用大模型+知识图谱把人说的“要做什么”自动转成可执行指令。
Intent-Driven Smart Manufacturing Integrating Knowledge Graphs and Large Language Models
- 用微调的大模型把自然语言转成结构化需求
- 准确率89.33%，比零样本高很多
- 适合想实现智能制造交互的工程师
智能制造环境日益复杂，亟需能将高层人类意图转化为机器可执行动作的接口。本文提出一个统一框架，将指令微调的大语言模型（LLM）与对齐本体的知识图谱（KG）结合，实现制造即服务（MaaS）生态中的意图驱动交互。我们基于领域数据集对Mistral-7B-Instruct-V02进行微调，使自然语言意图能够转化为结构化的JSON需求模型。这些模型语义映射到基于Neo4j、符合ISA-95标准的知识图谱，确保与制造流程、资源和约束一致。实验结果表明，该方法显著优于零样本和三样本基线，精确匹配准确率达89.33%，整体准确率为97.27%。本工作为可扩展、可解释、自适应的人机交互奠定了基础。
原文摘要 · Abstract (English)
The increasing complexity of smart manufacturing environments demands interfaces that can translate high-level human intents into machine-executable actions. This paper presents a unified framework that integrates instruction-tuned Large Language Models (LLMs) with ontology-aligned Knowledge Graphs (KGs) to enable intent-driven interaction in Manufacturing-as-a-Service (MaaS) ecosystems. We fine-tune Mistral-7B-Instruct-V02 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. Our experimental results demonstrate significant performance gains over zero-shot and 3-shots baselines, achieving 89.33\% exact match accuracy and 97.27\% overall accuracy. This work lays the foundation for scalable, explainable, and adaptive human-machine
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。