A Generalized Query Framework for Geospatial Reasoning

Book One

Volume

Proceedings of the AAAI Conference on Artificial Intelligence, 21

AAAI / SIGART Doctoral Consortium

The ability to reason over geospatial entities using publicly available information is greatly enhanced by the abundance of data sources on the Internet. Traditional data sources such as satellite imagery, maps, gazetteers and vector data have long been used in geographic information systems (GIS). However, incorporating non-traditional sources such as phone books and property tax sites brings to light integration issues not previously considered. The ability to answer different types of queries about geospatial entities further complicates the problem. For example, assume we are provided with an image and consider the query "What is the name of this street?". There exist many different ways of answering this query depending on the types of data sources and operations available to a system. A mediator system could answer this query. However, in answering the query mentioned above, the traditional mediator would produce one plan of execution and assert that a valid plan produces an answer to the query. Yet, if during the execution of the plan an operation produces no data, we should have the recourse to abandon that plan and begin executing a different one. This capability is not available in current mediated systems and this research attempts to incorporate this type of reasoning into a generalized query-answering framework.