基于主题模型的法院文本典型案例推荐  

Typical Case Recommendation of Court Texts Based on Topic Model

作　　者：吕宾 侯伟亮 

机构地区：[1]北京华宇信息技术有限公司,北京100084

出　　处：《微电子学与计算机》2018年第2期128-132,共5页Microelectronics & Computer

基　　金：国家重点研发计划(2016YFC0800802)

摘　　要：考虑到案件不能量化、业务法官经验局限以及相似案件的认定缺乏统一的标准和尺度等因素,提出一种基于主题模型的法院文本典型案例推荐模型,基于本模型从相似度最大的文本中利用正则和加权的方法根据法院文本中判决年限和对应刑法给出推荐.同时对案件进行深度挖掘和分析,将相似度最高的案件定为最优推荐案件推荐给用户.实验结果表明,提出的基于主题模型的文本相似度计算方法跟传统的方法相比能够取得更好的F值.Taking into account that the case cannot be quantified, the limited experience of business judge, the lackof unified standards for the identification of similar cases and other factors, a typical model of court texts based ontopic model is proposed in this paper. The recommendation is given by regular and weighted method according to thenumber of years of judgment and corresponding criminal law from the maximum similarity text in court texts basedin this model. While the highest similarity of the case as the best recommendation case to the user. Experimentalresults show that the method based on topic model proposed in this paper is superior to the traditional text similaritymeasure in F-metrics.

关 键 词：主题模型LDA 多粒度文本特征提取 文本相似度 法院判决文本 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]