US 12,135,605 B2
Probabilistic root cause analysis
Sai Eswar Garapati, Hyderabad (IN); and Erhan Giral, Danville, CA (US)
Assigned to BMC Software, Inc., Houston, TX (US)
Filed by BMC Software, Inc., Houston, TX (US)
Filed on Mar. 31, 2022, as Appl. No. 17/657,628.
Claims priority of provisional application 63/269,807, filed on Mar. 23, 2022.
Claims priority of provisional application 63/262,997, filed on Oct. 25, 2021.
Claims priority of provisional application 63/262,994, filed on Oct. 25, 2021.
Claims priority of provisional application 63/262,995, filed on Oct. 25, 2021.
Claims priority of provisional application 63/261,627, filed on Sep. 24, 2021.
Claims priority of provisional application 63/261,629, filed on Sep. 24, 2021.
Prior Publication US 2023/0095270 A1, Mar. 30, 2023
Int. Cl. G06F 11/07 (2006.01); G06F 16/901 (2019.01); G06N 3/08 (2023.01); G06N 5/022 (2023.01); H04L 41/0631 (2022.01); H04L 41/12 (2022.01); H04L 41/14 (2022.01)
CPC G06F 11/0793 (2013.01) [G06F 11/0709 (2013.01); G06F 11/0769 (2013.01); G06F 11/079 (2013.01); G06F 16/9024 (2019.01); G06N 3/08 (2013.01); G06N 5/022 (2013.01); H04L 41/0636 (2013.01); H04L 41/065 (2013.01); H04L 41/12 (2013.01); H04L 41/145 (2013.01)] 21 Claims
OG exemplary drawing
 
1. A computer-implemented method for identifying root causes, the computer-implemented method comprising:
receiving an event group, wherein the event group includes a plurality of nodes;
constructing and extracting a causal graph for the plurality of nodes from the event group using one or more of historical priors, topological priors, real time priors, and custom knowledge priors, wherein the causal graph uses edges between nodes of the causal graph to indicate a probabilistic causal relationship between the nodes and a normalized causal strength of the probabilistic causal relationship between the nodes; and
identifying a probabilistic root cause from the plurality of nodes by ranking graph vertices from the causal graph using a root cause inspector.