Text data analysis method and device of electronic medical records

Abstract

The invention relates to a text data analysis method and device of electronic medical records. The method comprises steps of processing a sample file and acquiring all text information in the sample file; according to the acquired text information and a tag structure of the sample file, establishing a knowledge framework dictionary; acquiring a to-be-analyzed electronic medical record, and extracting original text information therein; carrying out comparing and judging on the original text information and contents in the knowledge framework dictionary, and finishing structuralization analysison the original text information. According to the invention, text contents can be extracted in a simple way under the conditions that there are a large number of tags in XML file or tag design and content filling are disordered; depending on XML tags of the current text analysis method is abandoned; quantity of codes is greatly reduced; and by combining the knowledge framework dictionary, accuracy of the structuralization analysis is ensured.

Description

technical field [0001] This application relates to the technical field of computer databases, in particular to a text data analysis method and device for electronic medical records. Background technique [0002] EMR (Electronic Medical Record, Electronic Medical Record) is a digital medical record that is stored, managed, transmitted and reproduced using electronic equipment (such as a computer), generally including the patient's disease and diagnosis and treatment conditions. EMR can replace handwritten paper medical records, which is convenient for digital and information management. Electronic medical records are generally presented in the form of text data under the XML structure. Due to the variety of electronic medical records and the large content, how to analyze them in a concise and efficient manner is a problem that needs to be considered. [0003] In related technologies, it is common to use XML tags for parsing. That is, after manually analyzing the XML file an...

AI Technical Summary

Problems solved by technology

This method has the following problems: First, there are many types of XML files involved in electronic medical records, often up to thousands, and the tag structures involved may be tens of thousands, and the corresponding code workload is heavy; second, the tags are generally provided by the electronic medical record manufacturers According to the definition of technicians, there may be multiple sub-level tags with the same name and different attributes under the same level of parent-level tags, which makes it difficult to implement the corresponding code; moreover, when filling in the content of electronic medical records, the content will be merged. , resulting in incorrect content fetched by label

Images