首页> 外国专利> MULTIDIMENSIONAL RECURSIVE LEARNING PROCESS AND SYSTEM USED TO DISCOVER COMPLEX DYADIC OR MULTIPLE COUNTERPARTY RELATIONSHIPS

MULTIDIMENSIONAL RECURSIVE LEARNING PROCESS AND SYSTEM USED TO DISCOVER COMPLEX DYADIC OR MULTIPLE COUNTERPARTY RELATIONSHIPS

机译:多维递归学习过程和系统,用于发现复杂的纠缠或多重对等关系

摘要

To provide a multidimensional recursive method used to discover dyadic or multi-counterparty relationships between parties.SOLUTION: A method includes: discovering counterparty relationships from information collected from a plurality of data sources; clustering parties to form clustered parties; determining whether the clustered parties are already linked based on linkage reference database; when the clustered parties are already linked, determining whether the clustered parties match an existing linkage; when the clustered parties are not linked, estimating a potential relationship by using indices or attributes from the data sources; activating an investigation task for the estimated potential linkage; and when the potential relationship is approved by the investigation test, updating the potential relationship stored in a relationship building information database with the linkage reference database.SELECTED DRAWING: Figure 4A
机译:提供一种多维递归方法,用于发现各方之间的二元关系或多方关系。解决方案:一种方法包括:从收集自多个数据源的信息中发现交易对手关系;聚集方组成聚集方;基于链接参考数据库确定聚类方是否已经链接;当聚类方已经链接时,确定聚类方是否与现有链接匹配;当聚集的各方没有链接时,通过使用数据源中的索引或属性来估计潜在的关系;激活调查任务以估计潜在的联系;当潜在关系被调查测试批准时,用链接参考数据库更新存储在关系建立信息数据库中的潜在关系。选定的图:图4A

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号