结合案件要素序列的罪名预测方法

doi:10.11959/j.issn.2096-0271.2021058

大数据 ›› 2021, Vol. 7 ›› Issue (6): 30-40.doi: 10.11959/j.issn.2096-0271.2021058

• 专题：大数据支撑的智能应用 • 上一篇下一篇

结合案件要素序列的罪名预测方法

孙倩¹, 秦永彬¹^,², 黄瑞章¹^,², 刘丽娟³, 陈艳平¹^,²

¹ 贵州大学计算机科学与技术学院，贵州贵阳 550025
² 公共大数据国家重点实验室，贵州贵阳 550025
³ 贵州师范学院，贵州贵阳 550018

出版日期:2021-11-15 发布日期:2021-11-01
作者简介:孙倩（1996- ），女，贵州大学计算机科学与技术学院硕士生，主要研究方向为自然语言处理
秦永彬（1980- ），男，博士，贵州大学计算机科学与技术学院教授、院长，主要研究方向为大数据处理、云计算、文本挖掘
黄瑞章（1979- ），女，博士，贵州大学计算机科学与技术学院副教授，主要研究方向为信息检索、文本挖掘
刘丽娟（1980- ），女，贵州师范学院讲师，主要研究方向为法学与思想政治教育
陈艳平（1980- ），男，博士，贵州大学计算机科学与技术学院副教授，主要研究方向为人工智能、自然语言处理
基金资助:
国家自然科学基金资助项目(62066008);贵州省科学技术基金重点项目([2020]1Z055)

Charge prediction method combined with case elements sequence

Qian SUN¹, Yongbin QIN¹^,², Ruizhang HUANG¹^,², Lijuan LIU³, Yanping CHEN¹^,²

¹ School of Computer Science and Technology, Guizhou University, Guiyang 550025, China
² State Key Laboratory of Public Big Data, Guiyang 550025, China
³ Guizhou Education University, Guiyang 550018, China

Online:2021-11-15 Published:2021-11-01
Supported by:
The National Natural Science Foundation of China(62066008);The Science and Technology Foundation of Guizhou Province([2020]1Z055)

摘要/Abstract

摘要：

罪名预测指根据给定的案情事实找到适用罪名。现有罪名预测方法主要使用文本内容进行分类，但无法有效地利用文本中的案件要素。针对现有方法的不足，提出了一种结合案件要素序列的罪名预测方法。该方法将案情事实过程表示为一系列以“行为”为核心且具有时序关系的案件要素序列，然后利用图卷积神经网络进行表示，最后融合文本语义特征来预测案件罪名。实验表明，该方法比现有方法具有更好的预测性能。同时，该方法在对易混淆罪名的区分方面也有较好的表现。

关键词: 案情事实, 图卷积神经网络, 案件要素, 文本分类

Abstract:

Charge prediction is to find the appropriate charges based on the facts of the given case.Existing methods mainly use text content for classification, but they cannot effectively use case elements.For the shortcomings of the existing methods, the method of accusation prediction based on the sequence of case elements was put forward.The way expressed the case factual processes as a series of case elements with “behavior” as the core and time-series relationship.Then graph convolutional network was used to represent.Finally, the semantic features of the text were fused to predict the crime.Experiments show that this method has better prediction performance than existing methods.Meanwhile, this method also has a good performance for the distinction between easily confusing charges.

Key words: facts of the case, graph convolutional network, case element, text classification

中图分类号:

TP391.1

孙倩, 秦永彬, 黄瑞章, 刘丽娟, 陈艳平. 结合案件要素序列的罪名预测方法[J]. 大数据, 2021, 7(6): 30-40.

Qian SUN, Yongbin QIN, Ruizhang HUANG, Lijuan LIU, Yanping CHEN. Charge prediction method combined with case elements sequence[J]. Big Data Research, 2021, 7(6): 30-40.

