基于张量分解的药品个性化推荐  

Personalized Medicine Recommendation Based on Tensor Decomposition

作　　者：王龙[1] 王嘉伦[1] 程转丽 李然[1] 张引[1] 

机构地区：[1]华中科技大学计算机学院,武汉430074

出　　处：《计算机科学》2015年第5期225-229,共5页Computer Science

基　　金：基于云计算的普适人体传感网关键技术研究(F020809)资助

摘　　要：在当前网购越来越流行的趋势下,网上买药也给很多病人带来了极大的便利。但是普通人在网上购买药品时普遍存在盲目购药、无法获得买药指导的问题,针对这一问题,提出首先根据药品的功能描述信息进行聚类,设计了基于用户相似度的协同过滤药品推荐算法;然后针对该算法的冷启动以及数据稀疏性等问题提出了基于张量分解的个性化药品推荐算法来对获取到的药品功能描述信息进行特征分析,构建标签特征向量,利用特征向量与用户对药品的评分值构建三阶张量,再利用张量分解方法对该三阶张量进行分解;最后得到推荐评估值,再利用该推荐评估值进行Top-N药品推荐。通过对真实的药品销售网站数据进行抓取并分析,构建了张量模型,并进行数据建模,与协同过滤的推荐结果相比,其得到了较好的推荐效果。As the online shopping is becoming more and more popular, buying medicine online has brought great convenience for many patients. But when ordinary people buy drugs online, they always purchase medicine blindly. There is a big problem that they do not have access to the medicine guidance. In order to solve this problem, firstly, we clustered the drug into several groups according to the functional description information of the drug, and proposed the personalized medicine recommendation based on user collaborative filtering. Then considering the shortcomings of the collaborative filtering algorithm, we used the tensor decomposition methods to model the relationship of the user, symptom and medicine, and recommended the top-N related medicines to the users according to their symptoms. We crawled the real data from the internet and compared the results with collaborative filtering method. The results show good performance.

关 键 词：药品个性化 协同推荐 K-MEANS聚类 张量分解 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]