讲座通知：
时间：2016年1月5号，上午9:30 – 11:30
地点：南一楼601
邀请人简介：郑凯，男，1983年生，博士，苏州大学特聘教授，博士生导师。2012年博士毕业于澳大利亚昆士兰大学，2012-2014年在昆士兰大学信息与电子工程系担任研究员。主要研究领域包括大数据管理，社交媒体数据分析，时空数据库，不确定数据库，内存数据库，数据挖掘等。在数据库、数据挖掘领域顶级会议(CCF A类)和期刊(SCI检索)，如SIGMOD，ICDE，EDBT，ACM TODS， The VLDB Journal，IEEE TKDE等，发表论文60余篇。2013年获澳大利亚优秀青年科研奖(Australia Research Council Discovery Early Career Research Award)；2015年获数据库顶级会议ICDE最佳论文奖。担任多个顶级数据库期刊，如IEEE TKDE， VLDB Journal，Geoinformatica等的专家评审和多个一流国际会议的程序委员，如ACM SIGMOD (2015/2016)，CIKM (2014/2015)，DASFAA (2013/2015)。
英文简介：Dr.Kai Zheng is Professor with the School of Computer Science at Soochow University. He received his PhD degree in Computer Science from The University of Queensland in 2012. His research focus is to find effective and efficient solutions for managing, integrating and analyzing big data for business, scientific and personal applications. He has been working in the area of spatial-temporal databases, uncertain databases, trajectory computing, social-media analysis and bioinformatics. He has published over 60 papers in the highly referred journals and conferences such as SIGMOD, ICDE, EDBT, The VLDB Journal, ACM Transactions and IEEE Transactions. He was the Program Committee Chair of the International Workshops on Human Mobility Computing (HuMoComp 2013/2014), and the International Workshop on Big Data Management and Service (BDMS) in 2013. He is on the reviewer board of several top database journals such as IEEE TKDE, ACM TODS, VLDB Journal, KAIS and Geoinformatica. He is on program committee of SIGMOD2015/2016, CIKM 2014/2015, as well as several other international and regional database conferences.
报告题目: Interactive Top-k Spatial Keyword Queries （交互式top-k空间关键词查询）
摘要：传统的top-k关键词查询技术需要用户详细指定在空间相似度和关键词相似度之间的偏好。在这个工作中，我们研究如何通过用户交互来提高传统的查询技术，从而消除需要用户指定便好的限制，最终完成交互式的top-k关键词查询。通过理论分析确定了可行性之后，我们针对有效性和查询效率，提出了一种三阶段的解决方案。第一阶段，通过高效地检索一个空间文本k-skyband的对象集合作为初始候选，为后续阶段极大地缩小了搜索空间。第二阶段，提出三种策略来选择候选子集。最后一个阶段，讨论如何确定搜索结束条件，通过用户反馈，判断用户的偏好。
Abstract: Conventional top-k spatial keyword queries require users to explicitly specify their preferences between spatial proximity and keyword relevance. In this work we investigate how to eliminate this requirement by enhancing the?conventional queries with interaction, resulting in Interactive Top-k Spatial Keyword (ITkSK) query. Having confirmed the feasibility by theoretical analysis, we propose a three-phase solution focusing on both effectiveness and efficiency. The first phase substantially narrows down the search space for subsequent phases by efficiently retrieving a set of geo-textual k-skyband objects as the initial candidates. In the second phase three practical strategies for selecting a subset of candidates are developed with the aim of maximizing the expected benefit for learning user preferences at each round of interaction. Finally we discuss how to determine the termination condition automatically and estimate the preference based on the user’s feedback.
