CPC G06F 9/30036 (2013.01) [G06F 9/542 (2013.01); G06F 18/214 (2023.01); G06N 3/08 (2013.01)] | 18 Claims |
1. A method comprising:
receiving, by one or more computer systems, occurrence data including information for a plurality of computing processes and a plurality of events associated with the plurality of computing processes;
training, by the one or more computer systems, a neural network using a self-supervised machine learning (ML) algorithm, the training resulting in generation of:
a set of distributed process representations based on the occurrence data, the set of distributed process representations including, for each computing process in the plurality of processes, a distributed process representation that encodes a sequence of events associated with the computing process in the occurrence data; and
a set of distributed event representations based on the occurrence data, the set of distributed event representations including, for each event in the plurality of events, a distributed event representation that encodes one or more processes associated with the event and one or more events that occur within a window of the event in the occurrence data; and
training, by the one or more computer systems, one or more ML models using the set of distributed process representations and the set of distributed event representations.
|