Universal text information extraction method and device, computer device and storage medium

Abstract

The invention relates to the artificial intelligence, and provides a general text information extraction method and device, a computer device and a storage medium. The method comprises the steps of inputting a model training sample into a labeling model for labeling, and obtaining a labeling rule corresponding to the model training sample; establishing a basic annotation model according to annotation rules, and inputting the to-be-processed text into the basic annotation model for annotation to obtain an annotation sequence; obtaining a sequence resolution rule corresponding to the annotationsequence, and determining an annotation text corresponding to the annotation sequence according to the sequence resolution rule; obtaining a target syntactic feature and a target semantic feature in the annotated text; inputting the target syntactic feature and the target semantic feature into a trained syntactic semantic analysis model for analysis to obtain a syntactic semantic analysis result corresponding to the labeled text; and determining target extraction information corresponding to the to-be-processed text according to the labeled text and the syntactic semantic analysis result, so that various types of text information can be extracted under the condition that only a small number of samples are needed.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to a general text information extraction method, device, computer equipment and storage medium. Background technique [0002] With the rapid development of the computer technology field and the information age, people need to face massive amounts of information every day, among which text information needs to be contacted almost every day. When faced with massive text information, people often need to spend a lot of time searching and extracting it. [0003] The traditional extraction of different types of text information needs to be modeled for the field of the extracted text, and the fields to be extracted need to be defined in advance before modeling, and a large number of related labeled data sets are obtained for modeling. Only a small number of samples are needed It is impossible to extract various types of text information under the circumstances. Contents of ...

AI Technical Summary

Problems solved by technology

[0003] The traditional extraction of different types of text information needs to be modeled for the field of the extracted text, and the fields to be extracted need to be defined in advance before modeling, and a large number of related labeled data sets are obtained for modeling. Only a small number of samples are needed It is impossible to extract various types of text information in the case of

Images