Fault Propagation Extraction via Graph Embedding
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing fault propagation condition extraction methods in communications networks have low fault coverage rates, are time-consuming, laborious, unreproducible, and not extensible, making them inefficient for wide application.
Innovation Solution
A method that uses event-object connection graphs to determine fault propagation conditions by converting them into subgraphs, updating object types, and applying graph embedding and clustering algorithms to extract and filter fault propagation conditions, thereby identifying fault sources and propagation times.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If fault propagation condition is manually summarized, then the method is simple to implement, but the fault coverage rate is low and the process is time-consuming and laborious
Solution Approach 1:
The system automatically extracts fault propagation conditions by self-serving through automated graph processing and pattern recognition, eliminating the need for manual summarization while improving fault coverage rate through comprehensive automated analysis of event-object connection graphs
Solution Approach 2:
The manual mechanical process of summarizing fault conditions is replaced with an automated computational system that processes event-object connection graphs using graph embedding algorithms and pattern recognition, substituting human labor with machine-based automated extraction
2Ease of manufacture
If manual summarization is used for fault propagation condition, then implementation is straightforward, but the method is unreproducible and inextensible
Solution Approach 1:
The automated extraction system provides universal applicability across different fault types and network configurations by processing event-object connection graphs through standardized graph embedding and pattern recognition algorithms, making the method extensible to various scenarios without manual reconfiguration
3Productivity
If automated graph processing is used, then fault coverage rate is improved, but device complexity increases
Solution Approach 1:
Graph embedding algorithms serve as intermediaries that transform complex event-object connection graphs into simplified vector representations, enabling automated pattern recognition while managing system complexity through dimensionality reduction and feature extraction
Data Source
Figure 1
Figure 2~3
Figure 4
AI summary
This application discloses a fault propagation condition extraction method and apparatus, and a storage medium, belongs to the field of communications technologies, and further relates to application of AI in the field of the communications technologies. The method includes: A network device obtains, at different time, a plurality of event-object connection graphs corresponding to a communications network; determines a plurality of subgraphs based on the plurality of event-object connection graphs; updates an object in each of the plurality of subgraphs to a corresponding object type based on a correspondence between an object and an object type, to obtain a plurality of updated subgraphs; and determines a fault propagation condition based on the plurality of updated subgraphs, where the fault propagation condition is used to indicate a path through which a fault is propagated in the communications network. In this application, the fault propagation condition does not need to be manually summarized, so that labor costs can be reduced, and efficiency of extracting the fault propagation condition can be improved. Moreover, the extracted fault propagation condition has a relatively high fault coverage rate, and the method is reproducible and extensible, and can be widely applied.