基于自然语言空间关系描述的地图近似表达方法

doi:10.12082/dqxxkx.2018.180288

地球信息科学学报 ›› 2018, Vol. 20 ›› Issue (11): 1541-1549.doi: 10.12082/dqxxkx.2018.180288

• 地球信息科学理论与方法 • 下一篇

基于自然语言空间关系描述的地图近似表达方法

曹青^1,^3,⁴(), 洪必文^1,³, 张翎^1,^2,^3,^*(), 阮陵^1,^2,³, 龙毅^1,³

1. 南京师范大学地理科学学院,南京 210023
2. 南京师范大学常州创新发展研究院,常州 213000
3. 江苏省地理信息资源开发与利用协同创新中心,南京 210023
4. 中国电信股份有限公司物联网分公司,南京 210023

收稿日期:2018-06-19 修回日期:2018-10-03 出版日期:2018-11-20 发布日期:2018-11-20
作者简介:作者简介：曹青（1992-）,女,硕士生,主要从事空间认知与地图可视化。E-mail: <email>2454295083@qq.com</email>
基金资助:
国家自然科学基金项目（41571382、61472191）;江苏省高校自然科学研究重大项目（15KJA420001）

Map Approximate Expression Method Based on Spatial Relationship Description in Natural Language

CAO Qing^1,^3,⁴(), HONG Biwen^1,³, ZHANG Ling^1,^2,^3,^*(), RUAN Ling^1,^2,³, LONG Yi^1,³

1. School of Geography Science Nanjing Normal University, Nanjing 210023, China
2. Changzhou Institute of Innovation and Development, Nanjing Normal University, Changzhou 213000, China
3. Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application, Nanjing 210023, China
4. China Telecom Company Limited, Internet of Things branch, Nanjing 210023, China

Received:2018-06-19 Revised:2018-10-03 Online:2018-11-20 Published:2018-11-20
Contact: ZHANG Ling
Supported by:
National Natural Science Foundation of China, No.41571382, 61472191;College Natural Science Research Key Program of Jiang Su Province, No.15KJA420001.

摘要/Abstract

摘要：

自然语言和地图都具备表达地理实体空间关系的能力,自然语言使用方便、抽象化程度高,而地图更为直观,从自然语言转换到地图,有助于人们更深入地了解自然语言描述的地理实体空间关系。然而,如何让计算机具有从自然语言构建图形信息的能力,使计算机具有智能化空间认知思维是当前研究的难点。本文总结了自然语言空间关系描述的类型及特点,提出了基于自然语言描述的地理实体抽象表达方法以及空间关系近似转换方法,建立了一种基于自然语言空间关系描述的地图近似表达策略。实验结果表明,本文方法有效可行,能够实现定性描述的自然语言空间关系向定量（或近似定量）的图形空间关系的转换,为自然语言到地图的转换研究奠定了基础。

关键词: 自然语言, 地理实体, 定性空间关系, “文-图”转换;, 近似表达

Abstract:

With the further development of mobile GIS, intelligent GIS and socialized GIS, the geospatial information service based on natural language processing is an inevitable trend in the field of geographical information science. The intelligent conversion from text to map is one of the important research directions. Both natural language and maps have the ability to express spatial relationship of geographical entities. Natural language has the natural characteristic of usability and is highly abstract, while map language is more intuitive and revealing. The ubiquitous natural language contains a great deal of geographic information. Converting natural language to map language can help people intuitively understand the geographic space environment and bring out new discoveries. The current research difficulties focus on that how to make a computer construct graphical information from natural language and have the intelligent spatial cognitive thinking ability. This paper proposes a method that using point coordinated pairs, straight line segments and rectangular/circular shapes to quantitatively represent point, polyline and polygon geographical entities in natural language respectively. First the spatial relations description types in natural language between point and point, point and line, point and surface, line and line, line and surface, surface and surface geographic entities are summarized. Second, approximate transformation model of spatial relationships in natural language which considering the geometric types of geographical entities is constructed, and an approximate expression strategy based on spatial relationships description in natural language is proposed. Third, a prototype system is designed to implement "text-map" conversion, and scenic spot travel notes are selected as the experimental text to finish the experiment. The experimental results showed that the method mentioned above was feasible, the goal that converting qualitative spatial relationships in natural language to quantitative (or approximately quantitative) graphical spatial relationships could be achieved. This paper lays a foundation for the study of the conversion from natural language to map.

