Text alignment method and device, computer equipment and storage medium

Abstract

The invention discloses a text alignment method, which is applied to the technical field of text processing and is used for improving the accuracy of text alignment. The method comprises the steps of obtaining a to-be-aligned text, performing sentence segmentation on the to-be-aligned text, and generating reference sentence vectors of sentences of the to-be-aligned text; obtaining audio data corresponding to the to-be-aligned text, generating a transcriptional text of the audio data, and generating a paragraph vector of each basic paragraph in the transcriptional text; based on the first paragraph information, determining the sequence of each basic paragraph in the transcriptional text, and according to the sequence, sequentially calculating the vector similarity between the paragraph vector of each basic paragraph and the reference sentence vector to obtain a similarity set; and for each basic paragraph, comparing the similarity value corresponding to the basic paragraph with a preset similarity threshold to obtain a comparison result, and determining the basic paragraph corresponding to the to-be-aligned text according to the comparison result as a target text to obtain a target aligned text of the to-be-aligned text.

Description

technical field [0001] The present application relates to the technical field of text processing, and in particular, to a text alignment method, apparatus, computer equipment and storage medium. Background technique [0002] In the pure text alignment scenario, the traditional statistical rule-based alignment method extracts feature information based on statistical information such as keywords or word data, and calculates the similarity between the original sentence and the target sentence according to the extracted feature information to achieve text alignment. This method requires manual formulation of rules, which is not universal, and the final text alignment effect is poor. SUMMARY OF THE INVENTION [0003] The present application provides a text alignment method, apparatus, computer equipment and storage medium to improve the accuracy of text alignment. [0004] A text alignment method that includes: [0005] Obtaining the text to be aligned, segmenting the text to...

AI Technical Summary

Problems solved by technology

[0002] In the pure text alignment scenario, the traditional alignment method based on statistical rules extracts feature information based on statistical information such as keywords or word data, and calculates the similarity between the original sentence and the target sentence according to the extracted feature information to achieve text alignment. This method requires manual formulation of rules, which is not universal, and the final text alignment effect is poor

Images