Patent · US Active

Methods and systems for detecting anomalies in cloud services based on mining time-evolving graphs

US11500888B2 · kind B2 · utility

0Cited by

0References

14Claims

0Family size

Assignee

NEC Laboratories Europe GmbH · DE

Inventors

Josep Xavier Salvat Lozano · Heidelberg, DE
Andres Garcia-Saavedra · Heidelberg, DE
Xi Li · New York, US
Xavier Costa Perez · Heidelberg, DE

Key dates

Filing date	Aug 7, 2020
Grant date	Nov 15, 2022
Priority date	—
Expiry date	Aug 7, 2040

Classification

Technology area (CPC H)Electricity
CPC primaryH04L43/026
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

A method for anomaly detection of cloud services based on mining time-evolving graphs includes steps of receiving tracing data for a plurality of micro-services of the deployed cloud service, wherein the tracing data defines relationships between the plurality of micro-services of the deployed cloud service at a plurality of different time intervals, computing a functional graph based on the tracing data for each of the plurality of different time intervals, wherein nodes of each functional graph include the plurality of micro-services and wherein links between the nodes represent relationships between the plurality of micro-services, comparing the functional graphs for each of the plurality of time intervals to determine an anomaly score for each of the functional graphs, and detecting a presence of one or more anomalies based on the anomaly scores.

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