AI-Driven Log Event Association Through Dependency Clustering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current techniques for analyzing log events are difficult to automate and often result in incorrect correlations due to the inability to determine the dependency or independence between log events, leading to imprecise event association.
Innovation Solution
A computer-implemented method that determines the dependence and independence of training log events, clusters them based on these characteristics, and generates an event association model using machine learning algorithms to improve the precision of log event clustering.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If current techniques are used to analyze log events, then automation is difficult to achieve, but manual analysis is time-consuming and labor-intensive
Solution Approach 1:
The system performs self-service by automatically analyzing log events through machine learning models without requiring manual intervention. The event association model autonomously determines dependencies, clusters events, and identifies issues, enabling the system to serve itself in the log analysis process.
Solution Approach 2:
The patent replaces manual mechanical analysis with automated computational systems. Machine learning algorithms and event association models substitute human analysts, using computational processing to determine event dependencies and cluster log events automatically, thereby eliminating time-consuming manual review while achieving high-level automation.
2Extent of automation
If current techniques are used to correlate log events, then automation can be implemented, but incorrect correlations occur due to inability to determine dependency
Solution Approach 1:
The system changes the parameter of event analysis by introducing dependency and independence as new parameters to evaluate log events. The event association model computes these parameters to determine whether events are related or independent, enabling accurate correlation by considering additional dimensional information beyond simple event matching.
Solution Approach 2:
The system implements feedback mechanisms where the event association model continuously learns from clustered log events and refines its dependency determination. The model uses feedback from event clustering results to improve future correlations, adjusting its analysis based on patterns discovered in the data to reduce incorrect associations.
3Device complexity
If traditional log event analysis is performed, then processing is simple, but event association is imprecise and lacks accuracy
Solution Approach 1:
The system segments the log event analysis process into distinct components: event parsing, dependency determination, event clustering, and issue identification. This segmentation allows each component to be optimized independently, maintaining manageable complexity while improving overall precision through specialized processing at each stage.
Solution Approach 2:
The event association model serves as an intermediary between raw log events and final analysis results. This intermediary layer computes dependency parameters and performs intelligent clustering, bridging the gap between simple event collection and precise event association, thereby enhancing accuracy without overwhelming system complexity.
Data Source
AI summary
A computer implemented method processes log events. A computer system determines dependence and independence of training log events. The computer system clusters the training log events with determined dependence and independence to form clustered training log events. The computer system generates an event association model using the clustered training log events. The computer system clusters the log events using the event association model.