Information extraction method and device and electronic equipment

Abstract

The embodiment of the invention provides an information extraction method and device and electronic equipment, and the method comprises the steps: obtaining a target text to be subjected to information extraction, and carrying out the splicing processing of the target text, and obtaining a to-be-recognized text; adopting a first recognition mode to recognize preset key fields and title lines in the to-be-recognized text to obtain a plurality of first key fields and a plurality of target title lines; on the basis of each first key field and each target title line, partitioning the to-be-recognized text to obtain a plurality of text sub-blocks; for each text sub-block, adopting a second identification mode to extract a preset key field in the text sub-block to obtain a second key field; fusing the first key field and the second key field corresponding to each text sub-block to obtain preliminary extraction results corresponding to different text sub-blocks; and performing duplicate removal on the preliminary extraction result to obtain an information extraction result of the target text. According to the embodiment of the invention, the accuracy of information extraction can be improved.

Description

technical field [0001] The present invention relates to the technical field of natural language processing, in particular to an information extraction method, device and electronic equipment. Background technique [0002] Information extraction technology extracts structured text information by analyzing and processing structured, semi-structured and unstructured text data, which is a basic and important task link in the field of natural language processing. Resume is very important for knowing a person. Resume parsing is an important task in the field of intelligent recruitment. It automatically and intelligently parses and extracts personal basic information and experience information such as work, projects, internships, and activities in resume documents. Company recruitment, talent assessment and talent management all play an important role and have practical significance. [0003] In practical applications, due to the influence of many factors such as resume format and...

AI Technical Summary

Problems solved by technology

[0004] However, due to the influence of factors such as the diversification of resume templates and the diversification of personal writing habits, the method of using rules and keyword lists to obtain resume experience information may be able to accurately extract resume templates that are relatively standardized and ideal. Resume experience information, but for the situation that the ideal resume template is not standardized, the accuracy of the extracted resume experience information is low, and the overall generalization ability is poor, which leads to low overall accuracy of resume experience information extraction

Images