东篱科研大数据发现系统（DRDS）

位置：成果数据库 > 期刊 > 期刊详情页

结合似然关系模型和用户等级的协同过滤推荐算法

期刊名称：高滢, 齐红, 刘杰, 刘大有. 结合似然关系模型和用户等级的协同过滤推荐算法. 计算机研究与发展,
时间：0
分类：TP391[自动化与计算机技术—计算机应用技术;自动化与计算机技术—计算机科学与技术]
作者机构：[1]吉林大学计算机科学与技术学院,长春130012, [2]吉林大学符号计算与知识工程教育部重点实验室,长春130012
相关基金：国家自然科学基金重大项目（60496321）;国家自然科学基金项目（60573073,60773099）;国家“八六三”高技术研究发展计划基金项目（2006AA102245,2006AA10A309）;吉林省科技发展计划基金项目（20030523）;欧盟项目（TH/AsiaLink/010（111084）） This research is supported by NSFC Major Research Program under grant No. 60496321; the National Natural Science Foundation of China under grant Nos. 60773099 amd 60573073; the National High-Tech Research and Development Plan of China under grant Nos. 2006AA10Z245 and 2006AA10A309; the Major Program of Science and Technology Development Plan of Jilin Province under grant No. 20020303~ the Science and Technology Development Plan of Jilin Province under grant No. 20030523; and European Commission under grant No. TH/Asia Link/010 （111084）. Recommender systems help overcome information overload by providing personalized suggestions. Collaborative filtering is a very successful technique for building recommender systems, and it is the technique of using peer opinions to predict the interests of others. A target user is matched against the database to discover neighbors, who have historically similar interests to the target user. Items that neighbors like are then recommended to the target user. Although collaborative filtering has been successfully used in both research and practice, it suffers from sparsity and scalability problems. To address these problems, we present a collaborative filtering recommendation algorithm combining probabilistic relational models and user grade （PRM-UG-CF）. PRM-UG-CF can integrate item information, user information and user-item rating data, and find neighbors efficiently, and it solves the sparsity and scalability problems simultaneously.
相关项目：非规范知识的数学理论

中文摘要：

针对传统协同过滤推荐算法的稀疏性、扩展性问题，提出了结合似然关系模型和用户等级的协同过滤推荐算法．首先，定义了用户等级函数，采用基于用户等级的协同过滤方法，在不影响推荐质量的前提下有效提高了推荐效率，从而解决扩展性问题；然后，将其与似然关系模型相结合，使之能够综合利用用户信息、项目信息、用户对项目的评分数据，对不同用户给出不同的推荐策略，从而解决稀疏性问题，提高推荐质量．在MovieLens数据集上的实验结果表明，该算法比单纯使用基于似然关系模型或传统协同过滤技术的推荐算法，不仅推荐质量有所提高，推荐速度比传统协同过滤算法明显加快．

英文摘要：

Collaborative filtering is one of successful technologies for building recommender systems. Unfortunately, it suffers from sparsity and scalability problems. To address these problems, a collaborative filtering recommendation algorithm combining probabilistic relational models and user grade （PRM-UG-CF） is presented. PRM-UG-CF has primary two parts. First, a user grade function is defined, and user grade based collaborative filtering method is used, which can find neighbors for the target user only in his near grade, and the number of candidate neighbors can be controlled by a parameter, so recommendation efficiency is increased and it solves the scalability problem. Second, in order to use various kinds of information for recommendation, user grade based collaborative filtering method is combined with probabilistic relational models （PRM）, thus it can integrate user information, item information and user-item rating data, and use adaptive strategies for different grade users, so recommendation quality is improved and it solves the sparsity problem. The experimental results on MovieLens data set show that the algorithm PRM-UG-CF has higher recommendation quality than a pure PRM-based or a pure collaborative filtering approach, and it also has much higher recommendation efficiency than a pure collaborative filtering approach.

同期刊论文项目