US 12,008,567 B2 · Graph transformation based on directed edges

Abstract

Methods and systems are presented for analyzing transactions conducted through user accounts with an online service provider based on graph analysis. A graph is generated based on a set of seed accounts that are determined to be involved in suspicious activities. The graph includes a set of seed nodes representing the seed accounts, and a set of nodes representing user accounts that are connected to the set of seed accounts in downstream transactions. A random walk traversal based on multiple dimensions is performed on the graph to determine nodes that are closely related to the set of seed nodes. Transactions conducted through the seed accounts and accounts corresponding to nodes that are closely related to the set of seed nodes are analyzed to detect any malicious activities. The graph may also be presented according to a layered hierarchical structure for better visualization of transaction flows through the accounts.

Claims20

Dependent claims

A system, comprising:

a non-transitory memory;
and
one or more hardware processors coupled with the non-transitory memory and configured to read instructions from the non-transitory memory to cause the system to perform operations comprising:
displaying, on a computer device, a presentation of a graph comprising nodes connected with each other via directional edges, wherein the presentation has a non-hierarchical structure;
selecting, from the nodes of the graph, a seed node;
assigning each of the nodes in the graph to one of a plurality of layers within a layered hierarchical structure based on a traversal of the graph from the seed node;
iteratively identifying a node from the graph and determining whether to reassign the node to a different layer in the plurality of layers within the layered hierarchical structure based on a goal of minimizing reverse edges in the graph;
transforming the graph based on the layered hierarchical structure;
detecting a pattern of activities corresponding to a subset of nodes from the graph based on analyzing the transformed graph;
and
presenting the transformed graph on the computer device, wherein the subset of nodes is presented differently from other nodes in the graph based on the detected pattern of activities.

8 more elements

A method, comprising:

accessing, by one or more hardware processors, a graph comprising nodes connected with each other via directed edges;
determining, by the one or more hardware processors and from the nodes of the graph, a seed node;
assigning each of the nodes in the graph to a corresponding layer in a plurality of layers within a layered hierarchical structure based on a traversal of the graph from the seed node;
iteratively identifying a node from the graph and determining whether to reassign the node to a different layer in the plurality of layers within the layered hierarchical structure based on a goal of minimizing reverse edges in the graph;
transforming the graph based on the layered hierarchical structure;
detecting a pattern of activities corresponding to a subset of nodes from the graph based on analyzing the transformed graph;
and
presenting, by the one or more hardware processors, the transformed graph on a computer device, wherein the subset of nodes is presented differently from other nodes in the graph based on the detected pattern of activities.

5 more elements

A non-transitory machine-readable medium having stored thereon machine-readable instructions executable to cause a machine to perform operations comprising:

accessing a graph comprising nodes connected with each other via directional edges;
selecting, from the nodes of the graph, a seed node;
assigning each of the nodes in the graph to a corresponding one of a plurality of layers within a layered hierarchical structure based on a traversal of the graph from the seed node;
iteratively identifying a node from the graph and determining whether to reassign the node to a different layer in the plurality of layers within the layered hierarchical structure based on a goal of minimizing reverse edges in the graph;
transforming the graph based on the layered hierarchical structure;
detecting a pattern of activities corresponding to a subset of nodes from the graph based on analyzing the transformed graph;
and
presenting the transformed graph on a computer device, wherein the subset of nodes is presented differently from other nodes in the graph based on the detected pattern of activities.

5 more elements

Dependencies are inferred from the claim text.

Graph transformation based on directed edges

Life of this patent

Graph transformation based on directed edges

Life of this patent

Abstract

Claims20