Method and apparatus of identifying a transaction risk

• US 10,445,734 B2
• Filed: 08/05/2015
• Issued: 10/15/2019
• Est. Priority Date: 08/06/2014
• Status: Active Grant

• Current Assignee: Advanced New Technologies Company Limited (Ant Group Co., Ltd.)
• Original Assignee: Alibaba Group Holding Ltd.
• Inventors: Wang, Fengwei, He, Huimei, He, Dijun, Mao, Renxin
• Primary Examiner(s): Niquette, Robert R
• Application Number:
  US14/819,289
• Publication Number:
  US 20160042355A1
• Time in Patent Office: 1,532 Days
• Field of Search: 705 39
• CPC Class Codes: G06Q 20/4014 Identity check for transactions
• CPC Class Codes: G06Q 20/4016 involving fraud or risk level assessment in transaction processing

Abstract

A method and an apparatus for identifying a transaction risk are disclosed. The method includes obtaining risk identification information of a sub-network to which a node relating to a transaction to be identified belongs; and identifying a risk of the transaction to be identified based on the risk identification information of the sub-network to which the node relating to the transaction to be identified belongs, wherein the sub-network is a network acquired by partitioning a relationship network based on connectivity, the relationship network is a network built up with entities and activities relating to a plurality of transactions. Embodiments of the present disclosure build up entities and activities relating to a transaction to be identified into a relationship network, and identify whether a risk exists in the transaction to be identified using risk identification information of the network which is difficult to be found or changed, and thus are able to identify a transaction risk in a more effective manner.

Claims

1. A method implemented by one or more computing devices, the method comprising:

building a relationship network with entities and activities relating to a plurality of transactions;

partitioning the relationship network, in real time or at fixed intervals, into a plurality of unconnected sub-networks based on connectivity by;

comparing current node information and historical node information to determine and label node change information,

processing the deleted and split sub-networks using the node change information, and

processing newly added and merged sub-networks using the node change information;

acquiring a sub-network, to which a node relating to a transaction to be identified belongs, the transaction being one of the plurality of transactions;

obtaining risk identification information of the sub-network to which the node relating to the transaction to be identified belongs, the risk identification information of the sub-network including one or more of a static property of the sub-network, and dynamic change information of the sub-network that is caused by the transaction to be identified;

identifying a risk of the transaction to be identified based at least in part on the risk identification information of the sub-network to which the node relating to the transaction to be identified belongs; and

labeling the node relating to the transaction to be identified belongs as a risk node.

2. The method of claim 1, wherein the entities relating to the plurality of transactions are used as nodes in the relationship network, and the activities relating to the plurality of transactions are used as edges for connecting the nodes in the relationship network.

3. The method of claim 1, wherein each sub-network has a serial number that is unique in the relationship network, and the method further includes keeping a serial number of the sub-network steady if a dynamic change occurs in the sub-network.

4. The method of claim 3, wherein keeping the serial number of the sub-network steady comprises one or more of:

generating a random number that is unique to the relationship network for a first sub-network in response to adding the first sub-network into the relationship network;

deleting a serial number of a second sub-network in response to deleting the second sub-network from the relationship network;

enabling a serial number of a third sub-network to inherit a serial number of a largest sub-network of at least two sub-networks in response to merging the at least two sub-networks in the relationship network; and

enabling a serial number of a sub-network that is largest among a plurality of sub-networks to inherit a serial number of a fourth sub-network in response to splitting the fourth sub-network into the plurality of sub-network in the relationship network.

5. The method of claim 1, further comprising conducting a relationship query in the relationship network in response to determining that a potential risk exists in the transaction to be identified.

6. The method of claim 1, wherein the entities relating to the plurality of transactions comprise one or more of:

a user identifier (ID), a delivery address, a phone number, a bank card used in a particular transaction, a Unique Material Identifier (UMID) and a Media Access Control (MAC) address.

7. The method of claim 1, wherein the activities relating to the plurality of transactions include at least one or more of an activity associated with a particular transaction, an activity associated with registration and an activity associated with login.

8. The method of claim 1, wherein the static property of the sub-network includes one or more of:

a number of nodes in the sub-network, a number of edges in the sub-network, a number of events in the sub-network, and a number of paths where a shortest path between any two nodes in the sub-network is less than a set threshold.

9. The method of claim 1, wherein identifying the risk of the transaction to be identified includes:

calculating a ratio between a number of events and a number of nodes in the sub-network to which the node relating to the transaction to be identified belongs; and

determining whether the ratio between the number of events and the number of nodes in the sub-network to which the node relating to the transaction to be identified belongs exceeds a set ratio range.

10. The method of claim 9, further comprising determining that a potential risk exists in the transaction to be identified in response to determining that the ratio between the number of events and the number of nodes in the sub-network to which the node relating to the transaction to be identified belongs exceeds the set ratio range.

11. The method of claim 1, wherein identifying the risk of the transaction to be identified includes:

calculating a density of the sub-network to which the node relating to the transaction to be identified belongs; and

determining whether the density of the sub-network to which the node relating to the transaction to be identified belongs exceeds a set density range.

12. The method of claim 11, further comprising determining that a potential risk exists in the transaction to be identified in response to determining that the density of the sub-network to which the node relating to the transaction to be identified belongs exceeds the set density range.

13. The method of claim 1, wherein identifying the risk of the transaction to be identified includes one or more of:

determining that the risk exists in the transaction to be identified when the transaction to be identified introduces a risk node into the sub-network; and

determining that the risk exists in the transaction to be identified when the transaction to be identified merges sub-networks having the risk.

14. The method of claim 1, wherein the dynamic change information of the sub-network includes information of one or more of:

a new sub-network addition, a sub-network deletion, a sub-network merging and a sub-network splitting.

15. An apparatus comprising:

one or more processors; and

memory coupled to the one or more processors, the memory storing a plurality of units executable by the one or more processors, the plurality of units including;

an acquisition unit configured to obtain risk identification information of a sub-network to which a node relating to a transaction to be identified belongs, the risk identification information of the sub-network including one or more of a static property of the sub-network, and dynamic change information of the sub-network that is caused by the transaction to be identified;

a risk identification unit configured to identify a risk of the transaction to be identified based on the risk identification information of the sub-network to which the node relating to the transaction to be identified belongs; and

a labeling unit configured to label the transaction as having the risk and to label the node relating to the transaction to be identified belongs as a risk node,

wherein the sub-network is a network acquired by partitioning a relationship network, in real time or at fixed intervals, into a plurality of unconnected sub-networks based on connectivity, and the relationship network is a network built up from entities and activities relating to a plurality of transactions.

16. The apparatus of claim 15, wherein the entities relating to the plurality of transactions are used as nodes in the relationship network, and the activities relating to the plurality of transactions are used as edges for connecting the nodes in the relationship network.

17. The apparatus of claim 15, wherein the static property of the sub-network includes one or more of:

a number of nodes in the sub-network, a number of edges in the sub-network, a number of events in the sub-network, and a number of paths where a shortest path between any two nodes in the sub-network is less than a set threshold.

18. The apparatus of claim 17, wherein the risk identification unit includes:

a first calculation sub-unit configured to calculate a ratio between the number of events and the number of nodes in the sub-network to which the node relating to the transaction to be identified belongs;

a first determination sub-unit configured to determine whether the ratio of the number of events and the number of nodes in the sub-network to which the node relating to the transaction to be identified belongs that is calculated by the first calculation sub-unit exceeds a set ratio range; and

a first identification sub-unit configured to identify that a potential risk exists in the transaction to be identified in response to the first determination sub-unit determining that the ratio exceeds the set ratio range.

19. One or more computer-readable media storing executable instructions that, when executed by one or more processors, cause the one or more processors to perform acts comprising:

building a relationship network with entities and activities relating to a plurality of transactions;

partitioning the relationship network, in real time or at fixed intervals, into a plurality of unconnected sub-networks based on connectivity by;

comparing current node information and historical node information to determine and label node change information,

processing the deleted and split sub-networks using the node change information, and

processing newly added and merged sub-networks using the node change information;

acquiring a sub-network, to which a node relating to a transaction to be identified belongs, the transaction being one of the plurality of transactions;

obtaining risk identification information of the sub-network to which the node relating to the transaction to be identified belongs, the risk identification information of the sub-network including one or more of a static property of the sub-network, and dynamic change information of the sub-network that is caused by the transaction to be identified;

identifying a risk of the transaction to be identified based at least in part on the risk identification information of the sub-network to which the node relating to the transaction to be identified belongs, identifying the risk of the transaction to be identified including;

upon identifying that the risk identification information of the sub-network includes the static property of the sub-network,

calculating a ratio between a number of events and a number of nodes in the sub-network to which the node relating to the transaction to be identified belongs,

determining whether the ratio between the number of events and the number of nodes in the sub-network to which the node relating to the transaction to be identified belongs exceeds a set ratio range, and

determining that a potential risk exists in the transaction to be identified in response to determining that the ratio between the number of events and the number of nodes in the sub-network to which the node relating to the transaction to be identified belongs exceeds the set ratio range; and

upon identifying that the risk identification information of the sub-network includes the dynamic change information of the sub-network that is caused by the transaction to be identified,

calculating a density of the sub-network to which the node relating to the transaction to be identified belongs,

determining whether the density of the sub-network to which the node relating to the transaction to be identified belongs exceeds a set density range, and

determining that the potential risk exists in the transaction to be identified in response to determining that the density of the sub-network to which the node relating to the transaction to be identified belongs exceeds the set density range; and

labeling the node relating to the transaction to be identified belongs as a risk node.

20. The one or more computer-readable media of claim 19, wherein the entities relating to the plurality of transactions are used as nodes in the relationship network, and the activities relating to the plurality of transactions are used as edges for connecting the nodes in the relationship network.