Value domain data matching method, value domain data matching device and related product

Abstract

The invention discloses a value domain data matching method, a value domain data matching device and a related product. The method comprises: acquiring a to-be-matched operation name in to-be-matchedvalue domain data; processing the to-be-matched operation name to obtain a to-be-matched feature vector group; and obtaining a matching result by utilizing a pre-trained data matching model and the to-be-matched feature vector group, so that the data matching model obtained through training can match a national standard operation name according to a non-national standard operation name, determinethe specific classification situation of the national standard operation name in a value domain classification tree and reflect the specific classification situation through a node index value, and indexing is performed by utilizing the matching result to obtain the national standard operation name matched with the to-be-matched operation name and determine the specific classification situation ofthe matched national standard operation name in the value domain classification tree. Compared with the prior art, the method of the invention has the following characteristics that manual labor is effectively saved, matching efficiency is improved, and the anti-interference performance of matching can be improved so as to improve the matching accuracy of the value domain data.

Description

technical field [0001] The present application relates to the technical field of data processing, in particular to a value range data matching method, device and related products. Background technique [0002] In recent years, with the continuous advancement of informatization and industrialization in the medical field, the display form of medical data has also undergone tremendous changes. This has had a profound impact on both the hospital's medical information system (Hospital Information System, HIS) and the national health information system. In order to effectively collect, analyze and use relevant information in the medical field such as regional disease incidence and disease treatment plans, a regional platform can now be established. [0003] Medical data contains a large number of value range data, some of which have fewer types of value range data and simple data organization, which can be called small value range value range data, such as medical insurance categ...

AI Technical Summary

Problems solved by technology

If the name of the operation is not matched, it will be difficult to effectively analyze and apply these range data

[0005] At present, in the medical field, the matching schemes for large value range data in medical data include fuzzy query, word segmentation comparison and manual comparison, but the matching effect of using fuzzy query or word segmentation comparison is not good, and the manual comparison method would consume a lot of manpower

Images