通信学报 ›› 2017, Vol. 38 ›› Issue (10): 18-25.doi: 10.11959/j.issn.1000-436x.2017160

• 学术论文 • 上一篇    下一篇

支持推荐非空率的关联规则推荐算法

何明1,刘伟世1,张江2   

  1. 1 北京工业大学信息学部计算机学院,北京 100124
    2 国网英大国际控股集团有限公司信息化工作部,北京 100005
  • 修回日期:2017-07-10 出版日期:2017-10-01 发布日期:2017-11-16
  • 作者简介:何明(1975-),男,陕西礼泉人,博士,北京工业大学副教授,主要研究方向为大数据、推荐系统、机器学习等。|刘伟世(1989-),男,山东菏泽人,北京工业大学硕士生,主要研究方向为推荐系统。|张江(1980-),女,北京人,博士,国网英大国际控股集团有限公司信息化工作部经理,主要研究方向为网络通信协议、网络自愈、大数据等。
  • 基金资助:
    国家自然科学基金资助项目(91646201);国家自然科学基金资助项目(91546111);北京市自然科学基金资助项目(4153058);北京市自然科学基金资助项目(4113076);北京市教委面上基金资助项目(KM201710005023)

Association rules recommendation algorithm supporting recommendation nonempty

Ming HE1,Wei-shi LIU1,Jiang ZHANG2   

  1. 1 College of Computer,Faculty of Information Technology,Beijing University of Technology,Beijing 100124,China
    2 State Grid YingDa International Holdings Co.,Ltd.,Beijing 100005,China
  • Revised:2017-07-10 Online:2017-10-01 Published:2017-11-16
  • Supported by:
    The National Natural Science Foundation of China(91646201);The National Natural Science Foundation of China(91546111);The Natural Science Foundation of Beijing(4153058);The Natural Science Foundation of Beijing(4113076);General Project of Beijing Municipal Education Commission(KM201710005023)

摘要:

现有的关联规则推荐技术在数据提取时主要侧重于关联规则的提取效率,缺乏对冷、热门数据推荐平衡性的考虑和有效处理。为了提高个性化推荐效率和推荐质量,平衡冷门与热门数据推荐权重,对关联规则的Apriori算法频繁项集挖掘问题进行了重新评估和分析,定义了新的测评指标推荐非空率以及k前项频繁项集关联规则的概念,设计了基于 k 前项频繁项集的剪枝方法,提出了优化 Apriori 算法且适合不同测评标准值的 k前项频繁项集挖掘算法,降低频繁项集提取的时间复杂度。理论分析比较与实验表明,k 前项剪枝方法提高了频繁项集的提取效率,拥有较高的推荐非空率、调和平均值和推荐准确率,有效地平衡了冷、热门数据的推荐权重。

关键词: 关联规则, 推荐系统, 推荐非空率, 数据挖掘

Abstract:

Existing association rule recommendation technologies were focus on extraction efficiency of association rule in data mining.However,it lacked consideration of recommendation balance between popular and unusual data and efficient processing.In order to improve the quality and efficiency of personalized recommendation and balance the recommendation weight of cold and hot data,the problem of mining frequent itemset based on association rule was revaluated and analyzed,a new evaluation metric called recommendation RecNon and a notion of k-pre association rule were defined,and the pruning strategy based on k-pre frequent itemset was designed.Moreover,an association rule mining algorithm based on the idea was proposed,which optimized the Apriori algorithm and was suitable for different evaluation criteria,reduced the time complexity of mining frequent itemset.The theoretic analysis and experiment results on the algorithm show that the method improved the efficiency of data mining and has higher RecNon,F-measure and precision of recommendation,and efficiently balance the recommendation weight of cold data and popular one.

Key words: association rule, recommender system, recommendation nonempty, data mining

中图分类号: 

  • TP319