Key words: natural language, geographical entity, qualitative spatial relationship, "text - map" conversion, approximate expression

曹青, 洪必文, 张翎, 阮陵, 龙毅. 基于自然语言空间关系描述的地图近似表达方法[J]. 地球信息科学学报, 2018, 20(11): 1541-1549.DOI:10.12082/dqxxkx.2018.180288

CAO Qing, HONG Biwen, ZHANG Ling, RUAN Ling, LONG Yi. Map Approximate Expression Method Based on Spatial Relationship Description in Natural Language[J]. Journal of Geo-information Science, 2018, 20(11): 1541-1549.DOI:10.12082/dqxxkx.2018.180288

图/表 9

图1

图2

图3

图4

图5

图6

图7

表1

图8

参考文献 24

[1]	Egenhofer M J, Franzosa Robert D.Point-set topological spatial relations[J]. International Journal of Geographical Information Systems, 1991,5(2):161-174. doi: 10.1080/02693799108927841
[2]	Egenhofer M, Mark D.Modelling conceptual neighbourhoods of topological line-region relations[J]. International Journal of Geographical Information Systems, 1995,9(5):555-565. doi: 10.1080/02693799508902056
[3]	Egenhofer M J, Herring J R.Categorizing binary topological relations between regions, lines, and points in geographic databases[J]. Statistics & Information Forum, 1990,20:1-28.
[4]	Mark D, Egenhofer M J.Modeling spatial relations between lines and regions: Combining formal mathematical models and human subjects testing[J]. American Cartographer, 1994,21(4):195-212. doi: 10.1559/152304094782540637
[5]	Egenhofer A R S M, Rashid A, Shariff B M. Natural-language spatial relations between linear and areal objects: the topology and metric of english-language terms[J]. International Journal of Geographical Information Science, 1998,12(3):4956-4961.
[6]	许珺. 关于线状地理特征空间关系的自然语言描述的形式化表达[J].遥感学报,2007,11(2):152-158. doi: 10.11834/jrs.20070220
	[ Xu J.Fomalizing the natural language descriptions about the spatial relations between linear geographic objects[J]. Journal of Remote Sensing, 2007,11(2):152-158. ] doi: 10.11834/jrs.20070220
[7]	Frank A U.Qualitative spatial reasoning about cardinal direction[C]. Baltimore: The ACSM-ASPRS Auto-Carto, 1991:148-167.
[8]	Frank A U.Qualitative spatial reasoning about distances and directions in geographic space[J]. Journal of Visual Languages & Computing, 1992,3(4):343-371. doi: 10.1016/1045-926X(92)90007-9
[9]	Frank A U.Qualitative spatial reasoning: Cardinal directions as an example[J]. International Journal of Geographical Information Science, 1996,10(3):269-290. doi: 10.1080/02693799608902079
[10]	Papadias D, Egenhofer M J, Sharma J.Hierarchical reasoning about direction relations[C]. Rockville: Proceeding GIS '96 Proceedings of the 4th ACM international workshop on Advances in geographic information systems, 1996,5:105-112.
[11]	Papadias D, Sellis T.Qualitative representation of spatial knowledge in two-dimensional space[J]. The VLDB Journal, 1994,3(4):479-516. doi: 10.1007/BF01231605
