一种新的重名消解算法在保险领域中的应用研究

Application of data mining in customer name disambiguation of insurance field

研究客户重名消解问题。针对以往重名消解方法如文本聚类的方法需考虑大量无用词汇并需要人工设定阈值以及类别数量,而基于信息抽取的人物相关属性相似度方法对于人物信息的抽取具有依赖性,提出了一种改进的重名消解算法。该算法首先对具有相同标志的客户进行属性匹配,合并匹配成功的标志;然后进行链接分析,对客户合作网的结构进行分析,将具有相同标志并与同一个代理人实体合作的客户归为一个客户实体,并把具有相同合作对的信息加以分析合并;最后通过原子团簇分析法进行聚类分析。仿真实验结果表明,所提改进算法对中文字符串的匹配处理进行了优化,执行效率高,适合于以大量数据为特征的保险领域的重名消解。

This paper researched the solution to customer name disambiguation of the field of insurance. Aiming at the former name disambiguation methods such as text clustering method need to be considered in a lot of useless words, manually set the threshold, and gave he numbers of type, and the method of character-related properties of similarity based on information extraction depends on the character information, proposed a new name disambiguation method. Firstly, applied the same attribute matching, merging the identity of a successful match and then used link analysis, analyzed structural analysis of customers network, the entities had the same identity and classified cooperate with the same policy to a customer entity, merged the same cooperating information. Finally, analyzed cluster analysis cluster. Experiment results show that the proposed method can optimize the chinese text string matching process and have the high implementation efficiency, especially suitable for large amounts of data to the insurance sector is characterized by digestion of the same name.