摘要
提出了基于知识图谱的包装产业信息查询技术架构,并对知识体系构建、知识抽取、知识融合和知识应用等核心技术进行了阐述。提出一种基于领域本体的问题分类方法和结构化语义信息提取方法,根据给定的种子模板,从大规模训练数据中可以自动学习相关的模板。以中国包装产业数据库搜索为例,提出一种能处理自然语言查询的基于知识图谱的中国包装产业数据库查询方法,给出了基于知识图谱的中国包装产业数据库查询系统的具体构建步骤。
The packaging industry information inquiry technology architecture based on knowledge graph is proposed, and the knowledge hierarchy construction, the knowledge extraction, the knowledge fusion, and the knowledge application are described. In this paper, we introduce a new method of classifying questions with the help of domain-specific ontology and obtain structural semantic information for the question. Given a seed pattern, relevant pattern can be learned automatically from large-scale training corpus. The packaging industry database search method based on the knowledge graph for handling query natural language query is proposed, and the constructing procedures of the packaging industry information inquiry system based on knowledge graph are provided.
出处
《计算机科学与应用》
2017年第9期858-868,共11页
Computer Science and Application
基金
湖南省科技厅重点研发计划项目“工业装备智能监测与健康管理平台研发及应用(2016GK2017)”
中国包装联合会项目“中国包装产业大数据知识图谱的构建与应用(17ZBLWT001KT006)”。
