CN102117459A - Risk control system and method - Google Patents
Risk control system and method Download PDFInfo
- Publication number
- CN102117459A CN102117459A CN2010100014792A CN201010001479A CN102117459A CN 102117459 A CN102117459 A CN 102117459A CN 2010100014792 A CN2010100014792 A CN 2010100014792A CN 201010001479 A CN201010001479 A CN 201010001479A CN 102117459 A CN102117459 A CN 102117459A
- Authority
- CN
- China
- Prior art keywords
- risk
- data
- value
- probability
- model
- 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
Images
Abstract
The invention provides a risk control system and method for monitoring risks of transaction data in a network transaction platform. The method comprises the following steps of: (1) acquiring transaction data; (2) calculating a risk value of the transaction according to the transaction data; (3) screening out risk data according to the risk value and the preset risk rules; and (4) freezing the operation authority of the screened risk data. According to the system and the method, the risk data can be intercepted with pertinence, and the interception efficiency and the accuracy of the risk data are effectively ensured.
Description
Technical field
The application relates to the network monitoring technology, particularly can guarantee a kind of risk control system and the method thereof of risk funds interception efficient.
Background technology
Along with the fast development of internet, various forms ofly continue to bring out, as the online service business based on the internet such as online bank, on-line payment, online shopping at line service.People accepted and more and more custom carry out various commercial activitys on the net.
Because the internet is the network of an opening, anyone can be connected on the internet Anywhere easily the world.The internet has also brought risk when facilitating to the human lives.Especially in recent years, along with rapid development of electronic commerce, network finance crime and online swindle constantly occurred, and this also becomes the focus that people pay close attention to.Therefore, if can not carry out effective risk monitoring and control to online operation system, the consumer just can't feel at ease to use these at line service, relates in particular to the business of treasury trade.
In order to be provided a better environment at line service, the common method that adopts is to formulate a risk rule, and by risk rule online business datum is monitored.As China national Patent Office application number is that the patented claim of 200610066301.X has proposed a kind of method and system to online service risk monitoring, sees also Fig. 1, and its method may further comprise the steps:
S101 catches customer parameter and business datum and is packaged into event object.
S103 analyzes event object according to risk rule.
Whether S105 exists risk according to the analysis result decision event, if exist risk then to carry out step S107.
S107 generates risk record according to event object.
S109 determines that go forward side by side sector-style danger of risk processing mode handles.
Said method is found out the risk object in line service by risk rule and is handled, for example work as risk rule and be defined as " if dealing money is greater than 400 yuan; transaction interception so ",, conclude the business so and will be blocked and generate risk record then in case transaction meets rule condition.Therefore the effective risk of filtering in line service is for the user provides a good network environment.
But existing risk monitoring and control method still exists some problems:
1, risk rule is normally by manually setting according to business experience, need cost great amount of manpower and time cost, particularly under the very big situation of network traffic, it is particularly difficult that the summing-up meeting of experience becomes, thereby just need to drop into more staff and time, bring extra financial burden can for the operator of network trading platform.
2, because human judgement unavoidably can have subjectivity to a certain degree, be difficult to all sidedly various potential risks situations all be taken into account, make risk rule have one-sidedness, leaked some implicit risk data easily, cause the loss of Fail Transaction even fund.
Summary of the invention
The application's purpose provides a kind of risk control system, to solve the problem of existing network risks method for supervising cost height, weak effect.
The application's purpose in addition provides a kind of risk control method, to solve the problem of existing network risks method for supervising cost height, weak effect.
The application proposes a kind of risk control system, is used for the transaction data of network trading platform is carried out risk monitoring and control, comprises computing unit, interception unit and processing unit.Computing unit links to each other with network trading platform, is used for transaction data is monitored, and calculates the value-at-risk of transaction data.Interception unit links to each other with computing unit, is used for filtering out risk data according to value-at-risk and predefined risk rule.Processing unit links to each other with interception unit and network trading platform respectively, is used to the operating right of the risk data freezing to filter out.
According to the described risk control system of the application's preferred embodiment, it also comprises the model training unit, and itself and computing unit are used to make up risk model.
According to the described risk control system of the application's preferred embodiment, it also comprises the case database, and it links to each other with processing unit, is used to deposit risk data.
