Title text generation method and device, computer storage medium and electronic equipment

Abstract

The invention relates to the technical field of computers, in particular to a title text generation method and device, a storage medium and electronic equipment. The method comprises the following steps: obtaining the confusion degree of a first-level candidate title; filtering the first-level candidate title according to the confusion degree to obtain a second-level candidate title; obtaining a click probability of the second-level candidate title; and sorting the secondary candidate titles based on the click probability, and determining a target candidate title from the sorted secondary candidate titles. According to the method and the device, the obtained selected titles are comprehensively sorted and filtered to determine the target candidate titles by combining the confusion degree and the click probability of the candidate titles, so that the accuracy and logicality of the target candidate titles are improved, and the attraction degree of the target candidate titles to users is also increased.

Description

technical field [0001] The present disclosure relates to the field of computer technology, and more specifically, to a method for generating title text, a device for generating title text, a computer storage medium, and electronic equipment. Background technique [0002] With the development of computer technology and Internet technology, Internet platforms generally have the need to increase the number of content visits (such as article information, page views of news information, etc.). Finding the target content in the shortest time and providing high-quality and attractive title texts have become one of the issues that cannot be underestimated. [0003] In related technologies, titles of relevant content are mainly generated based on preset rules or language models. However, these methods are difficult to balance the accuracy, fluency and attractiveness of title texts. On the one hand, they lack the quality of generated titles. Evaluation, it is difficult to control the...

AI Technical Summary

Problems solved by technology

[0003] In related technologies, titles of relevant content are mainly generated based on preset rules or language models. However, these methods are difficult to balance the accuracy, fluency and attractiveness of title texts. On the one hand, they lack the quality of generated titles. Evaluation, it is difficult to control the fit between the title and related content, resulting in low accuracy of the generated title; on the other hand, in order to improve the accuracy of the generated title, the consideration of the potential attractiveness of the title to users is often ignored

Images