.................................

AI integration into university career planning courses has emerged as a crucial step toward individualized and successful student development in the rapidly changing higher education landscape. This project investigates using AI-driven assessment models to optimize teaching results in career planning at the university level. The efficacy of several teaching strategies was evaluated using eight major criteria, such as engagement, AI-driven feedback, career target clarity, and flexibility to meet the requirements of individual students. Data was gathered from a variety of instructional options, including AI-enhanced virtual simulations and conventional lectures. These choices were ranked and evaluated using neutrosophic set. The single valued neutrosophic set (SVNS) is used to solve uncertainty information. We combine Probabilistic with SVNS to deal with uncertainty information. The findings show that AIintegrated teaching models perform noticeably better than traditional approaches in terms of providing individualized career counseling, raising student happiness, and coordinating education with the needs of the labor market. The results give educators and policymakers a framework for using intelligent technology to improve the caliber and effectiveness of career planning education.