Patent · US Active

Using random forests to generate rules for causation analysis of network anomalies

US10771313B2 · kind B2 · utility

10Cited by

4References

20Claims

0Family size

Assignee

Cisco Technology, Inc. · US

Inventors

David Tedaldi · Zürich, CH
Grégory Mermoud · Veyras, CH
Jean-Philippe Vasseur · Meylan, FR

Key dates

Filing date	Jan 29, 2018
Grant date	Sep 8, 2020
Priority date	—
Expiry date	Aug 20, 2038

Classification

Technology area (CPC H)Electricity
CPC primaryH04L41/5025
WIPO fieldDigital communication
WIPO sectorElectrical engineering

Abstract

In one embodiment, a network assurance service receives one or more sets of network characteristics of a network, each network characteristic forming a different feature dimension in a multi-dimensional feature space. The network assurance service applies machine learning-based anomaly detection to the one or more sets of network characteristics, to label each set of network characteristics as anomalous or non-anomalous. The network assurance service identifies, based on the labeled one or more sets of network characteristics, an anomaly pattern as a collection of unidimensional cutoffs in the feature space. The network assurance service initiates a change to the network based on the identified anomaly pattern.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.