DETECTION, CHARACTERIZATION, AND PREDICTION OF REAL-TIME EVENTS OCCURRING APPROXIMATELY PERIODICALLY

摘要

Systems and methods for detection, characterization, and prediction of real-time events having approximate periodicity include detection of events from raw data that are approximately periodic. The detection includes obtaining (501) data from monitoring a system, wherein the data includes a plurality of records each includes at least a start time and a unique identifier; sorting (502) the plurality of records into one or more queues; analyzing (503) each of the one or more queues to detect approximate periodic chains of events in the plurality of records, wherein the periodic chains of events include periodicity that is detected based on a plurality of parameters including some missing occurrences therein; and one or more (504) of presenting detected periodic chains of events in a user interface, storing the detected periodic events, and transforming the detected periodic chains of events into statistics reflecting period characteristics for use in predictions using a machine learning model.