According to the described risk control system of the application's preferred embodiment, the model training unit further comprises data acquisition subelement and comparer unit again.The data acquisition subelement links to each other with database in case database and the network trading platform respectively, is used to gather a certain amount of normal data and risk data.The comparer unit links to each other with the data acquisition subelement, is used for normal data and risk data are compared, and makes up risk model.
According to the described risk control system of the application's preferred embodiment, it also comprises the verification unit, and it is arranged between processing unit and the described case database, is used for the data of freezing are verified.
According to the described risk control system of the application's preferred embodiment, described computing unit further comprises value-at-risk computation subunit and risk probability computation subunit again.The value-at-risk computation subunit links to each other with described network trading platform and described model training unit respectively, is used for calculating according to described risk model the value-at-risk of transaction data.The risk probability computation subunit links to each other with described value-at-risk computation subunit, is used for according to described value-at-risk calculation risk probability, and the value of described risk probability is between 0 to 1.
According to the described risk control system of the application's preferred embodiment, during value-at-risk computation subunit calculation risk value according to following formula:
x=k1a1+k2a2+...+knan,
Wherein, x is a value-at-risk, and a1, a2...an are the discrete variable of various transaction data, and k1, k2...kn are the importance parameter of various transaction data.
According to the described risk control system of the application's preferred embodiment, during risk probability computation subunit calculation risk probability according to following formula:
y=e
x/(1+e
x),
Wherein, y is a risk probability, and x is a value-at-risk, and e is a natural constant.
The application proposes a kind of risk control method in addition, is used for the transaction data of network trading platform is carried out risk monitoring and control, and may further comprise the steps: (1) obtains transaction data.(2) calculate the value-at-risk that obtains this transaction according to described transaction data.(3) filter out risk data according to described value-at-risk and predefined risk rule.(4) freeze the operating right of the risk data that filters out.
According to the described risk control method of the application's preferred embodiment, calculate described value-at-risk and further may further comprise the steps again: (1) gathers a certain amount of normal data and risk data.(2) normal data and risk data are compared, and construct risk model.(3) calculate described value-at-risk by described risk model.
According to the described risk control method of the application's preferred embodiment, risk model is:
x=k1a1+k2a2+...+knan,
Wherein, x is a value-at-risk, and a1, a2...an are the discrete variable of various transaction data, and k1, k2...kn are the importance parameter of various transaction data.
According to the described risk control method of the application's preferred embodiment, obtain further to comprise step after the value-at-risk: (1) according to described value-at-risk calculation risk probability, the value of described risk probability is between 0 to 1.(2) filter out risk data according to risk probability and predefined risk rule.
According to the described risk control method of the application's preferred embodiment, during the calculation risk probability specifically according to following formula:
y=e
x/(1+e
x),
Wherein, y is a risk probability, and x is a value-at-risk, and e is a natural constant.
According to the described risk control method of the application's preferred embodiment, the operating right that freezes risk data also comprises step afterwards: risk data is verified.
According to the described risk control method of the application's preferred embodiment, after being handled, risk data also further comprises step: the storage risk data, and for subsequent acquisition and inquiry.
With respect to prior art, the application's beneficial effect is:
1, the application be with the output of the risk model input as risk rule all the time, and the different output of risk model may refer to different risk judgment rules, can improve the effect of risk interception so greatly in the process of monitoring risk data.
2, the used risk model of the application is the autonomous structure of computing machine, with respect to the risk model of tradition with the artificial experience training, can avoid occurring in the model factor of subjectivity and one-sidedness, and with the basis of formation of data itself as model, some potential risks factors can be included in the computation process of model, improved the interception efficient of risk data effectively.
Certainly, arbitrary product of enforcement the application might not need to reach simultaneously above-described all advantages.
Description of drawings
Fig. 1 is the method flow diagram of a kind of method and system to the monitoring of online service risk of 200610066301.X for Patent Office of the People's Republic of China's application number;
Fig. 2 is a kind of example structure figure of the application's risk control system;
Fig. 3 is the another kind of example structure figure of the application's risk control system;
Fig. 4 is a kind of embodiment process flow diagram of the application's risk control method;
Fig. 5 trains a kind of embodiment process flow diagram of risk model for the application;
Fig. 6 is a kind of embodiment process flow diagram of the application's calculation risk probability.
Embodiment
The user often is to finish by network trading platform, as Taobao, Netease etc. when carrying out the network trading business.The application's risk control system is exactly to be used for the trading activity in the network trading platform is monitored, and filters out the transaction data with risk, and returns to network trading platform and carry out respective handling such as freezing of funds, to avoid the loss of user's property.And risk control system both can be a server of setting up separately, also can be a subsystem that is integrated in the network trading platform.
