基于机器学习的动态信誉评估模型研究

Research on Dynamic Trust-Level Evaluation Mechanism Based on Machine Learning

为在开放网络环境中建立资源消费者(用户)和资源提供者(主机)之间的信任关系,提出基于机器学习的动态信誉评估模型.模型中用户的信誉级别可以根据其行为和一些其他监测数据动态变化,而资源的信誉级别也可以根据用户对资源所提供服务的评价动态变化.给出了用于生成评估规则和信誉级别的模糊信誉级别评估算法(FTEA),算法采用基于规则的机器学习方法,具有从大量输入数据中自学习以获取评估规则的能力.实验结果表明,1000组输入数据能够生成理想的规则库,并且算法执行时间随输入判定因素数目成指数形式增长,因此需要选择5～6个因素和1000个左右的样本数据以进行系统实现.

For the purpose of developing a usable trust relationship between the resource consumers （users） and the resource providers （hosts） in an open computing environment, a dynamic trust evaluation framework based on machine learning is proposed. In this framework, the trust-level of users changes dynamically according to their behaviors and some other common inspect parameters. And the trust-level of resources changes dynamically with the users＇ assessments and the service quality that resources provide. In this paper, a fuzzy trust-level evaluating algorithm （FTEA） based on fuzzy logic is put forward to generate the evaluation rules and integrated overall trust-level. The FTEA utilizes the rule-based machine learning method and has the advantage of self-learning to get reasoning rules from large amount of input data. The experiment shows that only 1000 groups of data are adequate to generate the reasoning rules, and the execution time of FTEA increases exponentially with the expansion of determination factors, so, an open computing system only need to select 5 to 6 factors or 1000 sample data for implementation.