TEXT CLASSIFICATION METHOD AND APPARATUS

Title:

TEXT CLASSIFICATION METHOD AND APPARATUS

Document Type and Number:

WIPO Patent Application WO/2017/202125

Kind Code:

A1

Abstract:

A text classification method and device, falling within the technical field of computers. The method comprises: for each keyword in a plurality of keywords included in a keyword library of a service information base, determining a word vector corresponding to the keyword according to a word vector model (301); based on the word vector corresponding to the keyword, determining a potential expansion word of the keyword (302); when an expansion rule input for the potential expansion word is received and when an addition instruction for the potential expansion word is detected, adding the potential expansion word into the keyword library, and adding the expansion rule to a matching rule base of the service information base (303); based on the keyword library and the matching rule base, determining, by a model matching classifier, a first probability that text to be classified belongs to each pre-set category of a plurality of pre-set categories (304); and based on the first probability that the text to be classified belongs to each pre-set category of a plurality of pre-set categories, determining, from the plurality of pre-set categories, a category to which the text to be classified belongs (305). The method can reduce the labour cost of constructing a service information base, and can improve the coverage rate and accuracy rate of text classification.

Inventors:

LIU BINGYUAN (CN)
ZHANG XU (CN)

Application Number:

PCT/CN2017/077729

Publication Date:

November 30, 2017

Filing Date:

March 22, 2017

Export Citation:

Click for automatic bibliography generation Help

Assignee:

HUAWEI TECH CO LTD (CN)

International Classes:

G06F17/30

Foreign References:

CN103793474A	2014-05-14
CN104933183A	2015-09-23
CN103092875A	2013-05-08
US20160104074A1	2016-04-14

Other References: