Airworthiness regulation structure semantic association method and system

Abstract

The invention discloses an airworthiness regulation structure semantic association method and system. The method comprises the steps of performing format cleaning on airworthiness regulation texts; constructing a clause hierarchical feature rule template according to the hierarchical structure features of the airworthiness regulation text after format cleaning; according to the article level feature rule template, identifying the article level of the current row unit, extracting the content of the basic article unit as a node, and allocating a corresponding attribute value to each basic article unit, wherein the attribute value is a title level; judging whether a semantic connection relationship exists between the node pairs or not according to an edge structure judgment mechanism; and performing structure conversion on the airworthiness regulation text according to a judgment result. According to the invention, the special article structure of the airworthiness regulation is convertedinto a general type of natural language structure with complete semantic information and syntax structure, so that the adverse effect of the special article structure of the airworthiness regulationtext on natural language processing related tasks is eliminated, and subsequent data intelligent and automatic analysis and processing are facilitated.

Description

technical field [0001] The invention relates to the technical field of airworthiness safety, in particular to a method and system for semantic association of airworthiness regulation structures. Background technique [0002] Natural language processing technology integrates the knowledge framework of linguistics and computer science, the purpose is to understand, analyze and apply human language through computers, so as to improve the effectiveness of communication and control between humans and computers. At present, the objects of natural language processing are mainly texts in the form of general language, such as: "Yao Ming's height is 226 centimeters". This type of text data has no special format, complete semantic information and grammatical structure, and is suitable for tasks related to natural language processing. However, the safety information contained in airworthiness regulations is organized and stored in a special textual structure of laws and regulations, wh...

AI Technical Summary

Problems solved by technology

Graph-based natural language processing methods, such as rhetorical structure theory and dependency syntactic analysis, can solve discourse analysis and syntactic analysis of general types of texts, but cannot be applied to airworthiness regulations

The main reasons include the following two points: 1) All the article units of the airworthiness regulations (in units of articles, clauses, items, and items) have the problem of incomplete syntax structure, that is, the semantic information, and must be combined with the corresponding superior basic article units Only then can a complete syntactic structure be formed to express complete semantic information; 2) The hierarchical structure relationship of legal provisions leads to multiple and multiple nested relationships between entities, adding syntactic analysis, chapter-level relationship extraction and knowledge map construction The complexity of natural language processing tasks such as

For the hierarchical structure of special provisions of airworthiness regulations, there is still a lack of corresponding text structure processing and semantic cohesion methods

Images