Various ideation methods, such as morphological analysis and design-by-analogy, have been developed to aid creative problem-solving and innovation. Among them, the Theory of Inventive Problem Solving (TRIZ) stands out as one of the best-known methods. However, the complexity of TRIZ and its reliance on users’ knowledge, experience, and reasoning capabilities limit its practicality. To address this, we introduce AutoTRIZ, an artificial ideation system that integrates Large Language Models (LLMs) to automate and enhance the TRIZ methodology. By leveraging LLMs’ vast pre-trained knowledge and advanced reasoning capabilities, AutoTRIZ offers a novel, generative, and interpretable approach to engineering innovation. AutoTRIZ takes a problem statement from the user as its initial input, automatically conduct the TRIZ reasoning process and generates a structured solution report. We demonstrate and evaluate the effectiveness of AutoTRIZ through comparative experiments with textbook cases and a real-world application in the design of a Battery Thermal Management System (BTMS). Moreover, the proposed LLM-based framework holds the potential for extension to automate other knowledge-based ideation methods, such as SCAMPER, Design Heuristics, and Design-by-Analogy, paving the way for a new era of AI-driven innovation tools.

In traditional innovation practices, concept and IP generation are often iteratively integrated. Both processes demand an intricate understanding of advanced technical domain knowledge. Existing large language models (LLMs), while possessing massive pre-trained knowledge, often fall short in the innovative concept generation due to a lack of specialized knowledge necessary for the generation. To bridge this critical gap, we propose a novel knowledge finetuning (KFT) framework to endow LLM-based AI with the ability to autonomously mine, understand, and apply domain-specific knowledge and concepts for invention generation, i.e., concept and patent generation together. Our proposed PatentGPT integrates knowledge injection pre-training (KPT), domain-specific supervised finetuning (SFT), and reinforcement learning from human feedback (RLHF). Extensive evaluation shows that PatentGPT significantly outperforms the state-of-the-art models on patent-related benchmark tests. Our method not only provides new insights into data-driven innovation but also paves a new path to fine-tune LLMs for applications in the context of technology. We also discuss the managerial and policy implications of AI-generating inventions in the future.

Divergent thinking is a process in design by exploring multiple possible solutions, is crucial in the early stages of design to break fixation and expand the design ideation. Design-by-Analogy promotes divergent thinking, by studying solutions have solved similar problems and using this knowledge to make inferences and solve problems in new and unfamiliar situations. Bio-inspired design (BID) is a form of design by analogy and its knowledge provides diverse sources for analogy, making BID knowledge as a potential source for divergent thinking. Existing BID database has focused on collecting BID cases and facilitating the retrieval of biological knowledge. Despite its success, applying BID knowledge into divergent thinking still encounters challenge, as the association between source domain and target domain are always limited within a single case. In this work, a novel approach is proposed to support divergent thinking from three subsequent phases: encoding, retrieval and mapping. Specifically, biological knowledge is encoded in a triple form by employing a large language model (LLM) to extract key information from a well-known BID knowledge base. The created triples are implemented in a semantic network to facilitate bidirectional retrieval modes: problem-driven and solution-driven, as well as mapping for divergent thinking. The mapping algorithm calculates the semantic similarity between nodes in the semantic network based on their attributes in three progressive steps by following the paradigm of divergent thinking. The proposed approach is implemented as tool called AskNatureNet,1 which supports divergent thinking by retrieving and mapping knowledge in a visualized interactive semantic network. An ideation case study on evaluating the effectiveness of AskNatureNet shows that our tool is capable of supporting divergent thinking efficiently.

Abstract Knowledge proximity refers to the strength of association between any two entities in a structural form that embodies certain aspects of a knowledge base. In this work, we operationalize knowledge proximity within the context of the US Patent Database (knowledge base) using a knowledge graph (structural form) named “PatNet” built using patent metadata, including citations, inventors, assignees, and domain classifications. We train various graph embedding models using PatNet to obtain the embeddings of entities and relations. The cosine similarity between the corresponding (or transformed) embeddings of entities denotes the knowledge proximity between these. We compare the embedding models in terms of their performances in predicting target entities and explaining domain expansion profiles of inventors and assignees. We then apply the embeddings of the best‐preferred model to associate homogeneous (e.g., patent–patent) and heterogeneous (e.g., inventor–assignee) pairs of entities.

Recent works in the information science literature have presented cases of using patent databases and patent classification information to construct network maps of technology fields, which aim to aid in competitive intelligence analysis and innovation decision making. Constructing such a patent network requires a proper measure of the distance between different classes of patents in the patent classification systems. Despite the existence of various distance measures in the literature, it is unclear how to consistently assess and compare them, and which ones to select for constructing patent technology network maps. This ambiguity has limited the development and applications of such technology maps. Herein, we propose to compare alternative distance measures and identify the superior ones by analyzing the differences and similarities in the structural properties of resulting patent network maps. Using United States patent data from 1976 to 2006 and the International Patent Classification (IPC) system, we compare 12 representative distance measures, which quantify interfield knowledge base proximity, field‐crossing diversification likelihood or frequency of innovation agents, and co‐occurrences of patent classes in the same patents. Our comparative analyses suggest the patent technology network maps based on normalized coreference and inventor diversification likelihood measures are the best representatives.

In the information science literature, recent studies have used patent databases and patent classification information to construct network maps of patent technology classes. In such a patent technology map, almost all pairs of technology classes are connected, whereas most of the connections between them are extremely weak. This observation suggests the possibility of filtering the patent network map by removing weak links. However, removing links may reduce the explanatory power of the network on inventor or organization diversification. The network links may explain the patent portfolio diversification paths of inventors and inventing organizations. We measure the diversification explanatory power of the patent network map, and present a method to objectively choose an optimal tradeoff between explanatory power and removing weak links. We show that this method can remove a degree of arbitrariness compared with previous filtering methods based on arbitrary thresholds, and also identify previous filtering methods that created filters outside the optimal tradeoff. The filtered map aims to aid in network visualization analyses of the technological diversification of inventors, organizations, and other innovation agents, and potential foresight analysis. Such applications to a prolific inventor (Leonard Forbes) and company (Google) are demonstrated.