Text structured information extraction method, server and storage medium

Abstract

The invention relates to a data processing technology, and provides a text structured information extraction method, a server and a storage medium. The method comprises the following steps: firstly, obtaining an original document of to-be-extracted structured information, inputting the original document into a trained first segmentation model to obtain a plurality of first-level tags of the original document, and obtaining first-level text contents corresponding to the first-level tags according to a first preset rule; and then inputting each first-level text content into the trained second segmentation model to obtain a plurality of second-level tags, then obtaining second-level text contents corresponding to each second-level tag according to a second preset rule, storing each obtained tag and text content as logic pages in a preset database, and generating corresponding files to feed back the files to the client. Each first-level tag and each second-level tag in the original document are determined by utilizing the segmentation model, then the structural information is extracted according to the tag content, the extraction of the structured information of the document is automatically realized, and the method is convenient and efficient.

Description

technical field [0001] The invention relates to the field of data processing, in particular to a method for extracting text structured information, a server and a storage medium. Background technique [0002] Portable Document Format (PDF) is used to exchange files in a way independent of applications, operating systems, and hardware. It belongs to a format document and will faithfully reproduce every character, color, and image of the original manuscript, but the storage of PDF is very important. The structured data storage format does not record logical elements such as the logical structure and tables of the document. [0003] At present, optical character recognition (Optical Character Recognition, OCR) technology is usually used to extract the information of PDF documents, but the information of PDF documents extracted by OCR technology is rendered in the form of vectors, and there is no space between each character. Logically, the text formed by the extracted characte...

AI Technical Summary

Problems solved by technology

[0004] In view of the above, the present invention provides a method for extracting text structured information, a server and a storage medium, the purpose of which is to solve the problem that when extracting document information, there is a large randomness in the format and text position, and it is impossible to obtain structured information conveniently

Images