Summary of the invention
This specification embodiment provides a kind of signing risk quantification method, withholds risk quantification method, device and equipment.Solution
Existing signing of having determined withholds link and does not have systematic risk control solution problem.
In order to solve the above technical problems, this specification embodiment is achieved in that
A kind of signing risk quantification method that this specification embodiment provides, this method comprises:
Obtain the preceding historical information of payment account signing and/or payment account signing information instantly;
Extract the characteristic value of historical information before the payment account is contracted and/or the payment account signing information instantly
Characteristic value;
Historical information before the characteristic value of historical information and the payment account are contracted before being contracted according to the payment account
Weight and/or the payment account signing weight of the characteristic value of information and payment account signing information instantly instantly, obtain
To signing risk quantification point.
One kind that this specification embodiment provides withholds risk quantification method, this method comprises:
Obtain at least one of payment account and facility information, environmental information and the consumption information of merchant account;
By at least one of the facility information of the payment account, environmental information and consumption information and the merchant account
At least one of corresponding facility information, environmental information and consumption information are compared, and obtain facility information comparison result, ring
At least one of border information comparison result and consumption information comparison result;
Extract at least one in the facility information comparison result, environmental information comparison result and consumption information comparison result
The characteristic value of person;
According at least one in the facility information comparison result, environmental information comparison result and consumption information comparison result
The characteristic value of person and its corresponding weight obtain withholding risk quantification point.
A kind of signing risk quantification device that this specification embodiment provides, the device include: to obtain module, extraction module
With acquisition module;
The acquisition module, for obtaining the preceding historical information of payment account signing and/or payment account signing information instantly;
The extraction module, for extracting the characteristic value and/or the payment of historical information before the payment account is contracted
The characteristic value of account signing information instantly;
The acquisition module, characteristic value and the payment account for historical information before being contracted according to the payment account
The characteristic value of information and payment account signing are worked as instantly for the weight of historical information and/or payment account signing before contracting
The weight of lower information obtains signing risk quantification point.
One kind that this specification embodiment provides withholds risk quantification device, which includes: acquisition module, compares mould
Block, extraction module and acquisition module;
The acquisition module, for obtaining facility information, environmental information and the consumption information of payment account and merchant account
At least one of;
The comparison module, for by the facility information of the payment account, environmental information and consumption information at least
At least one of one facility information corresponding with the merchant account, environmental information and consumption information are compared, and are obtained
At least one of facility information comparison result, environmental information comparison result and consumption information comparison result;
The extraction module, for extracting the facility information comparison result, environmental information comparison result and consumption information
The characteristic value of at least one of comparison result;
The acquisition module, for according to the facility information comparison result, environmental information comparison result and consumption information
The characteristic value of at least one of comparison result and its corresponding weight obtain withholding risk quantification point.
A kind of signing risk quantification equipment that this specification embodiment provides, comprising: memory and processor, it is described to deposit
Reservoir stores program, and is configured to execute above-mentioned signing risk quantification method by the processor.
One kind that this specification embodiment provides withholds risk quantification equipment, comprising: memory and processor, it is described to deposit
Reservoir stores program, and is configured to be executed by the processor and above-mentioned withholds risk quantification method.
At least one above-mentioned technical solution that this specification embodiment uses can reach following the utility model has the advantages that having erected
Whole air control frame;The experience for weakening people, carries out risk identification not against the experience of expert;The quantization for obtaining signing and withholding
While dividing, the signing portrait of user is given;The double-point information of payment mechanism and trade company is compared, collaboration is played and makees
With generating more data values.
Specific embodiment
This specification embodiment provides a kind of signing risk quantification method, withholds risk quantification method, apparatus and equipment.
In order to make those skilled in the art more fully understand the technical solution in this specification, below in conjunction with this explanation
Attached drawing in book embodiment is clearly and completely described the technical solution in this specification embodiment, it is clear that described
Embodiment be merely a part but not all of the embodiments of the present application.Based on this specification embodiment, this field
Those of ordinary skill's every other embodiment obtained without creative efforts, all should belong to the application
The range of protection.
Fig. 1 is a kind of flow diagram for signing risk quantification method that this specification embodiment provides, process signal
Figure includes:
Step 105, the preceding historical information of payment account signing and/or payment account signing information instantly are obtained;
In this specification embodiment, the executing subject of the step can set for such as mobile phone, tablet computer, PC terminal
It is standby, or server end.
