Learning-Based Incident Resolution Using Historical Log Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In enterprise environments, timely and efficient resolution of incidents or defects is challenging due to the complexity of reproducing errors, identifying root causes, and the subjective nature of plain-text descriptions, which can lead to inconsistent results and penalties.
Innovation Solution
A learning-based apparatus and method that analyzes historical data to extract patterns, reproduce incidents or defects, and provide sequences of actions for resolution, using machine learning models to match recent data with historical patterns and offer suggestions for control flow structures, enabling continuous learning from user interactions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If machine learning models are used to analyze historical data and provide resolution suggestions, then incident resolution efficiency and consistency are improved, but system complexity and implementation difficulty increase
Solution Approach 1:
The patent introduces machine learning models as intermediary components that mediate between historical incident data and resolution suggestions. These models process and transform raw historical data into structured patterns and actionable insights, reducing the complexity burden on the overall system while maintaining high resolution efficiency.
Solution Approach 2:
The system performs preliminary analysis by pre-processing historical incident data to extract patterns, relationships, and resolution strategies before actual incident resolution occurs. This preliminary action creates a knowledge base that accelerates future incident handling without requiring complex real-time processing.
2Measurement precision
If detailed analysis of historical incident data is performed to identify patterns, then resolution accuracy improves, but processing time and computational resources increase
Solution Approach 1:
The patent applies preliminary action by pre-processing historical incident data offline to extract patterns, relationships, and resolution strategies. This creates a prepared knowledge base that can be quickly queried during actual incident resolution, achieving high accuracy without time-consuming real-time analysis.
Solution Approach 2:
The system creates simplified copies or representations of complex historical data through pattern extraction and feature engineering. Instead of analyzing raw detailed data during incident resolution, the system works with condensed pattern representations that retain essential information while reducing processing requirements.
3Adaptability or versatility
If machine learning models continuously learn from user interactions, then system adaptability and resolution quality improve, but computational overhead and resource consumption increase
Solution Approach 1:
The patent implements periodic action by scheduling continuous learning operations at specific intervals or triggers rather than continuously. The machine learning models learn from user interactions periodically, updating their knowledge bases at manageable intervals that balance adaptability improvements with computational resource constraints.
Data Source
AI summary
In some examples, learning based incident or defect resolution, and test generation may include ascertaining historical log data that includes incident or defect log data associated with operation of a process, and generating, based on the historical log data, step action graphs. Based on grouping of the step action graphs with respect to different incident and defect tickets, an incident and defect action graph may be generated to further generate a machine learning model. Based on an analysis of the machine learning model with respect to a new incident or defect, an output that includes a sequence of actions may be generated to reproduce, for the new incident, steps that result in the new incident, reproduce, for the new defect, an error that results in the new defect, identify a root cause of the new incident or defect, and/or resolve the new incident or defect.