Text matching method and device, terminal and storage medium

Abstract

The embodiment of the invention discloses a text matching method and device, a terminal and a storage medium, and the method comprises the steps: obtaining a target text, carrying out the splitting ofthe target text, obtaining a target phrase set and a target sentence segment set, and determining a first position relation between target phrases in the target phrase set, obtaining a second position relationship among the target sentence segments in the target sentence segment set; constructing a target feature matrix corresponding to the target text based on the target text, the target phraseset, the target sentence segment set, the first position relationship and the second position relationship; and determining a reference feature matrix corresponding to the reference text, and processing the target feature matrix and the reference feature matrix through a matching model to obtain a matching degree of the target text and the reference text. By implementing the method, the text can be matched based on the features of different dimensions of the text, and the accuracy of text matching is improved.

Description

technical field [0001] The present invention relates to the field of computer technology, is specifically applied to the field of medical technology, and in particular relates to a text matching method, device, terminal and storage medium. Background technique [0002] With the development of computer technology, text matching has become one of the research hotspots, that is, to determine the similarity between different texts by matching words in the text, which has great uses in data retrieval, such as users can search If you input a text in the text field, other texts that match the input text can be retrieved from the database through the calculation of the matching degree between the texts for users to browse. [0003] Currently, text matching is usually splitting the text into multiple phrases, and the matching degree between the phrases is used to determine the previous matching degree of the text. However, there are differences in the splitting methods of the phrases...

AI Technical Summary

Problems solved by technology

[0003] Currently, text matching is usually splitting the text into multiple phrases, and the matching degree between the phrases is used to determine the previous matching degree of the text. However, there are differences in the splitting methods of the phrases, and the importance of different phrases to the text It is also different (for example, the phrase in the text title is more important), simply matching the phrase will ignore the characteristics of the text itself, resulting in a lower text matching accuracy

Images