In this specification embodiment, historical information includes payment account history signing habit, branch before payment account is contracted
It pays a bill at least one of identity before conflict and payment account are contracted before operation, payment account signing before the signing of family;Payment account
Instantly information includes payment account signing time segment information, payment account signing channel information, payment account signing equipment for signing
At least one of information and payment account signing environmental information.In practical applications, payment account contract before historical information and
Instantly information is not limited to above- mentioned information for payment account signing.Wherein, signing channel information include short message certification, finger print identifying and
At least one of face authentication;Facility information of contracting includes device operating system and/or device model;Signing environmental information packet
Include IP world and/or LBS environment.
Further, in this specification embodiment, payment account history signing habit includes that payment account is contracted
Whether there is or not signings to withhold history and historical behavior performance under same merchant account for the preference and/or payment account for withholding consumption;Branch
The preceding operation of family signing of paying a bill includes that payment account changing in special time period ties up mobile phone number, payment account in special time period
Interior changes at least one of the deletion record number of close number and payment account in special time period;Before payment account signing
Conflict jumps the equipment of performance and payment account in special time period including IP of the payment account in special time period and jumps
Performance;Identity includes whether payment account be easy in the high-risk list of signing and/or payment account before payment account is contracted
Stolen crowd.Specifically, in this specification embodiment, above-mentioned special time period include but is not limited to 00:00-07:00 and
Signing first 3 minutes to when contracting.
Step 110, historical information characteristic value and/or the payment account before the payment account is contracted is extracted to contract instantly
Information characteristics value;
In this specification embodiment, historical information characteristic value and/or branch before being contracted using WOE model extraction payment account
It pays a bill family signing information characteristics value instantly.In practical applications, the payment account extracted carries out the preference that signing withholds consumption
Spending characteristic value is 6, and payment account has signing to withhold history and historical behavior performance 5 under same merchant account, and payment account is 01:
It is 3 that changing in the 00-03:00 period, which ties up 4 sub-eigenvalue of mobile phone, and payment account changes in 3 minutes before signing and ties up 1 spy of mobile phone
Value indicative is 1, and it is 2 that payment account changes close 4 sub-eigenvalue within the 01:00-03:00 period, 3 minutes before signing of payment account
Inside changing close 1 sub-eigenvalue is 1, and 4 several characteristic values of deletion record of the payment account within the 01:00-03:00 period are 5, payment
It is 2 that IP of the account within the 01:00-03:00 period, which jumps 2 sub-eigenvalues, and payment account is within the 01:00-03:00 period
It is 2 that equipment, which jumps 2 sub-eigenvalues, and payment account is 3 in high-risk name single eigenvalue of contracting, and payment account is that easily stolen crowd is special
Value indicative is 3, and it is 3 that the payment account signing time, which is 02:30 characteristic value, and it is 0 that payment account signing channel, which is finger print identifying characteristic value,
It is 1 that payment account signing equipment mobile phone, which is iPhone6 characteristic value, and payment account signing environment LBS information is that Beijing characteristic value is
1。
Step 115, it is gone through before the characteristic value of historical information and payment account signing before being contracted according to the payment account
The weight of history information and/or the payment account signing characteristic value of information and payment account signing instantly information instantly
Weight obtains signing risk quantification point.
In this specification embodiment, by the characteristic value of historical information before the payment account signing of WOE model extraction and its
Multiplied result simultaneously is added to obtain first and value by corresponding multiplied by weight;Further, go out payment account using WOE model discrimination
It is greater than the characteristic value of corresponding first preset threshold before contracting in the characteristic value of historical information;And/or by the payment of WOE model extraction
Multiplied result the corresponding multiplied by weight of information and is added to obtain second and value by account signing instantly;Further, it utilizes
WOE model discrimination goes out the characteristic value that payment account signing is greater than corresponding second preset threshold in the characteristic value of information instantly;
In this specification embodiment, payment account carries out signing and withholds the first preset threshold of preference of consumption to be 3, branch
Paying a bill, to have signing to withhold history and historical behavior to show the first preset threshold under same merchant account be 3 at family, and payment account is in spy
Changing in section of fixing time and tying up the first preset threshold of mobile phone number is 3, and it is default that payment account changes close number first in special time period
Threshold value is 3, and payment account deletion record number first threshold in special time period is 3, and payment account is in special time period
The first preset threshold of IP number of hops be 1, equipment number of hops first preset threshold of the payment account in special time period
It is 2, payment account is 2 in high-risk the first preset threshold of list of contracting, and payment account is easily stolen the first preset threshold of crowd
It is 2.
