带有匹配估计方法物联网基于内容的实体搜索机制  

Content-Based Entity Search with a Matching Estimation Approach for Internet of Things

作　　者：张普宁[1] 刘元安[1] 吴帆[1] 唐碧华[1] 李论[1] 

机构地区：[1]北京邮电大学智慧无线移动信息技术中心,北京100876

出　　处：《上海交通大学学报》2016年第7期1060-1064,1070,共6页Journal of Shanghai Jiaotong University

基　　金：国家自然科学基金项目(61272518);民用航天十二五科技项目;北京市高等学校青年英才计划项目;安全生产智能监控北京市重点实验室资助

摘　　要：提出了实体状态预测方法,基于传感器采集的实体状态原始数据,预测实体在用户搜索时刻的状态,设计了实体匹配估计方法,依据实体的预测状态对实体的匹配状态进行分类,并估计其与搜索需求的匹配概率,返回匹配概率较高的实体作为搜索结果.结果表明,所提机制在物联网中基于内容的实体搜索的查全率与查准率方面均有较大的性能增益.An entity state prediction method based on the raw entity state data observed by the attached sensor was proposed to predict the state of entities at the query time. Moreover, an entity matching esti- mation approach was designed to classify these entities and estimate their matching probabilities with the search needs based on the state of entities predicted. The entities that own higher matching probabilities will be returned as the search results. Numerical results show that the search mechanism proposed can achieve a better recall ratio and precision performance in terms of content-based entity search in the Internet of Things.

关 键 词：物联网 实体搜索 状态预测 匹配估计 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]