《计算机应用》唯一官方网站 ›› 2023, Vol. 43 ›› Issue (6): 1719-1729.DOI: 10.11772/j.issn.1001-9081.2022060860

• CCF第37届中国计算机应用大会 (CCF NCCA 2022) • 上一篇    下一篇

基于社交关系和时序信息的团购推荐方法

孙男男1,2, 朴春慧1,3(), 马新娜1,3   

  1. 1.石家庄铁道大学 信息科学与技术学院, 石家庄 050043
    2.北京全路通信信号研究设计院集团有限公司, 北京 100070
    3.河北省电磁环境效应与信息处理重点实验室(石家庄铁道大学), 石家庄 050043
  • 收稿日期:2022-06-15 修回日期:2022-07-08 接受日期:2022-07-25 发布日期:2022-10-11 出版日期:2023-06-10
  • 通讯作者: 朴春慧
  • 作者简介:孙男男(1997—),女,河北衡水人,硕士,主要研究方向:大数据、推荐算法;
    马新娜(1978—),女,河北顺平人,教授,博士,CCF会员,主要研究方向:大数据、模式识别、智能控制、故障诊断。
  • 基金资助:
    国家自然科学基金资助项目(12172234);河北省重点研发计划项目(21355902D)

Group buying recommendation method based on social relationship and time-series information

Nannan SUN1,2, Chunhui PIAO1,3(), Xinna MA1,3   

  1. 1.School of Information Science and Technology,Shijiazhuang Tiedao University,Shijiazhuang Hebei 050043,China
    2.CRSC Research and Design Institute Group Company Limited,Beijing 100070,China
    3.Hebei Key Laboratory for Electromagnetic Environmental Effects and Information Processing (Shijiazhuang Tiedao University),Shijiazhuang 050043,China
  • Received:2022-06-15 Revised:2022-07-08 Accepted:2022-07-25 Online:2022-10-11 Published:2023-06-10
  • Contact: Chunhui PIAO
  • About author:SUN Nannan, born in 1997, M. S. Her research interests include big data, recommendation algorithm.
    MA Xinna, born in 1978, Ph. D., professor. Her research interests include big data, pattern recognition, intelligent control, fault diagnosis.
  • Supported by:
    National Natural Science Foundation of China(12172234);Key Research and Development Program of Hebei Province(21355902D)

摘要:

针对目前团购推荐方法较少结合单个用户与群组用户,并且对时间间隔、社交关系等上下文相关信息的利用不充分的问题,提出了一种基于社交关系和时序信息的团购推荐方法。对单个用户进行推荐时,针对循环神经网络(RNN)的门控循环单元(GRU)在团购推荐时没有考虑时序信息的影响,以及用户-商品交互序列中不相关的商品数据会产生噪声等问题,提出了融合时序感知GRU和自注意力的团购推荐模型(RTSA)。首先,通过计算用户购买的任意两个商品之间的个性化时间间隔,构建了时序感知GRU(TGRU)模型;然后,采用自注意力网络研究商品位置及个性化时间间隔的影响;最后,实验结果表明在Amazon Beauty数据集中,RTSA相较于对单个用户推荐的最优的基线模型——基于时间间隔感知自注意力的序列化推荐模型(TiSASRec),前10个商品命中率提升了11.73%。对群组用户进行推荐时,针对团购群组推荐中预定义的融合策略不能动态获取群组用户权重,以及群组-项目交互数据的稀疏性等问题,提出了融合社交网络和分层自注意力的团购推荐模型(SSAGR)。首先,采用RNN捕捉团购中用户随时间变化的复杂潜在兴趣;其次,利用分层自注意力网络将社交网络信息整合到用户表示中,在不同权重下实现群组偏好聚合策略;然后,通过神经协同过滤(NCF)挖掘群组-项目交互,并实现了团购推荐;最后,实验结果表明,在MaFengWo数据集中,SSAGR相较于对群组用户推荐的最优的基线模型AGREE(Attentive Group REcommEndation),前5个商品命中率提升了3.53%。

关键词: 门控循环单元, 自注意力网络, 团购, 个性化时间间隔, 社交网络

Abstract:

Aiming at the problems that there are few researches on the combination of single users and group users in group buying recommendation methods, and the context-related information such as time interval and social relationship is not fully utilized, a group buying recommendation method based on social relationship and time series information was proposed. When recommending for single users, the Gated Recurrent Unit (GRU) of Recurrent Neural Network (RNN) do not consider the influence of time series information, and the irrelevant commodity data in the user-commodity interaction sequence will generate noise. Therefore, a group buying Recommendation model integrating Time-series aware GRU and Self-Attention (RTSA) was proposed. Firstly, a Time-series aware GRU (TGRU) model was constructed by calculating the personalized time interval between any two commodities purchased by the user. Then, the influence of the commodity locations and the personalized time intervals was studied by using a self-attention network. Finally, experimental results show that on Amazon Beauty dataset, compared with the optimal baseline model of recommending for single users — Time interval aware Self-Attention for Sequential Recommendation (TiSASRec), RTSA has the hit rate for top-10 commodities increased by 11.73%. When recommending for group users, the pre-defined fusion strategy in group buying group recommendation cannot dynamically obtain group user weights, and there is sparseness in group-item interaction data. Therefore, a Group buying Recommendation model integrating Social network and hierarchical Self-Attention (SSAGR) was proposed. Firstly, an RNN was employed to capture the complex potential interests of users in group buying changing over time. Secondly, a hierarchical self-attention network was used to integrate social network information into user representations, and a group preference aggregation strategy was implemented under different weights. Thirdly, the group-item interactions were mined through Neural Collaborative Filtering (NCF) to complete group buying recommendations. Finally, experimental results show that on MaFengWo dataset, compared with the optimal baseline model of recommending for group users — AGREE (Attentive Group REcommEndation), SSAGR has the hit rate for top-5 commodities improved by 3.53%.

Key words: Gated Recurrent Unit (GRU), self-attention network, group buying, personalized time interval, social network

中图分类号: