Control instruction classification method based on semantic network

Abstract

The invention discloses a control instruction classification method based on a semantic network, and aims to construct a computer readable structured control instruction and provide a basis for automatic processing of the control instruction, and form a predicate logic structure to provide a basis for realizing a knowledge reasoning system. By processing an unstructured control instruction, the method can realize the following auxiliary functions: extracting information carried by a basic control term appearing in the control instruction; extracting action, state and other information of the aircraft and performing analog simulation; and forming computer readable structured information to provide data for knowledge reasoning. According to the method, aiming at the condition that a complexcontrol instruction comprises a plurality of control intentions, whether different arguments in the control instruction are associated with verbs of the different control intentions or not is judged through a deep neural network, and the associated verbs and argument words are brought into a semantic network for semantic role marking.

Description

technical field [0001] The invention belongs to the technical field of air traffic control automation systems, in particular to a method for classifying control instructions based on semantic web. Background technique [0002] With the vigorous development of China's civil aviation industry in the past 30 years, the demand for air traffic management has continued to expand, resulting in increasingly prominent safety hazards. According to statistics, in the past flight safety accidents, human factors accounted for more than 75%, and accidents caused by controller errors accounted for 25%. At present, the mainstream method to solve conflicts caused by controller errors is to strengthen the monitoring equipment of the scene, and prevent conflicts by using equipment such as surface surveillance radar and multilateration system sensors. At the same time, some more advanced solutions based on artificial intelligence have also been proposed, such as using speech recognition techno...

AI Technical Summary

Problems solved by technology

Semantic analysis of control instructions needs to design a structured instruction template. The traditional method is to design a structured template based on ground and air call rules, and extract the basic control terms, subject, predicate and other keywords in the instruction by extracting keywords. The method cannot describe the relationship between different component words, and cannot understand complex regulatory instructions containing multiple verbs with different regulatory intentions more precisely, so it is limited in the process of semantic analysis and understanding of actual regulatory instructions

Images