DTScribe: Generating Models for Digital Twin Reporting using Local Large Language Models
作者: Kérian Fiter, Angelica Portocarrero, Bentley Oakes
分类: cs.SE, cs.AI
发布日期: 2026-10-13
💡 一句话要点
提出DTScribe以自动化数字双胞胎报告模型生成
🎯 匹配领域: 支柱九：具身大模型 (Embodied Foundation Models)
关键词: 数字双胞胎 大型语言模型 本体建模 自动化生成 模型评估 可视化技术 工业应用
📋 核心要点
- 现有的数字双胞胎建模过程繁琐且耗时，缺乏有效的自动化工具来支持可视化和共识构建。
- 本文提出了一种利用大型语言模型自动生成数字双胞胎报告的方法，通过提取文档中的关键信息并生成可视化和报告页面。
- 实验结果表明，使用中型本地模型的精度与大型模型相当，且通过多次推理循环显著提高了生成文档的质量。
📝 摘要（中文）
数字双胞胎的开发涉及多个利益相关者和技术组件。本文探讨了利用大型语言模型自动生成数字双胞胎报告所需模型的过程。我们的方法能够从输入的数字双胞胎文档中提取关键信息，并生成概念架构可视化和报告页面。通过使用本体建模语言生成描述模型，并结合大型语言模型的评估和本体推理，我们提升了生成文档的质量。研究还分析了架构和参数选择对文档质量的影响，并提供了实践者可用的见解和经验教训。
🔬 方法详解
问题定义：本文旨在解决数字双胞胎建模过程中的繁琐性和时间消耗问题，现有方法缺乏高效的自动化生成工具。
核心思路：通过利用大型语言模型自动化生成数字双胞胎报告，提取文档中的关键信息并生成相应的可视化和报告页面，以提高建模效率。
技术框架：整体流程包括输入数字双胞胎文档、提取关键信息、生成本体建模语言描述模型、进行质量评估和推理循环，最终输出可视化和报告。
关键创新：本研究的创新在于结合大型语言模型和本体推理，利用本地中型模型实现高质量文档生成，显著降低了对大型模型的依赖。
关键设计：采用约200亿参数的中型本地模型，避免使用大型语言模型作为评估者，并建议至少进行两次推理循环以优化本体建模语言的生成。
🖼️ 关键图片
📊 实验亮点
实验结果显示，使用中型本地模型的生成质量与大型模型相当，且通过多次推理循环，生成文档的质量显著提升，达到了预期的质量标准。这一方法为数字双胞胎报告的自动化生成提供了有效的解决方案。
🎯 应用场景
该研究的潜在应用领域包括数字双胞胎的开发、工业自动化和智能制造等。通过加速报告生成过程，实践者能够更高效地进行项目管理和决策，提升整体工作效率。未来，该方法还可扩展至其他模型生成任务，具有广泛的应用前景。
📄 摘要（原文）
The development of a digital twin brings together many stakeholders and technical components. We have previously investigated the reporting of the conceptual architecture for these digital twins as an artifact for discussion. However, we find that the activity of modeling the digital twin for visualization and consensus-building can be quite tedious and time-consuming. In this article, we explore the automation of model generation using large language models, targeting the model required for digital twin reporting. Our approach is designed to ingest digital twin documents and output both the conceptual architecture visualization and a reporting page for that digital twin. We first extract from the input the key details aligning with our twenty-one-characteristic Digital Twin Description Framework described in previous work. Then, we generate a description model in the Ontological Modeling Language, representing the digital twin as a constellation of models, data, enablers, and services. We utilize refinement loops with large language models acting as judges and ontological reasoning to increase artifact quality as measured by our metrics. We investigate how architectural and parameter choices affect artifact quality, such as how refinement loops enable local large language models to produce sufficiently high-quality results comparable to larger models. We also detail insights and lessons learned useful for practitioners, such that they can integrate our techniques to accelerate their digital twin reporting or for other model generation tasks. These insights include the use of medium-sized local models (around 20 billion parameters), the avoidance of large language models as judges and clustering for characteristic extraction, and the recommendation of at least two reasoner loops for Ontological Modeling Language refinement.