[1]张龙昌,白 静 *.基于用户满意度的大数据服务可信评价与优化[J].计算机技术与发展,2023,33(08):1-8.[doi:10. 3969 / j. issn. 1673-629X. 2023. 08. 001]
　ZHANG Long-chang,BAI Jing *.Research on Trustworthy Evaluation and Optimization of Big Data Services Based on User Satisfaction Degree[J].,2023,33(08):1-8.[doi:10. 3969 / j. issn. 1673-629X. 2023. 08. 001]
点击复制

基于用户满意度的大数据服务可信评价与优化()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
33
期数:
2023年08期
页码:
1-8
栏目:
综述
出版日期:
2023-08-10

文章信息/Info

Title:
Research on Trustworthy Evaluation and Optimization of Big Data Services Based on User Satisfaction Degree
文章编号:
1673-629X(2023)08-0001-08
作者:
张龙昌1; 2 ; 白 静3 *
1. 宿迁学院 信息工程学院,江苏 宿迁 223800;
2. 北京邮电大学深圳研究院,广东 深圳 518038;
3. 东北财经大学 管理科学与工程学院,辽宁 大连 116025
Author(s):
ZHANG Long-chang1; 2 ; BAI Jing3 *
1. School of Information Engineering,Suqian University,Suqian 223800,China;
2. Shenzhen Research Institute,Beijing University of Posts and Telecommunications,Shenzhen 518038,China;
3. School of Management Science and Engineering,Dongbei University of Finance and Economics,Dalian 116025,China
关键词:
大数据服务; 用户满意度; 可信评价与博弈优化; 服务质量; 服务参与者行为
Keywords:
big data services;  user satisfaction degree;  trustworthy evaluation and game optimization;  quality of service;  serviceparticipant behaviors
分类号:
TP311
DOI:
10. 3969 / j. issn. 1673-629X. 2023. 08. 001
摘要:
传统基于 QoS 的服务评价和优化不能最大化大数据服务的用户满意度,从服务评价和服务运行优化,研究大数据服务用户满意度最大化方法。 阐明用户满意度形成机理,研究情景感知的用户满意度模型,解决用户满意度模型不准确问题;揭示评价用户搭便车行为机理,研究评价用户参与评价激励机制,解决用户满意度数据不全面问题;在 Logistic 回归和社会网络理论的基础上,研究评价用户可信度综合评估方法,解决用户满意度数据不可信问题;探索情景相似的用户Top-K 查询和用户满意度数据云模型描述方法,研究基于云模型的可信服务评价方法,解决服务评价不可信问题;阐明服务运行期的服务参与者行为及博弈机理,研究服务运行期的博弈优化方法,解决单方优化方法无法使服务参与者收益最大化问题。 为大数据服务的评价和优化提供新的研究思路。
Abstract:
The traditional service evaluation and optimization based on QoS cannot maximize the user satisfaction degree of big dataservice. From the evaluation and the optimization of services,this research studies the method of maximizing user satisfaction degree ofbig data services. The formation mechanism of user satisfaction degree is expounded and the user satisfaction model based on contextawareness is studied to solve the problem of inaccurate user satisfaction model. The mechanism of the evaluation user free ridingbehaviors is revealed and the incentive mechanism is studied to motivate the evaluation user to solve the problem of user satisfactiondegree data is incomplete. On the basis of Logistic regression and social network theory, the comprehensive evaluation method isresearched to evaluate the credibility of evaluation user to solve the problem of unreliable user satisfaction degree. The user Top-K querybased on scenario similar and user satisfaction data description method of cloud model is explored, and trustworthy service evaluationmethod is studied to solve the problem of untrustworthy in service evaluation. The behaviors and game mechanism of service participantsduring the service running period are expounded and the game optimization method of the service running period is studied to solve theproblem that the unilateral optimization cannot maximize the income of the service participants. This research provides a new researchidea for the evaluation and optimization of big data services.
更新日期/Last Update: 2023-08-10