Journal of Computer Applications ›› 2021, Vol. 41 ›› Issue (2): 398-406.DOI: 10.11772/j.issn.1001-9081.2020050677

Special Issue: 数据科学与技术

• Data science and technology • Previous Articles     Next Articles

Point-of-interest recommendation algorithm combing dynamic and static preferences

YANG Li1, WANG Shihui1, ZHU Bo2   

  1. 1. School of Computer Science and Information Engineering, Hubei University, Wuhan Hubei 430062, China;
    2. 709 Research Institute of China Shipbuilding Industry Corporation, Wuhan Hubei 420205, China
  • Received:2020-05-21 Revised:2020-08-12 Online:2021-02-10 Published:2020-09-15
  • Supported by:
    This work is partially supported by the Youth Program of National Natural Science Foundation of China (11401187), the National Natural Science Foundation of China (61403132), the Youth Talents Program of Science and Technology Research Project of Hubei Education Department (165301301003).


杨丽1, 王时绘1, 朱博2   

  1. 1. 湖北大学 计算机与信息工程学院, 武汉 430062;
    2. 中国船舶重工集团公司第709研究所, 武汉 420205
  • 通讯作者: 杨丽
  • 作者简介:杨丽(1985-),女,山西长治人,讲师,博士,主要研究方向:智能推荐、深度学习;王时绘(1965-),男,湖北武汉人,教授,博士,主要研究方向:智能推荐、深度学习;朱博(1982-),男,湖北武汉人,高级工程师,硕士,主要研究方向:智能推荐、深度学习。
  • 基金资助:

Abstract: Since most existing Point-Of-Interest (POI) recommendation algorithms ignore the complexity of the modeling of the fusion of user dynamic and static preferences, a POI recommendation algorithm called CLSR (Combing Long Short Recommendation) was proposed that combined complex dynamic user preferences and general static user preferences. Firstly, in the process of modeling complex dynamic preferences, a hybrid neural network was designed based on the user's check-in behaviors and the skip behaviors in check-in behaviors to achieve the modeling of complex dynamic interests of the user. Secondly, in the process of general static preference modeling, a high-level attention network was used to learn the complex interactions between the user and POIs. Thirdly, a multi-layer neural network was used to further learn and express the above dynamic preferences and static preferences. Finally, a unified POI recommendation framework was used to integrate the preferences. Experimental results on real datasets show that, compared with FPMC-LR (Factorizing Personalized Markov Chain and Localized Region), PRME (Personalized Ranking Metric Embedding), Rank-GeoFM (Ranking based Geographical Factorization Method) and TMCA (Temporal and Multi-level Context Attention), CLSR has the performance greatly improved, and compared to the optimal TMCA among the comparison methods, the proposed algorithm has the precision, recall and normalized Discounted Cumulative Gain (nDCG) increased by 5.8%, 5.1%, and 7.2% on Foursquare dataset, and 7.3%, 10.2%, and 6.3% on Gowalla dataset. It can be seen that CLSR algorithm can effectively improve the results of POI recommendation.

Key words: Point-Of-Interest (POI), recommendation algorithm, Deep Neural Network (DNN), multi-layer projection, attention network

摘要: 针对大多数现有主流兴趣点(POI)推荐算法忽略了融合用户复杂动态偏好和一般静态偏好建模的复杂性问题,提出一个融合复杂动态用户偏好和一般静态用户偏好的POI推荐算法CLSR。首先,在复杂动态偏好建模过程中,基于用户的签到行为及其中的跳过行为设计一个混合神经网络,实现用户的复杂动态兴趣的建模;其次,在一般静态偏好建模过程中,利用高阶注意力网络学习用户与POI之间复杂的交互关系;然后,利用多层神经网络进一步学习和表示上述动态偏好和静态偏好;最后,基于统一的POI推荐框架对偏好进行整合。在真实数据集上的实验结果表明,与个性化马尔可夫链和用户位置受限的推荐方法FPMC-LR、基于个性化排名度量嵌入的推荐方法PRME、基于排名的地理分解兴趣点推荐方法Rank-GeoFM和基于时间和多级上下文注意力机制的下一个兴趣点推荐方法TMCA相比,CLSR的性能有了较大的提高,该算法的准确率、召回率和归一化折损累计增益(nDCG)和对比方法中较优的TMCA相比,在Foursquare数据集上分别提高了5.8%、5.1%和7.2%,在Gowalla数据集上分别提高了7.3%、10.2%和6.3%,可以有效地改善POI推荐的结果。

关键词: 兴趣点, 推荐算法, 深度神经网络, 多层投影, 注意力网络

CLC Number: