Paragraph searching method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of artificial intelligence, and provides a paragraph searching method and device, electronic equipment and a storage medium. The method comprises the stepsof expanding a text data set on the basis of a Transformer model, and the search comprehensiveness is improved; performing regression analysis on the extended data set based on a BERT model; obtaining a base dataset, understanding semantics with depth, responding to the received to-be-searched problem; determining an initial text representation of the to-be-searched problem; adjusting the initialtext representation based on a named entity recognition model; obtaining a target text representation of the to-be-searched problem; according to the method and the system, important words are highlighted, a BM25 algorithm is adopted, searching is carried out in a basic data set based on target text representation, a classification model trained based on a BERT algorithm is adopted to screen initial segments, paragraphs are output, and the searching speed and the accuracy of query results are improved through a traditional and depth combined data processing form. In addition, the invention also relates to a blockchain technology, and the text data set can be stored in a blockchain.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence and data processing, in particular to a paragraph search method, device, electronic equipment and storage medium. Background technique [0002] Search is an important way for users to query knowledge, and it plays a very important role in daily life. [0003] However, the existing search engines mainly rely on keywords or statistical information based on literals when searching. Since they cannot fully understand the user's search intent and are only limited to the superficial meaning of the words, the query results are often not accurate enough. [0004] In addition, the existing search engines cannot simultaneously take into account the accuracy and efficiency of the search. Contents of the invention [0005] In view of the above, it is necessary to provide a paragraph search method, device, electronic device and storage medium, which can strengthen the association bet...

AI Technical Summary

Problems solved by technology

[0003] However, the existing search engines mainly rely on keywords or statistical information based on literals when searching. Since they cannot fully understand the user's search intent and are only limited to the superficial meaning of the words, the query results are often not accurate enough.

[0004] In addition, the existing search engines cannot take into account both the accuracy of the search and the efficiency of the search.

Images