公开(公告)号：US12278747B1

公开(公告)日：2025-04-15

申请号：US17958159

申请日：2022-09-30

Applicant: Amazon Technologies, Inc.

Inventor： Rajendra Kumar Vippagunta ,  Syed Furqhan Ulla ,  Sunayana Vempati ,  Yekesa Srinivasa Kosuru ,  Namita Das ,  Devesh Ratho ,  Shashwat Srijan ,  Lenon Alexander Minorics ,  Patrick Bloebaum ,  David Kernert

IPC: H04L43/067 ,  H04L41/0631 ,  H04L43/0817

Abstract: A system obtains a graph representing a set of resources of a distributed system. At least one node of the graph represents a resource-metric pair. The system further obtains time series data that indicates anomalies from the system. Then, the system determines a root cause anomaly that caused other anomalies based at least in part on the graph and the time series data.

公开(公告)号：US12192220B1

公开(公告)日：2025-01-07

申请号：US17851429

申请日：2022-06-28

Applicant: Amazon Technologies, Inc.

Inventor： Syed Ahsan Ishtiaque ,  Ketan Vijayvargiya ,  Mohammed Talal Yassar Azam ,  Jill Blue Lin ,  Mohammed Saad Ather ,  Ankur Mehrotra ,  Peter Goetz ,  Lenon Alexander Minorics ,  Patrick Bloebaum ,  Dominik Janzing ,  David Kernert ,  Sadanand Murthy Sachidananda ,  Shashank Srivastava ,  Laurent Callot ,  Ali Caner Turkmen

IPC: H04L9/40

Abstract: Techniques for anomaly and causality detection are described. An example includes receiving time series data; performing anomaly detection on the received time series data to detect at least one anomaly using an anomaly detection model; detecting a causal relationship between measures, wherein a set of measures are related when a first of the set of measures has a causal influence on a second of the set of measures, wherein a single time series is a metric and a measure is a numerical or categorical quantity a metric describes; and outputting a result of the anomaly and causality relationship detections.