BigDataBench

BigDataBench是由中国科学院计算技术研究所与多家工业伙伴合作开发的大数据基准套件，专注于搜索引擎领域。该数据集包含251,564名跨260所大学和研究所的研究人员信息，涵盖了从公开来源收集的多类别数据，如研究兴趣和教育背景。创建过程中，研究团队广泛调研了开源搜索引擎解决方案，并开发了名为ProfSearch的语义搜索引擎。BigDataBench旨在为系统与架构研究提供真实且多样化的数据集，以评估和比较大数据系统的性能、能效和成本效益。

BigDataBench is a big data benchmark suite developed by the Institute of Computing Technology, Chinese Academy of Sciences in collaboration with multiple industrial partners, focusing on the search engine domain. This dataset contains information of 251,564 researchers affiliated with 260 universities and research institutes, covering multi-category data collected from public sources such as research interests and educational backgrounds. During its development, the research team conducted extensive surveys on open-source search engine solutions and developed a semantic search engine named ProfSearch. BigDataBench aims to provide realistic and diverse datasets for system and architecture research to evaluate and compare the performance, energy efficiency and cost-effectiveness of big data systems.