Knowledge Graph Navigation for Root Cause Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The cognitive load from numerous intelligence reports in root cause analysis (RCA) can overwhelm users, hindering effective navigation and analysis, as existing methods lack efficient organization and visualization tools.
Innovation Solution
A method for automatically constructing and organizing a navigation graph using input data from reports, where nodes represent individual reports and edges connect reports sharing common variables, with edge weights indicating relationship strength, facilitating hierarchical clustering and user interface navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If exhaustive intelligence reports are used for root cause analysis, then analysis completeness is improved, but cognitive load increases and navigation becomes difficult
Solution Approach 1:
The patent segments the exhaustive intelligence reports into a hierarchical knowledge graph structure with multiple levels (L1-L4). Reports are organized into clusters at different abstraction levels, allowing users to navigate from high-level summaries to detailed information progressively, reducing cognitive load while maintaining access to complete analysis data.
Solution Approach 2:
The patent introduces a new dimensional organization by creating a hierarchical knowledge graph structure that adds vertical layers (L1-L4) to the traditional flat report structure. This multi-dimensional organization allows users to navigate through levels of abstraction rather than linearly through reports, improving both completeness and navigability.
2Measurement precision
If multiple intelligence reports are provided for comprehensive analysis, then diagnostic accuracy is improved, but information overload occurs
Solution Approach 1:
The patent merges multiple intelligence reports into a unified knowledge graph structure where related reports are clustered together and connected through shared variables. This consolidation presents comprehensive diagnostic information in an integrated view rather than as separate reports, maintaining diagnostic accuracy while reducing information overload.
Solution Approach 2:
The patent applies local quality by providing different levels of information detail at different hierarchical levels. L1 provides high-level summaries, L2 provides cluster-level details, L3 provides report-level information, and L4 provides granular data. Users access appropriate levels of detail based on their needs, receiving comprehensive information without being overwhelmed by all details simultaneously.
Data Source
AI summary
A method for automatically constructing and organizing a navigation graph includes receiving input data including a plurality of reports, at least two of the reports including plots, extracting a plurality of variables from the plots, building a knowledge graph from the input, wherein each node of the knowledge graph is associated with an individual one of the plots and an edge is added between two of the nodes sharing at least one of the variables in common, adding an edge weight to each of the edges of the knowledge graph, and organizing the nodes of the knowledge graph for navigation, wherein the knowledge graph is displayed in a user interface.