US 11,940,894 B2
Machine learning models for automated anomaly detection for application infrastructure components
Michael D. Trapani, Victor, NY (US); and Jeevan Kumar Goud Bandharapu, Lodi, NJ (US)
Assigned to Express Scripts Strategic Development, Inc., St. Louis, MO (US)
Filed by Express Scripts Strategic Development, Inc., St. Louis, MO (US)
Filed on Aug. 15, 2022, as Appl. No. 17/888,104.
Application 17/888,104 is a continuation of application No. 17/126,250, filed on Dec. 18, 2020, granted, now 11,416,369.
Prior Publication US 2022/0391300 A1, Dec. 8, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 11/34 (2006.01); G06F 11/30 (2006.01); G06F 17/18 (2006.01); G06N 20/00 (2019.01); H04L 41/14 (2022.01); H04L 43/045 (2022.01); H04L 43/08 (2022.01)
CPC G06F 11/3409 (2013.01) [G06F 11/3055 (2013.01); G06F 11/3457 (2013.01); G06F 17/18 (2013.01); G06N 20/00 (2019.01); H04L 41/145 (2013.01); H04L 43/045 (2013.01); H04L 43/08 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer system for automated detection of anomalous performance of application infrastructure components, the computer system comprising:
a memory device configured to store at least one machine learning model and measured historical performance metrics for the application infrastructure components; and
at least one processor communicatively coupled to the memory device, the at least one processor configured to:
train the at least one machine learning model using the measured historical performance metrics to generate key performance indicators associated with the application infrastructure components;
generate an element for display in a multi-level application monitoring interface, wherein the element corresponds to a first component of the application infrastructure components, and wherein the element includes a status indicator;
use the at least one machine learning model to generate the key performance indicators for the first component, based on a reporting window time period associated with measured performance metrics and an outlier threshold value;
in response to generating the key performance indicators for the first component, automatically present the key performance indicators for the first component using the element including the status indicator, via a display device visible to an operator and communicatively coupled to the at least one processor; and
in response to the key performance indicators indicating a performance anomaly condition for the first component, automatically perform a self-healing operation associated with the key performance indicators, wherein the self-healing operation includes:
(i) automatically modifying operation of the first component, including at least one of:
restarting the first component, and
starting a new instance of the first component, and
(ii) automatically generating a ticket request to monitor the operation of the first component.