基于情境要素和用户偏好的旅行方式推荐

doi:10.3969/j.issn.0255-8297.2019.03.011

应用科学学报 ›› 2019, Vol. 37 ›› Issue (3): 407-418.doi: 10.3969/j.issn.0255-8297.2019.03.011

基于情境要素和用户偏好的旅行方式推荐

王峰, 屈俊峰, 赵永标, 谷琼

湖北文理学院计算机工程学院, 湖北襄阳 441053

收稿日期:2018-09-17 修回日期:2018-12-12 出版日期:2019-05-31 发布日期:2019-05-31
作者简介:王峰,博士生,研究方向:基于位置的服务、社交网络、城市计算,E-mail:afengcom@163.com
基金资助:
湖北省自然科学基金（No.2018CFB162，No.2017CFB723）；国家语委科研项目基金（No.YB135-22，No.YB135-33）；湖北省教育厅自然科学基金（No.Q20182605）；湖北省教育厅人文社科项目基金（No.18Q148）；"机电汽车"湖北省优势特色学科群开放基金（No.XKQ2019027）资助

User Transportation Mode Recommendation Based on Contextual Factor and User Preference

WANG Feng, QU Junfeng, ZHAO Yongbiao, GU Qiong

School of Computer Engineering, Hubei University of Arts and Science, Xiangyang 441053, Hubei Province, China

Received:2018-09-17 Revised:2018-12-12 Online:2019-05-31 Published:2019-05-31

摘要/Abstract

摘要： 为给用户推荐满意的旅行方式，针对用户旅行构建旅行情境，并基于移动社交软件采集用户行为数据，进而提取情境要素并完成情境构建过程.根据用户出行具有目的性和偏好的特点，将情境要素与用户偏好相结合，利用情境要素组合间的差异性进行实验.实验表明，在不同情境下，不同的情境要素组合与偏好会导致用户选择不一样的旅行方式.实验综合考虑情境组合差异性，从不同情境组合的视角出发，充分展示用户选择单一旅行方式和组合旅行方式在各种旅行客观条件下的占比，并通过用户满意度来证明该文模型可为用户推荐更加契合需求的旅行方案.在不同数据集NDCG@5、NDCG@10和MAP上的T测试结果显示，该文提出的推荐方法性能相比于Pearson相关系数的CF方法和加权slot-one算法具有显著优势.

关键词: 移动互联网, 城市计算, 旅行方式

Abstract: In order to recommend satisfactory transportation mode, context of user transportation is firstly built, and then context factors are extracted from data of user behavior which is generated by social application based on Mobile Internet. According to the travel purposiveness and preference of users, context factors and user preference are taken into comprehensive consideration in this paper. In the view of context factors, there is a great deal of difference among users' selections of transportation mode due to different travel conditions and their preference. Experiment results show that the proposed scheme can present the selection percentage of single transportation mode and composite transportation mode under different circumstances of context factors. It is also proven that the recommended travel plans are closely aligned with users' needs in terms of user satisfaction. The proposed method shows superior performance on the T-test of different datasets, such as NDCG@5, NDCG@10, and MAP, to the collaborative filtering method based on Pearson correlation coefficients and the weighted slot-one algorithm.

Key words: mobile internet, transportation mode, urban computing

中图分类号:

TP399

王峰, 屈俊峰, 赵永标, 谷琼. 基于情境要素和用户偏好的旅行方式推荐[J]. 应用科学学报, 2019, 37(3): 407-418.

WANG Feng, QU Junfeng, ZHAO Yongbiao, GU Qiong. User Transportation Mode Recommendation Based on Contextual Factor and User Preference[J]. Journal of Applied Sciences, 2019, 37(3): 407-418.

