PermitGPT：用于施工危险预测、许可证预测及社区影响评估的统一生成式AI流水线
PermitGPT: A Unified Generative-AI Pipeline for Construction Hazard Forecasting, Permit Prediction, and Community Impact
- University of Rajshahi（拉杰沙希大学）
- University of Aizu（会津大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
PermitGPT是用于施工治理的统一生成式AI框架，对齐多源数据生成9万对训练样本，微调三类模型在2833个测试用例上取得互补表现，助力施工危险、许可及社区影响的决策支持。
AI中文摘要：
城市施工治理需要将 workplace safety（工地安全）、许可要求与社区影响关联起来的早期决策，但相关证据往往分散在不同的市政及监管数据源中。本文提出PermitGPT，这是一个统一的生成式人工智能框架，用于将非结构化的施工许可描述转换为三个领域的结构化决策支持输出：安全隐患识别、许可要求规范及社区影响评估。为解决数据碎片化问题，我们对纽约市建筑局（NYC Department of Buildings）、职业安全与健康管理局（Occupational Safety and Health Administration）及NYC 311服务请求的记录进行时空对齐，通过基于规则的对齐和领域知情的现场检查，生成90000个结构化提示-响应对。我们使用参数高效适配方法对三个开源权重语言模型进行微调，并在2833个保留的测试用例上对其进行评估。结果显示各模型表现互补：Gemma-3-1B推理效率最高，达每秒3.07个样本且内存占用低；Llama-3.2-3B在监管风格输出中词汇重叠度最高，BLEU分数为0.0091；4-bit Mistral-7B-Instruct-v0.3在语义对齐方面表现最强，BERTScore-F1为0.7747。由于该任务涉及开放式结构化生成，低BLEU值需结合语义指标和定性输出结构进行解读，而非作为效用的独立指标。总体而言，PermitGPT为AI辅助施工治理迈出了初始一步，同时也指明了更强的任务级评估及现实世界验证的方向。
英文摘要：
Urban construction governance requires early decisions that connect workplace safety, permitting requirements, and community impact, yet the relevant evidence is often scattered across separate municipal and regulatory data sources. This paper presents PermitGPT, a unified generative artificial intelligence framework for converting unstructured construction permit descriptions into structured decision-support outputs across three domains: safety hazard identification, permit requirement specification, and community impact assessment. To address data fragmentation, we spatially and temporally align records from the New York City Department of Buildings, Occupational Safety and Health Administration, and NYC 311 service requests, producing 90,000 structured prompt-response pairs derived through rule-based alignment and domain-informed spot checking. We fine-tune three open-weight language models using parameter-efficient adaptation and evaluate them on 2,833 held-out test cases. The results show complementary model behavior: Gemma-3-1B provides the most efficient inference at 3.07 samples per second with low memory usage, Llama-3.2-3B gives the highest lexical overlap for regulatory-style outputs with a BLEU score of 0.0091, and 4-bit Mistral-7B-Instruct-v0.3 achieves the strongest semantic alignment with a BERTScore-F1 of 0.7747. Because the task involves open-ended structured generation, low BLEU values are interpreted alongside semantic metrics and qualitative output structure rather than as standalone indicators of utility. Overall, PermitGPT provides an initial step toward AI-assisted construction governance while identifying directions for stronger task-level evaluation and real-world validation.
