Computer Algorithm Optimization of BIM and Reinforcement Learning in Complex Building Structure Construction Process Optimization Under Big Data Environment

In the big data environment, the combination of Building Information Modeling (BIM) and reinforcement learning provides new ideas for optimizing the construction process of complex building structures. The current construction is facing problems such as unreasonable resource allocation, poor process connection, and low construction efficiency, which urgently require effective optimization methods. This article aims to use BIM technology to establish a digital model of the construction process, while introducing reinforcement learning algorithms to achieve intelligent optimization of the construction process. The article first establishes a detailed building model and construction process dataset through BIM technology; secondly, the article designs a reinforcement learning environment, defines state, action, and reward functions, and uses the Deep Q-Network (DQN) algorithm for training; next, the article simulates different construction strategies and adjusts the construction process in real time to improve efficiency. The experimental results show that the optimized construction process has improved construction efficiency by 25% compared to traditional methods, increased resource utilization by 15%, and reduced costs by 20%. The combination of BIM and reinforcement learning provides an effective solution for optimizing the construction process of complex building structures, with broad application prospects.