基于ElasticSearch的输变电工程全文检索研究
Research and Application of ElasticSearch in Full-text Search of Power Transmissionand Transformation Engineering
张建广 1徐鲲 1董鉥涛 1刘迪 1王向上 1李春林1
作者信息
- 1. 北京洛斯达科技发展有限公司,北京 100044
- 折叠
摘要
随着输变电工程建设工作的开展,多源异构的全过程非结构化文档体量日益增大,需要对这些非结构化文档进行稳定管理.为实现输变电工程非结构化文档的高效检索,研究了基于ElasticSearch的输变电工程全文检索方案,构建电网专用术语词典对智能化分词进行辅助优化,融合输变电工程资料的特征信息,对分词成果进行语义赋值,基于语义标签改进分词算法,进一步提升全文检索效率和准确率,搭建了输变电工程全文检索系统,以验证此技术方案的可行性.
Abstract
With the development of power transmission and transformation engineering construction,the volume of unstructured documents with multi-source heterogeneity throughout the entire process is increasing,and stable management of these unstructured documents is needed.In order to achieve efficient retrieval of unstructured documents in power transmission and transformation engineering,the study designs a full-text retrieval scheme for power transmission and transformation engineering based on ElasticSearch,constructs a grid specific terminology dictionary to assist in intelligent segmentation optimization,integrates feature information of power transmission and transformation engineering data to assign semantic values to the segmentation results,and improves the segmentation algorithm based on semantic labels to further improve the efficiency and accuracy of full-text retrieval.Finally,the study establishes a full-text retrieval system for power transmission and transformation engineering to verify the feasibility of the proposed technical solution.
关键词
输变电工程/全文检索/ElasticSearch/中文分词/语义检索Key words
Power transmission and transformation engineering/Full-text search/ElasticSearch/Chinese word segmentation/Semantic search引用本文复制引用
出版年
2024
NETL
NSTL
万方数据