Traffic named entity identification method and device, computer equipment and storage medium

Abstract

The embodiment of the invention discloses a traffic named entity recognition method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining a corpus set, and carrying out the preprocessing of the corpus set, which comprises the steps: carrying out the text division of each corpus into a plurality of text sequences through employing a regular expression; inputting the plurality of text characters into a trained bidirectional recurrent neural network and a conditional random field to obtain a traffic named entity; thus, the language preprocessing model based on the self-attention mechanism can learn the dependency relationship of long-distance texts, enhance the semantic features of characters, overcome the problem that proper nouns in the traffic field are high in professionality, improve the accuracy of NER tasks, and compared with a traditional mainstream RNN-CRF model, BERT can perform parallel processing, the training speed is high, the comprehensive recognition performance is better, and meanwhile, the recognition efficiency is improved. BERT-Bi-LSTM-CRF is good at mining semantic information of characters, and can effectively solve the problem of lack of training corpora in the traffic field.

Description

technical field [0001] The present invention relates to the technical field of traffic name recognition, and in particular, to a traffic named entity recognition method, device, computer equipment and storage medium. Background technique [0002] With the improvement of the level of autonomy of complex transportation systems, Intelligent Transportation System (ITS) gradually transitions to Autonomous Transportation System (ATS), and more physical components are incorporated into it. However, descriptive knowledge about physical components usually exists in unstructured data such as transportation industry data. The degree of knowledge integration and sharing is not high, the display form is not intuitive, and it is easy to cause errors in the process of dissemination. How to extract these components efficiently and accurately is one of the most important steps in the information representation and management of complex giant systems of transportation. [0003] Knowledge gra...

AI Technical Summary

Problems solved by technology

[0005] In view of this, the present invention provides a traffic named entity recognition method, computer equipment and storage medium, this method is aimed at the field of autonomous traffic, overcomes the problem that the prior art fails to effectively identify the component entities in this field

Images