专利名称:Graph-based recommendations service
systems and methods
发明人:Lawrence Kelley申请号:US14087603申请日:20131122公开号:US09760609B2公开日:20170912
专利附图:
摘要:A recommendation engine may provide recommendations by obtaining acompact graph representation representing a recommendations graph comprising ofnodes and weighted edges. Each node is associated with type metadata indicating that it
represents a recommendable item or a non-recommendable item. Each weighted edge isassociated with edge-weight metadata. The compact graph representation can be storedin primary memory. When servicing a request for an item recommendation, therecommendation engine selects an entry node based at least in part on contextmetadata associated with the request, and traverses only a highly-weighted portion ofthe compact graph representation that is proximate to an entry node to select pathsleading respectively to potential recommendation nodes. Each path is scored based onthe edge-weight metadata of all segments, and at least one recommendation node isselected based at least in part on the path scores.
申请人:HERE GLOBAL B.V.
地址:Veldhavon NL
国籍:NL
代理机构:Ditthavng & Steiner, P.C.
更多信息请下载全文后查看
因篇幅问题不能全部显示,请点此查看更多更全内容
Copyright © 2019- awee.cn 版权所有 湘ICP备2023022495号-5
违法及侵权请联系:TEL:199 1889 7713 E-MAIL:2724546146@qq.com
本站由北京市万商天勤律师事务所王兴未律师提供法律服务