transaction fraud detection |
| CN107767138A (en) * | 2017-10-20 | 2018-03-06 | 杭州呯嘭智能技术有限公司 | On-line payment is counter to cheat method and system |
| CN107798390A (en) * | 2017-11-22 | 2018-03-13 | 阿里巴巴集团控股有限公司 | A kind of training method of machine learning model, device and electronic equipment |
| CN107844977A (en) * | 2017-10-09 | 2018-03-27 | 中国银联股份有限公司 | A kind of method of payment and device |
| CN108133372A (en) * | 2017-12-28 | 2018-06-08 | 阿里巴巴集团控股有限公司 | Assess the method and device of payment risk |
-
2018
- 2018-06-29 CN CN201810714606.XA patent/CN109063965A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102117459A (en) * | 2010-01-06 | 2011-07-06 | 阿里巴巴集团控股有限公司 | Risk control system and method |
| CN101976419A (en) * | 2010-10-19 | 2011-02-16 | 中国工商银行股份有限公司 | Processing method and system for risk monitoring and controlling of transaction data |
| CN102722814A (en) * | 2012-06-01 | 2012-10-10 | 汪德嘉 | Self-adaption controllable management system for cheat risk of online transaction |
| CN102722814B (en) * | 2012-06-01 | 2015-08-19 | 苏州通付盾信息技术有限公司 | A kind of self-adaptation controllable management system of online transaction risk of fraud |
| US20160104163A1 (en) * | 2014-10-14 | 2016-04-14 | Jpmorgan Chase Bank, N.A. | ldentifying Potentially Risky Transactions |
| CN105590055A (en) * | 2014-10-23 | 2016-05-18 | 阿里巴巴集团控股有限公司 | Method and apparatus for identifying trustworthy user behavior in network interaction system |
| CN105719033A (en) * | 2014-12-02 | 2016-06-29 | 阿里巴巴集团控股有限公司 | Method and device for identifying risk in object |
| CN105550876A (en) * | 2015-10-30 | 2016-05-04 | 东莞酷派软件技术有限公司 | Mobile payment monitoring method and system and intelligent terminal |
| WO2017071147A1 (en) * | 2015-10-30 | 2017-05-04 | 宇龙计算机通信科技(深圳)有限公司 | Mobile payment monitoring method and system, and intelligent terminal |
| WO2018035373A1 (en) * | 2016-08-17 | 2018-02-22 | Fair Isaac Corporation | Customer transaction behavioral archetype analytics for cnp merchant transaction fraud detection |
| CN107844977A (en) * | 2017-10-09 | 2018-03-27 | 中国银联股份有限公司 | A kind of method of payment and device |
| CN107767138A (en) * | 2017-10-20 | 2018-03-06 | 杭州呯嘭智能技术有限公司 | On-line payment is counter to cheat method and system |
| CN107798390A (en) * | 2017-11-22 | 2018-03-13 | 阿里巴巴集团控股有限公司 | A kind of training method of machine learning model, device and electronic equipment |
| CN108133372A (en) * | 2017-12-28 | 2018-06-08 | 阿里巴巴集团控股有限公司 | Assess the method and device of payment risk |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020135242A1 (en) * | 2018-12-25 | 2020-07-02 | 瞬联软件科技（北京）有限公司 | Method and system for displaying security risk value of online payment by color |
| CN109794066A (en) * | 2018-12-28 | 2019-05-24 | 广州卓动信息科技有限公司 | Game payment means of defence, equipment, medium and system based on big data |
| CN110675252A (en) * | 2019-09-29 | 2020-01-10 | 北京市商汤科技开发有限公司 | Risk assessment method and device, electronic equipment and storage medium |
| CN113516480A (en) * | 2021-08-19 | 2021-10-19 | 支付宝(杭州)信息技术有限公司 | Payment risk identification method, device and equipment |
| CN113516480B (en) * | 2021-08-19 | 2024-04-26 | 支付宝(杭州)信息技术有限公司 | Payment risk identification method, device and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107808289B (en) | Electronic payment platform, control method and device | |
| CN104965844A (en) | Information processing method and apparatus | |
| CN109242261A (en) | Save the method and terminal device of risk from damage based on big data assessment | |
| US10043165B2 (en) | Cloud service integration pay trading system | |
| Shaikh et al. | Consumers' perceptions of mobile banking continuous usage in Finland and South Africa | |
| CN109063965A (en) | A kind of network payment methods of risk assessment, device and server | |
| CN107590546A (en) | A kind of hotel information processing system | |
| CN105744005A (en) | Client positioning and analyzing method and server | |
| CN107748952A (en) | Prestige checking method, device and storage medium based on consumer's risk control | |
| CN109685645A (en) | User credit methods of risk assessment and device, storage medium | |
| CN110941644B (en) | Policy data generation method, device, equipment and storage medium | |
| CN106033571A (en) | Trading method of electronic signature devices, electronic signature devices and trading system | |
| CN107798536A (en) | Credit line treating method and apparatus | |
| JP6883494B2 (en) | Used car assessment system | |
| US10637991B1 (en) | Systems and methods for intelligent routing call center solutions | |
| CN112150252A (en) | Credit-based service processing method and device | |
| CN107730215A (en) | Settlement of insurance claim on-line processing method and system | |
| CN111192150B (en) | Method, device, equipment and storage medium for processing vehicle danger-giving agent service | |
| CN114971017A (en) | Bank transaction data processing method and device | |
| CN112085469B (en) | Data approval method, device, equipment and storage medium based on vector machine model | |
| CN112950221B (en) | Method and device for establishing wind control model and risk control method and device | |
| CN114757497A (en) | Technology trust-increasing method for science and technology enterprise, device, equipment and medium thereof | |
| CN114723206A (en) | Asset data processing method, computer equipment and readable storage medium | |
| KR20110064119A (en) | Payment processing service system and payment processing service method | |
| CN109242274A (en) | A kind of assessment method of vehicle, apparatus and system |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200925 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant after: Innovative advanced technology Co.,Ltd. Address before: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant before: Advanced innovation technology Co.,Ltd. Effective date of registration: 20200925 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant after: Advanced innovation technology Co.,Ltd. Address before: A four-storey 847 mailbox in Grand Cayman Capital Building, British Cayman Islands Applicant before: Alibaba Group Holding Ltd. |
|
| TA01 | Transfer of patent application right | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181221 |
|
| RJ01 | Rejection of invention patent application after publication |