The application's main thought is to introduce the benchmark that risk model and risk rule two conceptions of species are used as judging risk data in risk control system respectively, and, realize risk data interception function efficiently with the input of the calculating of risk model output as risk rule.
Below in conjunction with accompanying drawing, specify the application.
See also Fig. 2, it is a kind of example structure figure of the application's risk control system.This risk control system 20 comprises model training unit 21, computing unit 22, interception unit 23 and processing unit 24.Computing unit 22 is connected to network trading platform 25, and model training unit 21 and interception unit 23 link to each other with computing unit 22 respectively, and processing unit 24 links to each other with interception unit 23 and network trading platform 25 respectively.
In operational process, computing unit 22 can be monitored in real time to the transaction data in the network trading platform 25, and calculates the risk probability of transaction data by risk model.And the risk model here is to be made up by the mode of model training unit 21 with machine learning.After calculating risk probability, interception unit 23 is understood according to this risk probability, and filters out risk data in conjunction with predefined risk rule.At last, the operating right of the risk data that processing unit 24 can freeze to filter out, and feed back to network trading platform 25.
It should be noted that in the monitor procedure output of risk model is the input as risk rule, and the different output of risk model may refer to different risk judgment rules, can improve the effect of risk interception so greatly.For instance, the transaction of one 8000 yuan transaction and 80 yuan, if risk probability is the same, the loss of both risks will have hundred times gap, this shows, different transaction, risk loss expectation is also different.Therefore in order to intercept risk funds more efficiently, the risk probability control that the application adopts the transaction of difference loss expectation is different.Can be set at such as risk rule: if dealing money greater than 8000 yuan and risk probability greater than 0.4, transaction interception so; If dealing money greater than 80 yuan and risk probability greater than 0.8, transaction interception so.
In addition, the risk model among the application is can be made up by the mode of machine learning (Machine Learning) by model training unit 21.Machine learning is computer simulation or a kind of technology that realizes human learning behavior, be to obtain new knowledge or skills, and reorganize the existing structure of knowledge, and making it constantly to improve a kind of method of the performance of self, it uses the every field that has spreaded all over artificial intelligence.And replace the mode of artificial experience to set up risk model with machine learning techniques, and can eliminate human knowledge's subjectivity and one-sidedness, some potential risks factors can be included in the computation process of model, help to improve the accuracy of risk probability.
In order more in depth to understand the present invention, now provide another comparatively detailed risk control system example structure figure, see also Fig. 3.The risk control system 30 of present embodiment equally also comprises model training unit 21, computing unit 22, interception unit 23 and processing unit 24.Different with Fig. 2 is that this risk control system 30 also comprises verifies unit 31 and case database 32.Verify unit 31 and link to each other, be used for the data that processing unit 24 freezes are verified, and the risk of these data is checked once more, and checked result is returned to processing unit 24 with processing unit 24.Wherein, verify the risk that unit 31 can be judged transaction at the data content in the transaction data, for example can access the historical data of same subscriber, then these data and historical data comparison are judged.Verifying unit 31 also can be by manually-operated, such as getting in touch definite risk of concluding the business with the user.
In addition, the model training unit 21 of present embodiment has further comprised data acquisition subelement 33 and comparer unit 34 again.Data acquisition subelement 33 links to each other with case database 32 with network trading platform 25 respectively, it can extract a certain amount of normal data (normal data is meant the data of Successful Transaction) at set intervals automatically from network trading platform 25, and from case database 32, extract a certain amount of risk data, give comparer unit 34 with these data transmission then.Normal data and risk data are compared in 34 of comparer unit, and construct risk model.Owing to often include several data value (such as dealing money, exchange hour, both parties' registration fate etc.) in transaction data, therefore can give its variable separately for every kind of data value, and make up described risk model by relation between each variable and importance that risk is judged.For ease of understanding, the applicant provides a kind of risk model formula commonly used:
x=k1a1+k2a2+...+knan,
Wherein, x is a value-at-risk; A1, a2...an are the discrete variable of various transaction data, and it utilizes least square method to carry out regression fit various transaction data and obtains; K1, k2...kn are the importance parameter of various transaction data.
