Self-Learning Integrity Management System and Related Methods
AssigneeIntegrien Corporation
InventorMazda A. Marvasti
Life of this patent
Estimating the term…
Abstract
An integrity management system predicts abnormalities in complex systems before they occur based upon the prior history of abnormalities within the complex system. A topology of the nodes of a complex system is generated and data is collected from the system based on predetermined metrics. In combination with dynamic thresholding, fingerprints of the relevant nodes within a complex system at various time intervals prior to the occurrence of the abnormality are captured and weighted. The fingerprints can then be applied to real-time data provide alerts of potential abnormality prior to their actual occurrence.
Claims39
A integrity management system comprising, in combination:
- a topology of nodes;
- a data collector;
- at least one heuristic generator that provides at least one heuristic;
- and
- an alerter, the alerter providing a notice of an occurrence of a potential event prior to the occurrence of the potential event;
- and
- wherein data is collected by the data collector and compared to the at least one heuristic to provide a probability of a potential event;
- and
- wherein if the probability crosses a threshold value, the alerter provides the notice.
A integrity management system comprising, in combination:
- a computer;
- a topology of nodes;
- a data collector;
- at least one heuristic generator that provides at least one heuristic;
- and
- an alerter, the alerter providing a notice of a potential event prior to the occurrence of the potential event;
- and
- wherein data is collected by the data collector and compared to the at least one heuristic to provide a probability of a potential event using the computer;
- and
- wherein if the probability crosses a threshold value, the alerter provides the notice.
A dynamic thresholding system comprising, in combination:
- at least one dynamically determined threshold associated with a metric, the dynamically determined threshold being changed at set intervals based on the metric's observed data for a historical time period;
- and
- a subsystem for detecting trend states, the trend state occurring when any dynamically determined threshold is exceeded continuously for a time period;
- wherein when the subsystem detects a trend, an alert state is activated.
A method for detecting abnormalities in nodes by providing an integrity management system that performs steps comprising, in combination:
- discovering a plurality of nodes;
- constructing a topology of node interconnectedness;
- collecting data;
- using historical data to form at least one heuristic;
- applying the at least one heuristic to the data, the application of the at least one heuristic outputting a probability of a potential event occurring prior to the actual occurrence of the event;
- and
- at least one of generating an alert prior to the occurrence of the event and ameliorating the potential event.
A machine-readable medium having program instructions stored thereon executable by a processing unit for performing the steps of:
- discovering a plurality of nodes;
- constructing a topology of node interconnectedness;
- collecting data;
- using historical data to form at least one heuristic;
- applying the at least one heuristic to the data, the application of the at least one heuristic outputting a probability of a potential event occurring prior to the actual occurrence of the event;
- and
- at least one of generating an alert prior to the occurrence of the event and ameliorating the potential event.
Dependencies are inferred from the claim text.