All Collections
Usage instructions
Quick guide for novelty searching based on (draft) Claims / Descriptions
Quick guide for novelty searching based on (draft) Claims / Descriptions

How to carry out a novelty search based on patent texts efficiently

Sakari Arvela avatar
Written by Sakari Arvela
Updated over a week ago

This guide covers the basic steps of carrying out a novelty search for an invention, when you have Claims of a patent application available - either as draft versions or as filed.

Professionally drafted Claims are an optimal input for IPRally, since the graph AI is trained with millions of professionally drafted claims.

In addition, you you may have the draft description or description as filed available, and that can be used to further improve the search is some cases.

The guide is specifically intended for

  • Examiners in Patent Patent and Trademark Offices (search reports and office actions)

  • Patent Attorneys and Patent Managers to support the drafting process (pre-filing "claim scope sanity checks")

Four steps of an efficient novelty search

The basic steps of a novelty search are:

1. Enter the whole Claims set to the Free text search field

2. Review the search results

3. Mark the best findings as Favorites

4. Re-run the search using Zoom to Favorites

Additionally you can (but not covered in this guide):

The four steps are described in more detail and with screenshots below.

1. Enter the whole Claims set to the Free text search field and press SEARCH PATENTS

Search with the whole set of Claims first

Statistically, the whole Claims set alone is proven to provide almost as accurate search results as using the whole patent text, and is usually a sufficient input for a high-quality search.

Improve by adding key parts of the description

If the claims are very broad or vague, it may be beneficial to enter ALSO key parts of the description AFTER the claims in the text box. The key part can the part that describes embodiments according to the claims in more concrete terms and with more specific examples, or the part that gives more context or technical field information for the invention (if not evident from the claims).

Try with a single independent claim, too

It may also be beneficial to run a search with ONLY the broadest independent claim. This is because then the AI will focus only on the claimed features, without paying so much emphasis on broader context or embodiments, and can often find accidental prior art from e.g. distant patent classes.

2. Review the search results

IPRally provides many functionalities for processing the search results both inside the platform and by exporting data into another review platform.

Patent Examiners using EPOQUE Net

IPRally supports (PTO accounts only) exporting to XFT format, which is directly importable to EPOQUE Net. You will find the export option in the ACTIONS menu:

Note: Once you have reviewed the results in EPOQUE Net, or find relevant hits with classical searches, it is beneficial to use the closest prior art again in IPRally to find more relevant hits using AI (see steps 3 and 4: Zoom to Favorites).

Initial review inside the platform

The tool is self-explanatory when it comes to result analysis.

The result list and expanding the bibliographic data:

Showing image mosaics:

Smart image viewer by clicking the mosaic images:

AI-based relevant passage highlighting:

3. Mark the best findings as Favorites

If the closest prior art appears among the results of IPRally, you can click the heart symbol to make the hit a Favorite.

If, for some reason (yes, that happens 😊), the closest prior art is not among the hits of IPRally, you can manually enter the publication in the Favorites tab:

We recommend using 1-5 best hits as favorites. Provided that they do not contain a lot of contradictory information, carrying out the next step (step 4) usually improves the quality of the search results.

4. Re-run the search using Zoom to Favorites

Toggling Zoom to Favorites on and pressing SEARCH PATENTS again, will utilize the Favorites information (together with the original graph) to find more relevant hits.

Note: you can track the new hits in the list using the VIEWED status of the hits (blue: unviewed / white: viewed):

The viewed status changes also automatically, if you open the full document view.

Once you have re-run the search, get back to the analysis step 2 and repeat iteratively, if needed.

Did this answer your question?