用因果分析+大模型，让智能建筑自动解释能耗异常原因。
InsightBuild: LLM-Powered Causal Reasoning in Smart Building Systems
- 先用格兰杰因果检验找传感器数据间的因果关系
- 再用微调过的LLM生成清晰可操作的中文解释
- 在谷歌和伯克利真实数据上验证，效果优于传统方法
智能建筑产生大量传感器与控制数据，但设施管理人员常难以理解异常能耗的原因。我们提出InsightBuild，一种两阶段框架，将因果分析与微调的大语言模型结合，生成人类可读的能耗模式因果解释。第一阶段，轻量级因果推断模块对来自Google Smart Buildings和Berkeley Office数据集的建筑遥测数据（如温度、空调设置、人员密度）进行格兰杰因果检验与结构因果发现。第二阶段，一个在传感器级原因与文本解释对上微调的LLM接收检测到的因果关系，生成简洁、可操作的解释。我们在两个真实数据集（Google：2017–2022；Berkeley：2018–2020）上评估，使用专家标注的真实因果关系作为保留异常样本的基准。结果表明，显式因果发现与基于LLM的自然语言生成相结合，能提供清晰精准的解释，帮助设施管理人员诊断并缓解能源效率问题。
原文摘要 · Abstract (English)
Smart buildings generate vast streams of sensor and control data, but facility managers often lack clear explanations for anomalous energy usage. We propose InsightBuild, a two-stage framework that integrates causality analysis with a fine-tuned large language model (LLM) to provide human-readable, causal explanations of energy consumption patterns. First, a lightweight causal inference module applies Granger causality tests and structural causal discovery on building telemetry (e.g., temperature, HVAC settings, occupancy) drawn from Google Smart Buildings and Berkeley Office datasets. Next, an LLM, fine-tuned on aligned pairs of sensor-level causes and textual explanations, receives as input the detected causal relations and generates concise, actionable explanations. We evaluate InsightBuild on two real-world datasets (Google: 2017-2022; Berkeley: 2018-2020), using expert-annotated ground-truth causes for a held-out set of anomalies. Our results demonstrate that combining explicit causal discovery with LLM-based natural language generation yields clear, precise explanations that assist facility managers in diagnosing and mitigating energy inefficiencies.
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。