参考文献 11

[1]	He J, Li X, Liao L J. Category-aware next point-of-interest recommendation via listwise bayesian personalized ranking[C]//International Joint Conference on Artificial Intelligence, IJCAI 2017, Melbourne, Australia, 2017:1837-1843.
[2]	Steffen R, Freudenthaler C, Gantner Z, Schmidt-Thieme L. BPR:Bayesian personalized ranking from implicit feedback[C]//Conference on Uncertainty in Artificial Intelligence, UAI 2009, Montreal, Canada, 2009:452-461.
[3]	Yang C, Bai L X, Zhang C, Yuan Q, Han J W. Bridging collaborative filtering and semisupervised learning:a neural approach for POI recommendation[C]//Knowledge Discovery and Data Mining, KDD 2017, Halifax, Nova Scotia, Canada, 2017:1245-1254.
[4]	Eliezer de Souza da S, Langseth H, Ramampiaro H. Content-based social recommendation with Poisson matrix factorization[C]//Machine Learning and Knowledge Discovery in Databases-European Conference, ECML PKDD 2017, Proceedings, Part I. Skopje, Macedonia, Springer, 2017:530-546.
[5]	Li H Y, Ge Y, Lian D F, Liu H. Learning user's intrinsic and extrinsic interests for point-ofinterest recommendation:a unified approach[C]//International Joint Conference on Artificial Intelligence, IJCAI 2017, Melbourne, Australia, 2017:2117-2123.
[6]	Kim H, Iwata T, Fujiwara Y. Read the silence:well-timed recommendation via admixture marked point proceses[C]//Association for the Advancement of Artificial Intelligence, AAAI 2017, San Francisco, California, USA, 2017:132-139.
[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. Ren X Y, Song M N, Song J D. Point-of-interest recommendation based on the user check-in behavior[J]. Chinese Journal of Computers, 2017, 40(1):28-51. (in Chinese)
[8]	任星怡,宋美娜,宋俊德. 基于位置社交网络的上下文感知的兴趣点推荐[J]. 计算机学报,2017, 40(4):824-841. Ren X Y, Song M N, Song J D. Context-aware point-of-interest recommendation in locationbased social networks[J]. Chinese Journal of Computers, 2017, 40(4):824-841. (in Chinese)
[9]	高榕,李晶,杜博,余永红,宋成芳,丁永刚. 一种融合情景和评论信息的位置社交网络兴趣点推荐模型[J]. 计算机研究与发展,2016, 53(4):752-763. Gao R, Li J, Du B, Yu Y H, Song C F, Ding Y G. A synthetic recommendation model for point-of-interest on location-based social networks:exploiting contextual information and review[J]. Journal of Computer Research and Development, 2016, 53(4):752-763. (in Chinese)
[10]	廖国琼,姜珊,周志恒,万常选. 基于位置社会网络的双重细粒度兴趣点推荐[J]. 计算机研究与发展,2017, 54(11):2600-2610. Liao G Q, Jiang S, Zhou Z H, Wang C X. Dual fine-granularity POI recommendation on location-based social networks[J]. Journal of Computer Research and Development, 2017, 54(11):2600-2610. (in Chinese)
[11]	余永红,高阳,王皓. 基于Ranking的泊松矩阵分解兴趣点推荐算法[J]. 计算机研究与发展,2016, 53(8):1651-1663. Yu Y H, Gao Y, Wang H. A Ranking based Poisson matrix factorization model for pointof-interest recommendation[J]. Journal of Computer Research and Development, 2016, 53(8):1651-1663. (in Chinese)

基于情境要素和用户偏好的旅行方式推荐

User Transportation Mode Recommendation Based on Contextual Factor and User Preference

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献 11

相关文章 8

编辑推荐

Metrics

本文评价

[1]	方俊杰, 雷凯. 面向边缘人工智能计算的区块链技术综述[J]. 应用科学学报, 2020, 38(1): 1-21.
[2]	雷凯, 黄硕康, 方俊杰, 黄济乐, 谢英英, 彭波. 智能生态网络:知识驱动的未来价值互联网基础设施[J]. 应用科学学报, 2020, 38(1): 152-172.
[3]	朱文强, 钟元生. 基于声誉计算的可信O2O服务提供商推荐方法[J]. 应用科学学报, 2017, 35(5): 585-601.
[4]	岳珂娟, 郑明才, 肖建华, 伍炯星. 结合背景先验和对象先验的显著性检测[J]. 应用科学学报, 2016, 34(4): 451-460.
[5]	毕景芝1，刘湘南1，赵冬2. 基于粗糙集约简的水稻叶片叶绿素含量高光谱反演[J]. 应用科学学报, 2014, 32(4): 394-400.
[6]	郝琨1,2，金志刚1. 一种基于确定性网络编码的P2P文件分发机制[J]. 应用科学学报, 2014, 32(3): 246-250.
[7]	方欢1;2，陆阳1;3，葛方振1，黄镇谨1. 基于Petri 网的复杂空竭休假排队系统的性能评价[J]. 应用科学学报, 2012, 30(4): 379-386.
[8]	吕杰，刘湘南. 利用支持向量机构建水稻镉含量高光谱预测模型[J]. 应用科学学报, 2012, 30(1): 105-110.