Journal of Geo-information Science >
A Place Name Information Retrieval Method Considering Geographic Entity
Received date: 2015-06-04
Request revised date: 2015-08-31
Online published: 2015-11-10
Copyright
:With the popularization of online map application, place name information retrieval has become a key issue in the related study areas and many promising findings have been achieved. However, these studies mainly focused on the efficiency of retrieval and the matching quality of text information, without considering possible contradictories between the practical application requirements and place name retrieval methods. Currently, many online map platforms generally take POI or point of place name as the retrievable objects, and get results through retrieving text key words. However, this approach ignores the spatial information of place name. This paper studies the forms and methods of place name information retrieval by combining geographic entity and place name based on analyzing the relationship between them. From the view of data feature and application scenes, a new place name information retrieval mode is proposed, which can fully express the structure of geographic entity. This retrieval mode takes geographic entities' attributes and their spatial relationship as the retrieval feature items. With this mode, this paper proposes a place name information retrieval model based on geographic entity similarity. In the meantime, the similarity calculation method for attribute that integrates text attribute and number attribute, and the similarity calculation method for spatial relationship that integrates qualitative spatial filtration and quantitative distance calculation are also presented. Finally, a series of validation experiments are conducted to test the practicability and accuracy of the proposed model. Results show that the retrieval method not only considers the details and spatial characteristics of the retrieval objects, but also ensures the accuracy as well as the quality of the search results.
ZHOU Jing , ZHANG Shuliang , ZHANG Xiaobo . A Place Name Information Retrieval Method Considering Geographic Entity[J]. Journal of Geo-information Science, 2015 , 17(11) : 1362 -1369 . DOI: 10.3724/SP.J.1047.2015.01362
Tab.1 Place name information retrieval mode based on geographic entity表1 顾及地理实体的地名信息检索模式 |
检索模式大类 | 检索模式小类 | 检索形式示例 |
---|---|---|
基于属性特征的地名信息检索 | 单一属性 | 苏果超市 |
复合属性 | 长度小于3 km的主干道路 | |
基于空间关系的地名信息检索 | 拓扑关系+单一属性 | 南京师范大学内的图书馆 |
方位关系+单一属性 | 南京师范大学以东的居民区 | |
距离关系+单一属性 | 距离学则路地铁站500 m的餐馆 | |
拓扑关系+方位关系+单一属性 | 南京师范大学东区的学生公寓 | |
方位关系+距离关系+单一属性 | 仙林湾以东500 m的地铁站 | |
拓扑关系+距离关系+单一属性 | 鼓楼医院周边500 m的超市 | |
拓扑关系+复合属性 | 南京师范大学内超过6层的建筑 | |
方位关系+复合属性 | 南京师范大学以东的大型超市 | |
距离关系+复合属性 | 学则路地铁站附近价格便宜的餐馆 | |
拓扑关系+方位关系+复合属性 | 文苑路以东与其相交的主干道路 | |
方位关系+距离关系+复合属性 | 金鹰天地以东1 km内最高的建筑 | |
拓扑关系+距离关系+复合属性 | 学则路地铁站周边500 m的连锁酒店 | |
拓扑关系+方位关系+距离关系+单一属性 | 苏果超市以东200 m与其邻近的饭店 | |
拓扑关系+方位关系+距离关系+复合属性 | 苏果超市以东200 m与其邻近的面积最大的饭店 |
Tab.2 Concept set of spatial relationship表2 空间关系概念集合 |
空间关系大类 | 空间关系子类 |
---|---|
拓扑关系 | 相交、包含、相等、相接、相离 |
方位关系 | 内方位(东、西、南、北、东北、西北、东南、西南)、外方位(同内方位) |
距离关系 | 精确距离(单位:m、km等) |
Tab.3 Similaritymatrix of topology relationship表3 拓扑关系相似矩阵 |
检索条件 | 目标条件 | |||||
---|---|---|---|---|---|---|
相离 | 相接 | 相交 | 相等 | 包含 | 被包含 | |
相离 | 1 | 0.50 | 0.50 | 0.50 | 0 | 0 |
相接 | 0 | 1 | 0.50 | 0.25 | 0.25 | 0.25 |
相交 | 0 | 0.50 | 1 | 0.50 | 0.25 | 0.25 |
相等 | 0 | 0 | 0 | 1 | 0.50 | 0.50 |
包含 | 0 | 0 | 0 | 0.50 | 1 | 0 |
被包含 | 0 | 0 | 0 | 0.50 | 0 | 1 |
Tab.4 Similaritymatrix of direction relationship表4 方位关系相似矩阵 |
方位关系 | N | NE | E | SE | S | SW | W | NW | O |
---|---|---|---|---|---|---|---|---|---|
N | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 |
NE | 0.50 | 1 | 0.50 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 |
E | 0 | 0.50 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 |
SE | 0 | 0.25 | 0.50 | 1 | 0.50 | 0.25 | 0 | 0 | 0.25 |
S | 0 | 0 | 0 | 0.50 | 1 | 0.50 | 0 | 0 | 0.50 |
SW | 0 | 0 | 0 | 0.25 | 0.50 | 1 | 0.50 | 0.25 | 0.25 |
W | 0 | 0 | 0 | 0 | 0 | 0.50 | 1 | 0.50 | 0.50 |
NW | 0.50 | 0.25 | 0 | 0 | 0 | 0.25 | 0.50 | 1 | 0.25 |
O | 0.50 | 0.25 | 0.50 | 0.25 | 0.50 | 0.25 | 0.50 | 0.25 | 1 |
Tab. 5 Quality evaluation of experiment results表5 实验结果检索质量评价 |
检索条件 | 本文的检索方法 | 基于SQL的空间查询方法 | |||||
---|---|---|---|---|---|---|---|
查全率(%) | 查准率(%) | F值 | 查全率(%) | 查准率(%) | F值 | ||
南京师范大学附近500 m的超市 | 95 | 94 | 0.945 | 70 | 100 | 0.824 | |
南京师范大学东区的学生公寓 | 100 | 91 | 0.953 | 93 | 95.7 | 0.943 | |
与文澜路相交的道路 | 100 | 100 | 1 | 91.7 | 100 | 0.956 | |
学海路以西1 km的酒店 | 93.8 | 95.6 | 0.947 | 93.8 | 89.5 | 0.916 | |
南京财经大学以南1 km的餐厅 | 94.2 | 98.5 | 0.963 | 87.1 | 92.1 | 0.895 | |
仙林主干道 | 94.7 | 100 | 0.973 | 94.7 | 94.7 | 0.947 | |
距离学则路2 km内的居民区 | 93.3 | 85.4 | 0.891 | 86.7 | 92.1 | 0.893 |
Fig.1 Retrieval result of “the student apartments in the east of Nanjing Normal University”图1 “南京师范大学东区的学生公寓”检索结果 |
The authors have declared that no competing interests exist.
[1] |
|
[2] |
|
[3] |
|
[4] |
|
[5] |
|
[6] |
|
[7] |
|
[8] |
|
[9] |
|
[10] |
|
[11] |
|
[12] |
国家测绘地理信息局.CH9010-2011,地理信息公共服务平台地理实体与地名地址数据规范[S]. 2011.
|
[13] |
|
[14] |
|
[15] |
|
[16] |
|
[17] |
|
[18] |
|
[19] |
|
/
〈 |
|
〉 |