Aviation safety accident causal relationship extraction method

Abstract

The invention discloses an aviation safety accident causal relationship extraction method. The method comprises the steps of text data preprocessing; extracting explicit causal relationships; Extracting an implicit causal relationship; and generating a causal relationship chain. The method has the advantages that the mode matching method is applied to extraction of the explicit causal relationshipof the aviation safety accident, and the bidirectional LSTM method based on the self-attention mechanism is adopted; applying the At-BiLstm + PI to implicit causal relationship extraction, giving a single accident causal relationship chain on the basis that identification and extraction of a single aviation safety accident causal relationship pair are effectively achieved, and good data and method support is provided for scene reproduction and comprehensive analysis of aviation safety accidents.

Description

technical field [0001] The invention belongs to the technical field of aviation, and in particular relates to a method for extracting causality of aviation safety accidents. Background technique [0002] The analysis of the causality of aviation safety accidents is an effective means to prevent and avoid aviation safety accidents. With the development of the civil aviation industry, the causes of aviation unsafe accidents are diverse and complex, so the analysis of accident causality faces new difficulties. The current research on the causality analysis of aviation safety accidents mainly uses statistical methods to analyze the category distribution of accident causes, or uses Bayesian networks to analyze the probability distribution of a single cause on the accident results. On the one hand, these methods are difficult to cover all categories of accident causes, and on the other hand, they cannot effectively explore the complete process of the occurrence and development of ...

AI Technical Summary

Problems solved by technology

According to whether there are causal prompt words in the sentence, the causal relationship can be divided into explicit causal relationship and implicit causal relationship. The extraction methods include pattern matching-based methods and machine learning-based methods. For explicit causal relationship extraction, generally use Pattern matching method, the extraction accuracy of this method is high, but the premise is that an extraction template with causal prompt words needs to be constructed, and the extraction efficiency of implicit causal relationship is not high; causal relationship is a kind of relationship, and in relationship extraction The machine learning method can be used for the extraction of implicit causal relationship. In addition to the common CNN, RNN, LSTM method, the RHNB method and Ab-NTM method are also used for relationship extraction, but most of the above models need external knowledge base or natural language processing tools to select high-quality features, and the relationship extraction effect is affected by the quality of the selected features

Images