Cross-language recommendation method and system

Abstract

The invention discloses a cross-language recommendation method and system. The method comprises following steps: creating and renewing a bilingual search term vector model based on user's search of session logs and mining relevance of bilingual search terms; and creating and renewing a bilingual concept vector model based on a Chinese-English bilingual parallel corpus, creating and renewing a concept word vector model and mining related bilingual concepts. The system comprises a search string pre-processing module used for analyzing serial strings inputted by a user and filtering noise characters, a recommendation word calculation module set up by the bilingual search word vector model and the bilingual concept word vector model and used for searching and calculating similar recommendation words, a long-tail search word processing module used for searching not common low-frequency search words through rewriting of search words and searching of synonyms, and a result output module used for showing recommendation words processed to a user. The cross-language recommendation method and system have following beneficial effects: without on-line artificial translation, search efficiency of the user is increased; through the recommendation method for relevant search words for long-tail search words, recommendation coverage rate is increased; a support range of relevant search words is broadened; by dynamically renewing a mechanism of a recommendation model, the model can timely reflect newest research hotspots and study trends of the search system to which the user pays attention.

Description

technical field [0001] The invention relates to the technical field of information retrieval and recommendation systems, in particular to a cross-language recommendation method and system. Background technique [0002] The development of the Internet provides the basic conditions for knowledge sharing without borders. With the increasing amount of document information, users have increasingly rich search requirements for Chinese and foreign documents. Effective screening of massive academic resources is inseparable from reasonable retrieval strategies. When searching for Chinese literature, users are usually eager to learn about foreign research trends in the corresponding research direction; due to the need to declare national research projects, etc., when searching for foreign language literature, there is also a demand for relevant domestic trends. Due to the diversity of language expression itself, for Chinese people, the main problem of searching foreign literature res...

AI Technical Summary

Problems solved by technology

Therefore, how to intelligently guide users, recommend bilingual related search terms, help users express their search needs, find needed resources, expand the scope of knowledge discovery, and understand the research trends of domestic and foreign counterparts in professional fields is an important part of the academic literature search system. However, the existing problems in the current related search word recommendation system include: (1) often only consider the recommendation at the same language level; (2) user search terms present a long-tail distribution, and there is a lack of reasonable strategies to deal with long-tail query words; (3) ) did not consider the dynamic update problem when building the model. Due to the particularity of literature resources, the timeliness of user search terms is very strong, and the static model is difficult to reflect the latest research hotspots and possible latest research trends that users are concerned about.

Images