基于CTM模型的在线轻问诊医生推荐研究  

Research on doctor recommendation for online light consultation based on CTM model

作　　者：张锦红 张云华[1] ZHANG Jinhong;ZHANG Yunhua(School of Informatics Science and Technology,Zhejiang Sci-Tech University,Hangzhou 310018,China)

机构地区：[1]浙江理工大学信息学院,杭州310018

出　　处：《智能计算机与应用》2021年第2期35-39,共5页Intelligent Computer and Applications

摘　　要：本文采用CTM主题模型对现有的在线医生专家推荐模型进行优化,首先利用患者提出的健康问题,得到问题-主题概率分布,然后根据医生历史回答的所有问题得到医生-主题概率分布,接着对得到的两项分布用杰卡德相似系数计算方法计算相似度,进而将主题相似度高的医生列表推荐给患者。实验阶段先对好大夫在线轻问诊模块的过敏反应科的数据进行采集和处理,再进行建模与测试,结果证实本文提出的医生推荐方法比该科室现存推荐方法更高效。This paper uses the CTM topic model to optimize the existing online doctor expert recommendation model.Firstly,the paper uses the health questions raised by the patient to obtain the question-topic probability distribution,secondly obtains the doctor-topic probability distribution based on all the questions answered by the doctor’s history.Then the paper uses the Jackard similarity coefficient calculation method to calculate the similarity of the obtained two distributions,finally recommends a list of doctors with high topic similarity to the patient.In the experimental stage,the data of the Allergic Reactions Department of the Doctor Online Inquiry Module is collected and processed,and modeling and testing are performed.The results confirm that the doctor recommendation method proposed in this article is more efficient than the existing recommendation method in the department.

关 键 词：CTM 专家推荐 在线轻问诊 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]