基于语句相似度计算的智能答疑系统机理研究  

Research on Mechanism of Intelligent Question Answering System Based on Sentence Similarity Computation

作　　者：李春生[1] 卢鹏飞 张可佳[1] LI Chun-sheng;LU Peng-fei;ZHANG Ke-jia(School of Computer and Information Technology,Northeast Petroleum University,Daqing 163318,China)

机构地区：[1]东北石油大学计算机与信息技术学院,黑龙江大庆163318

出　　处：《计算机技术与发展》2018年第4期91-94,共4页Computer Technology and Development

基　　金：黑龙江省自然科学基金面上项目(F2015020);黑龙江省教育科研规划重点课题(GJB1215013)

摘　　要：在使用互联网进行在线学习的过程中,为了解决现有答疑方式答疑实时性差、准确度低、效率低的问题,提出了一种基于语句相似度计算的智能答疑方案。首先分析现有的答疑方式及其不足;其次详细阐述了智能答疑系统的工作流程、总体结构和相关数据库结构,针对原有答疑方式检索效率低的问题加入了常用问题库,并引入基于字符串匹配的分词方法完成对学习者提出的问题的拆分;最后结合基于词信息的语句相似度计算方法对语句相似度进行计算并将结果呈现给学习者,以达到提高答疑系统的准确度、效率以及实时性的目的,满足学习者的需求。实验结果表明,基于语句相似度计算的智能答疑方案相对于原有答疑方案具有较高的准确度与效率。In order to solve the problem of poor real-time performance,low accuracy and low efficiency of the existing question answering methods in the process of online learning with the Internet,we present an intelligent question answering scheme based on the similarity calculation of sentences.First,we analyze the existing methods of question answering and their defects,then elaborate the work flow,the overall structure and the related database structure of the intelligent answering system.The common problem database is added for the problem of low retrieval efficiency of the original question answering method,and the word matching method based on the string matching is introduced to complete the separation of questions raised by learners.Finally,the similarity calculation method based on the word information is used to calculate the statement similarity of which the result is given to the learner,so as to improve the accuracy,efficiency and real-time performance of the system and meet the needs of learners.Experiments show that the scheme has higher accuracy and efficiency than original answering scheme.

关 键 词：分词 相似度计算 智能 答疑系统 

分 类 号：TP302[自动化与计算机技术—计算机系统结构]