Designing tailored patent search approaches – A case study on nursing care technology

Patent searches support innovation, legal compliance, and business decisions, but are often complicated by extensive data, diverse systems and linguistic challenges. This paper presents a multi-perspective, keyword-based approach drawing on design theory to address the ‘fuzzy’ nature of complex technology fields. Using the example of Nursing Care Technology (NCT), an interdisciplinary domain lacking a specific patent classification, we develop three search strategies reflecting the perspectives of designers, users, and systems. In order to measure the effectiveness of each search perspective in identifying relevant documents, we use a Large Language Model (LLM) to assess the precision of the respective results, including their subsets and intersections. Patents identified from all three design-theory perspectives have the highest precision, suggesting that the combination of viewpoints helps to isolate core innovations. Our analysis of patent classifications and assignees also demonstrates the value of the method for exploring ‘fuzzy’ technology fields. By adapting design theory to keyword-based patent searches and using an LLM to assess the precision of tailored search results, we advance both the theory and practice of patent information retrieval. This is especially useful for ‘fuzzy’ technology fields where conventional search methods often fall short. • Introduces a design-theory, multi-perspective keyword method for patent search in fuzzy technology fields. • Demonstrates the approach on Nursing-Care Technology, an interdisciplinary domain without a dedicated IPC/CPC class. • Uses a large language model to measure and compare the precision of each strategy and their intersections. • Shows that combining all three perspectives yields the highest precision and reveals core innovations and assignees.