As background knowledge of geographic information retrieval (GIR),the gazetteers have their limitations. In this paper we propose to develop and implement a com-mon sense geographic knowledge base (CSGKB) instead of the gazetteers. We define that CSGKB is concerned with the representation of geographic knowledge in human brain and the simulation of geographic reasoning in daily life. Traditional geographic information system (GIS) is based on the model of map with its data based on geographic coordinates and its computation based on geometry. However,CSGKB,which is made up of geographic features and relationships and is based on qualitative spatio-temporal reasoning,can be viewed as the direct model of geographic world. This paper also discusses the characters of CSGKB and pre-sents its structure which is composed of knowledge base,inference engine,geo-graphic ontology and learner. The applications using CSGKB include geographic information retrieval (GIR),natural language processing (NLP),named entity rec-ognition (NER),Semantic Web,etc. At present,our work focuses on the design of geographic ontology and the implementation of the CSGKB knowledge base. In this paper we describe the CSGKB ontology structure,top ontology,geographic loca-tion ontology,spatial relationship ontology,and domain ontologies. Finally,we in-troduce the current state of implementation of CSGKB and give an outlook on our future researches.
ZHANG Yi,GAO Yong,XUE LuLu,SHEN Si & CHEN KaiChen Institute of Remote Sensing and Geographic Information System,Peking University,Beijing 100871,China
With the rapid development of Internet,much spatial information contained in non-structured or semi-structured documents is available on the World Wide Web.In such documents,localities are always textually described using spatial relationships and named places,instead of numerical coordinates.Hence,extracting positional information from locality descriptions is an important task.In this paper,we bridge two aspects of locality descriptions,namely generating locality descriptions and positioning localities,and provide a method to compute probability density according to the selection probability of a reference object to describe the position of the target object.Refinement operation on uncertainty field is used to deal with locality description involving multiple reference objects.Three metrics are introduced to measure the results of positioning localities.We choose the mixed selection probability function based on Euclidean distance and Voronoi stolen-area to compute probability density function.Finally,we use three cases to demonstrate the proposed methods.
GONG YongXi 1,2,3,LI GuiCai 1,LIU Yu 2 & YANG Jian 1 1 Shenzhen Key Lab of Recycling Economy,Peking University Shenzhen Graduate School,Shenzhen 518055,China
A metro map is usually optimized for the readability of connections and transportation networks structure.In order to assure good readability and meet aesthetic considerations,a set of principles for good metro map layout are proposed.According to these principles,a new methodology based on dynamic segmentation is presented to produce the metro maps automatically.Firstly,routes are constructed according to the line attribute similarity and geometry continuity.Then a set of cartographic generalization methods about the shape,angle,length,and topology are presented for these routes.This method is validated by Beijing metro plan map.From the experiment results,it can be concluded that this new method is more effective than the static segmentation method to produce metro maps with better readability for route plans.
DONG WeiHua 1,TIAN Yuan 2 & ZHANG Yi 2 1 Institute of Geography and Remote Sensing,Beijing Normal University,Beijing 100875,China
