High occupational injury and fatality rate in the construction industry is a serious global concern. Recognizing AI as a solution to enhance safety performance, this study reviews 153 papers to assess and categorize current AI applications in construction, focusing on text, visual, and audio data, while also identifying challenges and future research opportunities. Real-time monitoring, hazard detection, and information extraction are identified as key areas where AI is applied, with a notable reliance on deep neural networks, object recognition, and Natural Language Processing. The review highlights major challenges, including the need for high-quality data management, semantic feature representation, and occluded object detection. Additionally, it underscores the untapped potential of audio-based AI and the advancements possible with Large Language Models for text interpretation. The findings emphasize the need for integrated, multi-faceted AI systems and advocate for responsible AI deployment to mitigate safety risks on construction sites.

中文翻译：

---

建筑安全中的人工智能集成：基于文本、视觉和音频的应用程序的现状、挑战和未来机遇


建筑业的高职业伤害和死亡率是全球严重关注的问题。这项研究认识到人工智能是提高安全性能的解决方案，回顾了 153 篇论文，对当前建筑中的人工智能应用进行评估和分类，重点关注文本、视觉和音频数据，同时还确定了挑战和未来的研究机会。实时监控、危险检测和信息提取被认为是人工智能应用的关键领域，尤其依赖深度神经网络、对象识别和自然语言处理。该评论强调了主要挑战，包括对高质量数据管理、语义特征表示和遮挡对象检测的需求。此外，它还强调了基于音频的人工智能尚未开发的潜力以及大型语言模型在文本解释方面可能取得的进步。调查结果强调需要集成的、多方面的人工智能系统，并提倡负责任的人工智能部署，以减轻建筑工地的安全风险。