System and method for a multi view learning approach to anomaly detection and root cause analysis

Invention Grant

US09961571B2 System and method for a multi view learning approach to anomaly detection and root cause analysis 有权

Please log in to see more content

Patent Title: System and method for a multi view learning approach to anomaly detection and root cause analysis
Application No.: US14864360

Application Date: 2015-09-24
Publication No.: US09961571B2

Publication Date: 2018-05-01
Inventor: Kai Yang , Ruilin Liu , Yanjia Sun
Applicant: Futurewei Technologies, Inc.
Applicant Address: US TX Plano
Assignee: Futurewei Technologies, Inc.
Current Assignee: Futurewei Technologies, Inc.
Current Assignee Address: US TX Plano
Agency: Slater Matsil, LLP
Main IPC: H04Q7/10
IPC: H04Q7/10 ; H04W24/04

System and method for a multi view learning approach to anomaly detection and root cause analysis

Abstract:

A system and method for detecting anomalies in a communication network includes detecting first outliers in a first set of quality indicators for a cellular group, detecting second outliers in a second set of performance indicators for the cellular group, correlating the first outliers and the second outliers to produce an anomaly candidate, determining a confidence threshold for the anomaly candidate, and indicating a network anomaly in response to the confidence threshold exceeding a predetermined threshold.

Public/Granted literature

US20170094537A1 System and Method for a Multi View Learning Approach to Anomaly Detection and Root Cause Analysis Public/Granted day:2017-03-30

Information query

Espacenet