US 12,254,423 B2
Dynamic anomaly reporting
Kanwaldeep K. Dang, Sammamish, WA (US); Anand Nikhil Mehta, Bellevue, WA (US); Kiran Kumar Bushireddy, Woodinville, WA (US); Swapnesh Patel, Bothell, WA (US); and Bnayahu Makovsky, KirYat-Ono (IS)
Assigned to ServiceNow, Inc., Santa Clara, CA (US)
Filed by ServiceNow, Inc., Santa Clara, CA (US)
Filed on Aug. 8, 2022, as Appl. No. 17/818,140.
Application 17/818,140 is a continuation of application No. 16/721,629, filed on Dec. 19, 2019, granted, now 11,410,061.
Claims priority of provisional application 62/869,888, filed on Jul. 2, 2019.
Prior Publication US 2022/0385529 A1, Dec. 1, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 3/0482 (2013.01); G06F 3/04847 (2022.01); G06N 7/00 (2023.01); H04L 41/0686 (2022.01); H04L 41/22 (2022.01); H04L 67/10 (2022.01); G06N 20/00 (2019.01)
CPC G06N 7/00 (2013.01) [G06F 3/0482 (2013.01); G06F 3/04847 (2013.01); H04L 41/0686 (2013.01); H04L 41/22 (2013.01); H04L 67/10 (2013.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A system, comprising:
one or more hardware processors; and
a non-transitory memory storing instructions that, when executed by the one or more hardware processors, cause the one or more hardware processors to perform actions comprising:
receiving an input indicative of one or more anomaly detection action options associated with time-series metric data for one or more configuration items of an information technology infrastructure, wherein the one or more configuration items comprise one or more hardware components, one or more software applications, one or more databases, or a combination thereof, wherein the time-series metric data comprises information related to at least one of a network bandwidth, a temperature, or a CPU load, and wherein the one or more anomaly detection action options indicate respective actions to process the time-series metric data;
determining one or more classifications of the time-series metric data;
generating a statistical model used to identify anomalies in the time-series metric data based on the one or more classifications of the time-series metric data;
automatically selecting a particular anomaly detection action option of the one or more anomaly detection action options based upon the statistical model;
updating a configuration setting of the time-series metric data using the particular anomaly detection action option; and
performing an action on the time-series metric data based upon the configuration setting.