Adaptive AI Event Grouping for Multi-Granularity AIOps Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing event grouping methods in AIOps are inflexible and require significant manual intervention, failing to adapt to diverse customer requirements and relying heavily on engineer expertise, leading to inefficient data management.
Innovation Solution
A customizable event grouping system utilizing adaptive learning to automatically adjust to different needs through multi-granularity approaches, combining trained classification models and modified event parsers to generate tailored analytics outputs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If existing event grouping solutions are used, then basic log parsing and clustering can be performed, but the solutions cannot adapt to different customer requirements and require significant manual intervention
Solution Approach 1:
The system dynamically adjusts event grouping parameters and thresholds based on user feedback and historical data. The event parser and clustering methods are configured to learn from user corrections and automatically refine grouping criteria, transforming static event grouping into a dynamic, adaptive process that evolves with user needs
Solution Approach 2:
The system enables users to directly configure and customize event grouping parameters through an intuitive interface. Users can define their own event criteria, adjust granularity levels, and modify grouping behavior without requiring engineer intervention, allowing the system to serve its own customization needs
2Adaptability or versatility
If engineers manually review massive data records, then event grouping can be customized, but the process becomes time consuming and dependent on engineer expertise
Solution Approach 1:
The system replaces manual mechanical review of data records with automated computational methods. The event parser automatically processes logs and tickets using configurable rules, while clustering algorithms automatically group events based on similarity metrics, eliminating the need for manual data examination while maintaining customization capabilities
Solution Approach 2:
The system allows dynamic adjustment of event grouping parameters such as similarity thresholds, time windows, and event criteria. By changing these parameters based on user feedback and performance metrics, the system adapts to different customization needs without requiring manual re-examination of data records
3Productivity
If basic log parsers or cluster methods are used, then event grouping can be performed, but the solutions allow limited customization
Solution Approach 1:
The system combines multiple event grouping approaches (log parsing, clustering, machine learning) into a unified platform that can perform various customization functions. The same core engine supports different granularity levels, event types, and grouping strategies, allowing high productivity while maintaining extensive adaptability to different customer requirements
Data Source
AI summary
System and methods for adaptive multi-granularity event groupings are provided. In embodiments, a method includes: determining to group IT operations data at a first level of granularity for similar events or at a second level of granularity for related events based on user input of a data grouping event; parsing, by an event parser, the IT operations data into one or more groups of similar events based on text information and parser rules in response to determining to group the IT operations data at the first level of granularity; obtaining user feedback indicating the one or more groups of similar events require modification; determining one or more keywords of the IT operations data using an artificial intelligence model in response to the user feedback; and updating the parser rules for the event parser based on the one or more keywords, thereby generating updated parser rules.