Method and device for extracting medical relationship

Abstract

The invention discloses a method and device for extracting a medical relationship, comprising the following steps: counting the number of occurrences of medical concept pairs in a set time window from a medical electronic medical record, and obtaining two medical concept vectors in the medical concept pair; using the two medical concepts Match with the knowledge base to obtain the association relationship between two medical concepts, so as to construct a relationship concept triplet; according to the relationship concept triplet, a plurality of concept sentences are mined from the medical text set; a training sample set is constructed, and the training samples The set includes positive samples and negative samples, and each sample structure is composed of relational concept triples, two medical concept vectors, and concept sentences; use the training sample set to train the fusion model, and obtain the trained fusion model; use the trained fusion model The model performs medical relation extraction. The present invention can continuously mine the relationship between medical concepts. The introduction of chapter titles to form concept sentences increases the effective training samples.

Description

technical field [0001] The invention relates to the field of information technology, and in particular, to a method and device for extracting a medical relationship considering medical text and medical electronic medical records. Background technique [0002] In recent years, many models for relation mining have emerged, including mode matching and machine learning. With the rapid development of deep learning, researchers began to use neural network models in relation extraction, taking word embedding and position embedding vectors as input, and using recurrent neural networks. The sentence-level attention mechanism originally used in machine translation is now also applied to relation extraction to automatically capture important words and sentences, becoming a necessary mechanism in the model. However, these supervised models lack actual medical relationship data for training. Due to the high cost of manual labeling, the neural network does not have enough sample sentenc...

AI Technical Summary

Problems solved by technology

If the method of rule matching is adopted, the coverage and accuracy of the acquired relationship and medical knowledge are obviously insufficient

And if you want to use machine learning or deep learning for automatic relationship extraction, there is no existing training set and model for target relationship mining, so it is impossible to quickly and parallelly mine the target relationship

Therefore, there can be a plan to do similar things, but the accuracy, timeliness and extensiveness of the invention cannot be achieved

Images