[12]	Clementini E.Directional relations and frames of reference[J]. Geoinformatica, 2013,17(2):235-255. doi: 10.1007/s10707-011-0147-2
[13]	杜世宏,王桥,李治江.GIS中自然语言空间关系定义[J].武汉大学学报·信息科学版,2005,30(6):533-538. doi: 10.3321/j.issn:1671-8860.2005.06.016
	[ Du S H, Wang Q, Li Z J.Definitions of natural-language spatial relations in GIS[J]. Geomatics and Information Science of Wuhan University, 2005,30(6):533-538. ] doi: 10.3321/j.issn:1671-8860.2005.06.016
[14]	Minock M, Mollevik J.Context-dependent “near” and “far” in spatial databases via supervaluation[J]. Data & Knowledge Engineering, 2013,86:295-305.
[15]	John W, Qing H G, Hijmans R."The point-radius method for georeferencing locality descriptions and calculating associated uncertainty"[J]. International Journal of Geographical Information Science, 2004,18(8):745-767. doi: 10.1080/13658810412331280211
[16]	Gong Y, Li G, Liu Y, et al.Positioning localities from spatial assertions based on voronoi neighboring[J]. Science China Technological Sciences, 2010,53(1):143-149 doi: 10.1007/s11431-010-3203-5
[17]	曹青,唐天琪,张翎,等.一种基于行人位置描述的道路模拟表达方法[J].地理与地理信息科学, 2017,33(6):8-13.
	[Cao Q, Tang T Q, Zhang L, et al. A road simulation representation method based on location descriptions of pedestrians[J]. Geography and Geo-information Science, 2017,33(6):8-13. ]
[18]	刘瑜,高勇,林报嘉,等.基于受限汉语的GIS路径重建研究[J].遥感学报,2004,8(4):323-330. doi: 10.3321/j.issn:1007-4619.2004.04.006
	[ Liu Y, Gao Y, Lin B J, et al.Research on GIS path reconstruction based on constrained Chinese language[J]. Journal of Remote Sensing, 2004,8(4):323-330. ] doi: 10.3321/j.issn:1007-4619.2004.04.006
[19]	黄亮,朱欣焰,呙维,等.一种线状位置文本描述的估算方法[J].武汉大学学报·信息科学版, 2014,39(4):481-485. doi: 10.13203/j.whugis20120155
	[Huang L, Zhu X Y, Guo W, et al. A method of geo-referencing linear locality descriptions[J]. Geomatics and Information Science of Wuhan University, 2014,39(4):481-485. ] doi: 10.13203/j.whugis20120155
[20]	Belouaer L, Brosset D, Claramunt C.A rule-based genetic algorithm for mapping route descriptions towards map representations[A]. ACM Sigspatial International Workshop on Computational MODELS of Place[C]. ACM, 2013:50-53.
[21]	Belouaer L, Brosset D, Claramunt C.From verbal route descriptions to sketch maps in natural environments[A]. ACM Sigspatial International Conference[C]. Association for Computing Machinery, 2016:1-10.
[22]	Moncla L.Automatic reconstruction of itineraries from descriptive texts[D]. Zaragoza: Universidad de Zaragoza, 2015.
[23]	Moncla L, Gaio M, Nogueras-Iso J, et al.Reconstruction of itineraries from annotated text with an informed spanning tree algorithm[J]. International Journal of Geographical Information Science, 2016,30(6):1-24. doi: 10.1080/13658816.2015.1108422
[24]	Vasardani M, Timpf S, Winter S, et al.From Descriptions to Depictions: A Conceptual Framework[A]. Spatial Information Theory, Proceedings of COSIT 2013[C]. 2013:299-319.

