Synonym sentence generation method and device based on BERT model, equipment and storage medium

Abstract

The invention relates to the technical field of artificial intelligence, and provides a synonym sentence generation method and device based on BERT model, equipment and a storage medium. The method comprises the steps of obtaining a template statement of a to-be-generated synonym sentence, performing word segmentation operation on the template statement to obtain a plurality of segmented words, generating a candidate word set corresponding to each segmented word and a score of each candidate word in the candidate word set based on a pre-trained BERT model, extracting at least one keyword from the plurality of segmented words, performing replacement operation on the keyword based on a candidate word set corresponding to the keyword to obtain a plurality of candidate statements corresponding to the template statement, calculating a logic score of each candidate statement based on the score of the candidate word, and when the logic score is greater than a preset threshold value, taking the candidate statement as a synonym sentence of the template statement. The synonym sentences of the sentences can be massively and accurately generated. The invention further relates to the technical field of block chains. The synonym sentence can be stored in a node of a block chain.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a method, device, equipment and storage medium for generating synonymous sentences based on a BERT model. Background technique [0002] With the rapid development of artificial intelligence and the development of hospital informatization, the intelligent auxiliary medical consultation system has also emerged. The intelligent auxiliary medical consultation system can support auxiliary disease diagnosis, health management, remote consultation and other functions. [0003] Since the intelligent question answering system (for example, the intelligent assisted consultation system) needs to understand the consultation information input by the patient, so as to assign the appropriate department to the patient, and the query sentences with different meanings and different expressions will cause serious problems to the system's semantic understanding of the sentence...

AI Technical Summary

Problems solved by technology

[0004] The existing technology usually uses the synonyms of the word2vec model to output the vocabulary to replace the original words to obtain synonymous sentences, but word2vec cannot distinguish the different semantics of polysemous words

For example, the word "car" has different meanings in "a car" and "cherry", which leads to the low accuracy of synonymous questions generated by this method

Images