计算机科学 ›› 2015, Vol. 42 ›› Issue (5): 225-229.doi: 10.11896/j.issn.1002-137X.2015.05.045

• 人工智能 • 上一篇    下一篇

基于张量分解的药品个性化推荐

王 龙,王嘉伦,程转丽,李 然,张 引   

  1. 华中科技大学计算机学院 武汉430074,华中科技大学计算机学院 武汉430074,华中科技大学计算机学院 武汉430074,华中科技大学计算机学院 武汉430074,华中科技大学计算机学院 武汉430074
  • 出版日期:2018-11-14 发布日期:2018-11-14
  • 基金资助:
    本文受基金项目:基于云计算的普适人体传感网关键技术研究(F020809)资助

Personalized Medicine Recommendation Based on Tensor Decomposition

WANG Long, WANG Jia-lun, CHENG Zhuan-li, LI Ran and ZHANG Yin   

  • Online:2018-11-14 Published:2018-11-14

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。

关键词: 药品个性化,协同推荐,K-means聚类,张量分解

Abstract: 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 personali-zed 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 perfor-mance.

Key words: Personalized medicine,Collaborative filtering,K-means clustering,Tensor decomposition

[1] Hripcsak G,Albers D J.Next-generation phenotyping of electronic health records[J].J AmMed InformAssoc,2013,20(1):117-121
[2] Deshpande R,Thuptimdang W,DeMarco J,et al.A collaborative framework for contributing DICOM RT PHI (Protected Health Information) to augment data mining in clinical decision support[C]∥SPIE Medical Imaging.International Society for Optics and Photonics,2014
[3] http://www.drugstore.com
[4] Duan L,Street W,Xu E.Healthcare information systems:data mining methods in the creation of a clinical recommender system[J].Enterp Inf Syst,2011,5(2):169-181
[5] Jsang A,Guo G,Pini M S,et al.Combining Recommender and Reputation Systems to Produce Better Online Advice[M].Mo-deling Decisions for Artificial Intelligence.Springer Berlin Heidelberg,2013:126-138
[6] Cho Young-Sung,et al.Clustering Method using Item Prefer-ence based on RFM for Recommendation System in u-Commerce[M].Ubiquitous Information Technologies and Applications.Springer Netherlands,2013:353-362
[7] Yuan X,Lee J H,Kim S J,et al.Toward a user-oriented recommendation system for real estate websites[J].Information Systems,2013,38(2):231-243
[8] Barragáns-Martínez A B,Costa-Montenegro E,Burguillo J C,et al.A hybrid content-based and item-based collaborative filtering approach to recommend TV programs enhanced with singular value decomposition[J].Information Sciences,2010,180(22):4290-4311
[9] Cai X,Bain M,Krzywicki A,et al.Collaborative filtering for people to people recommendation in social networks[M].AI 2010:Advances in Artificial Intelligence.Springer Berlin Heidelberg,2011:476-485
[10] Lops P,de Gemmis M,Semeraro G.Content-based recommender systems:State of the art and trends[M].Recommender Systems Handbook.Springer US,2011:73-105
[11] Carrer-Neto W,Hernández-Alcaraz M L,Valencia-García R,et al.Social knowledge-based recommender system.Application to the movies domain[J].Expert Systems with Applications,2012,39(12):10990-11000
[12] Dunham M H.Data Mining:Introductory and Advanced Topics[M].Pearson Education,2007
[13] Zhang Y J,Cheng E.An optimized method for selection of theinitial centers of k-means clustering[M]∥Integrated Uncertainty in Knowledge Modelling and Decision Making.Springer Berlin Heidelberg,2013:149-156
[14] Liu J,Musialski P,Wonka P,et al.Tensor completion for estimating missing values in visual data[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(1):208-220
[15] Werner D,Cruz C.A Method to Manage the Precision Difference between Items and Profiles[C]∥2013 International Conference on a Context of Content-Based Recommender System and Vector Space Model.Signal-Image Technology & Internet-Based Systems (SITIS).IEEE,2013:337-344
[16] Huang X,Wu Q.Micro-blog commercial word extraction based on improved TF-IDF algorithm[C]∥2013 IEEE Region 10 Conference on TENCON.IEEE,2013:1-5

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!