Scholarlink

<p>The rapid evolution of the electric vehicle (EV) ecosystem has produced vast and heterogeneous data across technical, infrastructural, policy, and consumer domains. However, this knowledge remains fragmented and inconsistently structured, limiting its use for evidence-based decision-making. This paper presents an ontology-driven framework on Electric Vehicle Decision Support Ontology (EV-DSS), that unifies and semantically enriches EV knowledge for intelligent analytics and reasoning. EV-DSS integrates structured datasets with unstructured consumer reviews using natural language processing (TF-IDF, Word2Vec) and rule-based ontology mapping, enabling continuous enrichment and semantic inference. The resulting ontology-driven knowledge graph supports SPARQL-based querying, reasoning, and decision support across the EV lifecycle. Applied case studies covering battery performance analysis, charging infrastructure optimization, and policy effectiveness and environmental impact assessment demonstrate EV-DSS’s ability to bridge technical, experiential, and regulatory perspectives. The ontology exhibits high enrichment accuracy, logical consistency, and practical relevance for manufacturers, policymakers, and end-users. By combining semantic modeling with data-driven enrichment, EV-DSS advances EV ontology research beyond static representation toward dynamic, knowledge-driven decision support<Emphasis Type="Underline">,</Emphasis> providing a scalable foundation for intelligent and sustainable mobility analytics.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Ontology-Driven Knowledge Discovery and Decision Support in the Electric Vehicle Ecosystem

  • 期刊论文

  • 发表日期：

    2026年1月19日

查看全文
  • S. Lakshminarayanan,
  • V. Bhuvaneswari

摘要

The rapid evolution of the electric vehicle (EV) ecosystem has produced vast and heterogeneous data across technical, infrastructural, policy, and consumer domains. However, this knowledge remains fragmented and inconsistently structured, limiting its use for evidence-based decision-making. This paper presents an ontology-driven framework on Electric Vehicle Decision Support Ontology (EV-DSS), that unifies and semantically enriches EV knowledge for intelligent analytics and reasoning. EV-DSS integrates structured datasets with unstructured consumer reviews using natural language processing (TF-IDF, Word2Vec) and rule-based ontology mapping, enabling continuous enrichment and semantic inference. The resulting ontology-driven knowledge graph supports SPARQL-based querying, reasoning, and decision support across the EV lifecycle. Applied case studies covering battery performance analysis, charging infrastructure optimization, and policy effectiveness and environmental impact assessment demonstrate EV-DSS’s ability to bridge technical, experiential, and regulatory perspectives. The ontology exhibits high enrichment accuracy, logical consistency, and practical relevance for manufacturers, policymakers, and end-users. By combining semantic modeling with data-driven enrichment, EV-DSS advances EV ontology research beyond static representation toward dynamic, knowledge-driven decision support, providing a scalable foundation for intelligent and sustainable mobility analytics.