基于知识图谱的旅游景点问答系统
|
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.
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.
引文
[1]阮彤,孙程琳,王昊奋,等.中医药知识图谱构建与应用[J].医学信息学杂志,2016,37(4):8-13.
[2]熊晶,钟珞,王爱民.甲骨文知识图谱构建中的实体关系发现研究[J].计算机工程与科学,2015,37(11):2188-2194.
[3]李文鹏,王建彬,林泽琦,等.面向开源软件项目的软件知识图谱构建方法[J].计算机科学与探索,2017,11(6):851-862.
[4] MUKHOPADHYAY D,MUKHERJEE S,GHOSH S,et al.Architecture of a scalable dynamic parallel webcrawler with high speed downloadable capability for a web search engine[C]//MSPT Proceedings of the 6th International Workshop,2006:103-108.
[5]林哲.桂林靖江王府[M].桂林:广西师范大学出版社,2009:52-92.
[6] WEBBER J.A programmatic introduction to Neo4j[C]//Conference on Systems,Programming,and Applications:Software for Humanity,2012:217-218.
[7] NGUYEN L.Tutorial on hidden Markov model[J].Applied and Computational Mathematics,2017:6(4-1):16-38.
[8] VOGEL S,NEY H,TILLMANN C.HMM-based word alignment in statistical translation[J].Coling,1996:9(1):836-841.
[9] FININ T,MAYFIELD J,JOSHI A,et al.Information retrieval and the semantic web[C]//IEEE International Conference on Educational and Information Technology,2017:461-463.
[10]黄洪,丰旭.涉及地名的句子相似度计算方法的改进[J].浙江工业大学学报,2015,43(6):624-629.
[11] RUAN H,LI Y,WANG Q,et al.A research on sentence similarity for question answering system based on multi-feature fusion[C]//IEEE/WIC/ACM International Conference on Web Intelligence,2017:507-510.
[12]葛斌,李芳芳,郭丝路,等.基于知网的词汇语义相似度计算方法研究[J].计算机应用研究,2010,27(9):3329-3333.
[13] NGO H Q,RUDRA A.FAQ:questions asked frequently[C]//ACM Sigmod-Sigact-Sigai Symposium on Principles of Database Systems,2016:13-28.
[14] CAO B,YUN J W,CHEN H R.Levenshtein distance based process retrieval method[J].Computer Integrated Manufacturing Systems,2012,18(8):1766-1773.
[2]熊晶,钟珞,王爱民.甲骨文知识图谱构建中的实体关系发现研究[J].计算机工程与科学,2015,37(11):2188-2194.
[3]李文鹏,王建彬,林泽琦,等.面向开源软件项目的软件知识图谱构建方法[J].计算机科学与探索,2017,11(6):851-862.
[4] MUKHOPADHYAY D,MUKHERJEE S,GHOSH S,et al.Architecture of a scalable dynamic parallel webcrawler with high speed downloadable capability for a web search engine[C]//MSPT Proceedings of the 6th International Workshop,2006:103-108.
[5]林哲.桂林靖江王府[M].桂林:广西师范大学出版社,2009:52-92.
[6] WEBBER J.A programmatic introduction to Neo4j[C]//Conference on Systems,Programming,and Applications:Software for Humanity,2012:217-218.
[7] NGUYEN L.Tutorial on hidden Markov model[J].Applied and Computational Mathematics,2017:6(4-1):16-38.
[8] VOGEL S,NEY H,TILLMANN C.HMM-based word alignment in statistical translation[J].Coling,1996:9(1):836-841.
[9] FININ T,MAYFIELD J,JOSHI A,et al.Information retrieval and the semantic web[C]//IEEE International Conference on Educational and Information Technology,2017:461-463.
[10]黄洪,丰旭.涉及地名的句子相似度计算方法的改进[J].浙江工业大学学报,2015,43(6):624-629.
[11] RUAN H,LI Y,WANG Q,et al.A research on sentence similarity for question answering system based on multi-feature fusion[C]//IEEE/WIC/ACM International Conference on Web Intelligence,2017:507-510.
[12]葛斌,李芳芳,郭丝路,等.基于知网的词汇语义相似度计算方法研究[J].计算机应用研究,2010,27(9):3329-3333.
[13] NGO H Q,RUDRA A.FAQ:questions asked frequently[C]//ACM Sigmod-Sigact-Sigai Symposium on Principles of Database Systems,2016:13-28.
[14] CAO B,YUN J W,CHEN H R.Levenshtein distance based process retrieval method[J].Computer Integrated Manufacturing Systems,2012,18(8):1766-1773.