CPC G06F 11/3457 (2013.01) [G06F 11/0709 (2013.01); G06F 11/0769 (2013.01); G06F 18/214 (2023.01); G06N 3/04 (2013.01)] | 20 Claims |
1. A method of monitoring for faults in a cloud based network for a plurality of features comprising an application and dependent features, the method comprising:
generating a graphical representation of the plurality of features comprising a plurality of nodes and corresponding relationships between the nodes, each node corresponding to one of the plurality of features;
monitoring for events for the plurality of features, the events corresponding to one or more of the nodes, to generate monitored events;
populating a graph database with the monitored events;
training a graph neural network (GNN) using a training dataset derived from the monitoring and the populating;
classifying each of the nodes with the trained GNN, the classification comprises a prediction of a failure of at least one node;
based on the classifying, for a first failure node corresponding to the prediction, automatically revising a threshold for an existing alert for the first failure node; and
retraining the trained GNN using the revised threshold for the existing alert.
|