期刊论文

中文

数字图书馆论坛

1673-2286

2018

11

11-18

10.3772/j.issn.1673-2286.2018.11.002

本研究得到教育部人文社会科学研究规划基金项目“智慧教室环境下课堂交互有效性量化研究”(编号:17YJA880030)资助。

本校为第一机构

针对数字资源信息过载、信息异构、资源推荐效果不理想等问题,改进传统数字资源聚合模型和相似度计算方式,本文提出一种数字资源聚合模型,并融合协同过滤的推荐思想,利用该聚合模型进行相似度计算得出资源和用户的近邻集合,基于此设计精准化资源推荐算法,最后以馆藏图书资源为例对模型进行验证。结果表明,本文构建的方法能够对数字资源进行有效聚合,并挖掘图书的语义信息,同时结合用户兴趣模型,为用户提供精准化的资源推荐。

In view of the problems of information overload,heterogeneous information and unsatisfactory recommendation effect of digital resources,this paper aims to improve the traditional digital resource integration model and similarity calculation method,and combine a multi-label collaborative filtering methods to improve the accuracy of recommendation.Based on the idea of collaborative filtering recommendation,a digital resource integration method is used to calculate the similarity then find close neighbors of resources and users.Based on this,the p...