The proposed method for linking entities in power distribution dispatch texts to a power distribution network knowledge graph is based on a deep understanding of these networks. This method leverages the unique features of entities in both the power distribution network's knowledge graph and the dispatch texts, focusing on their semantic, phonetic, and syntactic characteristics. An enhanced model, the Lexical Semantic Feature-based Skip Convolutional Neural Network (LSF-SCNN), is utilized for effectively matching dispatch text entities with those in the knowledge graph. The efficacy of this model, compared to a control model, is evaluated through cross-validation methods in real-world power distribution dispatch scenarios. The results indicate that the LSF-SCNN model excels in accurately linking a variety of entity types, demonstrating high overall accuracy in entity linking when the process is conducted in English.

翻译：针对配电网调度文本与配电网知识图谱间的实体链接问题，提出一种基于配电网深度理解的实体链接方法。该方法利用配电网知识图谱和调度文本中实体的独特特征，重点关注其语义特征、语音特征和句法特征。采用基于词汇语义特征的跳跃式卷积神经网络（LSF-SCNN）增强模型，有效匹配调度文本实体与知识图谱实体。在实际配电调度场景中，通过交叉验证方法将该模型与对照模型进行效能评估。结果表明，LSF-SCNN模型在多种实体类型的精准链接中表现优异，当链接过程以英文进行时，实体链接的整体准确率较高。