Text structured processing method and device, storage medium and computer equipment

Abstract

The invention discloses a text structured processing method and device, a storage medium and computer equipment. The method comprises the following steps: based on entities and entity types in a knowledge dictionary, performing entity extraction coding processing on text information to be structured to obtain entity coding features of each entity in the text information, and splicing text character features corresponding to the text information with the entity coding features to obtain a text character feature; obtaining a feature set comprising text character features and entity coding features, obtaining an entity attention weight of each feature in the feature set relative to the text information, and coding the text information according to the entity attention weight to obtain text coding features corresponding to the text information; and decoding the text coding features to obtain structured information in the text information. According to the method, the incidence relation and the entities in the text information can be extracted at the same time, error propagation is eliminated, information interaction between different entities is enhanced, and the accuracy of text structured processing is improved.

Description

technical field [0001] The present application relates to the technical field of data processing, and in particular to a text structured processing method, device, computer-readable storage medium, and computer equipment. Background technique [0002] Document structuring is one of the important tasks in natural language processing, which aims to identify entities in documents and the relationship between entities. In many fields, such as education, medical care, finance, and industrial manufacturing, there are many kinds of documents. For example, in the medical field, a large number of electronic medical records, inspection reports, medical textbooks, and medical guidelines are involved. These unstructured documents or Semi-structured documents are converted into structured documents. Through structured documents, the content of the document can be quickly understood, which can effectively improve the work efficiency of the staff in the corresponding field, and better mine...

AI Technical Summary

Problems solved by technology

[0003] At present, document structure processing includes a two-stage approach, that is, document structure processing is divided into two subtasks: entity recognition and relationship recognition. The two subtasks are performed in series, and the results of entity recognition are used for relationship Recognition, in this way, the error of entity recognition will affect the relationship recognition, and the two subtasks of entity recognition and relationship recognition are carried out independently, without considering the dependencies between the two subtasks, resulting in inaccurate results of document structured processing

Images