Electronic medical record named entity recognition method based on character and word pronunciation fusion feature model

Abstract

The invention discloses an electronic medical record named entity recognition method based on a character and word pronunciation fusion feature model. The method comprises the following steps of generating a set of character and word vectors of characters corresponding to a character sequence of an electronic medical record of a named entity to be recognized, generating a pronunciation vector corresponding to the character sequence, inputting the pronunciation vector into a first neural network for processing to obtain a pronunciation enhanced word vector corresponding to the character sequence, performing word frequency weight and pronunciation weight processing and fusion on the pronunciation enhanced word vectors to generate a word pronunciation feature model, and inputting the word pronunciation feature model into a second neural network for processing to obtain a named entity recognition result of the electronic medical record. The method has mobility, reduces the complex working degree of model construction, performs a named entity recognition task in the field with less annotation data, and has a good electronic medical record named entity recognition effect.

Description

technical field [0001] The invention belongs to the technical field of computers, and relates to a named entity recognition method of an electronic medical record based on a word pronunciation fusion feature model. Background technique [0002] With the vigorous development of my country's social economy and the improvement of people's living standards, people's health awareness is also increasing. How to use a large amount of medical data to build an intelligent medical system is an urgent need for the current society. Electronic medical records are the medical data texts with the largest amount of medical data and the most information, which has its unique professionalism. Many intelligent medical information systems are constructed based on information from electronic medical records. In the process of building intelligent medical information systems and systems, named entity recognition is the basis for the important task of information extraction from a large amount of...

AI Technical Summary

Problems solved by technology

[0004] In view of the above problems, the present invention proposes a named entity recognition method for electronic medical records based on word pronunciation fusion feature model, which solves the complex model construction, low inference efficiency and poor effect of named entities in the prior art. question

Images