移动环境下情境导向的推荐系统  

Context-Oriented Recommender System in Mobile Circumstances

作　　者：李旭[1] 李长云[1] 张清清[1] 胡淑新 周玲芳[1] 

机构地区：[1]湖南工业大学计算机与通信学院,株洲412007

出　　处：《计算机系统应用》2016年第6期249-253,共5页Computer Systems & Applications

基　　金：2013年度科技部科技支撑计划课题(2013BAJ10B14-5)

摘　　要：本文提出了一种在移动情境下基于协同过滤算法的推荐模型.针对现有算法与情境之间融合程度不足,在传统协同过滤算法基础上设计了情境导向的协同过滤推荐系统模型框架.采用MAE和F1评价指标对本文所提出的模型与情境过滤以及普通情境建模的方法之间的推荐质量进行评估,实验表明本文提出的方案能在推荐质量上拥有更好的表现.This paper puts forward a mobile recommendersystem model based on collaborative filtering algorithm under the mobile circumstances. We aim at the insufficient degree in integration of the existing algorithm and the instant context, and design a circumstance oriented collaborative filtering recommendation system framework model based on the traditional collaborative filtering algorithm. We use MAE and F1 evaluation index to evaluate the commendation quality between our proposed model, pre-filteringmodel and the general context modeling. Through a series of experiments, it shows that the proposed scheme has the better performance in recommendation quality.

关 键 词：移动情境 情境相似度 协同过滤算法 推荐质量评估 

分 类 号：TP391.3[自动化与计算机技术—计算机应用技术]