面向医疗设备的深度问答系统的设计
|
摘要
提出辅助医疗设备维修保养的深度问答系统的设计方案。为医院设备工程师提供智能化的设备信息咨询平台,提供日趋复杂而广泛的设备知识服务,增加医院设备的效益。系统包括算法模块和应用模块,算法模块通过深度学习卷积神经网络实现。通过设计实验进行答案搜索任务测试,在问题相似度前三的反馈信息里面,包含搜索目标的准确率达65%,证明算法可搜索到有效信息。将算法模型嵌入到Web应用中,进一步实现问答的功能。
This paper presented a design of deep question answering system to assist medical equipment maintenance. It provided an intelligent equipment information consulting platform for hospital equipment engineers, provided increasingly complex and extensive equipment knowledge services, and increased the benefits of hospital equipment. The system included algorithm module and application module. The algorithm module was implemented by deep learning convolutional neural network. We designed the experiment and tested the answer search task. The accuracy of the search target contained in the feedback information with the first three questions' similarity was up to 65%. This proves that the algorithm can search for effective information, and embeds the algorithm model into the Web application to further realize the function of question answering.
This paper presented a design of deep question answering system to assist medical equipment maintenance. It provided an intelligent equipment information consulting platform for hospital equipment engineers, provided increasingly complex and extensive equipment knowledge services, and increased the benefits of hospital equipment. The system included algorithm module and application module. The algorithm module was implemented by deep learning convolutional neural network. We designed the experiment and tested the answer search task. The accuracy of the search target contained in the feedback information with the first three questions' similarity was up to 65%. This proves that the algorithm can search for effective information, and embeds the algorithm model into the Web application to further realize the function of question answering.
引文
[1] 童其荣,刘伟,亢德洪.医疗设备维修成本分析与管理[J].中国医疗设备,2011,26(8):84-85.
[2] 黄鑫,刘尚军.现代医院大型医疗设备维修存在问题与对策探讨[J].医疗卫生装备,2012,33(12):103-105.
[3] 黄昌宁.从IBM深度问答系统战胜顶尖人类选手所想到的[J].中文信息学报,2011,25(6):21-26.
[4] 陈谷川,陈豫.自动问答系统QA的研究与实现[J].数字图书馆论坛,2006(5):37-41.
[5] 丰国庆.降低医疗设备维修成本有效途径的探讨[J].中国设备工程,2018(17):34-35.
[6] Feng M,Xiang B,Glass M R,et al.Applying Deep Learning to Answer Selection:A Study and An Open Task[C]//2015 IEEE Workshop on Automatic Speech Recognition and Understanding(ASRU).IEEE,2015:813-820.
[7] 严军.医院医疗设备维修信息化管理现状和发展[J].医疗装备,2016(16):76-77.
[8] 徐海琴,王雅军,南玉萍.大数据在医疗设备管理中的应用[J].医疗卫生装备,2017(6):136-137.
[9] 刘康,张元哲,纪国良,等.基于表示学习的知识库问答研究进展与展望[J].自动化学报,2016,42(6):807-818.
[10] 赵洁.基于搜索引擎的中文自动问答系统的设计与实现[D].北京:北京工业大学,2016.
[11] 刘宝瑞,郭宏娇.基于Deep QA的图书馆数字参考咨询问答系统研究[J].情报科学,2017(4):103-108.
[12] Deck P.Spring MVC学习指南[M].林仪明,崔毅,译.2版.北京:人民邮电出版社.
[13] 郑文超,徐鹏.利用word2vec对中文词进行聚类的研究[J].软件,2013(12):160-162.
[14] Mikolov T,Chen K,Corrado G,et al.Efficient Estimation of Word Representations in Vector Space[EB].arXiv:1301.3781,2013.
[15] 张少应,程传旭.基于Hibernate持久化层的设计与实现[J].计算机技术与发展,2014(12):101-104.
[2] 黄鑫,刘尚军.现代医院大型医疗设备维修存在问题与对策探讨[J].医疗卫生装备,2012,33(12):103-105.
[3] 黄昌宁.从IBM深度问答系统战胜顶尖人类选手所想到的[J].中文信息学报,2011,25(6):21-26.
[4] 陈谷川,陈豫.自动问答系统QA的研究与实现[J].数字图书馆论坛,2006(5):37-41.
[5] 丰国庆.降低医疗设备维修成本有效途径的探讨[J].中国设备工程,2018(17):34-35.
[6] Feng M,Xiang B,Glass M R,et al.Applying Deep Learning to Answer Selection:A Study and An Open Task[C]//2015 IEEE Workshop on Automatic Speech Recognition and Understanding(ASRU).IEEE,2015:813-820.
[7] 严军.医院医疗设备维修信息化管理现状和发展[J].医疗装备,2016(16):76-77.
[8] 徐海琴,王雅军,南玉萍.大数据在医疗设备管理中的应用[J].医疗卫生装备,2017(6):136-137.
[9] 刘康,张元哲,纪国良,等.基于表示学习的知识库问答研究进展与展望[J].自动化学报,2016,42(6):807-818.
[10] 赵洁.基于搜索引擎的中文自动问答系统的设计与实现[D].北京:北京工业大学,2016.
[11] 刘宝瑞,郭宏娇.基于Deep QA的图书馆数字参考咨询问答系统研究[J].情报科学,2017(4):103-108.
[12] Deck P.Spring MVC学习指南[M].林仪明,崔毅,译.2版.北京:人民邮电出版社.
[13] 郑文超,徐鹏.利用word2vec对中文词进行聚类的研究[J].软件,2013(12):160-162.
[14] Mikolov T,Chen K,Corrado G,et al.Efficient Estimation of Word Representations in Vector Space[EB].arXiv:1301.3781,2013.
[15] 张少应,程传旭.基于Hibernate持久化层的设计与实现[J].计算机技术与发展,2014(12):101-104.