Case cause classification method based on key value memory network and medium

Abstract

The invention provides a case cause classification method based on a key value memory network and a medium. The case cause classification method comprises: 1) data preprocessing: extracting case description text information and legal provision information quoted by a document from a judicial document; 2) model construction: establishing a case cause classification model based on a key value memorynetwork, wherein the case cause classification model comprises modeling of citation laws, modeling of case casecase description texts and modeling of a key value memory enhancement neural network; 3)model training: optimizing the established cause classification model through training data to obtain optimal parameters; and 4) model prediction: inputting a case casecase description text of the test data set, and predicting the cause category corresponding to the case by the model. The key value memory enhanced neural network is used for case cause classification, case key information can be effectively extracted by means of reference information of legal provisions, the classification accuracy of case causes with a small number of samples is improved, and then the overall accuracy of casecause classification is improved.

Description

technical field [0001] The present invention relates to the technical field of data processing, in particular to a case classification method and medium based on a key-value memory network. In particular, it relates to a method for classifying reasons of case based on key-value memory enhanced neural network. Background technique [0002] The classification of the cause of action is of great significance to the construction of an intelligent legal document case review system, which provides convenient reference for professionals (such as judges and lawyers) and improves their work efficiency. The classification of the cause of action is also an unavoidable problem in filing and trial practice. The accuracy of the determination of the cause of action is conducive to the classification and management of accepted cases, and it is conducive to the people's courts to accurately determine the litigation issues of the case and correctly use the law in trial practice. The accuracy ...

AI Technical Summary

Problems solved by technology

However, the judgment and grasping accuracy of this method is low

Images