In the model such as x=2a1+3a2, a1 represents the discrete variable of buyer's hour of log-on, a2 represents the discrete variable of dealing money, and coefficient " 2 " and " 3 " before a1 and the a2 have represented that then buyer's hour of log-on and dealing money are for judging whether this transaction exists the importance of risk.The x value of calculating so just can be regarded the value-at-risk of transaction data as, and the big more risk of just representing of value is high more.Certainly, just provide a kind of mode that makes up risk model here, also can adopt other mode to make up this risk model according to actual needs.It should be noted that, because data acquisition subelement 33 can extract a certain amount of normal data and risk data at set intervals, so this risk model can in use constantly be upgraded and be perfect, and because model is as basis of formation with data itself, artificial subjectivity and one-sidedness can not occur, this has just produced the advantage of machine learning with respect to artificial experience.
The computing unit 22 of present embodiment further comprises value-at-risk computation subunit 35 and risk probability computation subunit 36 again.Value-at-risk computation subunit 35 links to each other with comparer unit 34 and network trading platform 25 respectively, and it can utilize risk model to calculate the value-at-risk of transaction data in the network trading platform 25, and value-at-risk is high more, represents that then these data are that the possibility of risk data is big more.Risk probability computation subunit 36 then is that this value-at-risk is converted to risk probability, thus the processing of 23 pairs of data of convenient follow-up interception unit.Such as, risk probability computation subunit 36 can be made value-at-risk following the processing:
y=e
x/(1+e
x),
Wherein, y is a risk probability, and x is a value-at-risk, and e is a natural constant.Like this, just can obtain a risk probability in 0 to 1 scope.
For the convenience of describing, the each several part of the above system is divided into various unit with function to be described respectively.Certainly, when implementing the application, can in same or a plurality of softwares or hardware, realize the function of each unit.
Corresponding to risk control system, the application proposes a kind of risk control method in addition, is used for the transaction data of network trading platform is carried out risk monitoring and control, sees also Fig. 4, and it may further comprise the steps:
S40 obtains transaction data.
S41 is according to transaction data calculation risk value.
S42 is according to value-at-risk calculation risk probability.
S43 filters out risk data according to risk probability and predefined risk rule, and described risk rule is to judge whether risk data is tackled according to the loss expectation parameter of risk data and the risk probability of correspondence.
S44, the operating right of the risk data of freezing to filter out.
S45 verifies risk data.
S46, the storage risk data is for subsequent acquisition and inquiry.
The application can the application risk model when calculating the value-at-risk (step S41) of transaction data, and the application's risk model makes up automatically by computing machine and forms.It can be included some potential risks factors in the computation process of model in, helps to improve the accuracy of risk probability.Wherein, a kind of preferable mode when the applicant has provided the computer aid training risk model specifically can comprise two steps shown in Figure 5:
S51 gathers a certain amount of normal data and risk data.Normal data is meant the data of Successful Transaction.
S52 compares normal data and risk data, and makes up described risk model.
Owing to often include several data value (such as dealing money, exchange hour, both parties' registration fate etc.) in transaction data, therefore can give its variable separately for every kind of data value, and make up described risk model by relation between each variable and importance that risk is judged.For ease of understanding, the applicant provides a kind of risk model formula commonly used:
x=k1a1+k2a2+...+knan,
Wherein, x is a value-at-risk; A1, a2...an are the discrete variable of various transaction data, and it utilizes least square method to carry out regression fit various transaction data and obtains; K1, k2...kn are the importance parameter of various transaction data.
In the model such as x=2a1+3a2, a1 represents the discrete variable of buyer's hour of log-on, a2 represents the discrete variable of dealing money, and coefficient " 2 " and " 3 " before a1 and the a2 have represented that then buyer's hour of log-on and dealing money are for judging whether this transaction exists the importance of risk.The x value of calculating so just can be regarded the value-at-risk of transaction data as, and the big more risk of just representing of value is high more.Certainly, just provide a kind of mode that makes up risk model here, also can adopt other mode to make up this risk model according to actual needs.It should be noted that, owing to just extract a certain amount of normal data and risk data at set intervals, so this risk model can in use constantly be upgraded and be perfect, and because model is as basis of formation with data itself, artificial subjectivity and one-sidedness can not occur, this has just produced the advantage of machine learning with respect to artificial experience.
Had after the risk model, just can the computational grid transaction platform on the risk probability (step 42) of transaction data, as shown in Figure 6, computation process can comprise following two steps:
S61 calculates the value-at-risk of transaction data according to described risk model.Risk model is used for the calculation risk value, and value-at-risk is high more, represents that then these data are that the possibility of risk data is big more.
