Terminology standardization method, system and corresponding equipment and storage medium

Abstract

The present application discloses a term standardization method, system, corresponding device and storage medium, wherein the method includes: performing word segmentation and part-of-speech tagging and entity recognition for each standard term; generating a first reference text space vector according to each standard term , wherein the entity recognition result includes a word type label; construct a vector search model according to the first reference text space vector; perform word segmentation and part-of-speech tagging on the term to be standardized and perform entity recognition; generate a text space vector to be standardized; search for similarity from the vector search model The highest M reference text space vectors; calculate the similarity of each word type label dimension; calculate the total similarity; use the standard term corresponding to the reference text space vector with the highest total similarity as the standard term of the term to be standardized. The invention can not only ensure the recall rate, but also improve the matching accuracy.

Description

technical field [0001] The present application relates to the field of electronic digital data processing, in particular to a term standardization method, system, corresponding equipment and storage medium. Background technique [0002] In many industries, due to historical and regional reasons, the data of each unit has its own set of terminology names. The inconsistency of these terms has a very restrictive effect on the development of informatization. With the development of technology, relevant state departments have successively issued terminology norms and standards in various fields. However, it is a very troublesome thing to map with the national standard. If there is no good technical means, it can only be mapped manually, which is very time-consuming and labor-intensive. The current popular method in the industry is to use computer program algorithms for standardized mapping. By calculating the similarity between the original term and the standard term, when the s...

AI Technical Summary

Problems solved by technology

However, the similarity calculated based on traditional algorithms is a scalar value, which cannot meet the standardization of terminology in some specific fields, and there are often cases of neglecting the beginning and the end

Some terms have a high degree of similarity to each other, thresholded and cannot be distinguished

If the threshold is too high, it will affect the recall rate; if the threshold is too low, it will affect the accuracy rate, so it is difficult to compromise

Images