Alibaba Group Holding Limited

Changlong Sun

Anxiang Zeng

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.

Providing search recommendation

The present disclosure provides example methods and apparatuses of labeling product identifiers and methods of navigating products. Description information of one or more products is extracted. The description information of the products is clustered into a text. A subject analysis is applied to the text by using a text analysis method based on subject models to obtain one or more subjects and definition names for the subjects. A subject that is correlated to the description information of the product is used as an identifier of the product to label the product. The present techniques label the products with identifiers that have one or more user dimension attributes so that users may easily and intuitively find their desired products.

Growing community of inventors

Hangzhou, China

Changlong Sun