摘要
针对目前搜索引擎对于旅游景点领域的问答反馈结果繁多、准确率低并且不具备智能性的问题,提出了以靖江王府为例,基于知识图谱的旅游景点问答系统。通过整合搜集到的靖江王府相关信息,构建知识图谱,从而实现问答系统的智能性。在问句分析模块使用问句分词、同类词替换和问句相似度计算方法,答案生成模块使用多策略答案生成方法。实验结果表明,将自然语言处理技术与知识图谱相结合的旅游景点问答系统功能完善,能够满足游客的一般问答需求。
Aiming at the problem that the search engine has many feedback results,low accuracy and no intelligence in the field of tourist attractions at present,aquestion and answer system based on knowledge graph for Princes Jingjiang Residence is put forward.By integrating the relevant information collected from Princes Jingjiang Residence,the system constructs the knowledge graph and realizes the intelligence of the question and answer system.The question segmentation,word substitution and question similarity calculation method has been used in the question analysis module,and the multistrategy answer generation method has been used in the answer generation module.The experimental results show that the question and answer system of tourist attractions,which combines natural language processing technology with knowledge graph,has fully function and can satisfy the general question and answer demand of the tourist.
作者
时雨
古天龙
宾辰忠
孙彦鹏
SHI Yu;GU Tianlong;BIN Chenzhong;SUN Yanpeng(Guangxi Key Laboratory of Trusted Software,Guilin University of Electronic Technology,Guilin 541004,China)
出处
《桂林电子科技大学学报》
2018年第4期296-302,共7页
Journal of Guilin University of Electronic Technology
基金
国家自然科学基金(61572146
U1501252
U1711263)
广西创新驱动重大专项(AA17202024)
广西自然科学基金(2016GXNSFDA380006)
关键词
问答系统
知识图谱
靖江王府
分词
答案生成
question and answer system
knowledge graph
Princes Jingjiang Residence
participle
answer generation