Event Window Classification for Automated IT Ticket Creation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing IT event monitoring systems are limited by relying on a single source of information and do not effectively group events into actionable windows, often requiring manual intervention for ticket creation.
Innovation Solution
A method utilizing a machine learning model to classify event windows as actionable by applying a classification model to information from multiple data sources, including logs, metrics, and topology data, and automatically creating event tickets.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a single source of information is used for event monitoring, then the system complexity is reduced, but the accuracy of identifying significant problems deteriorates
Solution Approach 1:
The patent merges multiple data sources (logs, metrics, topology data) into a unified event monitoring system that processes all sources through a single machine learning classification model, achieving accurate problem identification without proportionally increasing system complexity
Solution Approach 2:
The machine learning classification model serves as a universal component that handles multiple data types and sources, performing the function of analyzing diverse information streams through a single multi-functional model rather than requiring separate specialized systems
2Productivity
If manual intervention is required for ticket creation, then the system complexity is reduced, but the productivity deteriorates
Solution Approach 1:
The system performs self-service by automatically creating event tickets based on machine learning classification results without requiring manual intervention, where the system monitors itself and autonomously performs the ticket creation function
Solution Approach 2:
The patent replaces the mechanical manual process of ticket creation with an automated machine learning-based system that uses classification models to automatically generate tickets, substituting human operation with intelligent automation
3Reliability
If events are not grouped into windows, then the processing speed is improved, but the reliability of problem diagnosis deteriorates
Solution Approach 1:
The patent segments events into time windows to group related events together, allowing the machine learning model to analyze contextual patterns within each window while maintaining efficient processing through structured temporal organization
Data Source
AI summary
Computer hardware and/or software that performs the following operations: (i) identifying rules for relating events in an event monitoring system; (ii) determining an event window having a set of related events within a particular time window, based, at least in part, on the rules; (iii) classifying the event window as actionable by applying a machine learning based classification model to information pertaining to the event window, the information originating from a plurality of data sources; and (iv) creating an event ticket for the event window in the event monitoring system.