In this specification embodiment, filters out and be greater than corresponding first preset threshold before contracting in the characteristic value of historical information
Payment account history signing habit, payment account signing before it is high-risk operation, payment account signing before it is high-risk conflict and branch pay a bill
High-risk identity before family is contracted.Specifically, filter out the result is that: payment account carries out signing and withholds the preference feature of consumption
Value is 6, and payment account has signing to withhold history and historical behavior performance 5 under same merchant account, and payment account is in 01:00-03:
It is 4 that changing in 00 period, which ties up 4 sub-eigenvalue of mobile phone, payment account 4 numbers of the deletion record within the 01:00-03:00 period
Characteristic value is 4, and it is 2 that IP of the payment account within the 01:00-03:00 period, which jumps 2 sub-eigenvalues, and payment account is high in signing
Name single eigenvalue of endangering is 3, and payment account is that easily stolen crowd characteristic value is 3.
In this specification embodiment, the payment account filtered out carries out signing and withholds the preference characteristic value of consumption to be 6
Corresponding weight is -5, and payment account has signing to withhold history and historical behavior 5 corresponding weights of performance under same merchant account
It is -3.2, it is 2.6 that it is 4 corresponding weights that payment account changing within the 01:00-03:00 period, which ties up 4 sub-eigenvalue of mobile phone, branch
4 several characteristic values of deletion record of the family within the 01:00-03:00 period of paying a bill are that 4 corresponding weights are 2.4, and payment account exists
It is 1.8 that it is 2 corresponding weights that IP in the 01:00-03:00 period, which jumps 2 sub-eigenvalues, and payment account is in high-risk list of contracting
Characteristic value be 3 corresponding weights be 3.3, payment account be easily stolen crowd characteristic value be 3 corresponding weights be 4.3.By WOE
The characteristic value that model discrimination goes out is input in Logic Regression Models, and multiplied result is simultaneously added by corresponding multiplied by weight, is obtained
It is 0.4 to first and value.
In this specification embodiment, it is 2 that the payment account signing time, which is the second preset threshold of 02:30, payment account label
It is 1 that about channel, which is the second preset threshold of finger print identifying, and it is 1 that payment account signing equipment mobile phone, which is the second preset threshold of iPhone6,
It is 1 that payment account signing environment LBS information, which is the second preset threshold of Beijing,.
In this specification embodiment, filters out and be greater than corresponding second preset threshold in the characteristic value of information instantly of contracting
It is 3 that the payment account signing time, which is 02:30 characteristic value,.
The characteristic value that WOE model discrimination goes out is input in Logic Regression Models, corresponding multiplied by weight and by phase
Multiply results added, obtaining second with value is 0.3.
In this specification embodiment, it be 3 corresponding weights is 0.1 that the payment account signing time, which is 02:30 characteristic value,.
In this specification embodiment, if historical information and information instantly of contracting before being signing that step 105 obtains,
In step 115, first is added with value 0.4 with second with value 0.3, obtains signing risk quantification and be divided into 0.7.If step 105 obtains
What is taken is historical information before contracting, then in step 115, obtains signing risk quantification and be divided into 0.4.If what step 105 obtained is
Instantly information obtains signing risk quantification and is divided into 0.3 then in step 115 for signing.
It is highly preferred that taking separately obtained signing risk quantification with 100.If what step 105 obtained is history letter before contracting
Information, then the signing risk quantification obtained are divided into 70 instantly for breath and signing;If what step 105 obtained is historical information before contracting,
The signing risk quantification then obtained is divided into 40;If what step 105 obtained is information instantly of contracting, obtained signing risk quantification
It is divided into 30.
