摘要
个性化需求信息推荐是需求识别和获取的有效手段之一。文章提出了一种基于协同过滤和内容筛选的混合推荐模型,该模型利用用户特征相似性解决传统协同过滤的冷启动和稀疏性问题,并基于需求内容的特征提取和分析筛选掉与目标用户兴趣相差较大的需求,以此来提高推荐的准确性。实验表明,该模型能够避免数据稀疏问题,并提高需求推荐的质量。
Personalized requirement recommendation is an effective method to requirement recognition and acquisition.This paper presented a hybrid recommendation model based on collaborative filtering and content.The model solved the cold start and data sparseness problem of traditional collaborative filtering with user characteristics and improved recommendation accuracy based on user feature extraction and analysis.Finally, experiments showed that it can avoid data sparseness and improve recommendation quality.
作者
覃容
陈建峡
QIN Rong, CHEN Jian-xia(Collage of Computer, Hubei University of Technology, Wuhan, Hubei 430079, Chin)
出处
《企业技术开发》
2018年第2期67-69,共3页
Technological Development of Enterprise
关键词
协同过滤
基于内容
需求推荐
个性化需求
Collaborative filtering
Content-based
Requirement recommendation
Personalized requirement
