[目的/意义] 针对基于问答对的智能问答准确率和解决率低、用户满意度差等问题,研究构建知识图谱本体模型,构建基于知识图谱的智能问答,解决基于问答对的智能问题所面临的问题。[方法/过程] 首先,分析当前智能问答面临的问题及原因,提出构建知识图谱支撑智能问答的方案。其次,在已有本体模型构建方法的基础上,提出一种融合多层次数据的多轮循环方法,该方法分别以业务数据、用户数据和业务系统动态数据等多层次数据为数据来源,核心步骤为搭建基本框架、完善知识结构、对齐知识结构三轮循环。最后,以退换货领域为例阐述本体模型构建的具体步骤,从无到有,增量叠加,构建知识图谱本体模型。[结果/结论] 将以退换货本体模型为模式层的知识图谱部署在智能问答系统中进行试验,试验结果显示退换货知识图谱上线后智能问答的准确率提升50%,解决率提升300%。其中准确率是指回答正确的问题数量与回答的全部问题数量的比例,解决率是指答案精准解决了用户问题的数量与回答的全部问题数量的比例。本文提出的本体模型构建方法从零散的领域知识中梳理出完整的、细粒度的领域知识结构,支持智能问答为用户提供精准的答案,能够有效解决基于问答对的智能问答困境。
[Purpose/significance] Aiming at problems of intelligent Q&A based on Q&A pairs such as low accuracy and resolution rate and poor user satisfaction, this paper constructs a knowledge graph (KG) ontology model that supports the realization of dynamic and accurate intelligent Q&A based on the knowledge graph. [Method/process] First, the paper analyzed the current problems and causes of intelligent question answering, and proposed a plan to build a knowledge graph to support intelligent question answering. Second, On the basis of existing ontology model construction methods, the paper proposed a multi-round loop method integrating multi-level data, which used the business data provided by the enterprises, user data and business system dynamic data as the data sources. And the core steps were to build a basic framework, improve the knowledge structure, and align three cycles of the knowledge structure. Finally, this paper took the domain of return and exchange as a case to describe the concrete steps of ontology model construction, from zero, added incrementally, and constructed ontology model of knowledge graph. [Result/conclusion] This paper applies the knowledge graph with the return ontology model as the schema layer in an intelligent Q&A system for testing. The evaluation results show that the accuracy rate increased by 50% and the precision rate increased by 300% after the return and exchange knowledge graph is online. So, the proposed ontology model construction method sorts out the complete and fine-grained domain knowledge structure from scattered domain knowledge, can provide accurate answers to users in intelligent Q&A, and can effectively solve the intelligent Q&A dilemma based on Q&A pairs.
[1] SINGHAL A. Official Google blog:introducing the knowledge graph:things, not strings[EB/OL].[2021-07-02]. https://www.blog.google/products/search/introducing-knowledge-graph-things-not/.
[2] IRENE P. Knowledge graphs vs property graphs a brief overview and comparison[EB/OL].[2021-05-21]. https://www.topquadrant.com/wp-content/uploads/2020/08/Knowledge-Graphs-vs.-Property-Graphs-A-Brief-Overview-and-Comparison.pdf.
[3] GRUBER T R. A translation approach to portable ontology specifications[J]. Knowledge acquisition, 1993, 5(2):199-220.
[4] GRVNINGER M, FOX M S. Methodology for the design and evaluation of ontologies[EB/OL].[2021-12-21]. http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.44.8723&rep=rep1&type=pdf.
[5] USCHOLD M, KING M. Towards a methodology for building ontologies[M]. Edinburgh:University of Edinburgh, 1995.
[6] FERNÁNDEZ-LÓPEZ M, GÓMEZ-PÉREZ A, JURISTO N. Methontology:from ontological art towards ontological engineering[J]. Engineering workshop on ontological engineering,1997(Mar.):33-40.
[7] SURE Y, STAAB S, STUDER R. On-to-knowledge methodology (OTKM)[M]//Handbook on ontologies. Berlin:Springer, 2004:117-132.
[8] SUÁREZ-FIGUEROA M C, GÓMEZ-PÉREZ A, FERNÁNDEZ-LÓPEZ M. The NeOn methodology for ontology engineering[M]//Ontology engineering in a networked world. Berlin:Springer, 2012:9-34.
[9] DE NICOLA A, MISSIKOFF M, NAVIGLI R, et al. A software engineering approach to ontology building[J]. Information systems, 2009, 34(2):258-275.
[10] NOY N F, MCGUINNESS D L. Ontology development 101:a guide to creating your first ontology[EB/OL].[2021-12-21]. https://corais.org/sites/default/files/ontology_development_101_aguide_to_creating_your_first_ontology.pdf.
[11] GANGEMI A, PRESUTTI V. Ontology design patterns[M]//Handbook on ontologies. Berlin:Springer, 2009:221-243.
[12] PRESUTTI V, DAGA E, GANGEMI A, et al. eXtreme design with content ontology design patterns[C]//Procecdings of workshop on ontology patterns. Washington D.C.:CEUR-WS.Org., 2009:83-97.
[13] 朱妍昕,徐维,王霞,等.基于FAIR原则的循证医学文献本体构建——以哮喘药物治疗文献本体为例[J/OL].情报理论与实践:1-12[2021-09-30].http://kns.cnki.net/kcms/detail/11.1762.G3.20210819.1201.002.html.
[14] 贾君枝.《汉语主题词表》转换为本体的思考[J].中国图书馆学报,2007(4):41-44.
[15] 段瑞龙,宋文.国内外叙词表转换本体方法研究综述[J].情报杂志,2012,31(7):66-71.
[16] ZHEN Z,TANG A M,SHEN J Y,et al.Thesaurus-based approach for building domain ontology with a case study of military aircraft prototype ontology construction[J].Journal of Southeast University(English Edition),2006(3):353-356.
[17] WIŚNIEWSKI D, POTONIEC J, ŁAWRYNOWICZ A, et al. Analysis of ontology competency questions and their formalizations in SPARQL-OWL[J]. Journal of Web semantics, 2020(29):1-13.
[18] 杨波,廖怡茗.面向企业动态风险的知识图谱构建与应用研究[J].现代情报,2021,41(3):110-120.
[19] 张肃,许慧.基于知识图谱的企业知识服务模型构建研究[J].情报科学,2020,38(8):68-73.
[20] DE NICOLA A, MISSIKOFF M. A lightweight methodology for rapid ontology engineering[J]. Communications of the ACM, 2016, 59(3):79-86.
[21] SUÁREZ-FIGUEROA M C, GÓMEZ-PÉREZ A. Ontology requirements specification[M]//Ontology engineering in a networked world. Berlin:Springer, 2012:93-106.
[22] D'ANTONIO F, MISSIKOFF M, TAGLINO F. Formalizing the OPAL eBusiness ontology design patterns with OWL[M]//Enterprise interoperability II. London:Springer, 2007:345-356.
