Article generating method, device and storage medium

Abstract

The present invention provides an article generation method, device and computer storage medium, the method comprising: mining content sources based on demand information input by users; using a specific topic generation model to extract at least one topic dimension vector from the mined content sources; The extracted at least one topic dimension vector performs topic sentence mining on the content source to obtain a topic sentence corresponding to the topic dimension vector; and splicing and synthesizing the topic sentences corresponding to the topic dimension vector to generate information that meets the requirements article.

Description

technical field [0001] The present invention relates to artificial intelligence technology, in particular to an article generation method, equipment and computer storage medium. Background technique [0002] With the continuous upgrading of user consumption, low price is no longer the main factor determining user consumption, and users are more eager to obtain diversified information to support consumption decisions. As a result, headline articles with diversified information have gradually become a hot demand for major e-commerce and content platforms. The current article publishing platform mainly obtains articles in the following three ways: [0003] 1. Manually written, published content as a personal or official account; [0004] 2. Crawl the headlines of articles from external sources and distribute them on the content platform; [0005] 3. Generate articles by splicing templates. [0006] However, the existing ways of obtaining articles are far from meeting the ne...

AI Technical Summary

Problems solved by technology

[0010] The purpose of the present invention is to overcome the defects in the prior art that the automatic writing of articles cannot be realized based on user needs, and there is a long generation cycle, high cost, and substandard quality

Images