The democratization of data access and the adoption of OLAP in scenarios requiring hand-free interfaces push towards the creation of smart OLAP interfaces. In this paper, we introduce COOL, a framework devised for COnversational OLap applications. COOL interprets and translates a natural language dialogue into an OLAP session that starts with a GPSJ (Generalized Projection, Selection, and Join) query and continues with the application of OLAP operators. The interpretation relies on a formal grammar and on a repository storing metadata and values from a multidimensional cube. In case of ambiguous or incomplete text description, COOL can obtain the correct query either through automatic inference or user interactions to disambiguate the text. Our tests show very promising results in terms of effectiveness, efficiency, and user experience. Besides adding novel support to the interpretation and translation of complete analytical OLAP sessions, COOL achieves an average accuracy of 94% in the interpretation of GPSJ queries from real datasets.

在需要免提接口的情况下，数据访问的民主化和OLAP的采用推动了智能OLAP接口的创建。在本文中，我们介绍了COOL，这是一种为会话OLap应用程序设计的框架。COOL解释自然语言对话并将其转换为OLAP会话，该会话以GPSJ（广义投影，选择和联接）查询开始，并继续使用OLAP运算符。解释依赖于形式语法和存储多维多维数据集的元数据和值的存储库。在文本描述不明确或不完整的情况下，COOL可以通过自动推断或用户交互来消除歧义，从而获得正确的查询。我们的测试显示出在有效性，效率和用户体验方面非常有希望的结果。