Incremental parallel structure exception detection method for dynamic graph

A technology of anomaly detection and dynamic graph, applied in other database retrieval, special data processing applications, instruments, etc., can solve problems such as unsolved scalability problems

Inactive Publication Date: 2017-07-04
BEIHANG UNIV
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition, some methods try to discover anomalous subgraphs based on the whole graph, which do not solve the scalability problem

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Incremental parallel structure exception detection method for dynamic graph
  • Incremental parallel structure exception detection method for dynamic graph
  • Incremental parallel structure exception detection method for dynamic graph

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] In order to have a further understanding of the technical solution and beneficial effects of the present invention, the technical solution of the present invention and its beneficial effects will be described in detail below with reference to the accompanying drawings.

[0043] The structural anomaly detection method of the incremental parallel dynamic graph provided by the invention extends the anomaly detection method of the static graph to the abnormal detection of the large-scale dynamic graph. In the present invention, three basic types of graph exceptions are defined: adding, modifying and deleting exceptions. The addition exception is the addition of nodes or edges to the normal pattern. Modification exceptions contain a different label for a node or edge. Remove abnormal substructures that have fewer edges or nodes than normal substructures.

[0044] Incremental Parallel Dynamic Graph Structural Anomaly Detection Method Detecting graph anomalies is based on th...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to an incremental parallel structure exception detection method for a dynamic graph. The method comprises the steps of firstly, dividing the graph by using a time sliding window, and selecting N sub-graphs in an initialization stage to detect normal modes and exceptional sub-structures in parallel; and secondly, iteratively determining normal modes and exceptional sub-structures in the residual sub-graphs in parallel. A minimum description length principle is used in the normal mode detection, so that an original graph can be subjected to compression and exception detection in multiple levels. A proposed algorithm is verified in a plurality of large-scale graph data sets, and an experimental result shows that the proposed method can effectively and incrementally detect exceptions in large-scale graph flow data.

Description

technical field [0001] The invention relates to the field of computer data processing, in particular to a structural abnormality detection method of an incremental parallel dynamic graph. Background technique [0002] Anomaly structure detection of graphs can spot financial frauds, network intrusions, and suspicious social behaviors. [0003] The complex relationship between data in many application fields can be intuitively expressed through graphs, such as the Internet, social networks, and biological fields. The graph data in these real-world applications is usually large-scale, and the amount of data continues to increase over time. For example, in social media (blog, Weibo, and WeChat) and information sharing platforms (YouTube and Flicker), the continuous social behavior between users will generate a large amount of continuous, mutual interaction data, and these interactions can be naturally Use a dynamic graph to represent - nodes represent people, objects or other ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F17/30
CPCG06F16/903
Inventor 兰雨晴韩涛
Owner BEIHANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap