Research on full life cycle management in water conservancy engineering is currently limited, resulting in issues like improper project siting, high construction costs, and insufficient risk management capabilities. To address these challenges, this paper proposes an innovative management approach using the K-means clustering algorithm. This method leverages the K-means algorithm's simplicity and fast convergence to cluster and analyze diverse data from different stages of water conservancy projects. It then presents these clustering results visually to assist project managers in making informed decisions. Using the K-means algorithm in the planning and design stage of water conservancy projects as an example, we demonstrate its feasibility, efficiency, and scientific rigor in managing the entire project life cycle. The research findings indicate the following: The research results show that (1) In the planning and design stage, the K-means algorithm aids in making informed decisions about engineering construction sites by clustering and analyzing relevant data. (2) The improved K-means clustering algorithm exhibits high processing efficiency and accuracy when handling various types of water conservancy project data. (3) The K-means algorithm's application can span the construction, operation, and maintenance stages. It can cluster and analyze data related to material consumption, equipment usage, construction efficiency, and quality, ensuring compliance with quality standards, cost control, and project optimization. Additionally, it can be used to cluster and analyze data akin to water conservancy projects, like historical risk factors, aiding in risk evaluation and prediction.