Knowledge Graph Remediation for Performance Management Incidents
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Performance management systems face challenges in recommending timely and effective remediation actions for incidents, particularly for low-frequency incidents, which often require manual searches and domain expert involvement, leading to delays and inefficiencies.
Innovation Solution
A recommendation system constructs a knowledge graph from historical incident reports, classifies incidents as short head or long tail, and uses machine learning to determine remediation actions, combining knowledge graph traversal and web search results to provide ranked recommendations for administrators.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual searches and domain expert involvement are used to determine remediation actions for low-frequency incidents, then accuracy of remediation recommendations is improved, but time consumption and operational complexity increase
Solution Approach 1:
The system performs preliminary action by constructing a knowledge graph from historical incident reports before new incidents occur. The knowledge graph pre-stores problem descriptors, qualifier entities, and remediation actions with their relationships, enabling rapid retrieval and recommendation without manual searches when incidents occur.
Solution Approach 2:
The patent introduces an intermediary mechanism - the knowledge graph - that mediates between historical incident data and current incident resolution. The knowledge graph acts as a structured intermediary that automatically retrieves relevant remediation actions based on matched problem descriptors and qualifier entities, replacing manual expert searches.
2Reliability
If manual searches and expert involvement are used for incident remediation, then quality of remediation actions is improved, but productivity and automation level deteriorate
Solution Approach 1:
The system implements self-service by enabling automatic retrieval and recommendation of remediation actions through knowledge graph traversal. When a new incident occurs, the system automatically matches problem descriptors and qualifier entities against the knowledge graph, retrieves relevant remediation actions, and provides ranked recommendations without requiring manual expert intervention.
Solution Approach 2:
The patent replaces the mechanical system of manual expert searches and manual documentation with an automated information processing system. The knowledge graph stores structured relationships between problems and solutions, and automated algorithms traverse the graph to retrieve recommendations, substituting human manual work with computational processes.
3Measurement precision
If comprehensive historical incident data is analyzed to improve remediation recommendations, then accuracy is improved, but system complexity increases
Solution Approach 1:
The system applies segmentation by dividing the knowledge graph into distinct hierarchical levels: problem descriptors at the top level, qualifier entities as intermediate nodes with specific attributes, and remediation actions at the bottom level. This segmentation allows the system to manage complex historical data through structured, modular components that can be independently processed and retrieved.
Data Source
AI summary
According to an aspect, a (recommendation) system constructs a knowledge graph based on problem descriptors and remediation actions contained in multiple incident reports previously received from a performance management (PM) system. Each problem descriptor and remediation action in an incident report are represented as corresponding start node and end node in the knowledge graph, with a set of qualifier entities in the incident report represented as causal links between the start node and the end node. Upon receiving an incident report related to an incident identified by the PM system, the system extracts a problem descriptor and a set of qualifier entities. The system traverses the knowledge graph starting from a start node corresponding to the extracted problem descriptor using the set of qualifier entities to determine end nodes representing a set of remediation actions. The system provides the set of remediation actions as recommendations for resolving the incident.