Title:
時間的因果グラフにおける異常フュージョン
Document Type and Number:
Japanese Patent JP6609050
Kind Code:
B2
Abstract:
An exemplary method for detecting one or more anomalies in a system includes building a temporal causality graph describing functional relationship among local components in normal period; applying the causality graph as a propagation template to predict a system status by iteratively applying current system event signatures; and detecting the one or more anomalies of the system by examining related patterns on the template causality graph that specifies normal system behaviors. The system can align event patterns on the causality graph to determine an anomaly score.
More Like This:
Inventors:
Jean, Kai
Jean, Hui
Ju, Jian Woo
Gian, Guofei
Jean, Hui
Ju, Jian Woo
Gian, Guofei
Application Number:
JP2018525694A
Publication Date:
November 20, 2019
Filing Date:
November 16, 2016
Export Citation:
Assignee:
NEC Laboratories America, Inc.
International Classes:
G06N5/04; G06F11/07; G06F11/30; G06F11/34
Foreign References:
| US20140245443 | ||||
| US20150269491 |
Other References:
QIU, Hiuda et al.,Granger Causality for Time-Series Anomaly Detection,Proceedings of 12th International Conference on Data Mining,2012年,pp.1074-1079,URL,https://ieeexplore.ieee.org/document/6413806
Attorney, Agent or Firm:
Akio Miyazaki
Masaaki Ogata
Masaaki Ogata