US Patent Application 17824206. AUTOMATIC SEGMENTATION USING HIERARCHICAL TIMESERIES ANALYSIS simplified abstract
Contents
AUTOMATIC SEGMENTATION USING HIERARCHICAL TIMESERIES ANALYSIS
Organization Name
Inventor(s)
Adam Beauregard of Powhatan VA (US)
Peter Gaspare Terrana of Mechanicsville VA (US)
Vannia Gonzalez Macias of Glen Allen VA (US)
AUTOMATIC SEGMENTATION USING HIERARCHICAL TIMESERIES ANALYSIS - A simplified explanation of the abstract
This abstract first appeared for US patent application 17824206 titled 'AUTOMATIC SEGMENTATION USING HIERARCHICAL TIMESERIES ANALYSIS
Simplified Explanation
- The patent application describes methods and systems for segmenting a dataset using a feature hierarchy with multiple levels. - The feature hierarchy has different numbers of features at different levels. - The first level of the hierarchy is used to segment the dataset into multiple datasets. - A timeseries dataset is generated for each segment. - An anomaly detection model is used to identify anomalies within the timeseries datasets. - The number of anomalies detected is compared to a threshold. - If the number of anomalies does not reach the threshold, a second level of the hierarchy is used to further segment the dataset. - This process continues until a level of the hierarchy is found where the number of anomalies reaches the threshold. - Once the level is determined, a security rule is generated to address the anomalies.
Original Abstract Submitted
Methods and systems are disclosed for using a feature hierarchy with multiple levels with a different number of features at different levels to segment a dataset. The mechanism may use the first level of the hierarchy to segment a dataset into multiple datasets and then generate a timeseries dataset for each segment. Those timeseries datasets may be input into an anomaly detection model to identify a number of anomalies detected within those segments. Based on the number of anomalies not reaching a threshold, a second level of the hierarchy may be used to segment the dataset. Those segments may be input into the anomaly detection model to determine a number of anomalies for the second level. This process may continue until a level of the hierarchy is determined such that the number of anomalies reaches the threshold. The mechanism may then generate a security rule to deal with the anomalies.
