Learners confront the issue of navigating an enormous quantity of resources in the developing field of online education, which has been exacerbated by the COVID-19 pandemic. To solve this, our research proposes a novel Learner Path Planning (LPP) model that integrates blockchain and machine learning technologies to maximize the online learning experience. This model employs the ant colony optimization technique, which has been upgraded with blockchain for enhanced security and machine learning for intelligent path planning, to provide a more personalized and efficient learning experience. Our approach determines the extent of concept realization and interaction by examining the interaction degrees of knowledge points, establishing heuristic information and initial pheromone levels for the optimization process. This technique not only optimizes teaching duration based on instructional efficacy, but it also adapts dynamically to individual learner needs. Our empirical data reveal that goal success rates improve significantly across all learner levels. For example, elementary students in 2021 had the highest goal achievement rate of 0.5896. In 2019, intermediate and advanced learners attained rates of 0.7726 and 0.9058, with a significant association between course similarity and target achievement. Blockchain integration ensures secure and transparent processing of educational data, while machine learning algorithms successfully personalize learning routes to meet the various demands of learners. This study not only assists learners in effectively identifying suitable resources, but it also provides useful insights for instructors in improving online teaching approaches. The model's adaptability and scalability make it particularly applicable in the context of the COVID-19 pandemic's rapid developments and problems in the education sector.