Generative AI, guided by inventive heuristics, can systematically and rapidly generate hundreds of ideas for engineering inventive design problems. This paper examines the reliability and effectiveness of AI-powered “idea funnelling,” a process that generates, evaluates, filters, and synthesizes raw ideas into feasible solution concepts. Key challenges include the consistency and objectivity of AI-driven evaluations, the robustness of concept generation, and the collaboration of multiple AI chatbots such as ChatGPT and Gemini. The study explores the integration of human expertise in hybrid problem-solving teams to improve feasibility, contextual relevance, and innovation quality. Through comparative experiments, it provides insights to improve the reliability of AI-driven concept creation and the performance of hybrid AI-human teams in solving complex engineering design problems.

Nowadays, firms are constantly looking for methodological approaches that help them to decrease the time needed for the innovation process. Among these approaches, it is worth mentioning the TRIZ-based frameworks such as the Inventive Design Methodology (IDM), where the Problem Graph method is used to formulate a problem. However, the application of IDM is time-consuming due to the construction of a complete map to clarify a problem situation. Therefore, the Inverse Problem Graph (IPG) method has been introduced within the IDM framework to enhance its agility. Nevertheless, the manual gathering of essential information, including parameters and concepts, requires effort and time. This paper integrates the neural network doc2vec and machine learning algorithms as Artificial Intelligence methods into a graphical method inspired by the IPG process. This integration can facilitate and accelerate the development of inventive solutions by extracting parameters and concepts in the inventive design process. The method has been applied to develop a new lattice structure solution in the material field.