US 11,991,037 B2
Systems and methods for reducing a quantity of false positives associated with rule-based alarms
Bharatwaaj Shankar, Chennai (IN); Srinivasarao Valluru, Hyderabad (IN); and Ria V. Sijo, Flower Mound, TX (US)
Assigned to Verizon Patent and Licensing Inc., Basking Ridge, NJ (US)
Filed by Verizon Patent and Licensing Inc., Basking Ridge, NJ (US)
Filed on Feb. 8, 2021, as Appl. No. 17/170,098.
Prior Publication US 2022/0255791 A1, Aug. 11, 2022
Int. Cl. H04L 41/0631 (2022.01); G06N 5/04 (2023.01); G06N 20/00 (2019.01); H04L 9/40 (2022.01); H04L 41/0681 (2022.01)
CPC H04L 41/0636 (2013.01) [G06N 5/04 (2013.01); G06N 20/00 (2019.01); H04L 41/0681 (2013.01); H04L 63/1416 (2013.01); H04L 63/1441 (2013.01); H04L 63/20 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
receiving, by a device, alarm data identifying alarms associated with occurrences of an event;
determining, by the device, hit rates associated with the alarms of the alarm data;
determining, by the device, precisions associated with the alarms of the alarm data;
identifying, by the device, from the alarm data, and based on the hit rates and the precisions, a set of alarms that include false positives;
performing, by the device, feature engineering on the set of alarms to extract features from a feature store;
training, by the device, a model with the features to generate a trained model;
processing, by the device, the alarm data, with the trained model, to determine rules for reducing a quantity of future alarms that include the false positives;
identifying, by the device and from the rules for reducing the quantity of future alarms that include the false positives, a set of rules that satisfy a threshold for reducing the quantity of future alarms that include the false positives; and
performing, by the device, one or more actions based on the set of rules.