Driven by the dual forces of digital transformation and intelligent education, university libraries are transitioning from traditional document storage centers to smart service hubs. This paper focuses on data-driven theory and AI technology applications, integrating the characteristics of university library service scenarios to construct a closed-loop smart service model of "data collection-intelligent analysis-precise service-feedback optimization." By analyzing current pain points in university libraries regarding resource integration, service responsiveness, and user demand matching, it explores three dimensions: intelligent resource restructuring, precise service delivery, and smart management upgrades. Specific implementation pathways are proposed by integrating big data analytics, machine learning, and natural language processing technologies. The research provides theoretical references and practical insights for university libraries to overcome service bottlenecks, enhance user experience, and strengthen educational support functions.
Keywords: Data driven, AI empowered, university libraries, intelligent services, service models

The transportation model is a special form of the Linear Programming model. This model deals with transporting goods from sources (supply centers) to destinations (demand centers). A balance between the demand requirements of destinations and the supply quantities of sources must be ensured. The aim of the transportation model is to determine the amount of goods to be transported from each source to each destination such that the total transportation cost is minimized; in other words, to optimize transportation costs. Transportation models are widely used in real life. Given that these problems may contain numerous variables and constraints, it is important to solve them accurately and rapidly. With the rapid development of computer software, various package programs have been introduced. In this study, information regarding transportation models and solution methods is provided. Subsequently, a transportation model was constructed using a dataset compiled from information available on the Turkish Hard Coal Enterprise (TTK) website. This model was solved using Python, R, and Excel, and the results were compared to provide recommendations.
Keywords: Linear programming, Transportation model, Optimization, Python, R