Electronic countermeasure equipment relation extraction method based on BERT-TKNB model

Abstract

The invention provides an electronic countermeasure equipment relation extraction method based on a BERT-TKNB model, and belongs to the technical field of knowledge graph relation extraction. The method comprises the following steps: S1, acquiring and processing an electronic countermeasure equipment text data set; s2, constructing a word embedding model in the field of electronic countermeasure equipment; s3, constructing a bidirectional encoder composed of a multi-head self-attention mechanism and a feedforward neural network; s4, constructing a TKAN multilayer neural network model, and performing feature extraction; step S5, constructing a naive Bayes classifier so as to carry out classification; and S6, training the overall model on an electronic countermeasure equipment text data set, and evaluating a result. According to the method, the reliability and practicability of electronic countermeasure equipment text relation extraction can be improved.

Images