To address the complexity of the knowledge system amassed during the historical assembly of wind turbine products, which poses challenges in processing and leveraging this knowledge for designing new assembly processes, a method that integrates geometric and process semantics for reusing wind turbine assembly processes was developed. Firstly, an assembly process information model (knowledge graph-based wind turbine, KG-WT) was proposed, provided a unified and standardized representation of geometric and process semantics in the assembly process. Subsequently, an extraction method for geometric semantics from glTF models and process semantics from assembly process documents was introduced. This method extracted geometric and process semantic elements, mapped them to entities in the knowledge graph data layer. Finally, a graph matching neural network was employed to match the assembly body or unit to be designed with the historical assembly knowledge base, thereby retrieving reusable similar assembly process items. The research demonstrated the method’s effectiveness by reusing historical assembly knowledge in the design of the inner gear ring and connector assembly processes for wind turbine nacelles. The results indicate that the proposed method can provide a theoretical foundation for enhancing the efficiency and accuracy of assembly process design.