US 11,687,798 B2
Dynamic heuristic packages and metrics for network assurance using a deep fusion reasoning engine
Hugo Latapie, Long Beach, CA (US); Enzo Fenoglio, Issy-les-Moulineaux (FR); Carlos M. Pignataro, Cary, NC (US); Nagendra Kumar Nainar, Morrisville, NC (US); and David Delano Ward, Somerset, WI (US)
Assigned to Cisco Technology, Inc., San Jose, CA (US)
Filed by Cisco Technology, Inc., San Jose, CA (US)
Filed on Mar. 6, 2020, as Appl. No. 16/811,823.
Prior Publication US 2021/0279602 A1, Sep. 9, 2021
Int. Cl. G06F 17/00 (2019.01); G06N 5/025 (2023.01); G06N 5/022 (2023.01)
CPC G06N 5/025 (2013.01) [G06N 5/022 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A method comprising:
receiving, at a deep fusion reasoning engine, network telemetry data collected from a network, wherein the deep fusion reasoning engine is initiated with a seed ontology to populate a knowledge base of the deep fusion reasoning engine;
learning, by the deep fusion reasoning engine, resource utilizations for different heuristic packages that can be used in the network to evaluate operation of the network;
selecting, by the deep fusion reasoning engine, one of the heuristic packages based on the resource utilizations learned for the different heuristic packages, wherein the selected heuristic package comprises a subservice and a set of rules to be evaluated; and
deploying, by the deep fusion reasoning engine, the selected heuristic package for execution by a device in the network to evaluate operation of the network using the set of rules.