| 地理空间数据本质特征语义相关度计算模型 |
| |
| 引用本文： | 赵红伟,诸云强,杨宏伟,罗侃.地理空间数据本质特征语义相关度计算模型[J].地理研究,2016,35(1):58-70. |
| |
| 作者姓名： | 赵红伟 诸云强 杨宏伟 罗侃 |
| |
| 作者单位： | 1. 中国科学院地理科学与资源研究所,中国科学院资源与环境信息系统国家重点实验室,北京 1001012. 中国科学院大学,北京 1000493. 江苏省地理信息资源开发与利用协同创新中心,南京 2100234. 中国石油规划总院,北京 100083 |
| |
| 基金项目： | 基金项目：国家自然科学基金项目（41371381）;科技基础性工作专项项目（2013FY110900）;中国科学院科研信息化“科技领域云”项目;国家重大科学仪器设备开发专项（2012YQ06002704）;云南省科技计划项目（2012CA021） |
| |
| 摘 要： | 关联数据是跨网域整合多源异构地理空间数据的有效方式,语义丰富的关联是准确、快速发现目标数据的关键。根据地理空间数据在空间、时间、内容上的语义关系,提出地理空间数据本质特征语义相关度计算模型。通过构建本质特征的关联指标体系,分层次逐级计算地理空间数据的语义相关度。与传统的语义相关度计算方式不同,以地理元数据为语料库,充分考虑地理空间数据的特点及空间、时间、内容在检索中不同的重要程度,分别采用几何运算、数值运算、词语语义相似度计算和类别层次相关度计算的方式,构建地理空间数据的语义相关度计算模型。该模型具有构建简单、适用于多源异构数据、充分结合了数学运算和专家经验知识等特点。实验表明：模型能够有效地计算地理空间数据本质特征的语义相关度,并具备一定的扩展性。
|
| 关 键 词： | 地理空间数据 空间特征 时间特征 内容特征 语义相关度 |
| 收稿时间： | 2015-06-21 |
| 修稿时间： | 2015-11-18 |
The semantic relevancy computation model on essential features of geospatial data |
| |
| Hongwei ZHAO,Yunqiang ZHU,Hongwei YANG,Kan LUO.The semantic relevancy computation model on essential features of geospatial data[J].Geographical Research,2016,35(1):58-70. |
| |
| Authors: | Hongwei ZHAO Yunqiang ZHU Hongwei YANG Kan LUO |
| |
| Institution: | 1. State Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, CAS, Beijing 100101, China2. University of Chinese Academy of Sciences, Beijing 100049, China3. Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application, Nanjing 210023, China4. China Petroleum Planning & Engineering Institute, Beijing 100083, China |
| |
| Abstract: | Linked data is an effective way to integrate multi-source heterogeneous geospatial data cross domain. Semantic high association is the key point to find out target data accurately and quickly. Semantic relevancy directly reflects the value of semantic association between geospatial data, and has great value in retrieving and ranking the targets. According to the semantic relations of geospatial data in space, time and content, a semantic relevancy computation model focusing on essential features of geospatial data is proposed in this research. We compute the semantic relevancy hierarchically through building up a relevancy indices system for essential characteristics. Spatial semantic relevancy is calculated by taking spatial topology relationships and spatial measurement relationships into account. The spatial semantic relevancy is bigger when the distance is smaller and the relative area (or length) is bigger of two spatial objects in the same spatial topology relationship. Accordingly, the time semantic relevancy is calculated by taking into account time topology relationships and time measurement relationships. The time semantic relevancy is bigger when the distance is smaller and the relative time is bigger between two times. The content relevancy is calculated by taking into account the semantic similarity of content keywords and the category correlation degree. Taking geographic metadata as the corpus, this model, which is different from traditional ones, was built up by considering the characteristics of geospatial data and their different important degrees in retrieval and using the methods of geometry processing, numerical computation, semantic similarity calculation and analysis of category relevancy. This model has the advantages of simply building process, suitable for multi-source heterogeneous data, and fully combining mathematics computation and semantics judgment of experts. The result showed that the model can be used to calculate the semantic relevancy on essential characteristics of geospatial data effectively, which can improve the speed of searching targets and the accuracy of the retrieval, and has good expansibility. |
| |
| Keywords: | geospatial data spatial characteristic temporal characteristic content characteristic semantic relevancy |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《地理研究》浏览原始摘要信息 |
| 点击此处可从《地理研究》下载免费的PDF全文 |
|
