Chinese electronic medical record named entity recognition method

Abstract

The invention discloses a Chinese electronic medical record named entity identification method. The method comprises the following steps: 1) constructing a common vocabulary dictionary; 2) simple part-of-speech tagging; 3) constructing a text and part-of-speech vector mapping table; 4) training a prediction model of the named entity; and 5) predicting the label of the named entity. According to the method, the part-of-speech characteristics are added to improve the boundary distinguishability of the named entity and the common vocabularies, so that the boundary accuracy of the named entity isimproved. At the same time, a self-attention mechanism is introduced into the bidirectional LSTM-CRF model, and the relevancy between the input at each moment and other components in the sentence is calculated, so that the long dependency problem is relieved, and the named entity recognition accuracy is improved.

Description

technical field [0001] The invention relates to the technical field of named entity recognition of Chinese electronic medical records, in particular to a method for recognizing named entities of Chinese electronic medical records. Background technique [0002] Named Entity Recognition (NER) in electronic medical records is to find out some clinical entities related to patients from the descriptive text of electronic medical records, such as the patient's diseased part, symptoms, used drugs and operations, etc. . Named entity recognition of Chinese electronic medical records is the key to information extraction of Chinese electronic medical records, which can lay the foundation for Chinese health information processing such as medical record retrieval, disease prediction, and construction of medical knowledge graphs. However, there are many unregistered words in electronic medical records, and the number continues to increase. Moreover, compared with English, the recognition...

AI Technical Summary

Problems solved by technology

In model construction, most methods use LSTM to process input vectors and selectively retain historical information to deal with long-term dependency problems. However, with the growth of sentences and the movement of time steps, it gradually becomes incapable, and it is difficult to learn feature information farther away. , cannot handle the boundary extraction problem of named entities well

Images