Real-time microblog search method and device

Abstract

The invention provides a real-time microblog search method. The method includes: performing document expansion on each microblog in a microblog space so as to generate a document expansion logic form; acquiring keywords from a user; performing logic expansion on the keywords so as to generate expanded search logic forms; searching each document expansion logic form according to the expanded search logic forms so as to acquire final search results. The invention further provides a real-time microblog search device which comprises a document expansion module, a keyword module, a search expansion module and a matching module. The document expansion module is used for performing document expansion on each microblog in the microblog space so as to generate the document expansion logic form, the keyword module is used for acquiring the keywords from the user, the search expansion module is used for performing logic expansion on the keywords so as to generate the expanded search logic forms, and the matching module is used for searching each document expansion logic form according to the expanded search logic forms so as to acquire the final search results. By the method and device, accuracy of microblog search is improved.

Description

technical field [0001] The invention relates to the field of information retrieval, in particular to a microblog real-time retrieval method and device. Background technique [0002] Weibo has the following characteristics: 1. The length of Weibo is strictly limited within 140 characters; 2. Users can also interact with other users through symbols when posting Weibo; 3. Users can also use the # symbol to indicate Weibo The topic it belongs to. [0003] As a highly interactive and communicative tool, the number of microblogs often shows explosive growth with the occurrence of news events, which makes real-time information on the microblog platform more frequent; at the same time, due to the length of microblogs Restrictions make the microblog text more fragmented and highlight the problem of vocabulary-mismatch in the retrieval process. In general, the real-time, social and fragmented characteristics of microblogs have brought great challenges to information retrieval in the...

AI Technical Summary

Problems solved by technology

[0005] In traditional information retrieval, the documents to be retrieved often contain more text information, so as long as the query expansion technology is used, the problem of word mismatch can be better ...

Images