Supporting Vendor





IPRally offers a completely new way of searching patents: Knowledge graphs and supervised deep learning AI.

All features of +80M prior art specifications and claims are automatically extracted into a graph format and the AI trained to compare an input graph with the pre-converted prior art graphs. The deep learning AI is trained with real Patent Examiner citations to find the most relevant pieces of prior art. You can focus on the core of the technology of interest and let the AI do the tedious feature matching with deep level understanding of technology.

An intelligent search engine that thinks like a patent professional is born.


Trial available

Seat-based entry level pricing starting form 5 k€/year

Enterprise IP and R&D plans available.

Included Data

80 million full-text native English and machine translated documents from 25+ major jurisdictions.

All documents in text format and split into feature charts (graphs).


Form based

Methods Used

Graph-based supervised Machine Learning search. Each document is converted into graph format that separates the technology’s features. The search query is also in graph format that can be build from scratch, using a publication number or copy-based free text or claim text.

The Neural Network is trained using millions of Patent Examiner citations to mimic the professional search flow.

On top of the deep learning search, a set of traditional boolean filters are available.  

Iterative search: hits ranked by the user can be used to improve the results.

Value Added Data

Each specification, claim and claim set converted into graph format, i.e. its features automatically extracted.

API Available:


API Link:
Analysis Included

Automatic feature extraction.

AI based deep level feature matching: Most relevant passages of the results highlighted (built in synonym understanding and technical machine understanding).

Traditional keyword highlighting.

Search result statistics: coming

Data Export

Export available in XLS

File Support
File 2:
File 3:
File 4:
File 5:
No items found.

Sign Up for the Newsletter

Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.

©Copyright ML4Patents | Powered By Patinformatics