Theme extraction method and device, terminal and storage medium

Abstract

The invention discloses a theme extraction method and device, a terminal and a storage medium, and the method comprises the steps: obtaining a to-be-extracted text, responding to a tag start symbol recognized in the to-be-extracted text, and determining whether a preset tag end symbol exists after the tag start symbol; if a label end symbol exists after the label start symbol, determining the text content between the label start symbol and the label end symbol as a target theme of the to-be-extracted text; if the type of the label ending symbol is the same as that of the label starting symbol, determining whether a new label ending symbol exists after the label ending symbol or not; and if yes, determining the text content between the label ending symbol and the new label ending symbol as the target theme of the to-be-extracted text. According to the scheme, the probability of label omission and excessive extraction can be reduced, and the accuracy of a label extraction result is further improved.

Description

technical field [0001] The present application relates to the field of computer technology, and in particular to a subject extraction method, device, terminal and storage medium. Background technique [0002] In the current mainstream information application programs, there are two ways of double pound sign recognition mode and single pound sign recognition mode. In some applications using the single hash sign extraction mode, each tag starts with a hash sign and ends with a space or punctuation mark. If there are multiple hash signs, each hash sign extracts a tag backwards; but For the double pound tag, it may be over-extracted, and two tags are extracted. The second tag ends with a punctuation, and the normal body content is also wrongly extracted as a long tag. In some applications that use the double pound sign extraction mode, the content between the two pound signs will be extracted as a label only if it starts with a pound sign and ends with a pound sign. If only the...

AI Technical Summary

Problems solved by technology

In some applications that use the double pound sign extraction mode, the content between the two pound signs will be extracted as a label only if it starts with a pound sign and ends with a pound sign. If only the beginning or end contains a pound sign, Tags are not extracted; however, single hashtags cannot be recognized and processed directly as normal text

Images