地理信息检索中空间相似性度量的一种模糊方法  

A Fuzzy Method to Measure Spatial Similarity in Geographic Information Retrieval

作　　者：刘家骏[1] 李浩然[1] 钟翔[1] 高勇[1] 

机构地区：[1]北京大学遥感与地理信息系统研究所,北京100871

出　　处：《地理与地理信息科学》2015年第4期38-42,共5页Geography and Geo-Information Science

基　　金：国家自然科学基金项目"定性地理信息检索的模型与方法"(41271385)

摘　　要：一般使用地理信息检索技术提取互联网中以文本方式存在的地理信息,检索返回结果的排序需充分考虑其空间范围的相似性。但传统的空间相似性计算方式忽视了以文本形式存在的地理信息所隐藏的模糊性,从而导致片面性和局限性。该文对文本中以空间陈述形式存在的地理信息进行深入分析,将模糊性因素主要归纳为参照对象和空间关系。通过引入不确定场模型来描述每个因素对模糊性的贡献程度,整合得到空间陈述的模糊footprint表达,建立文档与查询的模糊footprint表达模型。在此基础上,提出了空间相似性模糊度量的计算方法,根据空间相似度对返回的检索结果进行排序。实验结果显示,该方法能够更好地反映空间检索的模糊性,更好地衡量空间检索和网页文档在空间位置上的相似程度,从而在检索结果的排序上优于传统方法。Geographical information retrieval is widely used to extract textually represented geographical knowledge in the Intemet. When ranking the retrieval results, the similarity of spatial range should be taken into consideratiorL But the traditional calculation of spatial similarity ignores the fuzziness hidden in the textually represented geographical information, which leads to limitation and partiali ty. In this paper,we analysis deeply into textually represented geographical information, namely spatial assertion, and classify the fuzzi ness factors into reference-object fuzziness and spatial-relationship fuzziness. The uncertainty field is introduced to evaluate the influence degree of each factor. With the uncertainty field, we build the fuzzy footprints of documents and retrievals. On the basis of this, we pro- pose a fuzzy method to measure spatial similarity in GIR, and rank the retrieval results according to their spatial similarities. Experiments show the method can reflect the fuzziness of spatial retrievals and measure the similarity between retrievals and documents better, and has a superior performance on ranking than traditional methods.

关 键 词：空间相似度 模糊性 footprint地理信息检索 

分 类 号：P208[天文地球—地图制图学与地理信息工程]