Fig. 2 is a kind of flow diagram for withholding risk quantification method that this specification embodiment provides, process signal
Figure includes:
Step 205, at least one in facility information, environmental information and the consumption information of payment account and merchant account is obtained
Person;
In this specification embodiment, the executing subject of the step can set for such as mobile phone, tablet computer, PC terminal
It is standby, or server end.
In this specification embodiment, the facility information of payment account and merchant account includes device geographical location information
And/or use number of devices;Environmental information includes geographical location information and/or IP information;Consumption information includes order number, payment
At least one of time and the means of payment.
Step 210, by least one of the facility information of the payment account, environmental information and consumption information with it is described
At least one of the corresponding facility information of merchant account, environmental information and consumption information are compared, and obtain facility information ratio
At least one of relatively result, environmental information comparison result and consumption information comparison result;
In practical applications, made past 7 days with the associated account 1 of AppleStore and Alipay, account 2 and account 3
As shown in table 1 with number of devices situation, account 1 is 0 using number of devices difference, and account 2 is 3 using number of devices difference, and account 3 makes
It is 0 with number of devices difference.
It withholds risk quantification point and to withhold risk as shown in table 1.
Table 1
|
AppleStore |
Alipay |
Withhold risk quantification point |
Withhold risk |
Account 1 |
Use number of devices 1 |
Use number of devices 1 |
15 |
Safety is withheld |
Account 2 |
Use number of devices 4 |
Use number of devices 1 |
84 |
It is high-risk to withhold |
Account 3 |
Use number of devices 4 |
Use number of devices 4 |
28 |
It is suspicious to withhold |
In practical applications, in past one month and the associated account 4 of AppleStore and Alipay, account 5 and account 6
The LBS information occurred respectively is as shown in table 2, and account 4LBS information difference is 0, and account 5LBS information difference is 4, account 6LBS
Information difference is 0.
Table 2
|
AppleStore |
Alipay |
Withhold risk quantification point |
Withhold risk |
Account 4 |
Always used in a city |
Always used in a city |
20 |
Safety is withheld |
Account 5 |
It is used in 5 cities |
Always used in a city |
88 |
It is high-risk to withhold |
Account 6 |
It is used in 5 cities |
It is used in 5 cities |
30 |
It is suspicious to withhold |
In practical applications, disappeared respectively past three months with the associated account 7 of AppleStore and Alipay and account 8
The quantity for taking game products is as shown in table 3, and the number differences that account 7 consumes game products are 0, and account 8 consumes game products
Number differences are 15.
Table 3
Step 215, it extracts in the facility information comparison result, environmental information comparison result and consumption information comparison result
The characteristic value of at least one;
In this specification embodiment, it is using the characteristic value of number of devices difference 0 using account 1 in WOE model extraction table 1
6, account 2 is 4 using the characteristic value of number of devices difference 3, and account 3 is 6 using the characteristic value of number of devices difference 0;Utilize WOE model
The characteristic value for extracting account 4LBS information difference 0 in table 2 is 4, and the characteristic value of account 5LBS information difference 4 is 6, account 6LBS letter
The characteristic value for ceasing difference 0 is 4;It is using the characteristic value that account 7 in WOE model extraction table 3 consumes the number differences 0 of game products
3, the characteristic value that account 8 consumes the number differences 15 of game products is 8.
Step 220, according in the facility information comparison result, environmental information comparison result and consumption information comparison result
The characteristic value of at least one and its corresponding weight, obtain withholding risk quantification point.
In this specification embodiment, using Logic Regression Models by the characteristic value of the facility information comparison result and its
Multiplied result simultaneously is added to obtain first and value by corresponding multiplied by weight;Further, go out facility information using WOE model discrimination
It is greater than the characteristic value of corresponding first threshold in the characteristic value of comparison result;Described it will be greater than corresponding first using Logic Regression Models
Multiplied result is simultaneously added by the corresponding multiplied by weight of the characteristic value of threshold value, obtains first and value;And/or utilize logistic regression
Model is by the corresponding multiplied by weight of the characteristic value of the environmental information comparison result and is added multiplied result to obtain second
And value;Further, gone out using WOE model discrimination in the characteristic value of environmental information comparison result and be greater than the spy of corresponding second threshold
Value indicative;It by the corresponding multiplied by weight of the characteristic value for being greater than corresponding second threshold and will be multiplied using Logic Regression Models
Results added obtains second and value;And/or utilize Logic Regression Models by the characteristic value of the consumption information comparison result and its
Multiplied result simultaneously is added to obtain third and value by corresponding multiplied by weight;Further, go out consumption information using WOE model discrimination
It is greater than the characteristic value of corresponding third threshold value in the characteristic value of comparison result;It described will be greater than corresponding third using Logic Regression Models
Multiplied result is simultaneously added by the corresponding multiplied by weight of the characteristic value of threshold value, obtains third and value.
