Keyword recommendation method and system

Abstract

The present invention provides a method and system for recommending keywords. The method includes: receiving a query word input by a user, and adopting a first recommendation strategy to acquire keywords whose correlation with the query word satisfies a preset first correlation requirement as Recommend word etymology; calculate the correlation between the query word and existing keywords; judge whether the correlation between the query word and existing keywords reaches the preset trigger threshold, if so, trigger personalized recommendation, if not , then obtain the recommendation result of the keyword; wherein, the triggering of the personalized recommendation specifically includes: expanding the etymology of the recommended word, and adopting the second recommendation strategy to obtain the existing keyword related to the query word or the user Keywords whose relevance meets the preset second relevance requirement are added to the etymology of recommended words. Compared with the prior art, the present invention introduces more user information when recommending, judges user needs, prevents blind personalized recommendation, and ensures the diversity of recommendation results.

Description

【Technical field】 [0001] The invention relates to Internet application technology, in particular to a keyword recommendation method and system. 【Background technique】 [0002] Internet promotion technology is a technology developed with the development of search engines, such as Baidu promotion, Google keyword advertising (AdWords) and advertising network (AdSense). When you enter keywords in the search engine to retrieve information, the system will deliver online advertisements that match the entered keywords, which will be placed in the blank space on the right side of the search result page in plain text, or appear as advertisements that match the corresponding keywords In the search results, and in a higher position. This type of advertisement is promoted according to the keywords purchased by users, and the choice of keywords is inseparable from the success of the promotion plan. In order to help users select better keywords when creating or improving promotion units...

AI Technical Summary

Problems solved by technology

[0004] In the process of actual use, due to the uncertainty of user input content, personalized recommendation is not required for every query. The existing recommendation methods cannot judge whether it is needed due to the lack of information they rely on, and blindly carry out personalized recommendation. The personalized recommendation leads to the wrong judgment of demand, the loss of diversity of recommendation results, and affects the actual recommendation quality

Images