A context-aware KG-LLM collaborated conceptual design approach for personalized products: A case in lower limbs rehabilitation assistive devices

With the rapid increase in demand for personalized Rehabilitation Assistive Devices (RADs), significant challenges have emerged in their design processes. Particularly in practical applications, designers face challenges such as ambiguity in user requirements, inefficiencies in cross-domain knowledge sharing, and deviations of generated solutions from actual user needs. To address these issues, this paper proposes a Context-Aware Conceptual design method based on Knowledge graph (KG) and Large language models (LLM), named CACKL. Firstly, to address the high complexity involved in eliciting user requirements, user profiles are constructed by integrating multi-source data, and fine-grained “requirement-function” mappings are extracted using fine-tuned LLM, thereby reducing the cost associated with manual intervention. Secondly, a KG-LLM collaborated reasoning mechanism guided by a Chain-of-Thought (CoT) prompting approach is proposed to align structured domain knowledge with implicit semantic representations from LLM, thus enhancing the contextual relevance and practical effectiveness of concept generation, aiming to improve the efficiency of personalized conceptual design. In a practical case involving lower-limb RADs, the proposed CACKL method was evaluated regarding user requirement mining and conceptual design. Experimental results demonstrated significant advantages in the automatic generation of personalized design solutions, particularly in enhancing design efficiency and meeting user requirements, thereby validating its effectiveness in real-world applications. This study provides an innovative paradigm for the intelligent design of RADs by integrating dynamic knowledge constraints with natural language interaction.