摘要
随着旅游产业的兴起,旅游信息呈爆炸式增长,信息过载问题日益突出。为使用户能够高效、准确地得到所需信息,本文针对传统协同过滤算法仅采用单一的总体评分,从而导致相似度计算不准确的问题,提出了基于属性特征的推荐算法。该算法考虑了项目各属性特征的相似性,改进了传统方法相似度的计算方式,分别从多个维度进行相似度的衡量。实验结果表明,该算法在个性化旅游推荐中得到了很好的应用,相对于传统协同过滤算法有着更高的推荐精度,能够提升推荐的质量。
With the rise of tourism industry,tourism information is increasing explosively,and the problem of information overload is increasingly prominent.In order to enable users to get the required information efficiently and accurately,this paper proposes a recommendation algorithm based on attribute features to solve the problem that traditional collaborative filtering algorithm only uses a single overall score,therefore leads to inaccurate similarity calculation.The algorithm takes into account the similarity of the attributes of items,improves the traditional method of similarity calculation,and measures the similarity from multiple dimensions.The experimental results show that this algorithm has been well applied in personalized tourism recommendation,and has higher recommendation accuracy compared with the traditional collaborative filtering algorithm,which can improve the recommendation quality.
作者
丁恒
黄全舟
DING Heng;HUANG Quanzhou(School of Computer Science,Xi'an Shiyou University,Xi'an 710065,China)
出处
《智能计算机与应用》
2020年第1期193-196,共4页
Intelligent Computer and Applications
关键词
协同过滤
属性特征
个性化旅游推荐
collaborative filtering
attribute features
personalized tourism recommendation