S62, according to described value-at-risk calculation risk probability, the value of described risk probability is between 0 to 1.Because the follow-up risk rule that also will adopt of the application judges whether data are tackled, so here value-at-risk is handled, and exports the probability between 0 to 1, can help the formulation of risk rule more, and the computation burden of mitigation system.For example, can do following processing for value-at-risk:
y=e
x/(1+e
x),
Wherein, y is a risk probability, and x is a value-at-risk, and e is a natural constant.Like this, just can obtain a risk probability in 0 to 1 scope.
After calculating risk probability,, and just can filter out risk data (step S43) in the transaction data in conjunction with risk rule according to this risk probability.For example: if dealing money greater than 8000 yuan and risk probability greater than 0.4, transaction interception so; If dealing money greater than 80 yuan and risk probability greater than 0.8, transaction interception so.
Especially, the output of risk model is the input as risk rule in monitor procedure, and the different output of risk model may refer to different risk judgment rules, can improve the effect of risk interception so greatly.For instance, the transaction of one 8000 yuan transaction and 80 yuan, if risk probability is the same, the loss of both risks will have hundred times gap, i.e. risk loss expectation is different.And if,, then can improve the interception efficient of risk data greatly, thereby can reduce whole risk loss effectively in conjunction with different risk probabilities for different risk loss expectations.
After filtering out risk data, the operating right of these data is freezed, and feed back to network trading platform (step S44).Carry out the account funds cancellation etc. of freezing, conclude the business then, wherein follow-up processing action can realize by transaction platform, and adopts existing technology to finish, and repeats no more herein.
Behind the data-frozen, really be risk data, can verify it (step S45) in order to guarantee data.The work of verifying both can independently be finished by computing machine, also can be by manually operating.For instance, can transfer out the historical data of same subscriber, then risk data and the historical data intercepted be compared,, illustrate that promptly there is bigger risk in this trading activity if differ greatly.And if still can't confirm the risk of data, then can investigate by manually relating to both parties.
At last, risk data is stored (step S46).The risk data that stores not only can be used as the foundation of inquiry, can also be for risk model improve the sampling data.
The application adopts the mode of machine learning to make up risk model, some potential risks factors can be included in the computation process of model, has improved the accuracy of interception risk data effectively.And the application is input as risk rule with the output of risk model, can improve the effect of risk interception greatly, and the risk loss that reduces network trading platform integral body.
More than disclosed only be several specific embodiments of the application, but the application is not limited thereto, any those skilled in the art can think variation, all should drop in the application's the protection domain.
Claims (15)
1. a risk control system is used for the transaction data of a network trading platform is carried out risk monitoring and control, it is characterized in that, comprising:
One computing unit, it links to each other with described network trading platform, is used for transaction data is monitored, and calculates the value-at-risk of transaction data;
One interception unit, it links to each other with described computing unit, is used for filtering out risk data according to value-at-risk and predefined risk rule;
One processing unit, it links to each other with described interception unit and network trading platform respectively, is used to the operating right of the risk data freezing to filter out.
2. risk control system as claimed in claim 1 is characterized in that, it also comprises a model training unit, and itself and described computing unit are used to make up risk model.
3. risk control system as claimed in claim 2 is characterized in that, it also comprises a case event data storehouse, and it links to each other with described processing unit, is used to deposit risk data.
4. risk control system as claimed in claim 3 is characterized in that, described model training unit further comprises again:
One data acquisition subelement, it links to each other with database in case database and the described network trading platform respectively, is used to gather a certain amount of normal data and risk data;
One comparer unit, it links to each other with this data acquisition subelement, is used for normal data and risk data are compared, and makes up described risk model.
5. risk control system as claimed in claim 3 is characterized in that, it comprises that also one verifies the unit, and it is arranged between described processing unit and the described case database, is used for the data of freezing are verified.
6. risk control system as claimed in claim 2 is characterized in that, described computing unit further comprises again:
One value-at-risk computation subunit, it links to each other with described network trading platform and described model training unit respectively, is used for calculating according to described risk model the value-at-risk of transaction data;
One risk probability computation subunit, it links to each other with described value-at-risk computation subunit, is used for according to described value-at-risk calculation risk probability, and the value of described risk probability is between 0 to 1.
