Abstract: Concept sketching, as a higher order human visual cognitive activity, is an important tool to assist designers in recording, ideating, creating, and evaluating ideas and has a positive impact on the generation of innovative concepts. In order to simulate this higher order visual cognitive behaviors of designers and to achieve intelligent assistance in creative sketching, a deep learning-based design integrated framework for intelligent generation of product concept sketches is proposed, which includes two core modules: an end-to-end sketch design GAN (Sketch2Render-GAN) and a sketch-neural style transfer network (Sketch-NST). The first module implements sketch generation and rendering, while the second performs sketch style features transformation. The hand drill and bicycle helmet were used as design objects respectively, and experimental results show that the proposed approach framework can quickly obtain many innovative concept sketches and implement automatic sketch rendering and style transformation. The findings also show that the approach framework helps designers to break through design solidification at the visual perception level and increase design efficiency. Furthermore, a smart-sketch design generator (S-SDG_v0.1) was developed to facilitate human-machine design collaboration between designers and AI models, which effectively reduces the threshold of designers to apply intelligent algorithms to assist design.