×

REAL-TIME DETECTION AND CLASSIFICATION OF ANOMALOUS EVENTS IN STREAMING DATA

  • US 20150106927A1
  • Filed: 10/14/2013
  • Published: 04/16/2015
  • Est. Priority Date: 10/14/2013
  • Status: Active Grant
First Claim
Patent Images

1. A method of detecting and classifying anomalous events, comprising:

  • receiving an input log file including a plurality of events, wherein each event comprises a data set;

    for each event, providing multiple contexts that group the data set into different sub-groups;

    generating an anomaly score for each context so that each event has at least two anomaly scores associated therewith;

    for each event, combining at least the anomaly scores to generate an overall event score so as to classify the event as being normal or abnormal; and

    outputting a plurality of the overall event scores for the input log file.

View all claims
  • 4 Assignments
Timeline View
Assignment View
    ×
    ×