Information extraction method and system for medical photograph

Abstract

The invention discloses an information extraction method and system for a medical photograph. The method comprises the steps of converting a medical photograph file into a to-be-recognized electronicfile; performing character recognition on the to-be-recognized electronic file by adopting an optical character recognition method to obtain an electronic document and feature information; performingfuzzy classification on the electronic document according to the feature information; performing information extraction on the electronic document subjected to fuzzy classification processing according to the category to which the electronic document belongs to obtain a preliminary extraction result; performing error correction processing on the preliminary extraction result to obtain an effectiveelectronic document; performing second information extraction on the effective electronic document according to a preset information extraction condition to obtain key information; and according to the key information, classifying the effective electronic document to obtain a classification result. The method can achieve more accurate character recognition accuracy under the condition of significantly reducing the labor cost, and can automatically recognize and classify according to the features of the text to achieve the purpose of unified processing.

Description

technical field [0001] The invention relates to the technical field of text processing, in particular to an information extraction method and system for medical photocopies. Background technique [0002] Digital construction is one of the key national construction projects that the country has vigorously promoted in the past ten years. For the pharmaceutical industry, a digital platform with complete data plays a vital role in standardized management and strict supervision. In the existing technologies, most of the various documents are manually scanned and classified, and processed into semi-structured data through OCR (Optical Character Recognition, Optical Character Recognition). Further data collation relies on the manual extraction process, which consumes huge financial, material and manpower. Moreover, when the existing OCR technology recognizes medical photocopies, the recognition efficiency is low due to its irregularity, diversity, and some official seals, imprint...

AI Technical Summary

Problems solved by technology

Further data collation relies on the manual extraction process, which consumes huge financial, material and manpower

Moreover, when the existing OCR technology recognizes medical photocopied documents, the recognition efficiency is low due to its irregularity, diversity, and some official seals, imprints, etc., which often requires post-correction, which increases labor costs.

Images