17962869. IDENTIFYING ROOT CAUSE ANOMALIES IN TIME SERIES simplified abstract (Oracle International Corporation)

IDENTIFYING ROOT CAUSE ANOMALIES IN TIME SERIES

Organization Name

Oracle International Corporation

Inventor(s)

Shwan Ashrafi of Bellevue WA (US)

Michal Piotr Prussak of Kirkland WA (US)

Hariharan Balasubramanian of Redmond WA (US)

Vijayalakshmi Krishnamurthy of Sunnyvale CA (US)

IDENTIFYING ROOT CAUSE ANOMALIES IN TIME SERIES - A simplified explanation of the abstract

This abstract first appeared for US patent application 17962869 titled 'IDENTIFYING ROOT CAUSE ANOMALIES IN TIME SERIES

Simplified Explanation

Techniques for Identifying Root Cause Anomalies in Time Series

• Obtaining information from a graph neural network (GNN) to construct a dependency graph with nodes representing each time series and directed edges representing dependencies between them.
• Removing nodes corresponding to time series without anomalies and edges connected to these nodes to create sub-graphs.
• Running a root cause analysis algorithm on the sub-graphs to create root cause graphs for each sub-graph.
• Using the root cause graphs to identify root cause anomalies and sequences of anomalies within the multiple time series.

Potential Applications

This technology could be applied in various industries such as finance, healthcare, manufacturing, and telecommunications for anomaly detection and root cause analysis in time series data.

Problems Solved

1. Efficiently identifying root cause anomalies in time series data. 2. Streamlining the process of root cause analysis for multiple time series.

Benefits

1. Improved accuracy in identifying root cause anomalies. 2. Faster detection and resolution of issues in time series data. 3. Enhanced decision-making based on root cause analysis results.

Potential Commercial Applications

Optimizing supply chain management, improving predictive maintenance processes, enhancing cybersecurity measures, and enhancing customer experience through proactive issue resolution.

Possible Prior Art

One possible prior art in this field is the use of traditional statistical methods for anomaly detection in time series data, which may not be as effective or efficient as the techniques described in this patent application.

How does this technology compare to existing anomaly detection methods in terms of accuracy and efficiency?

This article does not provide a direct comparison with existing anomaly detection methods, so it is unclear how this technology stacks up against traditional approaches.

What are the potential limitations or challenges of implementing this technology in real-world applications?

The article does not address any potential limitations or challenges that may arise when implementing this technology in practical settings, leaving room for further exploration and analysis.

Original Abstract Submitted

Techniques are described for identifying root cause anomalies in time series. Information to be used for root cause analysis (RCA) is obtained from a graph neural network (GNN) and is used to construct a dependency graph having nodes corresponding to each time series and directed edges corresponding to dependencies between the time series. Nodes corresponding to time series that do not contain anomalies may be removed from this dependency graph, as well as edges connected to these nodes. This edge and node removal may result in the creation of one or more sub-graphs from the dependency graph. A root cause analysis algorithm may be run on these one or more sub-graphs to create a root cause graph for each sub-graph. These root cause graphs may then be used to identify root cause anomalies within the multiple time series, as well as sequences of anomalies within the multiple time series.