基于知识图谱的电力标准智能问答系统研究

Knowledge Graph-based Intelligent Q&A System for Power Standards

随着人工智能技术和机器学习技术的快速发展,目前智能问答系统已成为自然语言处理领域的热点研究之一。构建了一种基于知识图谱的电力标准智能问答系统,该系统通过对用户提出的问题进行分析理解,自动从知识库资源中获取信息并将搜索结果以多维度可视化的方式展示给用户。重点介绍了电力标准知识库构建过程以及问答系统实现方式,其中知识构建过程包含实体识别、实体间关系抽取、基于BERT-TextCNN网络结构的意图识别。系统实现包含系统设计方案以及系统界面展示结果。该系统的开发能够满足用户对电力标准知识的问答需求。

At present,intelligent Q&A systems have become one of the research hotspots in the field of natural language processing owing to the rapid development of artificial intelligence and machine learning.This paper constructs a knowledge graph-based intelligent Q&A system for power standards.The system analyzes and understands the questions from users,automatically obtains information from knowledge base resources,and displays search results to users in a multi-dimensional visualization manner.The paper focuses on the construction process of the power standard knowledge base and the implementation method of the Q&A system.The knowledge construction process includes entity recognition,entity relationship extraction,and intention recognition method based on BERT-TextCNN network structure.The system implementation includes the system design scheme and the system interface display results.The development of this system can meet users′Q&A needs for knowledge of power standards.