Electronic document analysis system and method based on machine learning

Abstract

The invention discloses an electronic document analysis system and method based on machine learning. The document feature description module is used to describe the submitted electronic document structure. The description type of the document is followed by structural analysis; the machine learning algorithm module performs model training and information extraction based on the analysis results of the electronic document structure and the content characteristics of the target information, and the analyst modifies the content feature description or the target information extracted by the machine learning algorithm. The learning algorithm module will retrain the model corresponding to the modified content features; the analysis result review module will present the model training and information extraction results of the machine learning algorithm module to the electronic document analyst. The invention effectively solves the learning problem in the case of a limited number of machine learning algorithm documents and dynamic changes in features, enables the algorithm to truly assist document analysis, and improves analysis efficiency.

Description

technical field [0001] The invention relates to the technical field of computer information analysis, in particular to a machine learning-based electronic document analysis system and method. Background technique [0002] Electronic documents are information materials composed of text or text and graphics, such as electronic medical records, imaging reports, and legal documents. Most of the existing electronic document analysis techniques are document structuring techniques. Taking the electronic medical record structuring technology in the medical field as an example, the structuring of medical records mostly uses fixed rules and templates, combined with machine learning algorithms, to extract as much information as possible from the medical records at one time; then store and index them, and build similar search engines The application is convenient for doctors to search and query. This structured technology has the problems of low accuracy, heavy workload, poor flexibil...

AI Technical Summary

Problems solved by technology

Taking doctor's scientific research as an example, at present, doctors and their students mostly rely on doctors and their students to manually organize and analyze electronic medical records. Once the required document information changes, or the electronic medical record documents are obtained in batches, it will be difficult to coordinate and modify among different personnel. become cumbersome

Images