顾及地址语义和地理空间特征的多源POI位置融合

doi:10.13474/j.cnki.11-2246.2023.0327

测绘通报 ›› 2023, Vol. 0 ›› Issue (11): 54-60.doi: 10.13474/j.cnki.11-2246.2023.0327

顾及地址语义和地理空间特征的多源POI位置融合

李朋朋^1,2, 刘纪平^1,2, 王勇^1,2, 罗安^2,3, 桑瑜³, 闫雪峰²

1. 西南交通大学地球科学与环境工程学院, 四川成都 610031;
2. 中国测绘科学研究院, 北京 100830;
3. 江苏海洋大学海洋技术与测绘学院, 江苏连云港 222005

收稿日期:2023-02-17 发布日期:2023-12-07
通讯作者: 刘纪平。E-mail:liujp@casm.ac.cn
作者简介:李朋朋(1994—),男,博士生,研究方向为互联网地理大数据分析挖掘。E-mail:lipengpeng@my.swjtu.edu.cn
基金资助:
国家重点研发计划(2022YFC3005700);国家自然科学基金(42071384)

Multi-source POI location fusion considering address semantics and geospatial features

LI Pengpeng^1,2, LIU Jiping^1,2, WAGN Yong^1,2, LUO An^2,3, SANG Yu³, YAN Xuefeng²

1. Faculty of Geosciences and Environmental Engineering, Southwest Jiaotong University, Chengdu 610031, China;
2. Chinese Academy of Surveying and Mapping, Beijing 100830, China;
3. School of Marine Technologyand Geomatics, Jiangsu Ocean University, Lianyungang 222005, China

Received:2023-02-17 Published:2023-12-07

摘要/Abstract

摘要： 多源POI位置融合是实现地理空间数据匹配融合的关键技术之一。然而,由于不同POI数据源之间位置编码的差异及定位误差,导致位置融合更加困难。本文提出了一种顾及地址语义和地理空间特征的多源POI位置融合方法。首先,通过TextRCNN和图注意力网络提取地址属性的语义特征;然后,使用多层感知机提取位置属性的地理空间特征;最后,基于自注意力机制通过特征聚合实现多源POI位置融合,并对成都市百度地图、腾讯地图和高德地图的POI数据进行试验验证。结果表明,该方法显著优于现有方法,平均位置融合精度优于12 m。

关键词: 地址语义, 地理空间特征, TextRCNN, 图注意力网络, 多层感知机, 自注意力机制

Abstract: Multi-source POI location fusion is one of the key technologies for geospatial data matching and fusion. However, due to the difference of location coding and location error between different POI data sources, location fusion becomes more difficult. Multi-source POI location fusion considering address semantics and geospatial feature is proposed. Firstly, semantic features of address attributes are extracted by TextRCNN and graph attention network. Then, Multi-layer perceptron is used to extract geospatial features of location attributes. Finally, multi-source POI location fusion is realized by feature aggregation based on self-attention mechanism. We conduct experimental verification on the POI data of Baidu map, Tencent map and Amap in Chengdu. The results show that this method is significantly superior to the existing methods, and the average location fusion accuracy is better than 12 m.

Key words: address semantics, geospatial features, TextRCNN, graph attention network, multi-layer perceptron, self-attention mechanism

中图分类号:

P208

李朋朋, 刘纪平, 王勇, 罗安, 桑瑜, 闫雪峰. 顾及地址语义和地理空间特征的多源POI位置融合[J]. 测绘通报, 2023, 0(11): 54-60.

LI Pengpeng, LIU Jiping, WAGN Yong, LUO An, SANG Yu, YAN Xuefeng. Multi-source POI location fusion considering address semantics and geospatial features[J]. Bulletin of Surveying and Mapping, 2023, 0(11): 54-60.

