US 11,949,703 B2
Systems and methods for multivariate anomaly detection in software monitoring
Sampanna Shahaji Salunke, Dublin, CA (US); Dario Bahena Tapia, Tlaquepaque (MX); Dustin Garvey, Exeter, NH (US); Sumathi Gopalakrishnan, Fremont, CA (US); and Neil Goodman, San Rafael, CA (US)
Assigned to Oracle International Corporation, Redwood Shores, CA (US)
Filed by Oracle International Corporation, Redwood Shores, CA (US)
Filed on Nov. 15, 2022, as Appl. No. 18/055,773.
Application 18/055,773 is a division of application No. 16/400,392, filed on May 1, 2019, granted, now 11,533,326.
Prior Publication US 2023/0075486 A1, Mar. 9, 2023
Int. Cl. H04L 29/06 (2006.01); G06F 18/2411 (2023.01); G06N 20/10 (2019.01); H04L 9/40 (2022.01)
CPC H04L 63/1425 (2013.01) [G06F 18/2411 (2023.01); G06N 20/10 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
training an anomaly detection model to learn a plurality of anomaly regions within a multidimensional space including two or more dimensions of a computing application, wherein training the anomaly detection model comprises partitioning the multidimensional space into quadrants based on a quantile point within a set of training data;
storing a mapping between each respective anomaly region of the plurality of anomaly regions and a respective anomaly classifier from a set of anomaly classifiers;
evaluating a set of metrics for the computing application using the trained anomaly detection model to detect an anomaly in the computing application;
assigning, based at least in part on the mapping, a particular anomaly classifier to the anomaly from the set of anomaly classifiers;
performing a responsive action to address the anomaly based at least in part on the particular anomaly classifier.