Method for verifying semantic consistency of land-air conversation based on improved LSTM-RNN

Abstract

The invention discloses a method for verifying the semantic consistency of land-air conversation based on improved LSTM-RNN. The method comprises the steps: making a corpus: making a special vocabulary according to the conversation standard and the corpus of the civil aviation and obtaining a one-hot vector of the words: generating a semantic vector of two sentences in each sentence pair; processing the semantic vectors through an average pooling method and inputting the processed semantic vector into an MLP model; learning the degree of correlation between two semantic vectors through the MLP; determining the consistency of semantics through KNN. An original method for processing a sequence based on LSTM-RNN is lower in verification precision even if preventing the gradient of an independent RNN algorithm from disappearing. The method provided by the invention employs the average pooling method for preventing the overfitting phenomenon, innovatively employs the MLP for the computing,and enables the model to be more complete in the learning degree of the correlation. Because a model in deep learning is used for automatically learning the sample features, the method does not need the statistical analysis of mass data.

Description

technical field [0001] The invention belongs to the technical field of semantic consistency verification of land and air calls in civil aviation transportation, and in particular relates to a semantic consistency verification method for land and air calls based on improved LSTM-RNN. Background technique [0002] In the field of civil aviation, aviation radiotelephone communication between controllers and pilots is very important, and it can be said that it is closely related to the safety of aircraft. Because of land-air communication errors, many air accidents have been caused. With the advancement of science and technology, although the land and air communication errors caused by equipment and hardware have been greatly reduced, communication errors caused by human factors such as controllers or pilots working for a long time, fatigue, mental stress, and excessive pressure occur from time to time . Therefore, using artificial intelligence-related theories and technologie...

AI Technical Summary

Problems solved by technology

We also applied LSTM-RNN and RNN models to the semantic matching of land and air calls, but the matching accuracy is less than 85%

Images