| CPC G06F 16/35 (2019.01) [H04L 67/10 (2013.01)] | 20 Claims |
|
1. An apparatus comprising:
at least one processing platform comprising at least one processor coupled to at least one memory, the at least one processing platform, when executing program code, is configured to:
obtain data associated with execution of at least one of a plurality of applications in an information processing system;
extract features from the obtained data;
monitor, with a first agent of a plurality of first agents, the obtained data to identify a source application of the plurality of applications, wherein each first agent has a corresponding classifier for use in a machine learning classification process, and wherein each first agent is operatively coupled to a pretrained machine learning library selected based on a defined purpose of the information processing system;
capture the extracted features, in response to discovery thereof, using a second agent of a plurality of second agents, wherein respective ones of the plurality of second agents are operatively coupled to respective ones of the plurality of first agents and their corresponding classifiers;
select, using the second agent, a reduced subset of features from the extracted features for use in the machine learning classification process configured to determine an intent of the obtained data;
selectively update, using the second agent, the corresponding classifiers wherein an improving feature is discovered;
send an alert to the information processing system of an existence, a type, and a location of the obtained data; and
determine, using a third agent of a plurality of third agents, if the improving feature is applicable to all of the corresponding classifiers, wherein respective ones of the plurality of third agents are operatively coupled to respective ones of the plurality of second agents.
|