类型	示例	解析结果			模拟表达结果
类型	示例	参照物	空间关系	目标物	模拟表达结果
拓扑关系	长廊位于昆明湖和万寿山之间	昆明湖、万寿山	在……之间	长廊
方向关系	宜芸馆位于玉澜堂北面	玉澜堂	北面	宜芸馆
距离关系	仁寿殿距离东宫门很近	东宫门	很近	仁寿殿
多种空间关系组合	昆明湖中有一座南湖岛,由一座美丽的十七孔桥和东岸相连,十七孔桥东侧有个廓如亭,它与十七孔桥及南湖岛连接在一起。	昆明湖	包含+南	南湖岛
		南湖岛	相接+东	十七孔桥
		十七孔桥	相接+东	廊如亭

基于自然语言空间关系描述的地图近似表达方法

Map Approximate Expression Method Based on Spatial Relationship Description in Natural Language

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 24

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	李发东, 王海起, 孔浩然, 刘峰, 王志海, 王琼, 徐建波, 单宇飞, 周啸宇, 闫峰. 联合词汇增强的中文细粒度地理命名实体识别模型研究[J]. 地球信息科学学报, 2023, 25(6): 1106-1120.
[2]	唐曾杨, 艾廷华, 徐海江. 地理知识图谱下的建筑群空间分布模式推理[J]. 地球信息科学学报, 2023, 25(6): 1202-1214.
[3]	杨玉莹, 赵学胜, 刘会园, 彭舒, 吕源鑫. 基于地表覆盖数据的湿地知识图谱构建[J]. 地球信息科学学报, 2023, 25(6): 1240-1251.
[4]	陈晖萱, 郭旦怀, 葛世寅, 王婧, 王彦棡, 陈峰, 杨微石. M2T多源知识图谱融合的空间场景描述文本自动生成框架[J]. 地球信息科学学报, 2023, 25(6): 1176-1185.
[5]	尹文萍, 高宸, 樊辉, 谢菲, 张鑫. 一种融合文本中地理位置和土地利用/覆被信息的野生动物活动细粒度定位方法[J]. 地球信息科学学报, 2022, 24(7): 1363-1374.
[6]	赵桐, 李泽峰, 宋柳依, 熊美成, 廖一兰, 裴韬. 基于微博大数据的北京市流动人口情绪与职住分布的关系研究[J]. 地球信息科学学报, 2022, 24(10): 1898-1910.
[7]	徐召华, 诸云强, 宋佳, 孙凯, 王曙. 基于词嵌入的地理知识库实体类别对齐方法研究[J]. 地球信息科学学报, 2021, 23(8): 1372-1381.
[8]	李锐, 石佳豪, 董广胜, 刘朝辉. 多粒度时空对象组成结构表达研究[J]. 地球信息科学学报, 2021, 23(1): 113-123.
[9]	刘俊楠, 刘海砚, 陈晓慧, 郭漩, 郭文月, 朱新铭, 赵清波. 面向多源地理空间数据的知识图谱构建[J]. 地球信息科学学报, 2020, 22(7): 1476-1486.
[10]	贾梦姝, 张宇, 潘婷婷, 吴文周, 苏奋振. 面向互联网信息抽取的海洋环境灾害链本体构建——以台风灾害为例[J]. 地球信息科学学报, 2020, 22(12): 2289-2303.
[11]	高嘉良,余丽,仇培元,陆锋. 基于通用知识库的地理实体开放关系过滤方法[J]. 地球信息科学学报, 2019, 21(9): 1392-1401.
[12]	洪必文, 曹青, 张翎, 龙毅, 寇萱. 基于自然语言形态描述的地理实体模拟表达方法[J]. 地球信息科学学报, 2019, 21(10): 1491-1501.
[13]	王姬卜, 陆锋, 吴升, 余丽. 基于自动回标的地理实体关系语料库构建方法[J]. 地球信息科学学报, 2018, 20(7): 871-879.
[14]	唐天琪, 曹青, 张翎, 龙毅. 点线目标自然语言空间关系描述模拟表达方法研究[J]. 地球信息科学学报, 2018, 20(2): 139-146.
[15]	陈祖刚, 杨雅萍. 耦合尺度的地理实体空间相关度算法的建立与应用[J]. 地球信息科学学报, 2018, 20(1): 37-47.