基于CBR技术的中医诊疗系统中案例相似度计算方法研究

发布时间：2018-07-04 15:29

本文选题：CBR技术 + 中医诊疗系统　；参考：《中国科学院大学(中国科学院工程管理与信息技术学院)》2017年硕士论文

【摘要】：论文立足于“基于古代文献挖掘的新发突发传染病中医诊疗辅助方法”这个项目,以诊断和治疗方法的确定为切入点,借助古疫病文献开展的对于新发突发发热中医诊疗辅助方法的研究。目的是为了把人工智能(Artificial Intelligence,AI)技术中的基于案例推理(Case-based reasoning,CBR)技术和中医学知识进行相结合,设计和开发出灵活、有效、实用且操作性强的“基于CBR技术的中医诊疗系统”为新发突发传染病中医诊疗方案的制定提供决策支持。本文完成的主要工作如下:(1)研究了案例推理技术的理论知识。比较深入地探究了CBR技术的基本机理、进行推理的生命周期、CBR技术的应用和成长等。然后对CBR技术进行推理的整个过程中所涉及到的几个步骤进行了详细介绍,包括对案例的表示、案例检索(Retrieve)、案例重用(Reuse)、案例修正(Revise)与案例保存(Retain)。(2)在Huang、Ahmad等人的研究基础上,提出了计算混合类型数据之间相似性的度量方法。案例检索是整个推理过程中的核心,案例检索的效率会对用户的体验产生直接的影响。为了验证所提方法的有效性,选用了医疗领域关于乳腺癌和糖尿病诊断以及银行领域关于用户信用判断的数据集进行了相应的实验。并对实验结果进行了对比和分析,证实了提出的相似度测量方法的有效与可行。(3)把所提的混合相似度测量方法应用于基于CBR技术的中医诊疗系统中。在收集到的中医学治疗新发突发传染病的数据基础上,采用CBR技术,对要开发的中医诊疗系统的各个模块进行了设计,选用java语言完成了整个系统的开发。并对系统中的主要功能模块进行了展示。基于CBR技术的中医诊疗系统的研发,不单单可以使后人利用历代中医学家积累的治病经历和智慧来辅助中医治疗师进行决策,从而提高临床诊疗效果,减少误诊事件的发生;而且还可以对那些古人积累的中医学知识进行很好的保存,便于一些教育机构用于教学使用,实现中医学知识的共享和传承,更好的服务于人类。
[Abstract]:This paper is based on the project of "the assistant method of TCM diagnosis and treatment of emerging infectious diseases based on the ancient literature mining", which starts with the determination of diagnosis and treatment methods. The study on the assistant method of diagnosis and treatment of new sudden fever in TCM with the aid of ancient blight literature. The purpose of this paper is to combine Case-based reasoning (CBR) technology with traditional Chinese medicine (TCM) knowledge in Artificial Intelligence AI (AI) technology, and to design and develop flexible and effective Case-based reasoning (CBR) technology. The practical and operable Chinese medicine diagnosis and treatment system based on CBR technology provides decision support for the formulation of new infectious disease diagnosis and treatment scheme. The main work of this paper is as follows: (1) the theoretical knowledge of Case-Based reasoning (CBR) is studied. The basic mechanism of CBR technology and the application and growth of CBR technology are discussed. Then, several steps involved in the whole process of reasoning are introduced in detail, including case representation, case retrieval, case reuse, case revision and case). (2. A method to measure the similarity between mixed type data is proposed. Case retrieval is the core of the whole reasoning process, and the efficiency of case retrieval will have a direct impact on the user's experience. In order to verify the effectiveness of the proposed method, the data sets of breast cancer and diabetes diagnosis in the medical field and user credit judgment in the banking field were selected for corresponding experiments. The comparison and analysis of the experimental results show that the proposed similarity measurement method is effective and feasible. (3) the proposed hybrid similarity measurement method is applied to the traditional Chinese medicine diagnosis and treatment system based on CBR technology. On the basis of the collected data on the treatment of emerging infectious diseases in traditional Chinese medicine (TCM), the various modules of the TCM diagnosis and treatment system to be developed were designed by using CBR technology, and the whole system was developed with java language. The main function modules of the system are also shown. The research and development of TCM diagnosis and treatment system based on CBR technology can not only make future generations make use of the experience and wisdom accumulated by TCM scientists to assist TCM therapists to make decisions, so as to improve the effect of clinical diagnosis and treatment and reduce the occurrence of misdiagnosis. It can also preserve the knowledge of traditional Chinese medicine accumulated by the ancients, which is convenient for some educational institutions to use in teaching, to realize the sharing and transmission of traditional Chinese medicine knowledge, and to better serve human beings.
【学位授予单位】：中国科学院大学(中国科学院工程管理与信息技术学院)
【学位级别】：硕士
【学位授予年份】：2017
【分类号】：R24;TP18

【相似文献】