Anomaly and causality detection

US12192220B1 · kind B1 · utility

Assignee

• AMAZON TECHNOLOGIES, INC. · US

Inventors

• Syed Ahsan Ishtiaque · Renton, US
• Ketan Vijayvargiya · Redmond, US
• Mohammed Talal Yassar Azam · Snoqualmie, US
• Jill Blue Lin · Palo Alto, US
• Mohammed Saad Ather · Sammamish, US
• Ankur Mehrotra · Seattle, US
• Peter Goetz · Echterdingen, DE
• Lenon Alexander Minorics · Stuttgart, DE
• Patrick Bloebaum · Mountain View, US
• Dominik Janzing · Rottenburg am Neckar, DE
• David Kernert · Heidelberg, DE
• Sadanand Murthy Sachidananda · Bothell, US
• Shashank Srivastava · Jersey City, US
• Laurent Callot · Seattle, US
• Ali Caner Turkmen · Berlin, DE

Key dates

• Filing date: Jun 28, 2022
• Grant date: Jan 7, 2025
• Expiry date: May 6, 2043

Classification

• Technology area (CPC H): Electricity
• CPC primary: H04L63/1425
• WIPO field: Digital communication
• WIPO sector: Electrical engineering

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.