Method and device for verifying data standardization, electronic equipment and storage medium

Abstract

The invention discloses a method and a device for verifying data standardization, electronic equipment and a storage medium. The method comprises the steps of obtaining a to-be-processed text of a to-be-determined standardized entry; processing the to-be-processed text according to a predetermined inspection term knowledge base to obtain a first to-be-determined standard entry corresponding to the to-be-processed text; and / or, processing the to-be-processed text based on a comparison learning model obtained by pre-training to obtain a second to-be-determined standard entry corresponding to the to-be-processed text; and determining a target standardized entry corresponding to the to-be-processed text according to the first to-be-determined standard entry and / or the second to-be-determined standard entry. According to the embodiment of the invention, the problem that the existing test term matching method does not consider term interpretation of a semantic level to cause low test effect is solved, and the test term matching effect is improved.

Description

technical field [0001] The embodiments of the present invention relate to data processing technologies, and in particular, to a method, device, electronic device and storage medium for standardizing inspection data. Background technique [0002] At present, there are a large amount of unstructured text and structured text data in the medical field, and the data differences of regional medical data are becoming more and more obvious. When performing data inspection on medical data, terminology standardization has become the primary problem to be solved urgently. [0003] At present, most of the existing methods for testing terms are statistically scored through literal features, and only rely on name similarity to obtain data matching with terms. This traditional matching result obtained only by using literal features loses the usefulness of the test text If information cannot be fed back in a timely manner and accurate information, it will consume a lot of manpower and mater...

AI Technical Summary

Problems solved by technology

[0003] At present, most of the existing methods for testing terms are statistically scored through literal features, and only rely on name similarity to obtain data matching with terms. This traditional matching result obtained only by using literal features loses usefulness in the test text. Information, can not timely feedback term accurate information, great consumption of manpower and material resources, and delay the precious treatment time, but also cause unnecessary economic losses to patients

Images