Semi-supervised text classification method and system based on multi-granularity modeling

Abstract

The invention provides a semi-supervised text classification method and system based on multi-granularity modeling, and relates to the technical field of data processing and machine learning. According to the invention, a three-channel text vector model layer is formed in a multi-granularity text modeling mode, text modeling is conducted on the same text from the character level, the word level and the sentence level; modeling of the three levels serves as three channels respectively, and input and output of the three channels are connected into three base classifier sets; therefore, divergence between samples is obtained under the condition that the samples or characteristics are not lost, and a traditional resampling and random subspace method is replaced. Meanwhile, nine base classifiers are integrated into a design of three base classifier groups, the advantages of different base classifiers are integrated, different features of the same sample are obtained by using different baseclassifiers, and divergence among the base classifiers is obtained, so that the classification result accuracy of the semi-supervised text classification method is effectively improved.

Description

technical field [0001] The invention relates to the fields of data processing technology and machine learning technology, in particular to a semi-supervised text classification method and system based on multi-granularity modeling. Background technique [0002] The rapid development of Internet technology has made information transmission more and more rapid and convenient. In the process of continuous generation and interaction of information, more new information has been derived. This information has been growing exponentially. In these Massive information often contains many valuable things, which not only reflect a large number of potential needs of users from the side, but also feed back many problems existing in enterprise services. If these massive user information are quickly mined and effectively extracted, it is possible to easily grasp user needs, improve a large number of problems in enterprise services, provide users with better services, and seize a wider mark...

AI Technical Summary

Problems solved by technology

[0006] Aiming at the deficiencies of the prior art, the present invention provides a semi-supervised text classification method and system based on multi-granularity modeling, which solves the problem of missing samples or features in traditional semi-supervised classification methods, as well as the incomplete semantics and inability to solve a problem. polysemy problem

Images