Web page training methods and devices, and search intention identification methods and devices

摘要

The present invention relates to a web page train method and device. The web page training method may include, on a device including one or more processors and memories, obtaining a query string to be identified, and obtaining a history web page set corresponding to the query string, wherein the history web page set is the query string Includes web pages clicked using as a history-; Obtaining a predetermined webpage categorization model; Acquiring a category of each webpage in the history webpage set according to the webpage categorization model; The query string is obtained by collecting statistics on the number of web pages in each category in the history web page set, and performing calculations according to the number of web pages in each category and the total number of web pages in the history web page set. Obtaining an intention distribution of; And acquiring an intention identification result of the query string according to the intention distribution.