[论文解读] Generative AI in the Construction Industry: A State-of-the-art Analysis

Ridwan Taiwo, Idris Temitope Bello+5 more|arXiv (Cornell University)|Feb 15, 2024

BIM and Construction Integration被引用 17

一句话总结

对建筑领域生成式AI的前沿分析，提出定制化AI解决方案框架，并通过一个合同文件查询的案例研究进行演示。

ABSTRACT

The construction industry is a vital sector of the global economy, but it faces many productivity challenges in various processes, such as design, planning, procurement, inspection, and maintenance. Generative artificial intelligence (AI), which can create novel and realistic data or content, such as text, image, video, or code, based on some input or prior knowledge, offers innovative and disruptive solutions to address these challenges. However, there is a gap in the literature on the current state, opportunities, and challenges of generative AI in the construction industry. This study aims to fill this gap by providing a state-of-the-art analysis of generative AI in construction, with three objectives: (1) to review and categorize the existing and emerging generative AI opportunities and challenges in the construction industry; (2) to propose a framework for construction firms to build customized generative AI solutions using their own data, comprising steps such as data collection, dataset curation, training custom large language model (LLM), model evaluation, and deployment; and (3) to demonstrate the framework via a case study of developing a generative model for querying contract documents. The results show that retrieval augmented generation (RAG) improves the baseline LLM by 5.2, 9.4, and 4.8% in terms of quality, relevance, and reproducibility. This study provides academics and construction professionals with a comprehensive analysis and practical framework to guide the adoption of generative AI techniques to enhance productivity, quality, safety, and sustainability across the construction industry.

研究动机与目标

• 评估生成式AI在建筑领域的当前机会与挑战
• 提出一个使用公司数据构建定制化生成式AI解决方案的框架
• 通过合同文件查询的案例研究演示该框架

提出的方法

• 回顾并分类建筑领域现有及新兴的生成式AI机会与挑战
• 提出一个数据收集、数据集整理、训练自定义LLM、模型评估与部署的分步框架
• 通过案例研究说明开发用于查询合同文件的生成模型
• 评估检索增强生成（RAG）对基线LLM性能的影响

实验结果

研究问题

• RQ1 生成式AI在建筑行业当前的机会与挑战有哪些？
• RQ2 建筑公司如何利用自身数据构建定制化的生成式AI解决方案？
• RQ3 检索增强生成（RAG）在提升建筑任务的生成模型方面有多大效用？
• RQ4 是否可以以合同文件查询用例来端到端演示一个实用框架？

主要发现

• RAG 分别在基线 LLM 的质量、相关性和可重复性方面提升了 5.2%、9.4% 和 4.8%。
• 提出一个用于数据收集、数据集整理、定制化LLM训练、评估和部署的实用框架。
• 通过一个关于开发用于查询合同文件的生成模型的案例研究来演示该框架。
• 研究讨论了通过生成式AI提升建筑行业的生产力、质量、安全性和可持续性的机会。