【作者】 杨王黎；

【导师】 吴雅娟；

【作者基本信息】 大庆石油学院 ， 计算机技术， 2008， 硕士

【摘要】 随着网络技术及Internet技术的发展,计算机技术得到了广泛应用。现代远程教育是网络和Internet应用的一个强有力的例子,它融合了现代教育教学思想、教学模式和教学系统,实现了教学模式的转变,克服了传统教育的时间和空间限制,使得原本分散的教学资源融为一体。智能答疑系统作为现代远程教育系统不可缺少的一个子系统,它的发展和完善还有待于多种技术的成熟和综合应用。其中,分词技术是中文智能答疑系统的一个关键技术,分词技术的应用和完善更是中文智能答疑系统智能性的直接考验。它是中文智能答疑系统的一项基本性技术。本文就是紧紧抓住分词技术在智能答疑系统中的基础性地位进行研究的。首先分析智能答疑系统中问题的特点;然后根据这些特点研究适合智能答疑系统的分词算法;在分词结果的基础上再进行问题的性质研究;这些都研究清楚后,建立问题相似度计算公式。在学生提问后将学生的问题与问题库中的问题进行相似度计算,相似度越高说明问题库中的问题和学生提问的问题越相似,我们就把相似度较高的几个问题库中的问题及答案反馈给学生,实现答疑系统的智能性。预处理过程的词语粗切分,是整个中文词语分析的基础环节,对最终的召回率、准确率、运行效率起着重要的作用。词语粗分必须能为后续的过程提供少量的、高召回率的中间结果。本文提出了一种基于N—最短路径方法的粗分模型,旨在兼顾高召回率和高效率。N—最短路径方法是一种预处理过程中实用、有效的词语粗分手段。本文除研究分词技术及其在智能答疑系统中如何应用外,还给出了基于分词技术的智能答疑系统的总体设计模型以及系统的模块设计,为系统的详细设计提供参考。并采用ASP.NET设计出了一个基于Web的智能答疑系统。更多还原

【Abstract】 With the rapid development of network technology and Internet, computer technology had been used more and more widely. Distant education is a very good example that network technology and Internet are used. Distant education includes educational idea, educational pattern and educational system, implementes the change of educational pattern. Distant education overcomes the limit of traditional education on time and space, and integrates original dispersive resource of education.The development and maturity of intelligent answering system, that is a subsystem of the modern distant education system, depends on the maturity of the technologies involved and the synthetical use of them. Chinese automatic word segmentation is an important technology in intelligent answering system, this technology will immediately relate to the intellectuality of intelligent answering system.This paper mostly researches Chinese word segmentation, because it is a basal place in intelligent answering system. First, this paper will analyze the characteristics of the questions; then, research the arithmetic of Chinese word segmentation that fits intelligent answering system; research the properties of those questions based on the result of Chinese word segmentation; after those are well-know, establish the formula that computes the similitude degree between the questions. After students question, the system will automatically computer the similitude degree with the questions in Q&A database. The system returns some questions and their answers in Q&A database to students, those questions have higher similitude degree with the question that students ask.As the very first step in Chinese word segmentation, rough segmentation tries to cover the correct segmentation with as few candidates as possible. This paper presents a model of rough segmentation, which is based on the N-shortest-paths method, to achieve the goal. IN parallel, a statistical model can easily be obtained by attaching frequencies to the edges of the word-graphs. The N-shortest-paths method is effective for the task of rough segmentation.In addition, this paper presents the general design and the module design of intelligent answering system based on Chinese automatic word segmentation, this will be regarded as a reference when the system is detailedly designed.更多还原