Medical text information processing method and device and storage medium

Abstract

The invention provides a medical text information processing method and device and a computer readable storage medium. The method comprises: preset disease related text information and current medicalrecord data are acquired; wherein the preset disease-related text information represents various disease-related symptom descriptive languages and corresponding symptom crowd information; performingfeature coding on the preset disease-related text information and the current medical record data by utilizing a prediction classification model to obtain disease text features and medical record datafeatures; wherein the prediction classification model is obtained through model training according to preset disease-related text information and historical medical record data, and the correspondingrelation between the medical record data and disease classification is represented through the preset disease-related text information; and carrying out feature fusion and classification processing on the disease text features and the medical record data features through an attention mechanism to obtain a classification result.

Description

technical field [0001] The invention relates to data processing technology in the electronic application field, in particular to a medical text information processing method and device, and a storage medium. Background technique [0002] In recent years, artificial intelligence has been applied more and more in various fields, and has become an important means of decision-making and forecasting in various fields. [0003] At present, knowledge graphs are combined with neural network models in machine learning to achieve event decision-making or prediction in the medical field. Specifically, feature learning is performed on the knowledge map of the disease class to obtain low-dimensional vectors such as entity vectors and relationship vectors, and then these low-dimensional vectors are introduced into the neural network model to implement a certain event decision-making model, and complete event decision-making based on the model and current data . Or, combine the knowledge...

AI Technical Summary

Problems solved by technology

[0004] However, a rich, comprehensive and accurate knowledge map requires a lot of manpower and material resources for labeling, and it takes a long time to organize, and the data acquisition is more complicated. In addition, the processing of the knowledge map is relatively simple, which will lead to the accuracy of data processing. decrease, which in turn affects the classification results of event decisions

Images