Extracting knowledge from big document databases has long been a challenge. Most researchers do a literature review and manage their document databases with tools that just provide a bibliography and when retrieving information (a list of concepts and ideas), there is a severe lack of functionality. Researchers do need to extract specific information from their scholarly document databases depending on their predefined breakdown structure. Those databases usually contain a few hundred documents, information requirements are distinct in each research project, and technique algorithms are not always the answer. As most retrieving and information extraction algorithms require manual training, supervision, and tuning, it could be shorter and more efficient to do it by hand and dedicate time and effort to perform an effective semantic search list definition that is the key to obtain the desired results. A robust relative importance index definition is the final step to obtain a ranked importance concept list that will be helpful both to measure trends and to find a quick path to the most appropriate paper in each case.

中文翻译：

---

从学术文献数据库中智能提取信息

从大型文档数据库中提取知识一直是一个挑战。大多数研究人员使用仅提供参考书目的工具进行文献审查和管理其文档数据库，并且在检索信息（概念和思想列表）时，功能严重不足。研究人员确实需要根据其预定义的分解结构从其学术文献数据库中提取特定信息。这些数据库通常包含数百个文档，每个研究项目的信息需求都不尽相同，而技术算法也不总是答案。由于大多数检索和信息提取算法都需要人工培训，监督和调整，手动执行此操作可能会更短，更高效，并花费时间和精力来执行有效的语义搜索列表定义，这是获得所需结果的关键。可靠的相对重要性指数定义是获得排名重要性概念列表的最后一步，这将有助于衡量趋势并找到在每种情况下获取最合适论文的快速路径。