7. risk control system as claimed in claim 6 is characterized in that, during described value-at-risk computation subunit calculation risk value according to following formula:
x=k1a1+k2a2+...+knan
Wherein, x is a value-at-risk, and a1, a2...an are the discrete variable of various transaction data, and k1, k2...kn are the importance parameter of various transaction data.
8. risk control system as claimed in claim 7 is characterized in that, during described risk probability computation subunit calculation risk probability according to following formula:
y=e
x/(1+e
x),
Wherein, y is a risk probability, and x is a value-at-risk, and e is a natural constant.
9. a risk control method is used for the transaction data of a network trading platform is carried out risk monitoring and control, it is characterized in that, may further comprise the steps:
Obtain transaction data;
Calculate the value-at-risk that obtains this transaction according to described transaction data;
Filter out risk data according to described value-at-risk and predefined risk rule;
The operating right of the risk data of freezing to filter out.
10. risk control method as claimed in claim 9 is characterized in that, calculates described value-at-risk and further may further comprise the steps again:
Gather a certain amount of normal data and risk data;
Normal data and risk data are compared, and construct risk model;
Calculate described value-at-risk by described risk model.
11. risk control method as claimed in claim 10 is characterized in that, described risk model is:
x=k1a1+k2a2+...+knan
Wherein, x is a value-at-risk, and a1, a2...an are the discrete variable of various transaction data, and k1, k2...kn are the importance parameter of various transaction data.
12. risk control method as claimed in claim 9 is characterized in that, obtains value-at-risk and further comprises step afterwards:
According to described value-at-risk calculation risk probability, the value of described risk probability is between 0 to 1;
Filter out risk data according to risk probability and predefined risk rule.
13. risk control method as claimed in claim 12 is characterized in that, during the calculation risk probability specifically according to following formula:
y=e
x/(1+e
x),
Wherein, y is a risk probability, and x is a value-at-risk, and e is a natural constant.
14. risk control method as claimed in claim 9 is characterized in that, the operating right that freezes risk data also comprises step afterwards: risk data is verified.
15. risk control method as claimed in claim 9 is characterized in that, also further comprises step after risk data is handled: the storage risk data, for subsequent acquisition and inquiry.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2010100014792A CN102117459A (en) | 2010-01-06 | 2010-01-06 | Risk control system and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2010100014792A CN102117459A (en) | 2010-01-06 | 2010-01-06 | Risk control system and method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN102117459A true CN102117459A (en) | 2011-07-06 |
Family
ID=44216214
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2010100014792A Pending CN102117459A (en) | 2010-01-06 | 2010-01-06 | Risk control system and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102117459A (en) |
Cited By (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103049851A (en) * | 2012-12-27 | 2013-04-17 | 中国建设银行股份有限公司 | Transaction data-based anti-fraud monitoring method and device |
CN103186875A (en) * | 2011-12-28 | 2013-07-03 | 凌群电脑股份有限公司 | Attribute judgment method for entrusting order of risk control system |
CN103745345A (en) * | 2014-01-27 | 2014-04-23 | 上海坤士合生信息科技有限公司 | System and method applied to transaction platform for realizing grading safety processing of financial information |
CN104867011A (en) * | 2014-02-21 | 2015-08-26 | 中国电信股份有限公司 | Method and device for carrying out safety control on mobile payment |
CN104915842A (en) * | 2015-06-04 | 2015-09-16 | 浙江力石科技股份有限公司 | Electronic commerce transaction monitoring method based on internet transaction data |
CN105046562A (en) * | 2015-09-10 | 2015-11-11 | 腾讯科技(深圳)有限公司 | Risk control system and risk control data acquisition method |
CN105447755A (en) * | 2014-09-01 | 2016-03-30 | 阿里巴巴集团控股有限公司 | Transaction control method and apparatus |
