Text clustering method, question-answering system applying same and search engine applying same

Abstract

The invention provides a text clustering method, a question-answering system applying the same and a search engine applying the same. The method comprises the following steps of 1) clustering texts in various languages; 2) drawing character word vectors of clustered texts in the various languages; and 3) calculating similarity of character word vectors of the texts in different languages, and clustering all the texts. By using the method, the question-answering system and the search engine, the texts in the various languages can be clustered correctly.

Description

technical field [0001] The invention relates to the field of pattern recognition, more specifically, to a pattern recognition method for natural language. Background technique [0002] With the popularization of information network, the emergence of massive electronic text information urgently requires machines to automatically classify text. Automatic text classification can save a lot of manpower and material resources, and avoid many defects such as long cycle, high cost and low efficiency caused by manual classification. Automatic text classification is to automatically classify a large amount of text according to its content, so as to help people effectively process and organize text data. [0003] This demand is even stronger for search engines. People increasingly rely on search for knowledge and information. Facing hundreds of millions of web pages and information resources, the biggest problem that search engines will face is how to quickly and accurately provide...

AI Technical Summary

Problems solved by technology

[0007] However, the clustering of texts in the prior art only considers texts in a single language, ignoring the problem of language barriers

Images