The circular economy (CE) paradigm has recently gained increasing attention in both academic and policy circles. The existing literature has stressed that the transition to the CE paradigm implies innovation that aims to change consumption and production behaviors and technologies. Empirical studies have focused on the drivers and effects of the adoption and generation of CE innovations, based on survey and patent data, respectively. 

However, identifying and tracking CE innovations through patents has been challenging due to the lack of a domain-specific classification system. Existing methods are often insufficient to capture the diversity and complexity of CE technologies. 

This paper introduces a replicable methodology for identifying and analyzing CE patents, combining large language models (LLMs), a fine-tuned transformer classifier, and unsupervised topic modeling techniques. Applying this approach to European patent data uncovered sectoral and geographical patterns in CE innovation, highlighting key technological trends aligned with CE principles. 

The findings point to widespread and growing engagement with circular strategies, particularly reuse and recycling. The study provides a flexible tool for CE mapping and offers actionable insights for researchers, policymakers, and practitioners interested in innovation-led sustainability transitions.