计算机集成制造系统 ›› 2017, Vol. 23 ›› Issue (第5期): 1091-1102.DOI: 10.13196/j.cims.2017.05.020

• 产品创新开发技术 • 上一篇    下一篇

O2O服务推荐策略的计算实验比较

薛霄1,2,韩红芳1,王俊峰2,施曼1,王纪才1   

  1. 1.河南理工大学计算机科学与技术学院
    2.河南理工大学现代物流服务河南省高校工程技术中心
  • 出版日期:2017-05-31 发布日期:2017-05-31
  • 基金资助:
    国家自然科学基金资助项目(61175066,61379126);河南省科技创新杰出青年支持计划资助项目(2017JQ0008);河南省高校科技创新人才资助项目(2012HASTIT013);河南省自然科学基金面上资助项目(162300410121,152300410212,162102310426);河南省高校重点科研资助项目(16A520012,17A520034);河南理工大学博士基金资助项目(B2014-043)。

Comparative research on computational experiment of O2O service recommendation strategies

  • Online:2017-05-31 Published:2017-05-31
  • Supported by:
    Project supported by the National Natural Science Foundation,China(No.61175066,61379126),the Program for Science & Technology Innovation Talents of Henan Province,China(No.2017JQ0008),the Program for Science & Technology Innovation Talents in Universities of  Henan Province,China(No.2012HASTIT013),the Natural Science Foundation of Henan Province,China(No.162300410121,152300410212,162102310426),the Key Scientific Research Project in Universities of Henan Province,China(No.16A520012,17A520034),and the Doctor Foundation of Henan Polytechnic University,China(No.B2014-043).

摘要: 为了在复杂环境中对各种服务推荐策略进行准确评估以选出最合适的服务策略、提高O2O服务推荐质量,运用计算实验方法,从3个方面对O2O服务推荐策略进行了深入研究,包括服务推荐策略的设计(协同过滤推荐策略、考虑情境的协同过滤推荐策略、综合考虑情境和服务状态的推荐策略)、实验系统构建、服务推荐策略的实验分析。实验结果表明,在需求量不同的场景下,综合考虑情境和服务状态的推荐策略表现最优。

关键词: Online To Offline, 协同过滤, 情境, 服务状态, 服务推荐策略, 计算实验

Abstract: To evaluate various service recommendation strategies in complex environments for selecting the most appropriate service operation strategy and to improve the quality of Online to Offline (O2O) service recommendation,by utilizing the computational experiments method,O2O service recommendation strategies were researched from three aspects,which included the service recommendation strategy design (collaborative filtering recommendation strategy,context-based collaborative filtering recommendation strategy and the recommendation strategy considering context and service status),the construction of experiment system and the experiment evaluation analysis of service operation strategy.Through the computational experiments,the performance of recommendation strategy considering context and service status was optimal under different demand scenarios.

Key words: online to offline, collaborative filtering, context, service status, service recommendation strategy, computational experiment

中图分类号: