Updated Neural Net Patent Search!

We are excited to deploy NNv.2; the next iteration in Neural Net-based Patent Searches.

Starting today, users can search patents at a much higher resolution than was previously possible, at the claim and paragraph level, across the entire patent corpus. This update eliminates the need for error-prone and inefficient boolean and keyword-based search.

If you use IPDealRooms, you’ll undoubtedly notice the impact. NNv.2 is more finely tuned and returns far more relevant results requiring minimal hand-screening. Moreover, unlike most patent search systems, NNv.2 is trained on the entire patent corpus and gives cogent results across any area of technology – software, AI, robotics, biotechnology, medical devices, consumer goods and more.

This is an immensely powerful update, and we wanted to put it in your hands as soon as possible. We’re still improving runtime – the longest IPDealRooms take about an hour – set it to work in the background, go to lunch, and come back to your curated patent analysis.

It’s easier than ever – get started by inputting any patent, application, provisional, or invention disclosure into the ClearAccessIP’s platform, click on “DealRoom” and enable machine learning.

1. Create an IPDealRoom


2. Slide “on” the Enable Machine Learning Button

Screen Shot 2017-05-31 at 4.09.21 PM.png

3. Visit the IPDealRoom and select the “IP Map” button to review related technologies



4. Explore a list of the most closely related disclosures to the IPDealRoom portfolio.