CN105528383A (en) * | 2014-10-27 | 2016-04-27 | 阿里巴巴集团控股有限公司 | Method and device for indentifying risks of accounts |
CN105786820A (en) * | 2014-12-19 | 2016-07-20 | 阿里巴巴集团控股有限公司 | Method and device for risk identification |
CN105991574A (en) * | 2015-02-10 | 2016-10-05 | 阿里巴巴集团控股有限公司 | Risk behavior monitoring method and apparatus thereof |
CN106033575A (en) * | 2015-03-11 | 2016-10-19 | 阿里巴巴集团控股有限公司 | Risk account identification method and apparatus |
CN106067088A (en) * | 2016-05-30 | 2016-11-02 | 中国邮政储蓄银行股份有限公司 | E-bank accesses detection method and the device of behavior |
CN106656917A (en) * | 2015-10-30 | 2017-05-10 | 阿里巴巴集团控股有限公司 | Method and apparatus for managing account permissions |
CN106815754A (en) * | 2015-12-02 | 2017-06-09 | 阿里巴巴集团控股有限公司 | The charging method and air control system server of a kind of risk control system |
WO2018001195A1 (en) * | 2016-07-01 | 2018-01-04 | 阿里巴巴集团控股有限公司 | Method and device for controlling data risk |
CN108230151A (en) * | 2018-01-16 | 2018-06-29 | 平安科技(深圳)有限公司 | A kind of suspicious transaction detection method, apparatus, equipment and storage medium |
CN108985070A (en) * | 2018-07-11 | 2018-12-11 | 阿里巴巴集团控股有限公司 | Risk control method, risk control device, electronic equipment and storage medium |
CN109063965A (en) * | 2018-06-29 | 2018-12-21 | 阿里巴巴集团控股有限公司 | A kind of network payment methods of risk assessment, device and server |
WO2019063005A1 (en) * | 2017-09-30 | 2019-04-04 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for identifying incorrect order request |
CN109741066A (en) * | 2018-11-30 | 2019-05-10 | 广东康美通信息服务有限公司 | Method, electronic equipment, storage medium and the system of automatic stay customer account |
CN111629010A (en) * | 2015-11-23 | 2020-09-04 | 阿里巴巴集团控股有限公司 | Malicious user identification method and device |
-
2010
- 2010-01-06 CN CN2010100014792A patent/CN102117459A/en active Pending
Cited By (30)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103186875A (en) * | 2011-12-28 | 2013-07-03 | 凌群电脑股份有限公司 | Attribute judgment method for entrusting order of risk control system |
CN103049851A (en) * | 2012-12-27 | 2013-04-17 | 中国建设银行股份有限公司 | Transaction data-based anti-fraud monitoring method and device |
CN103745345A (en) * | 2014-01-27 | 2014-04-23 | 上海坤士合生信息科技有限公司 | System and method applied to transaction platform for realizing grading safety processing of financial information |
CN104867011A (en) * | 2014-02-21 | 2015-08-26 | 中国电信股份有限公司 | Method and device for carrying out safety control on mobile payment |
CN105447755B (en) * | 2014-09-01 | 2021-12-17 | 创新先进技术有限公司 | Transaction control method and device |
CN105447755A (en) * | 2014-09-01 | 2016-03-30 | 阿里巴巴集团控股有限公司 | Transaction control method and apparatus |
CN105528383B (en) * | 2014-10-27 | 2019-06-18 | 阿里巴巴集团控股有限公司 | The recognition methods of account risk and device |
CN105528383A (en) * | 2014-10-27 | 2016-04-27 | 阿里巴巴集团控股有限公司 | Method and device for indentifying risks of accounts |
CN105786820B (en) * | 2014-12-19 | 2019-07-12 | 阿里巴巴集团控股有限公司 | A kind of method and device of risk identification |
CN105786820A (en) * | 2014-12-19 | 2016-07-20 | 阿里巴巴集团控股有限公司 | Method and device for risk identification |
CN105991574A (en) * | 2015-02-10 | 2016-10-05 | 阿里巴巴集团控股有限公司 | Risk behavior monitoring method and apparatus thereof |
CN106033575A (en) * | 2015-03-11 | 2016-10-19 | 阿里巴巴集团控股有限公司 | Risk account identification method and apparatus |
CN104915842A (en) * | 2015-06-04 | 2015-09-16 | 浙江力石科技股份有限公司 | Electronic commerce transaction monitoring method based on internet transaction data |
CN105046562A (en) * | 2015-09-10 | 2015-11-11 | 腾讯科技(深圳)有限公司 | Risk control system and risk control data acquisition method |
CN106656917A (en) * | 2015-10-30 | 2017-05-10 | 阿里巴巴集团控股有限公司 | Method and apparatus for managing account permissions |
CN111629010A (en) * | 2015-11-23 | 2020-09-04 | 阿里巴巴集团控股有限公司 | Malicious user identification method and device |
CN111629010B (en) * | 2015-11-23 | 2023-03-10 | 创新先进技术有限公司 | Malicious user identification method and device |
CN106815754A (en) * | 2015-12-02 | 2017-06-09 | 阿里巴巴集团控股有限公司 | The charging method and air control system server of a kind of risk control system |
CN106067088A (en) * | 2016-05-30 | 2016-11-02 | 中国邮政储蓄银行股份有限公司 | E-bank accesses detection method and the device of behavior |
