Theoretical framework for risk identification and assessment in infrastructure projects through AI-knowledge retrieval

Robust risk identification and assessment strategies are required to reduce the likelihood of failures, delays, and cost overruns in today's complex infrastructure projects. The inability to respond to changing risks and the delay in identifying and assessing risks are both caused by the reliance on static methods commonly used in traditional methods of knowledge retrieval and risk identification and assessment. This study lays out a theoretical framework for better risk identification and assessment through the use of an AI-powered knowledge retrieval. A variety of unstructured data sources, such as contract documents, risk logs, site inspection reports, and emails, are automatically analysed by the framework using AI algorithms. By enhancing efficiency and providing project team members with anticipated knowledge, this framework promotes robustness in infrastructure projects and allows for preventive decision-making. This framework also improves infrastructure projects' ability to handle risk by laying the groundwork for AI integration into risk identification and assessment, filling in holes in current techniques.