In this specification embodiment, account 1 is 1 using the first threshold of number of devices difference in table 1, and 2 use of account is set
The first threshold 2 of standby number difference, account 3 are 2 using the first threshold of number of devices difference;Account 4LBS information difference in table 2
First threshold is 2, and the first threshold of account 5LBS information difference is 3, and the first threshold of account 6LBS information difference is 2;In table 3
The first threshold that account 7 consumes the number differences of game products is 3, and account 8 consumes the first threshold of the number differences of game products
Value is 4.
In this specification embodiment, the information gone out using WOE model discrimination is as follows: account 1 uses number of devices difference 0
Characteristic value is 6, and account 2 is 4 using the characteristic value of number of devices difference 3, and account 3 is 6 using the characteristic value of number of devices difference 0;Account
The characteristic value of family 5LBS information difference 4 is 6, and the characteristic value of account 6LBS information difference 0 is 4;The number of the consumption game products of account 8
The characteristic value for measuring difference 15 is 8.
In this specification embodiment, in table 1 account 1 using the characteristic value of number of devices difference 0 be 6 corresponding weights be-
1.3, it is 4.7 that account 2, which is 4 corresponding weights using the characteristic value of number of devices difference 3, and account 3 uses the feature of number of devices difference 0
It is -1.8 that value, which is 6 corresponding weights,;It is 1.6 that the characteristic value of account 5LBS information difference 4, which is 6 corresponding weights, in table 2, account
The characteristic value of 6LBS information difference 0 is that 4 corresponding weights are -2.3;Account 8 consumes the feature of the number differences 15 of game products
Value is that 1 corresponding weight is 0.2.
The characteristic value that WOE model discrimination goes out is input in Logic Regression Models, corresponding multiplied by weight and by phase
Multiply results added, obtain first and value be 0.2, second and value is 0.4 and third and value are at least one of 0.2.If step
Facility information, environmental information and the consumption information of payment account and merchant account are obtained in 205 simultaneously, then by first and value,
Second and value be added with third and value, obtain withholding risk quantification and be divided into 0.8;If payment account is obtained in step 205 simultaneously
With the facility information and environmental information of merchant account, then first and value is added with second and value, obtains withholding risk quantification point
It is 0.6;If the environmental information and consumption information of payment account and merchant account are obtained in step 205 simultaneously, by the second He
Value is added with third and value, is obtained withholding risk quantification and is divided into 0.6;If payment account and trade company are obtained in step 205 simultaneously
First and value are then added with third and value by the facility information and consumption information of account, obtain withholding risk quantification and are divided into 0.3;
If only obtaining the facility information of payment account and merchant account in step 205, using first and value as withholding risk quantification
Point;If only obtaining the environmental information of payment account and merchant account in step 205, using second and value as withholding risk amount
Change and divides;If only obtaining the consumption information of payment account and merchant account in step 205, using third and value as withholding risk
Quantization point.
It is highly preferred that taking separately the obtained risk quantification that withholds with 100.As shown in fig. 6, withholding risk quantification point is greater than 60
Withhold and withheld to be high-risk, withheld as shown in fig. 7, withholding risk quantification point withholding between 30-60 to be suspicious, such as Fig. 8 institute
Show, withholds risk quantification point withholding to withhold safely less than 30.
Fig. 3 is that the general signing that this specification embodiment provides withholds air control frame, to realize that one of Fig. 1 contracts
One of risk quantification method and Fig. 2 withhold risk quantification method.For signing link, first layer L1 obtains payment account label
About preceding historical information and/or information instantly of contracting;Historical information module in second layer L2 and instantly information module utilize WOE mould
Type extracts the characteristic value of the information obtained, and filters out the characteristic value greater than preset threshold;It will be greater than using Logic Regression Models
Multiplied result is added by the characteristic value of preset threshold multiplied by its corresponding weight, is obtained the sum value;Signing wind is obtained according to value
Danger quantization point (falseness signing risk point);Third layer L3 will contract risk quantification point output to Alipay account and merchant account.
