Zhe Song

Background

The primary focus of my research is to develop a more efficient and reliable warehouse management system, specifically for construction materials, while incorporating risk management strategies. My work aims to improve inventory tracking accuracy, reduce operational costs, enhance decision-making processes, and mitigate potential risks that may arise during the supply chain and warehouse management processes. A key aspect of this research involves advancing large language models (LLMs) to tackle specific challenges in construction material warehouse management, such as mitigating manual data entry errors, improving material tracking efficiency, optimizing overall inventory management, and addressing supply chain risks.

What sets this research apart is the tailored application of LLMs within the construction industry, facilitating the integration of diverse data sources and enabling real-time analytics. My work contributes to pioneering the use of LLMs in this domain, providing scalable solutions that integrate risk management practices, with the potential for applicability across other industries that face similar operational and risk-related challenges.

Research opportunities

My research interests lie at the intersection of advanced technology, warehouse management systems, and risk management, with a particular focus on applying large language models (LLMs) to the construction industry. I am particularly interested in developing innovative solutions that address the challenges faced in construction material warehouse management, such as improving inventory accuracy, optimizing material tracking, reducing operational costs, and managing risks effectively throughout the supply chain.

I am also keen on exploring how LLMs can be utilized to automate manual processes, such as data entry, and integrate real-time data analytics for more informed decision-making. Additionally, I aim to understand how LLMs can help mitigate risks within the supply chain, including disruptions, financial risks, and operational inefficiencies. My research extends to creating scalable, efficient solutions that have cross-industry applicability, with a strong emphasis on enhancing operational efficiency, enabling smart, data-driven workflows, and improving risk management practices.

Through my work, I aim to bridge the gap between emerging AI technologies and real-world industrial applications, fostering innovation, efficiency, and sustainability in warehouse management and supply chain risk management.

Current activities

I am currently engaged in a comprehensive literature review focusing on the application of generative artificial intelligence (AI) and large language models (LLMs) in supply chain management and risk management within the construction industry. This research aims to explore how these advanced AI technologies can enhance various aspects of supply chain operations, including inventory management, logistics optimization, decision-making processes, and risk mitigation. By critically analyzing existing studies, I seek to identify key trends, challenges, and opportunities in leveraging generative AI and LLMs to drive innovation, efficiency, and improved risk management practices in the construction sector’s supply chain.