Cboth generation method and device, equipment and storage medium

Abstract

The invention relates to an artificial intelligence technology, and discloses a copywriting generation method, which comprises the following steps: respectively carrying out key sentence extraction on a plurality of original text data in an original text data set based on a preset graph sorting algorithm to obtain a plurality of key sentence sets; forming a plurality of text information pairs by the plurality of key sentence sets and preset real copywriting corresponding to the plurality of original text data, and performing combination processing on the plurality of text information pairs to obtain a training sample set; training a preset copywriting generation model by using the training sample set to obtain a standard copywriting generation model; and extracting a text key sentence in a to-be-processed text, and inputting the text key sentence into the standard copywriting generation model to obtain a standard copywriting corresponding to the to-be-processed text. In addition, the invention also relates to a block chain technology, and the key sentence set can be stored in a node of a block chain. The invention further provides a copywriting generation device, electronic equipment and a storage medium. The copywriting generation efficiency can be improved while the copywriting accuracy can be guaranteed.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, and in particular to a copy generation method, device, electronic equipment and computer-readable storage medium. Background technique [0002] With the rapid development of the Internet advertising market, the amount of advertisements produced has also increased rapidly. Traditional manual advertisements have gradually been unable to meet the massive new information flow every day. Therefore, automatic copywriting by machines is particularly important. [0003] Existing copy generation methods usually use deep learning models. However, for complex deep learning models, their training time and convergence speed are important components that must be considered. In many fields, such as the news field, the amount of related data is large, and the deep learning model cannot meet the requirements of accurate copy generation while ensuring efficiency. Therefore, it is urgent to ...

AI Technical Summary

Problems solved by technology

[0002] With the rapid development of the Internet advertising market, the amount of advertisements produced has also increased rapidly. The traditional manual advertisements have gradually been unable to meet the massive new information flow every day. Therefore, the automatic copy generation of machines is particularly important.

[0003] Existing copy generation methods usually use deep learning models. However, for complex deep learning models, their training time and convergence speed are important components that must be considered

In many fields, such as the news field, the amount of relevant data is large, and the deep learning model cannot meet the requirements of accurate copy generation while ensuring efficiency. Therefore, it is urgent to propose a method to improve copy generation efficiency while ensuring copy accuracy.

Images