图/表 5

图1

图2

表1

表2

表3

参考文献 24

[1]	秦永彬, 冯丽, 陈艳平 ,等. “智慧法院”数据融合分析与集成应用[J]. 大数据, 2019,5(3): 35-46.
	QIN Y B , FENG L , CHEN Y P ,et al. “Intelligent Court” data fusion analysis and integrated application[J]. Big Data Research, 2019,5(3): 35-46.
[2]	KORT F . Predicting supreme court decisions mathematically:a quantitative analysis of the “right to counsel” cases[J]. American Political Science Review, 1957,51(1): 1-12.
[3]	NAGEL S S . Applying correlation analysis to case prediction[J]. Texas Law Review, 1963,42: 10061.
[4]	LIN W C , KUO T T , CHANG T J ,et al. Exploiting machine learning models for Chinese legal documents labeling,case classification,and sentencing prediction[C]// Proceedings of the 24th Conference on Computational Linguistics and Speech Processing.[S.l.:s.n.], 2012:140.
[5]	LIU Y H , CHEN Y L , HO W L . Predicting associated statutes for legal problems[J]. Information Processing ＆ Management, 2015,51(1): 194-211.
[6]	JIANG X , YE H , LUO Z ,et al. Interpretable rationale augmented charge prediction system[C]// Proceedings of the 27th International Conference on Computational Linguistics:System Demonstrations.[S.l.:s.n.], 2018: 146-151.
[7]	KANG L Y , LIU J , LIU L Q ,et al. Creating auxiliary representations from charge definitions for criminal charge prediction[J]. arXiv preprint,2019,arXiv:1911.05202.
[8]	YANG X T , SHI G Z , LOU J P ,et al. Interpretable charge prediction with multi-perspective jointly learning model[C]// Proceedings of 2019 IEEE 5th International Conference on Computer and Communications. Piscataway:IEEE Press, 2019: 1850-1855.
[9]	刘宗林, 张梅山, 甄冉冉 ,等. 融入罪名关键词的法律判决预测多任务学习模型[J]. 清华大学学报(自然科学版), 2019,59(7): 497-504.
	LIU Z L , ZHANG M S , ZHEN R R ,et al. Multi-task learning model for legal judgment predictions with charge keywords[J]. Journal of Tsinghua University (Science and Technology), 2019,59(7): 497-504.
[10]	LUO B F , FENG Y S , XU J B ,et al. Learning to predict charges for criminal cases with legal basis[J]. arXiv preprint,2017,arXiv:1707.09168.
[11]	HU Z K , LI X , TU C C ,et al. Few-shot charge prediction with discriminative legal attributes[C]// Proceedings of the 27th International Conference on Computational Linguistics.[S.l.:s.n.], 2018: 487-498.
[12]	HE C Q , PENG L , LE Y Q ,et al. SECaps:a sequence enhanced capsule model for charge prediction[C]// Proceedings of the 2019 International Conference on Artificial Neural Networks. Cham:Springer, 2019: 227-239.
[13]	敖绍林, 秦永彬, 黄瑞章 ,等. 基于卷积神经网络的辅助分案方法研究[J]. 大数据, 2021:已录用.
	AO S L , QIN Y B , HUANG R Z ,et al. Research on auxiliary division method based on convolutional neural network[J]. Big Data Research, 2021:accepted.
[14]	黄辉, 秦永彬, 陈艳平 ,等. 基于BERT阅读理解框架的司法要素抽取方法[J]. 大数据, 2021,7(6): 19-29.
	HUANG H , QIN Y B , CHEN Y P ,et al. Legal element extraction method based on BERT reading comprehension framework[J]. Big Data Research, 2021,7(6): 19-29.
[15]	张虎, 潘邦泽, 谭红叶 ,等. 基于法律裁判文书的法律判决预测[J]. 大数据, 2021,7(5): 164-175.
	ZHANG H , PAN B Z , TAN H Y ,et al. Legal judgment prediction based on legal judgment documents[J]. Big Data Research, 2021,7(5): 164-175.
[16]	YAO L , MAO C S , LUO Y . Graph convolutional networks for text classification[C]// Proceedings of the AAAI Conference on Artificial Intelligence.[S.l.:s.n.], 2019,33: 7370-7377.
[17]	ZHANG Y F , YU X L , CUI Z Y ,et al. Every document owns its structure:inductive text classification via graph neural networks[J]. arXiv preprint,2020,arXiv:2004.13826.
[18]	HU L M , YANG T C , SHI C ,et al. Heterogeneous graph attention networks for semi-supervised short text classification[C]// Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Stroudsburg:Association for Computational Linguistics, 2019: 4823-4832.
[19]	HUANG L Z , MA D H , LI S J ,et al. Text level graph neural network for text classification[J]. arXiv preprint,2019,arXiv:1910.02356.
[20]	XU N , WANG P H , CHEN L ,et al. Distinguish confusing law articles for legal judgment prediction[C]// Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg:Association for Computational Linguistics, 2020.
[21]	DEVLIN J , CHANG M W , LEE K ,et al. BERT:pre-training of deep bidirectional transformers for language understanding[J]. arXiv preprint,2018,arXiv:1810.04805.
[22]	KIM Y . Convolutional neural networks for sentence classification[J]. arXiv preprint,2014,arXiv:1408.5882.
[23]	李婷, 秦永彬, 黄瑞章 ,等. 基于神经网络的中文谓语动词识别研究[J]. 数据采集与处理, 2020,35(3): 582-590.
	LI T , QIN Y B , HUANG R Z ,et al. Research on Chinese predicate verb recognition based on neural network[J]. Journal of Data Acquisition and Processing, 2020,35(3): 582-590.
[24]	陈艳平, 冯丽, 秦永彬 ,等. 一种基于深度神经网络的句法要素识别方法[J]. 山东大学学报(工学版), 2020,50(2): 44-49.
	CHEN Y P , FENG L , QIN Y B ,et al. A syntactic element recognition method based on deep neural network[J]. Journal of Shandong University (Engineering Science), 2020,50(2): 44-49.

模型	精确率	召回率	F1(macro)
TFIDF_SVM	81.22%	76.32%	77.41%
TextRNN	94.84%	93.87%	94.29%
FastText	94.62%	94.41%	94.50%
TextCNN	95.07%	95.08%	95.07%
TextRNN_seq	95.38%	94.63%	94.97%
TextCNN_seq	96.30%	95.74%	95.99%

模型	精确率	召回率	F1(macro)
TextCNN	95.07%	95.08%	95.07%
TextCNN_seq	96.30%	95.74%	95.99%
TextCNN_seq_nopre	94.97%	94.04%	94.44%

模型	精确率	召回率	F1(macro)
SVM	90.38%	90.36%	90.37%
FastTest	97.54%	87.49%	97.51%
TextCNN	97.83%	97.81%	97.83%
TextCNN_seq	98.59%	98.62%	98.60%

结合案件要素序列的罪名预测方法

Charge prediction method combined with case elements sequence

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 5

参考文献 24

相关文章 2

Metrics

推荐阅读 0

[1]	张晓龙, 支龙, 高剑, 苗仲辰, 林越峰, 项雅丽, 熊贇. 一种半监督学习的金融新闻文本分类算法[J]. 大数据, 2022, 8(2): 134-144.
[2]	王一峰, 孙丽茹, 崔良乐, 赵毅. 适用于特殊类型自然语言分类的自适应特征谱神经网络[J]. 大数据, 2020, 6(4): 92-104.