This study addresses the growing need for sustainable and personalized learning solutions in online education by optimizing cross-course learning paths. With the increasing volume of e-learning resources, students often struggle to select appropriate courses and learning paths that align with their individual abilities and goals. A novel cross-course learning path planning model is proposed, which integrates resources from multiple courses using modified matching functions based on Item Response Theory (IRT) and a knowledge graph. This model effectively matches learner attributes, such as abilities, learning styles, and goals, with material attributes like difficulty, types, and prerequisites. An innovative variable-length continuous representation (VLCR) and an improved differential evolution algorithm are employed to optimize the multi-attribute matching (MAM) model, enhancing learning personalization. Results from numerical experiments indicate that cross-course learning paths significantly enhance learning outcomes for a wide range of learners, with over 45% benefiting from improved matches compared to single-course paths. Additionally, 70% of learners experienced similar or better results with cross-course learning. This approach not only promotes efficient learning but also supports sustainable educational practices, preparing educators and learners to meet the challenges of a rapidly changing world.

This paper pioneers the use of the symmetrical Hybrid-RAG strategy in the ship welding process domain, addressing the problems of fragmented, unstructured knowledge storage, as well as the limitations of traditional Retrieval-Augmented Generation (RAG), particularly high retrieval noise and low accuracy when answering complex procedural queries. This study proposes an intelligent three-stage symmetric “Generate–Retrieve–Generate” framework for the ship welding process (SWP-Chat), supported by dual retrieval engines: a Neo4j knowledge graph for symbolic reasoning and a vector database for semantic retrieval. Unlike approaches that rely solely on LLM-based process planning, SWP-Chat uses the LLM to generate a logical form, then executes Cypher queries on Neo4j, enabling transparent traceability, precise entity–relation constraints, and deterministic retrieval. Meanwhile, the vector channel supplements unstructured or contextual welding information to enhance semantic coverage. To further improve efficiency, principal component analysis (PCA) was employed for vector dimensionality reduction, reducing average retrieval latency by 31% while retaining more than 95% variance. In addition, an explainable structural–confidence fusion formula integrates evidence from both engines to produce auditable and trustworthy industrial responses. Experimental evaluation demonstrates that the framework achieves an F1 score of 79.35%, greatly surpassing typical RAG systems.