BERT model-based medical text understanding method and system

Abstract

The invention relates to the technical field of text processing, and discloses a BERT model-based medical text understanding method, which comprises the steps of obtaining medical text data, and filtering out invalid medical text data by utilizing a sentence filtering model; according to the filtered medical text data, generating large-scale medical text data by utilizing a medical text generationmodel based on text copying; training a medical text entity recognition model by utilizing the generated large-scale medical field text data; performing entity recognition on a to-be-processed medical text by utilizing the trained medical text entity recognition model; performing semantic extraction on the medical text entity by utilizing an attention-based information extraction method to obtainsemantic features of the medical text entity; and understanding the medical text by utilizing a multilayer perceptron according to the semantic features of the medical text entity. The invention further provides a BERT model-based medical text understanding system. According to the invention, understanding of medical texts is realized.

Description

technical field [0001] The present invention relates to the technical field of text processing, in particular to a BERT model-based medical text understanding method and system. Background technique [0002] With the improvement of the economic level, people will inevitably pay more attention to their own health status, and at the same time, the requirements for the level of medical services are also getting higher and higher. The existing medical services are limited by various factors such as resources and management, and it is difficult to meet the growing needs of the people. Intelligent medical care is becoming more and more important, and making full use of the knowledge in medical texts can speed up the process of intelligent medical care. [0003] At present, there are few studies on text understanding in the medical field. Traditional named entity recognition models based on neural networks require a large amount of labeled training data. However, data proper nouns...

AI Technical Summary

Problems solved by technology

[0003] At present, there are few studies on text understanding in the medical field. Traditional named entity recognition models based on neural networks require a large amount of labeled training data. However, data proper nouns in the medical field are highly specialized, and the cost of labeling is high, resulting in accurate labeled data. Fewer, lack of large-scale text datasets in the medical field

At the same time, due to the large differences in the writing habits of doctors, the current entity recognition model is difficult to classify entities in context and identify medical entities.

Images