For link is withheld, first layer L1 is obtained in facility information, environmental information and the consumption information of payment account and merchant account
At least one, and the information that will acquire is made comparisons;Device conflict module, environmental warfare module and consumption punching in second layer L2
Prominent module utilizes the characteristic value of WOE model extraction comparison result, and filters out the characteristic value greater than preset threshold;It is returned using logic
Return model to will be greater than the characteristic value of preset threshold multiplied by its corresponding weight, and multiplied result is added, obtains the sum value;According to
Value obtains withholding risk quantification point (falseness withholds risk point);Third layer L3 will withhold risk quantification point output to Alipay account
And merchant account.
Fig. 4 is a kind of structural schematic diagram for signing risk quantification device that this specification embodiment provides, the structural representation
Figure includes: to obtain module 405, extraction module 410 and acquisition module 415;
The acquisition module 405 is believed instantly for obtaining historical information and/or payment account signing before payment account is contracted
Breath;
The extraction module 410, for extracting the characteristic value and/or the branch of historical information before the payment account is contracted
The characteristic value for family signing information instantly of paying a bill;Specifically for historical information before being contracted using payment account described in WOE model extraction
Characteristic value and/or payment account signing information instantly characteristic value.
The acquisition module 415, characteristic value and the payment for historical information before being contracted according to the payment account
The weight of historical information and/or the payment account signing characteristic value of information and the payment account label instantly before account is contracted
The about weight of information instantly obtains signing risk quantification point.
Further, historical information includes: payment account history signing habit, payment account before the payment account is contracted
At least one of identity before conflict and payment account are contracted before operation, payment account signing before signing;The payment account label
About information includes: payment account signing time segment information, payment account signing channel information, payment account signing equipment letter instantly
At least one of breath and payment account signing environmental information.
Further, the acquisition module 415, being specifically used for will be before payment account signing using Logic Regression Models
Multiplied result is simultaneously added to obtain first and value by the corresponding multiplied by weight of the characteristic value of historical information, and/or by the branch
Multiplied result the corresponding multiplied by weight of characteristic value of information and is added to obtain second and value by family signing of paying a bill instantly;According to
Described first obtains signing risk quantification point with value and/or described second and value.Still further, being directed to the payment account label
The characteristic value of about preceding historical information goes out to be greater than using WOE model discrimination the characteristic value of corresponding first preset threshold;It is returned using logic
Return model for the corresponding multiplied by weight of characteristic value for being greater than corresponding first preset threshold and be added multiplied result, obtains
To first and value;And/or the characteristic value for payment account signing information instantly, go out to be greater than using WOE model discrimination pair
Answer the characteristic value of the second preset threshold;Using Logic Regression Models by described greater than the characteristic value for corresponding to the second preset threshold and its
Multiplied result is simultaneously added by corresponding multiplied by weight, obtains second and value.
Fig. 5 is a kind of structural schematic diagram for withholding risk quantification device that this specification embodiment provides, the structural representation
Figure includes: to obtain module 505, comparison module 510, extraction module 515 and acquisition module 520;
The acquisition module 505, for obtaining facility information, environmental information and the consumption letter of payment account and merchant account
At least one of breath;
The comparison module 510, for by the facility information of the payment account, environmental information and consumption information extremely
At least one of few one facility information corresponding with the merchant account, environmental information and consumption information are compared, and are obtained
At least one of to facility information comparison result, environmental information comparison result and consumption information comparison result;
The extraction module 515, for extracting the facility information comparison result, environmental information comparison result and consumption letter
Cease the characteristic value of at least one of comparison result;
The acquisition module 520, for being believed according to the facility information comparison result, environmental information comparison result and consumption
The characteristic value and its corresponding weight for ceasing at least one of comparison result obtain withholding risk quantification point.
Further, the facility information includes: device geographical location information and/or using number of devices;The environment
Information includes: geographical location information and/or IP information;The consumption information includes: in order number, time of payment and the means of payment
At least one.
Further, it is specifically used for extracting the facility information comparison result, environmental information comparison result and consumption information
The characteristic value of at least one of comparison result.
