To realize the design process of bionic mechatronic systems, involving mapping from engineering to biology and inversion from biology to engineering, a novel design paradigm is introduced that integrates BioTRIZ with multi-factor coupling bionics. In the mapping stage from engineering to biology, BioTRIZ is employed to frame the concrete engineering issue as a general conflicting problem. The biological solution is refined by amalgamating the BioTRIZ solution derived from the contradiction matrix with biological instances. In the inversion stage of biology to engineering, a novel approach is proposed for constructing a bionic multi-factor coupling model, drawing inspiration from the establishment of biological multi-factor coupling model. This allows for a seamless correspondence between biological elements, such as morphology and behavior, and their respective engineering counterparts, including structure and algorithms. This correspondence ultimately achieves the engineering conceptual model that is rooted in biological principles. The practical application of this methodology is exemplified through a multi-biometric fusion bionic active vision system, underscoring its feasibility and efficacy.

Cross-Domain Few-Shot Learning (CD-FSL) aims to empower machines with the capability to rapidly acquire new concepts across domains using an extremely limited number of training samples from the target domain. This ability hinges on the model’s capacity to extract and transfer generalizable knowledge from a source training set. Studies have indicated that the similarity between source and target-data distributions, as well as the difficulty of target tasks, determine the classification performance of the model. However, the current lack of quantitative metrics hampers researchers’ ability to devise appropriate learning strategies, leading to a fragmented understanding of the field. To address this issue, we propose quantitative metrics of domain distance and target difficulty, which allow us to categorize target tasks into three regions on a two-dimensional plane: near-domain tasks, far-domain low-difficulty tasks, and far-domain high-difficulty tasks. For datasets in different regions, we propose a Divide-and-Conquer Strategy (DCS) to tackle few-shot classification across various target datasets. Empirical results across 15 target datasets demonstrate the compatibility and effectiveness of our approach, improving the model performance. We conclude that the proposed metrics are reliable and the Divide-and-Conquer Strategy is effective, offering valuable insights and serving as a reference for future research on CD-FSL.