基于地理坐标和轨迹数据的路径推荐方法

doi:10.11959/j.issn.1000-436x.2017097

摘要/Abstract

摘要：

为弥补旅游相关网站旅游信息推荐的不足，以真实景区图片地理坐标数据和游览路径数据为研究基础，提出一种混合密度聚类方法识别景点热度，通过确定HITS算法预估景点吸引力，改进传统ACO算法，设计一种包含单景区内所有景点的游览路径生成算法，帮助用户检索旅游景点中优质资源并规划有效的游览路径。为评估景区热点和路线规划方法的效果，进行多种算法对比实验，结果表明所选方法具备高效性和实用性。

关键词: 旅游信息, 地理坐标数据, 景区热点, 聚类方法, 游览路径

Abstract:

In order to overcome the lacking of tourism information recommendation at the tourism websites,travel review websites and travel websites,a hybrid density clustering approach was proposed to identify scenic hotspot based on the data of geographical coordinates and tour route data.To help users searching high-quality resources and planning an effective tour path,a tour path generation algorithm was designed which contained all the attractions in the scenic area by using the HITS algorithm to evaluate the attraction and improving the traditional ACO algorithm.The multi algorithm comparison experiment was conducted to evaluate the effectiveness of the hot spots and route planning methods.The results show that the method is efficient and practical.

Key words: tourist information, geographic coordinate data, scenic hotspot, clustering approach, tour route

中图分类号:

TP399

蒋仲安,王明,陈雅. 基于地理坐标和轨迹数据的路径推荐方法[J]. 通信学报, 2017, 38(5): 165-171.

Zhong-an JIANG,Ming WANG,Ya CHEN. Path recommendation based on geographic coordinates and trajectory data[J]. Journal on Communications, 2017, 38(5): 165-171.

图/表 6

表1

图1

图2

图3

表2

图4

参考文献 24

[13]	VANSTEENWEGEN P , OUDHEUSDEN D V . The mobile tourist guide:an OR opportunity[J]. OR Insight, 2007 20(3): 21-27.
[14]	史永, 龙毅, 陈林 ,等. 面向智能导游的双加权图模型及其路径规划[J]. 地球信息科学学报, 2014(6): 867-873.
	SHI Y , LONG Y , CHEN L ,et al. Research on double-weighted graph model and optimal path planning for intelligent tourism navigation considering entrances and exits[J]. Geo-Information Science, 2014,16(6): 867-873.
[15]	鲍金玲, 王斌, 刘刚 ,等. 基于时间约束的人气最优路径搜索[J]. 东北大学学报(自然科学版), 2016(5): 629-633.
	BAO J L , WANG B , LIU G ,et al. Popularity-optimal path search based on time onstraint[J]. Journal of Northeastern University (Natural Science), 2016,37(5): 629-633.
[16]	吴潘, 吴晋峰, 周芳如 ,等. 目的地内部旅游交通通达性评价方法研究——以西安为例[J]. 浙江大学学报(理学版), 2016(3): 345-356.
	WU P , WU J F , ZHOU F R ,et al. Evaluating the traffic accessibility to the local tourist destinations with xi’an as the example[J]. Journal of Zhejiang University (Science Edition), 2016,43(3): 345-356.
[17]	KLEINBERG J . Hubs,authorities,and communities[J]. ACM Computing Surveys (CSUR), 1999,31(4): 101-125.
[18]	ESTER M , KRIEGEL H , SANDER J ,et al. A density-based algorithm for discovering clusters in large spatial databases with noise[C]// The 2nd International Conference on Knowledge Discovery and Data Mining. 1996: 226-231.
[19]	JARVIS R , PATRICK E . Clustering using a similarity measure based on shared near neighbors[J]. IEEE Transactions on Computer, 1973,100(11): 1025-1034.
[20]	ASHOUR W , SUNOALLAH S . Multi density DBSCAN[C]// The 12th International Conference on Intelligent Data Engineering and Automated Learning. 2011: 446-453.
[21]	POPESCU A , GREFENSTETTE G . Mining social media to create personalized recommendations for tourist visits[C]// The 2nd International Conference on Computing for Geospatial Research & Applications. 2011:37.
[22]	COLORNI A , DORIGO M , MANIEZZO V . Distributed optimization by ant colonies[C]// European Conference on Artificial Life. 1991: 134-142.
[23]	TEN HAGEN K , KRAMER R , HERMKES M ,et al. Semantic matching and heuristic search for a dynamic tour guide[C]// Information & Communication Technologies in Tourism,Enter. 2005: 149-159.
[1]	LU X , WANG C , YANG J M ,et al. Photo2Trip:generating travel routes from geo-tagged photos for trip planning[C]// The International Conference on Multimedia. 2010: 143-152.
[2]	CHENG A , CHEN Y , HUANG Y ,et al. Personalized travel recommendation by mining people attributes from community-contributed photos[C]// The 19th ACM International Conference on Multimedia. 2011: 83-92.
[3]	LI Q , ZHENG Y , XIE X ,et al. Mining user similarity based on location history[C]// The 16th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. 2008: 236-244.
[4]	MONREALE A , PINELLI F , TRASARTI R ,et al. WhereNext:a location predictor on trajectory pattern mining[C]// The 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2009: 637-646.
[5]	CHOUDHURY M D , FELDMAN M,AMER-YAHIA S , et al . Automatic construction of travel itineraries using social breadcrumbs[C]// The 21st ACM Conference on Hypertext and Hypermedia. 2010: 35-44.
[6]	CRANDALL D , BACKSTROM L , HUTTENLOCHER D ,et al. Mapping the world's photos[C]// The 18th International Conference on World Wide Web. 2009: 761-770.
[7]	KENNEDY L , NAMAN M . Generating diverse and representative image search results for landmarks[C]// The 17th International Conference on World Wide Web. 2008: 297-306.
[8]	ZHENG Y , ZHANG L , XIE X ,et al. Mining interesting locations and travel sequences from GPS trajectories[C]// The 18th International Conference on World Wide Web. 2009: 791-800.
[9]	YOON H , ZHENG Y , XIE X ,et al. Social itinerary recommendation from user-generated digital trails[J]. Personal and Ubiquitous Computing, 2011,16(5): 469-484.
[10]	SOUFFRIAU W , VANSTEENWEGEN P , BERGHE G V ,et al. Automated parameterisation of a metaheuristic for the orienteering problem[J]. Adaptive and Multilevel Metaheuristics, 2008: 255-269.
[11]	VANSTEENWEGEN P , SOUFFRIAU W , BERGHE G V ,et al. A guided local search metaheuristic for the team orienteering problem[J]. European Journal of Operational Research, 2009,196(1): 118-127.
[12]	SOUFFRIAU W , VANSTEENWEGEN P , VERTOMMEN J ,et al. A personalized tourist trip design algorithm for mobile tourist guides[J]. Applied Artifical Intelligence, 2008,22(10): 964-985.
[24]	VOUDOURIS C , TSANG E P K . Guided local search and its application to the traveling salesman problem[J]. European Journal of Operational Research, 1999,113(2): 469-499.

地点	照片数量
颐和园	4 250
天坛	1 996
后海	1 058
奥林匹克公园	287

算法类别	时间约束/h	平均效用	平均运行时间/s
	6	6.556 807	4.577 0
ACO
	4	5.250 714	5.076 2
	6	6.419 732	7.969 4
GLS
	4	5.055 734	5.870 6
	6	6.744 139	23.859 0
Greedy
	4	5.802 909	25.267 0