WO2018001195A1 (en) * | 2016-07-01 | 2018-01-04 | 阿里巴巴集团控股有限公司 | Method and device for controlling data risk |
TWI673666B (en) * | 2016-07-01 | 2019-10-01 | 香港商阿里巴巴集團服務有限公司 | Method and device for data risk control |
US11074350B2 (en) | 2016-07-01 | 2021-07-27 | Advanced New Technologies Co., Ltd. | Method and device for controlling data risk |
WO2019063005A1 (en) * | 2017-09-30 | 2019-04-04 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for identifying incorrect order request |
CN108230151A (en) * | 2018-01-16 | 2018-06-29 | 平安科技(深圳)有限公司 | A kind of suspicious transaction detection method, apparatus, equipment and storage medium |
WO2019140804A1 (en) * | 2018-01-16 | 2019-07-25 | 平安科技(深圳)有限公司 | Suspicious transaction monitoring method, device, and apparatus, and storage medium |
CN109063965A (en) * | 2018-06-29 | 2018-12-21 | 阿里巴巴集团控股有限公司 | A kind of network payment methods of risk assessment, device and server |
CN108985070B (en) * | 2018-07-11 | 2020-07-03 | 阿里巴巴集团控股有限公司 | Risk control method, risk control device, electronic device, and storage medium |
US11075941B2 (en) | 2018-07-11 | 2021-07-27 | Advanced New Technologies Co., Ltd. | Risk control method, risk control apparatus, electronic device, and storage medium |
CN108985070A (en) * | 2018-07-11 | 2018-12-11 | 阿里巴巴集团控股有限公司 | Risk control method, risk control device, electronic equipment and storage medium |
CN109741066A (en) * | 2018-11-30 | 2019-05-10 | 广东康美通信息服务有限公司 | Method, electronic equipment, storage medium and the system of automatic stay customer account |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102117459A (en) | Risk control system and method | |
CN107705149A (en) | Data method for real-time monitoring, device, terminal device and storage medium | |
CN107402921A (en) | Identify event-order serie data processing method, the apparatus and system of user behavior | |
CN108399509A (en) | Determine the method and device of the risk probability of service request event | |
CN107146152A (en) | A kind of credit management system kept accounts based on block chain | |
CN104881783A (en) | E-bank account fraudulent conduct and risk detecting method and system | |
CN102834809B (en) | Sight status processing system and method for computing in grid computing environment | |
CN109472610A (en) | A kind of bank transaction is counter to cheat method and system, equipment and storage medium | |
CN108898476A (en) | A kind of loan customer credit-graded approach and device | |
CN110363416A (en) | Financial resources distribution method, device and electronic equipment | |
CN107330641A (en) | A kind of real-time risk control system of financial derivatives based on Storm stream process framework and regulation engine and method | |
CN108805391A (en) | Determine the method and device of high risk user | |
CN107886431A (en) | Financial air control system based on big data and artificial intelligence | |
CN110866822B (en) | Wind control management method and device for securitization of assets, electronic equipment and storage medium | |
CN109816509A (en) | Generation method, terminal device and the medium of scorecard model | |
CN110472815A (en) | To the risk control method and system of financing enterprise in a kind of supply chain financial business | |
Korczak et al. | Risk avoiding strategy in multi-agent trading system | |
US20110208670A1 (en) | Execution Optimizer | |
CN108345995A (en) | A kind of enterprises economic management cost control system | |
CN114638696A (en) | Credit risk prediction model training method and system | |
CN111915316A (en) | Suspicious transaction monitoring method and device, computer equipment and storage medium | |
Pourdarab et al. | A hybrid method for credit risk assessment of bank customers | |
Chen et al. | Fuzzy computing applications for anti-money laundering and distributed storage system load monitoring | |
CN114358519A (en) | Intelligent credit limit interest rate adjusting method and device | |
US11475515B1 (en) | Adverse action methodology for credit risk models |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 1155259 Country of ref document: HK |
|
C12 | Rejection of a patent application after its publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20110706 |