基于图深度学习的司法判决预测综述
Review of Legal Judgment Prediction Based on Graph Deep Learning
摘要
Abstract
Legal judgment prediction aims to predict judgment results based on the description of case facts,such as law articles,charges,and term of penalty involved in the case.In recent years,graph deep learning methods have achieved remarkable success in the field of legal artificial intelligence,capturing complex relationships between case facts and the dependencies between law articles effectively.This paper summarizes the latest achievements in graph deep learning methods related to legal judgment prediction comprehensively.Firstly,this paper introduces the task definition and early research of legal judgment prediction.Secondly,this paper focuses on text representation methods for decision prediction based on graph structures,including causal graphs,element graphs,and knowledge graphs.Thirdly,this paper analyzes prediction methods based on graph deep learning,covering graph distillation operators,graph convolutional networks,gated graph neural networks,heterogeneous graph neural networks,graph attention networks,and graph reasoning networks.Fourthly,this paper introduces mainstream datasets,such as CAIL and ELAM,along with other datasets pertinent to judicial decision prediction,and arranges the evaluation metrics used in this domain.Finally,this paper envisions future research trends in legal judgment prediction,emphasizing the continuous innovation and application prospects of graph deep learning in this domain.关键词
法律人工智能/司法判决预测/图深度学习Key words
legal artificial intelligence/legal judgment prediction/graph deep learning分类
信息技术与安全科学引用本文复制引用
张亦菲,李艳玲,葛凤培..基于图深度学习的司法判决预测综述[J].计算机科学与探索,2025,19(8):2024-2042,19.基金项目
国家自然科学基金(62466046,62266033,12204062) （62466046,62266033,12204062）
无穷维哈密顿系统及其算法应用教育部重点实验室开放课题(2023KFZD03) （2023KFZD03）
内蒙古自然科学基金重点项目(2023ZD10) （2023ZD10）
内蒙古师范大学基本科研业务费项目(2022JBQN106,2022JBQN111) （2022JBQN106,2022JBQN111）
"一区两基地"建设项目(计算科学联合创新实验室).This work was supported by the National Natural Science Foundation of China(62466046,62266033,12204062),the Project of Key Laboratory of Infinite-Dimensional Hamiltonian System and Algorithm Application(Inner Mongolia Normal University),Ministry of Education(2023KFZD03),the Natural Science Foundation of Inner Mongolia(2023ZD10),the Basic Scientific Research Business Proj-ect of Inner Mongolia Normal University(2022JBQN106,2022JBQN111),and the"One District,Two Bases"Construction Project(Joint Innovation Laboratory of Computing Science). （计算科学联合创新实验室）
