摘要
介绍中文保险合同格式条款的数据结构和概念层次,将其非结构化的保险条款数据集作为处理对象。首先对保险格式条款结构及含义进行分析和研究;其次利用模板提取和匹配方法对其进行结构化处理,将其转变为结构化数据,实验表明该方法能获得较高的准确率。
Introduce the data structure and concept level of Chinese insurance contract format clauses,and treat its unstructured insurance clause data set as the object of processing.First,analyze and study the structure and meaning of insurance format clauses,and then use template extraction and matching methods to perform the operating,transform it into structured data.Experiments showthat this method can achieve higher accuracy.
作者
张晶晶
杜明
ZHANG Jingjing;DU Ming(School of Computer Science and Technology,Donghua University,Shanghai 201620,China)
出处
《智能计算机与应用》
2018年第3期87-90,共4页
Intelligent Computer and Applications
关键词
保险条款
模板提取
文本结构化
insurance policy
template extraction
structuring data
