Document information extraction method and system based on text classification and reading understanding

Abstract

The invention belongs to the technical field of information content processing, and particularly relates to a document information extraction method and system based on text classification and reading understanding. The method comprises the following steps: S1, converting a document into a plain text format; s2, preprocessing the document to obtain input data; s3, generating corresponding word vectors, word vectors and context vectors, and splicing the word vectors, the word vectors and the context vectors to obtain spliced vectors; s4, if the spliced vector is an answerable type, taking the spliced vector as the input of the next step; s5, obtaining the position of the most matched long label data; and S6, finally outputting the to-be-extracted long entity field. The system comprises a text information intelligent extraction module, a data preprocessing module, a feature extraction module, a text classification module, a reading understanding module, a long entity label data generation module and a data post-processing module. The method has the characteristics that the training and prediction time can be greatly shortened, and the field extraction precision and speed of the document extraction model are improved.

Description

technical field [0001] The invention belongs to the technical field of information content processing, and in particular relates to a document information extraction method and system based on text classification and reading comprehension. Background technique [0002] In today's highly informatized office, employees in corporate offices spend nearly one-third of their daily time dealing with text. For example, legal personnel have to review a large number of contracts and draft agreements; accounting personnel have to review a large number of reports. This kind of work has the characteristics of high repetition and heavy workload, and the efficiency of manual processing is low, and it is easy to cause huge irreparable losses due to mistakes. In recent years, with the application and development of machine learning and deep learning in the field of natural language processing, intelligent document review systems have entered a stage of rapid development. [0003] The intell...

AI Technical Summary

Problems solved by technology

[0016] The purpose of the present invention is to overcome the problems of model training difficulties, time-consuming increase and low extraction accuracy in existing document information extraction methods in the prior art, and provides a method that can greatly shorten training and prediction time, and improve document extraction. Document Information Extraction Method and System Based on Text Classification and Reading Comprehension Based on Accuracy and Speed ​​of Model in Field Extraction

Images