基于协同过滤的可信Web服务推荐  

Trustworthy Web Service Recommendation Based on Collaborative Filtering

作　　者：盛国军[1] 温涛[1,2] 郭权[2] 吴镝[1] 

机构地区：[1]东北大学信息科学与工程学院,辽宁沈阳110819 [2]大连东软信息学院,辽宁大连116023

出　　处：《东北大学学报（自然科学版）》2013年第6期806-809,共4页Journal of Northeastern University(Natural Science)

基　　金：国家自然科学基金资助项目(61170168;61170169;61100028;60803026)

摘　　要：提出一种基于开放网络环境和用户协同过滤的可信Web服务推荐方法 TWSRCF(trustworthy web service recommendation based on collaborative filtering).首先根据用户的查询请求得到一组功能相同或相似的候选Web服务集合,然后基于用户的历史共同评价得到目标用户的偏好相似用户集合,并求得候选Web服务集合中每个服务的可推荐用户集合,并根据可推荐用户的相似度、评价值和可信度计算各候选服务的推荐度,按照推荐度对各候选服务进行排序并向目标用户推荐.实验结果表明,随着用户评价数量的增加,该方法所获得的服务推荐效果也逐渐明显.A trustworthy Web service recommendation method was presented based on open network environment and collaborative filtering.First,a set of Web services with same or similar functions was searched according to user's requirement.Second,the collection of users that have similar preferences for the target user was computed based on their common evaluations,and the recommendable user set for each candidate service was obtained,then the recommendation degree for each service was computed using its similarity,and the candidate services was sorted according to the recommendation degree to the target user.The experimental results showed that the referral effect increased with the increase in the number of user evaluations.

关 键 词：WEB服务 可信服务 服务推荐 协同过滤 服务排名 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]