📄 中文摘要
随着智能制造环境的日益复杂，迫切需要能够将高层次人类意图转化为机器可执行动作的接口。研究提出了一个统一框架，将经过指令调优的大型语言模型（LLMs）与本体对齐的知识图谱（KGs）相结合，以实现制造即服务（MaaS）生态系统中的意图驱动交互。通过对Mistral-7B-Instruct-V02进行领域特定数据集的微调，使其能够将自然语言意图转换为结构化的JSON需求模型。这些模型与基于ISA-95标准的Neo4j知识图谱进行语义映射，确保与制造过程、资源和约束的操作一致性。
基于意图驱动的智能制造：知识图谱与大型语言模型的集成
📄 English Summary
Intent-Driven Smart Manufacturing Integrating Knowledge Graphs and Large Language Models
The increasing complexity of smart manufacturing environments necessitates interfaces that can translate high-level human intents into machine-executable actions. A unified framework is proposed that integrates instruction-tuned Large Language Models (LLMs) with ontology-aligned Knowledge Graphs (KGs) to facilitate intent-driven interaction in Manufacturing-as-a-Service (MaaS) ecosystems. The Mistral-7B-Instruct-V02 model is fine-tuned on a domain-specific dataset, enabling the translation of natural language intents into structured JSON requirement models. These models are semantically mapped to a Neo4j-based knowledge graph grounded in the ISA-95 standard, ensuring operational alignment with manufacturing processes, resources, and constraints.