基于供求关系及协同过滤技术的推荐模型研究  

Research on Recommendation Model Based on Supply and Demand Relation and Collaborative Filtering

作　　者：姜雅倩[1] 王直杰[1] 张珏[1] 

机构地区：[1]东华大学信息科学与技术学院,上海201620

出　　处：《计算机技术与发展》2007年第6期18-21,25,共5页Computer Technology and Development

基　　金：上海市科委资助项目(04BZ11068)

摘　　要：推荐系统已经成功地应用于电子商务、数字图书馆等方面。但随着近年来公共服务平台的发展,现存的推荐系统不能有效处理公共服务平台中不同类型企业之间供求关系的推荐问题,不能针对供求关系产业链做出准确、迅速的推荐。因此,根据公共服务平台的供求关系产业链并结合协同过滤技术,提出了一种新的个性化推荐模型,它基于网络平台中的企业分类、供求关系等来建立模型,并通过建立企业类用户群来缩小协同过滤时用户群体的数量,降低计算时属性空间的维度,从而提高推荐的效率。使用该模型进行推荐可以更好地帮助企业建立沟通渠道、获得服务信息,满足企业个性化的要求。Recommendation systems have gained successful applications in E - commerce, digital library and other domains. However, with the development of public service platform, existing recommendation systems can not effectively deal with recommendation issue of the supply and demand relation occurred in different kinds of enterprises and can not make proper and quick recommendations referring to supply and demand relation of industry chain. Thus, combining the feature of public service platform and collaborative filtering, presents a novel personalized recommendation model. The model is created on the basis of the enterprises categories and the supply and demand relation. By establishing enterprises user group, the model reduces the quantity of the user group when collaborative filtering, and eventually improves the efficiency of recommendation. Using this model for recommendation can make great help for the enterprises to establish communication channel and obtain the service information.

关 键 词：供求关系 协同过滤 个性化 推荐 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]