Turn abandoned patents
into your own filing
into your own filing
This invention describes a computer system that automatically assigns medical codes to clinical notes. It uses natural language processing to read the text, break it into parts, and match words to medical concepts stored in a structured database. These concepts are then converted into characters that fill specific slots in a multi-part medical code, with each slot representing a different aspect of a diagnosis or procedure, and the final code is shown to a user.
Why it matters: Filed before the widespread adoption of large language models (LLMs). LLMs are now significantly better at understanding complex narrative text and mapping it to structured data, making the core NLP and semantic mapping tasks described in the claims much more feasible and accurate than in 2018.
AI gives you a few directions you could take this. Pick one, and we check whether your version is different enough to patent, then write the filing.
Reinvent this with AI