Further, the acquisition module 520, specifically for the facility information is compared knot using Logic Regression Models
Multiplied result is simultaneously added to obtain first and value by the corresponding multiplied by weight of the characteristic value of fruit, and/or by the environmental information
Multiplied result simultaneously is added to obtain second and value by the corresponding multiplied by weight of the characteristic value of comparison result, and/or disappears described
Multiplied result is simultaneously added by the corresponding multiplied by weight of the characteristic value of charge information comparison result, obtains third and value;According to institute
First is stated to obtain withholding risk quantification point with value, described second and value and at least one of the third and value;Further,
For the characteristic value of the facility information comparison result, go out to be greater than the characteristic value of corresponding first threshold using WOE model discrimination;Benefit
With Logic Regression Models by the corresponding multiplied by weight of the characteristic value for being greater than corresponding first threshold and by multiplied result phase
Add, obtains first and value;And/or the characteristic value for the environmental information comparison result, go out to be greater than pair using WOE model discrimination
Answer the characteristic value of second threshold;Utilize the Logic Regression Models power that the characteristic value for being greater than corresponding second threshold is corresponding
Heavy phase multiplies and is added multiplied result, obtains second and value;And/or the characteristic value for the consumption information comparison result, benefit
Go out to be greater than the characteristic value of corresponding third threshold value with WOE model discrimination;It described will be greater than corresponding third threshold using Logic Regression Models
Multiplied result is simultaneously added by the corresponding multiplied by weight of the characteristic value of value, obtains third and value.
A kind of signing risk quantification equipment that this specification embodiment provides, comprising: memory and processor, it is described to deposit
Reservoir stores program, and is configured to be executed by the processor and obtains historical information and/or payment before payment account is contracted
Account signing information instantly;Extract the characteristic value of historical information and/or payment account signing before the payment account is contracted
Instantly the characteristic value of information;It is gone through before the characteristic value of historical information and payment account signing before being contracted according to the payment account
The weight of history information and/or the payment account signing characteristic value of information and payment account signing instantly information instantly
Weight obtains signing risk quantification point
One kind that this specification embodiment provides withholds risk quantification equipment, comprising: memory and processor, it is described to deposit
Reservoir stores program, and is configured to execute facility information, the ring for obtaining payment account and merchant account by the processor
At least one of border information and consumption information;It will be in the facility information of the payment account, environmental information and consumption information
At least one of at least one facility information corresponding with the merchant account, environmental information and consumption information are compared,
Obtain at least one of facility information comparison result, environmental information comparison result and consumption information comparison result;Described in extraction
The characteristic value of at least one of facility information comparison result, environmental information comparison result and consumption information comparison result;According to
The characteristic value of at least one of the facility information comparison result, environmental information comparison result and consumption information comparison result and
Its corresponding weight obtains withholding risk quantification point.
It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the present invention, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of computer, special purpose computer, Embedded Processor or other programmable data processing devices to generate one
A machine so that by the instruction that the processor of computer or other programmable data processing devices executes generate for realizing
The device for the function of being specified in one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
In a typical configuration, calculating equipment includes one or more processors (CPU), input/output interface, net
Network interface and memory.
Memory may include the non-volatile memory in computer-readable medium, random access memory (RAM) and/or
The forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM).Memory is computer-readable medium
Example.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer readable instructions, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase change memory (PRAM), static random access memory (SRAM), moves
State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable
Programmable read only memory (EEPROM), flash memory or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM),
Digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape magnetic disk storage or other magnetic storage devices
Or any other non-transmission medium, can be used for storage can be accessed by a computing device information.As defined in this article, it calculates
Machine readable medium does not include temporary computer readable media (transitory media), such as the data-signal and carrier wave of modulation.
It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability
It include so that the process, method, commodity or the equipment that include a series of elements not only include those elements, but also to wrap
Include other elements that are not explicitly listed, or further include for this process, method, commodity or equipment intrinsic want
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including element
There is also other identical elements in process, method, commodity or equipment.
The above is only the embodiments of this specification, are not limited to this specification.For those skilled in the art
For, this specification can have various modifications and variations.All any modifications made within the spirit and principle of this specification,
Equivalent replacement, improvement etc., should be included within the scope of the claims of this specification.