In short
A doctoral thesis on retrieving the patents that answer an inventive problem, and on running ARIZ with language models to generate concepts anchored in those patents. Defended in December 2025.
- Research question
Can specialised patent models and an LLM-orchestrated ARIZ produce concepts that experts judge relevant and novel?
- Results to date
Public patent embedding models and benchmarks (PatenTEB, DAPFAM); the PatentSpark demonstrator; the ARIZ Copilot demonstrator derived from the thesis.