Text information processing method, system, medium and device

Abstract

The present invention proposes a text information processing method, system, medium and equipment. In the text information processing method, on the basis of preprocessing the text information to obtain a data preprocessing set, according to the data reference set, based on keyword matching The first screening is performed on the data preprocessing set, and the second screening is performed on the data preprocessing set based on deep learning, and the processed text information is generated by combining the data sets that have been screened twice before and after, which can effectively prevent the misscreening of text information and improve The processing accuracy and processing efficiency of text information are improved; each data set includes professional noun sets, adjective sets, and parameter sets that have mapping relationships with each other. On the basis of separate comparison and screening of each subset, combined with mapping relationships The auxiliary verification of the screening results of other subsets can further improve the screening efficiency and accuracy of text information.

Description

technical field [0001] The present invention relates to the technical field of natural language processing, in particular to a text information processing method, system, medium and equipment. Background technique [0002] In natural language processing, texts with multiple input channels and multiple uses are usually involved. In terms of medical data, the old paper text information in the archives, the electronic medical record information of various hospitals or platforms, and the existing medical data The data is becoming more and more complicated, and there are differences in the definitions and recording methods of medical data in different hospitals or platforms. The corresponding diagnostic texts have specific terms, synonyms, abbreviations, spelling and typing errors, etc., resulting in inconsistencies in the diagnostic texts. [0003] Therefore, how to effectively summarize the complicated medical text information and improve the processing efficiency and accuracy ...

AI Technical Summary

Problems solved by technology

[0002] In natural language processing, texts with multiple input channels and multiple uses are usually involved. In terms of medical data, the old paper text information in the archives, the electronic medical record information of various hospitals or platforms, and the existing medical data The data is becoming more and more complicated, and there are differences in the definition and recording methods of medical data in different hospitals or platforms. The corresponding diagnostic texts have specific terms, synonyms, abbreviations, spelling and typing errors, etc., resulting in inconsistencies in the diagnostic texts.

Images