Topic word mining method and device, electronic device and storage medium

Abstract

The embodiment of the invention discloses a topic word mining method and device, an electronic device and a storage medium. The method comprises the following steps of receiving a query word inputted by a user, and obtaining at least one original topic word corresponding to the query word in a predetermined topic map; determining a basic information material recall set corresponding to all original theme words through a theme discrimination model in all pre-acquired information materials matched with the query words, wherein the basic information material recall set comprises at least one basic information material; in the basic information material recall set, mining the target topic word recall sets corresponding to all original topic words, wherein the target topic word recall set comprises at least one target topic word. According to the present invention, more topic words with higher writing value can be mined, so that a user can be helped to quickly select an appropriate focus point, and a more excellent article can be created within the shortest time.

Description

technical field [0001] The embodiments of the present invention relate to the technical field of data processing, and in particular, relate to a method, device, electronic equipment, and storage medium for mining keywords. Background technique [0002] In an era of increasingly fragmented information access, fascinating high-quality content is still very scarce in information flow applications and products. How to continuously create information content that the people like to hear and see. In the era of information explosion, it is the vision of every content creator to understand what users really want and let users receive the best quality information push in the shortest time. [0003] Taking self-media platforms such as Weibo, WeChat, and Baijiahao as examples, users can write on the self-media platforms according to their own industries, interests and hobbies, and provide them for other users to browse. In the current self-media platform, users can be guided in their ...

AI Technical Summary

Problems solved by technology

[0005] First of all, due to the lack of information in historical records and the lack of complete information on the entire network, fewer words related to query words are screened out in historical records, resulting in limited topic words recommended to users; secondly, query words The relationship between keywords and keywords is relatively simple, resulting in a relatively single keyword recommended to users; moreover, the keywords selected based on historical records may not have writing value and cannot achieve the effect of writing guidance

Images