导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks

链接本文: http://tb.chinasmp.com/CN/10.13474/j.cnki.11-2246.2023.0327

http://tb.chinasmp.com/CN/Y2023/V0/I11/54

参考文献

[1] HUANG Haosheng,GARTNER G,KRISP J M,et al.Location based services: ongoing evolution and research agenda[J].Journal of Location Based Services,2018,12(2): 63-93.
[2] 池娇,焦利民,董婷,等.基于POI数据的城市功能区定量识别及其可视化[J].测绘地理信息,2016,41(2): 68-73.
[3] 谷岩岩,焦利民,董婷,等.基于多源数据的城市功能区识别及相互作用分析[J].武汉大学学报(信息科学版),2018,43(7): 1113-1121.
[4] TU Wei,ZHU Tingting,XIA Jizhe,et al.Portraying spatial dynamics of urban vibrancy using multisource urban big data: a comparative study in Shenzhen[J].Computers Environment and Urban Systems,2019,80: 101428.
[5] LIU Shaojun,ZHANG Long.Urban vitality area identification and pattern analysis from the perspective of time and space fusion[J].Sustainability,2019,11(15): 4032.
[6] DING Ruifeng,CHEN Zhenzhong.RecNet: a deep neural network for personalized POI recommendation in location-based social networks[J].International Journal of Geographical Information Science,2018,32(8): 1631-1648.
[7] 任星怡,宋美娜,宋俊德.基于用户签到行为的兴趣点推荐[J].计算机学报,2017,40(1): 28-51.
[8] NOVACK T,PETERS R,ZIPF A.Graph-based matching of points-of-interest from collaborative geo-datasets[J].International Journal of Geo-Information,2018,7(3): 117.
[9] LI P,LIU J,LUO A,et al.Deep learning method for Chinese multisource point of interest matching[J].Computers,Environment and Urban Systems,2022,96: 101821.
[10] MILIAS V,PSYLLIDIS A.Assessing the influence of point-of-interest features on the classification of place categories[J].Computers,Environment and Urban Systems,2021,86: 101597.
[11] XU Liuchang,DU Zhenhong,MAO Ruichen,et al.GSAM: a deep neural network model for extracting computational representations of Chinese addresses fused with geospatial feature[J].Computers Environment and Urban Systems,2020,81(2): 101473.
[12] 江洲,李琦.地理编码(Geocoding)的应用研究[J].地理与地理信息科学,2003,19(3): 22-25.
[13] 吴张峰,夏兰芳.多源异构POI融合方法及应用[J].测绘通报,2018(3): 143-146.
[14] 陈瑞.基于多源POI数据的匹配融合方法研究[D].兰州: 兰州交通大学,2014.
[15] HOCHREITER S,SCHMIDHUBER J.Long short-term memory[J].Neural Computation,1997,9(8): 1735-1780.
[16] SANCHEZ-LENGELING B,REIF E,PEARCE A,et al.A gentle introduction to graph neural networks[J].Distill,2021,6(9): e33.
[17] KIPF T N,WELLING M.Semi-supervised classification with graph convolutional networks[EB/OL].[2023-02-10].https://arxiv.org/abs/1609.02907.
[18] VELIČKOVIĆ P,CUCURULL G,CASANOVA A,et al.Graph attention networks[EB/OL].[2023-02-10].https://arxiv.org/abs/1710.10903.
[19] HAMILTON W L,YING R,LESKOVEC J.Inductive representation learning on large graphs[EB/OL].[2023-02-10].https://arxiv.org/abs/1706.02216.
[20] LI Pengpeng,LUO An,LIU Jiping,et al.Bidirectional gated recurrent unit neural network for Chinese address element segmentation[J].International Journal of Geo-Information,2020,9(11): 635.
[21] LAI S,XU L,LIU K,et al.Recurrent convolutional neural networks for text classification[C]//Proceedings of the 29th AAAI Conference on Artificial Intelligence.[S.l.]:AAAI,2015.
[22] HORNIK K,STINCHCOMBE M,WHITE H.Multilayer feedforward networks are universal approximators[J].Neural Networks,1989,2(5): 359-366.
[23] VASWANI A,SHAZEER N,PARMAR N,et al.Attention is all you need[EB/OL].[2023-02-10].https://arxiv.org/abs/1706.03762.
[24] ZHANG Ye,WALLACE B.A sensitivity analysis of (and practitioners' guide to) convolutional neural networks for sentence classification[EB/OL].[2023-02-10].https://arxiv.org/abs/1510.03820.
[25] DEVLIN J,CHANG Mingwei,LEE K,et al.BERT: pre-training of deep bidirectional transformers for language understanding[EB/OL].[2023-02-10].https://arxiv.org/abs/1810.04805.
[26] LIU Yinhan,OTT M,GOYAL N,et al.RoBERTa: a robustly optimized BERT pretraining approach[EB/OL].[2023-02-10].https://arxiv.org/abs/1907.11692.

顾及地址语义和地理空间特征的多源POI位置融合

Multi-source POI location fusion considering address semantics and geospatial features

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价