Judicial document paragraph classification method and device, computer equipment and storage medium

Abstract

The invention relates to a judicial document paragraph classification method and device, computer equipment and a storage medium. The method comprises the steps of obtaining judicial documents; performing character segmentation on the judicial document to obtain a character matrix; carrying out vector extraction according to the character matrix to obtain sentence representation vectors; splicingthe sentence representation vectors to obtain a document representation vector; inputting the document representation vectors into a classification model for classification to obtain paragraph categories; feeding back the paragraph category to the terminal for the terminal to perform information extraction, wherein the classification model is obtained by training a model composed of a bidirectional recurrent neural network and a conditional random field by taking a document representation vector with a category label as sample data. According to the method, the sentence representation vectorsare classified through the classification model composed of the trained bidirectional recurrent neural network and the conditional random field to obtain the paragraph categories, judicial document paragraphs are automatically classified, the generalization ability is achieved, and the extraction accuracy and recall rate are high.

Description

technical field [0001] The present invention relates to a text information processing method, and more specifically refers to a judicial document paragraph classification method, device, computer equipment and storage medium. Background technique [0002] For the judicial field, obtaining more information from massive judicial cases has become one of the urgent needs in the era of big data. However, the structuring of judicial documents in the form of text is the prerequisite for subsequent efficient processing and in-depth analysis. Due to the rigor and standardization of judicial documents, the paragraph composition and writing method of judicial documents are usually relatively fixed. By dividing the documents into paragraphs, the document structure can be reduced, that is, the data complexity and difficulty of subsequent document information extraction, and the accuracy can be improved. sex. [0003] At present, the common way of classifying judicial document paragraphs...

AI Technical Summary

Problems solved by technology

However, rule extraction does not have generalization ability, and long-term manual intervention is required to iteratively correct rules to improve the recall rate of extraction.

Images