| 摘要 |
A first search term input by a user is obtained. The first search term is matched with at least one keyword in a list such as an offline lists to select at least one keyword from the list. Each keyword in the list corresponds to at least one search recommendation respectively. A search recommendation corresponding to the at least one keyword selected from the offline list is obtained and provided to the user as a search recommendation of the first search term. For example, a historical user behavior relating to the keyword is obtained from a log record. A document generated by the historical user behavior is obtained. At least one candidate recommendations are obtained from text segmentation of the document. The present techniques provide a large range of selection of search recommendations, reduce a number of user searches, and further reduce search time and traffic. |
