Method and device for automatic construction of domain vocabulary based on classification system

Abstract

The present invention relates to the technical field of automatic construction of domain vocabulary, in particular to a method and device for automatic construction of domain vocabulary based on a classification system. The method includes: obtaining data; determining the parent node and each child node of a domain node, and obtaining A plurality of related words corresponding to the node; determine the probability that the related words appear in the average thousand words in the domain node and the probability that the related words appear in the average thousand words in the sub-node domain; determine the average probability that the related words appear in each article in the domain node The reciprocal and the reciprocal of the average probability of occurrence in each article in the parent node field; determine the first intermediate score and the second intermediate score of each associated word; determine the total score of the associated word according to the first intermediate score and the second intermediate score; Obtain the preset score threshold, and determine the professional vocabulary according to the associated words whose total scores of all associated words are greater than the preset score threshold. By adopting the invention, the professional vocabulary can be automatically constructed simply and efficiently.

Description

technical field [0001] The present invention relates to the technical field of automatic construction of domain vocabulary, in particular to a method and device for automatic construction of domain vocabulary based on a classification system. Background technique [0002] In recent years, domain vocabulary is an important resource for professional and vocational education, and it is also widely used in industries, such as solving classification problems. There are usually two ways to obtain the vocabulary in the current field: generating a vocabulary through word frequency statistics and expert identification, or constructing a classification model through machine learning, and using the model to classify a large amount of data. However, both of these two methods have the disadvantages of low efficiency, and a large amount of calculation, and the accuracy cannot be guaranteed. Contents of the invention [0003] The embodiment of the present invention provides a method and...

AI Technical Summary

Problems solved by technology

But both of these two methods have the disadvantages of low efficiency, and the amount of calculation is large, and the accuracy cannot be guaranteed.

Images