Pull-down word recommendation method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention relates to a pull-down word recommendation method and device, electronic equipment and a storage medium. The method comprises the steps that search words input by a user are acquired, and an initial pull-down word recommendation candidate set is generated; obtaining search behavior data of a user; generating an associated word set according to the search behavior data of the user; and adjusting the initial drop-down word recommendation candidate set according to the associated word set to generate a drop-down word recommendation candidate set. According to the embodiment of the invention, the pull-down words related to the search words searched by the user (especially recent search) are displayed in the pull-down word recommendation candidate set, so that the search cost of the user is reduced, the user is ensured to search more coherently, and the real-time search requirement of the user on the concerned information is met in time; meanwhile, the utilization rate of the pull-down words and the search amount of the user are remarkably increased, and correspondingly, the total content of the user accessing the webpage is greatly increased.

Description

technical field [0001] The invention belongs to the technical field of search, and in particular relates to a pull-down word recommendation method, device, electronic equipment and storage medium. Background technique [0002] The drop-down word refers to the entry that the system recommends for the user to choose according to the search word entered by the user when the user enters the search word in the search box. When users browse content on the search results page, the drop-down word area of ​​the search box can recommend drop-down words based on the user's search behavior. Traditional drop-down words are mainly matched based on popularity and dictionary tree sorting to reduce user input costs. [0003] However, in the process of realizing the present invention, the inventor found that the drop-down word recommendation method in the prior art has at least the following problems: the prefix of the user's search behavior data is relatively short, and the matching is too g...

AI Technical Summary

Problems solved by technology

[0003] However, in the process of realizing the present invention, the inventor found that the drop-down word recommendation method in the prior art has at least the following problems: the prefix of the user's search behavior data is relatively short, and the matching is too generalized, such as in the search box of a certain browser , when the user enters the prefix "Liu", various matching words related to "Liu" appear in the drop-down word candidate set of the input association, such as "Liu Shishi, Liu Yifei, Liu Bei, Liu Cixin, Andy Lau" and so on, and then the user enters the prefix "四 When inputting Lenovo's drop-down word candidate set, various matching words related to "Four Heavenly Kings" appear, such as "Four Heavenly Kings Buddha Statues, Di Renjie's Four Heavenly Kings, Di Renjie's Four Heavenly Kings, Four Heavenly Kings Box Office", etc. etc.; then, when the user enters the prefix "Liu", the candidate set of input associations is still "Liu Shishi, Liu Yifei, Liu Bei, Liu Cixin, Andy Lau" and so on, so that the types and quantities of the drop-down words recommended to the user are very broad, Not enough to meet the real-time search needs of users for the information they care about

[0004] Therefore, the pull-down word recommendation method in the prior art cannot adjust the order of the recommended pull-down words according to the user's search behavior data, thereby increasing the user's input cost and making the user's search behavior not coherent and smooth.

Images