Root Cause Discovery Engine Using ML Dependency Graphs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Identifying root causes in complex IT infrastructures is challenging due to their complexity and the difficulty in managing large datasets, especially with technologies like micro-services and distributed or cloud environments, requiring manual human intervention and extensive data analysis.
Innovation Solution
A root cause discovery engine that utilizes a machine learning model and dependency graph to analyze operations data, identifying correlations between metrics, events, and conditions to automatically detect and resolve issues.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual analysis by specialized human operators is used to identify root causes, then comprehensive understanding and troubleshooting capability are achieved, but time consumption and operational complexity increase significantly
Solution Approach 1:
The system pre-computes and stores causal relationships, dependencies, and correlations among IT entities in a knowledge base before problems occur. When an issue arises, the system queries this pre-prepared knowledge base rather than analyzing raw data from scratch, enabling rapid root cause identification while maintaining high accuracy through pre-validated causal models.
Solution Approach 2:
The patent introduces an intermediary system (the automated root cause analysis system with knowledge base) that mediates between the complex IT infrastructure data and the human operator. This intermediary processes and structures the data, presenting pre-analyzed causal relationships to operators, thereby reducing both the time required and the manual analysis burden while preserving accurate root cause identification.
2Measurement precision
If comprehensive data collection from all IT entities is performed, then complete problem diagnosis is achieved, but data management complexity and processing burden increase
Solution Approach 1:
The system extracts and isolates only the relevant data and relationships needed for root cause analysis from the vast IT infrastructure data. The knowledge base stores pre-extracted causal relationships, entity dependencies, and correlation patterns, separating the essential diagnostic information from the overwhelming bulk of raw operational data, thereby reducing data management complexity while maintaining complete problem diagnosis capability.
Solution Approach 2:
The patent segments the complex IT infrastructure into discrete entities (nodes, endpoints, servers, applications) and their relationships. The knowledge base organizes data by entity types and relationship categories, allowing the system to query specific segments relevant to a problem rather than processing all infrastructure data uniformly, thus reducing processing burden while ensuring comprehensive diagnosis.
3Productivity
If automated systems are implemented to reduce manual analysis, then troubleshooting efficiency improves, but system complexity and implementation difficulty increase
Solution Approach 1:
The system creates a virtual copy of the IT infrastructure's causal relationships and dependencies in the knowledge base, rather than directly manipulating the actual infrastructure data. This copied representation allows automated analysis without complex real-time data collection and processing, simplifying system implementation while maintaining high troubleshooting efficiency through query-based analysis of the copied knowledge model.
Data Source
AI summary
The disclosed technology relates identifying causes of an observed outcome. A system is configured to receive an indication of a user experience problem, wherein the user experience problem is associated with observed operations data including an observed outcome. The system generates, based on the observed operations data, a predicted outcome according to a model, determines that the observed outcome is within range of the predicted outcome, and identifies a set of candidate causes of the user experience problem when the observed outcome is within range of the predicted outcome.