综合多尺度的重点人多维空间数据关联分析  

Integrated Multi-scale Association Analysis of Multi-dimensional Spatial Data for Object Persons

作　　者：张文宇 彭舒凡 叶乃夫 ZHANG Wenyu;PENG Shufan;YE Naifu(School of Information Technology and Cyber Security,People’s Public Security University of China,Beijing 100038,China)

机构地区：[1]中国人民公安大学信息网络安全学院,北京100038

出　　处：《地理空间信息》2023年第12期14-20,共7页Geospatial Information

摘　　要：在公安数据库中,重点人的空间数据呈现出多维特性,并由空间文本与空间实体构成。在传统的空间关联计算方法中,通常将单一的空间文本关联度或空间实体关联度作为最终结果,缺乏对二者的综合分析,并较少考虑到空间尺度对空间实体关联度的影响。因此,结合空间文本与空间实体2个方面,提出重点人空间数据关联分析方法。其中,对于空间实体,结合空间尺度,提出综合多尺度的空间实体关联度的计算方法,并通过空间实体的空间拓扑关系与空间度量关系量化了每个尺度下的实体关联度。最后,通过实验证明,对于重点人多维空间数据的关联分析,该方法优于传统方法,更能满足公安业务的需求。The spatial data of object persons in public security database exhibit multi-dimensional characteristics composed of spatial text and en-tities.Traditional spatial association calculation methods typically adopt either spatial text correlation or spatial entity correlation alone as the fi-nal result,while comprehensive analysis of both remains to be improved.Less consideration has been given to the influence of spatial scale on spatial entity relevance.Therefore,we proposed a focus on the human spatial data association analysis method by combining spatial text and spa-tial entities.We put forward a comprehensive multi-scale calculation of spatial entity relatedness that quantifies entity relatedness under each scale through the spatial topological relationship and spatial metric relationship of spatial entities.Experiments demonstrate that the method is su-perior to traditional methods for the association analysis of multi-dimensional spatial data of object persons and better meets the needs of public security applications.

关 键 词：多维空间数据 重点人 空间拓扑关系 空间度量关系 关联分析 空间尺度 

分 类 号：P208[天文地球—地图制图学与地理信息工程]