Neural Network Causal Impact Prediction for Complex Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing network event management tools struggle to adequately analyze, respond to, predict, or prevent undesired network events due to the sheer number of events and the complexity of network topologies.
Innovation Solution
A computer program product that inputs a situation event graph, topology data, and a knowledge graph into a neural network model to determine similarity estimates between the situation event graph and stored scenarios, allowing for the identification of causal impacts and priorities of situations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional network event management tools are used to analyze and respond to events, then the system can process events, but the sheer number of events and complexity of network topologies make adequate analysis, prediction, and prevention impossible
Solution Approach 1:
The patent creates synthetic scenarios by copying and transforming historical event data and network topology information. These synthetic scenarios serve as simplified representations that capture essential patterns without the full complexity of actual network events, enabling the neural network to learn and predict causal impacts efficiently.
Solution Approach 2:
The patent extracts relevant features and relationships from the complex network topology and event data. By identifying and isolating key causal relationships and patterns, the system reduces the complexity burden while maintaining the essential information needed for accurate prediction and analysis.
2Measurement precision
If the system processes a large number of events to ensure comprehensive analysis, then the accuracy of causal impact prediction improves, but the computational resources and time required increase significantly
Solution Approach 1:
The patent performs preliminary processing by pre-computing and storing synthetic scenarios that represent potential causal patterns. These pre-generated scenarios are ready for immediate comparison against new events, eliminating the need for time-consuming real-time analysis of all possible event combinations.
Solution Approach 2:
By creating synthetic copies of historical scenarios, the system can efficiently compare new events against a pre-computed library of patterns. This copying approach allows rapid matching and identification of causal impacts without re-analyzing the entire event history for each new event.
3Loss of information
If the system uses complex analysis methods to determine causal relationships between events, then the depth of root cause analysis improves, but the ease of operation and automation difficulty worsen
Solution Approach 1:
The patent replaces complex manual analysis mechanisms with a neural network model that automatically learns causal relationships from data. The neural network substitutes for human expertise and complex analytical procedures, enabling deep causal analysis through automated pattern recognition and inference.
Solution Approach 2:
The system performs self-service by automatically generating synthetic scenarios, comparing them against new events, and identifying causal impacts without requiring manual intervention. The neural network autonomously processes information, determines relationships, and provides recommendations for remediation actions.
Data Source
AI summary
A computer program product is tangibly embodied on a non-transitory computer-readable medium and includes instructions that, when executed by at least one computing device, are configured to cause the at least one computing device to input a situation event graph and a corresponding scenario into a neural network model, where the neural network model includes a plurality of scenarios, the situation event graph represents a situation, and the corresponding scenario represents a plurality of situations similar to the situation. The neural network model processes the situation event graph and the corresponding scenario to determine a causal impact of the situation.