Ancient poem keyword extraction and poem line generation method, device and equipment, and medium

Abstract

The invention relates to the field of big data processing, and provides ancient poem keyword extraction and poem line generation method, device and equipment, and a medium. The method comprises the following steps: obtaining poem information in a poem extraction instruction; inputting the poem information into a poem annotation model based on BERT and classical characters in an ancient poem keyword extraction model, and splitting and annotating the poem information through the poem annotation model to obtain poem sequence information; identifying a poem type through a poem type identificationmodel; inputting the poem sequence information into a CRF-based type constraint model corresponding to the poem type in an ancient poem keyword extraction model, and performing marking and constraintprediction processing on the poem sequence information to obtain a keyword result; and determining ancient poetry keywords according to keyword results. According to the method, the ancient poetry keywords reflecting the poetry in the poetry information are automatically extracted through the poetry labeling model based on BERT and classical characters and the type constraint model based on CRF.

Description

technical field [0001] The present invention relates to the field of data processing of big data, in particular to a method, device, computer equipment and storage medium for extracting keywords from ancient poems and generating verses. Background technique [0002] At present, artificial intelligence has realized the automatic generation of verses, most of which generate a verse through a keyword, that is, generate five-character or seven-character verses. In the existing technology, verses are often generated through a deep learning-based poetry model. The technical solution requires a large number of poetry samples, but the current poetry samples that can be used to train the poetry model are very scarce, and because the poetry samples are not poetically extracted from the keywords, the degree of fitting of the trained poetry model is not high. The verses generated by this poetry model often lack the poetic flavor of the sample verses, and there are various problems such ...

AI Technical Summary

Problems solved by technology

[0002] At present, artificial intelligence has realized the automatic generation of verses, most of which generate a verse through a keyword, that is, generate five-character or seven-character verses. In the existing technology, verses are often generated through a deep learning-based poetry model. The technical solution requires a large number of poetry samples, but the current poetry samples that can be used to train the poetry model are very scarce, and because the poetry samples are not poetically extracted from the keywords, the degree of fitting of the trained poetry model is not high. The verses generated by this poetry model often lack the poetic flavor of the sample verses, and there are also various problems such as incoherent sentences, which lead to low satisfaction and poor user experience for the generated verses.

Images