BIGDATA: Small: DA: Choosing a Needle in a Big Data Haystack

大数据：小：DA：大海捞针

• 批准号: 1250880
• 负责人: Hosagrahar Jagadish
• 金额: $ 67.48万
• 依托单位: Regents of the University of Michigan - Ann Arbor
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2013
• 资助国家: 美国
• 起止时间: 2013-03-15 至 2019-03-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1250880&HistoricalAwards=false
• 关键词: BIGDATA; Small; DA; Choosing; Needle

This big data project develops tools and algorithms to support users in the task of choosing one (or a few) object(s) from a very large set, particularly when there is a great deal of complex data on which to base this choice.Consider a traveler looking at hotel options on a travel site, a scientist trying to identify proteins to investigate further based upon the results of a high throughput experiment, or an intelligence analyst trying to identify suspected terrorists. In all of these cases we have a big data challenge in that there are likely to be hundreds, perhaps thousands or even millions, of options to choose from. While there are some criteria that can be expressed as simple functions of attribute values, e.g. price for a hotel room, these criteria capture only a part of the objective function. Other considerations, such as stylishness of a hotel, can be much harder to determine as a function of known attributes. The user may be compelled to examine candidate options individually. The computer's task is to help minimize the number of candidates examined, and to optimize the order of examination. This project examines how best to accomplish this task.Techniques explored include supporting human specification of information need against a variety of big data sources and machine presentation of relevant results with the volume of big data. The broader impact of this project is in effectively harnessing the power of big data in a variety of applications, including business, science, and national defense.

这个大数据项目开发了工具和算法来支持用户从一个非常大的集合中选择一个（或几个）对象，特别是当有大量复杂的数据作为选择的基础时。考虑一个旅行者在旅游网站上查看酒店选择，一个科学家试图根据高通量实验的结果识别蛋白质以进一步调查，或者一个情报分析师试图识别可疑的恐怖分子。在所有这些情况下，我们都面临着一个大数据挑战，因为可能有数百，甚至数千甚至数百万个选项可供选择。虽然有一些标准可以表示为属性值的简单函数，例如酒店房间的价格，但这些标准只捕获了目标函数的一部分。其他考虑因素，如酒店的风格，可能很难作为已知属性的函数来确定。用户可能被迫单独检查候选选项。计算机的任务是帮助减少考试的考生数量，并优化考试顺序。本项目研究如何最好地完成这项任务。探索的技术包括支持人类对各种大数据源的信息需求规范，以及用大数据量表示相关结果的机器。该项目更广泛的影响是有效地利用大数据在各种应用中的力量，包括商业、科学和国防。