This guide covers the basic steps of carrying out a Free-Text search for an invention, when you have an Invention Disclosure/Project Scope Description; Image or any other Technical Description. It will also cover what is not possible to do with Free-Text.

English is the native language of IPRally and optimal as input. German, French, Spanish, Chinese, Japanese, Italian, Dutch, Danish, Finnish and Swedish are supported via machine translation (with a maximum 5000 characters). The translation happens inside IPRally, making it secure.

Free-Text Search takes your input (see above) and curates a Knowledge Graph for searching. The results are shown by ranking (using the AI Score)

Free-Text Search Is Not a Generative Ai Search - meaning, you must describe the object(s) and features you are searching for, and NOT a 'ChatGPT' style prompt expecting the Ai engine to curate a more robust description (with potential hallucination).

If you have AI Assistants enabled, please review our article on the Refine button

The maximum score is 100 and it describes the overall graph similarity. The score is calculated as a vector distance between the query graph and prior art graph after AI processing of the graphs. With short (e.g. claim) query graphs, no scores higher than 60 are usually reached as there are many irrelevant features producing noise in the prior art graphs.

When using the Free-Text tool, please use the below insights to drive your searches:

Good: "The invention is a vehicle-to-vehicle (V2V) communication system for autonomous vehicles, using both wireless technologies (WiFi, LTE, 5G) and RFID. It features a dual-module framework that dynamically switches between high-bandwidth and low-bandwidth communication modes to optimize data transmission. This system enhances safety, efficiency, and passenger interaction in autonomous vehicles."

Poor: "A V2V system for autonomous vehicles using wireless tech and RFID to enhance safety."

Why? The good example has technical details around the objects, and how they interact to deliver the function being searched. There are functional relationships described, and the language is descriptive vs. prompting. The poor example is too brief, lacking functional relationships, and doesn't describe the 'novelty' well enough. The results will be too 'vague' compared to the good input.

Please...

It will greatly diminish the ability for our Graph-Ai to understand the subject, and therefor provide lower-quality results.

Example of a poor 'Prompt' inspired search input:

"A V2V system for autonomous vehicles using wireless tech (WiFi, LTE, 5G) and RFID to enhance safety. Focus on highlighting the dual-module communication approach that integrates high-bandwidth wireless technologies for real-time data and low-bandwidth RFID for stable communication. Emphasize how the system dynamically switches between these modes to optimize performance, targeting improvements in safety, efficiency, and passenger experience in autonomous vehicles."

Why? Our Graph Ai is not a LLM (As all GPT's are), but rather a Knowledge Graph Neural Network. This requires the input to be similar to the patent documents being searched, and does not operate as an LLM would in 'filling in the blanks'

* (Curated using ChatGPT 4.o - resemblance to any prior art is by chance)

Note 1:

Smart search was launched on December 16, 2025 and replaced Image search as a more powerful and flexible option for image-based searches (and more).

Note 2:

AI Assistants need to be enabled in order to use Smart Search.

Smart Search allows starting a patent search using any combination of

The documents and image files can contain content in text or images, and have any technically meaningful content: technical drawings, photos, formulas, flow charts, tables, etc. The content can be in any language.

Smart search makes a deep analysis of all the content given to define a search target, and performs an optimized patent search for it.

Smart search

Smart search uses Generative AI for steps 1 and 2, and IPRally's proprietary search AI for step 3. AI Assistants need to be enabled in order to use Smart Search.

Smart search is use case agnostic and suitable for searching with e.g.

In general, any technical material in the above-mentioned formats can serve as a starting point. Note that you can use Smart Search also with text-only inputs. The format really doesn't matter!

The ideal use cases include

The image shows a combination of a Word document, Powerpoint document and two image files, without any additional text description (which can be added).

Pressing the search button makes the AI start processing the materials for defining the essence of the technology and defining the target of the search.

Note:

Studying the materials can take even several minutes, if the content is complex and heavy in image format data. But good is worth waiting for!

We present the search query in intuitive and editable "mock claim" format

At this point, it is easy refocus the search by removing or adding claims or features. All claims and features will be considered by the search. Therefore, for focused searches, keep only the most relevant claims and features.

Clicking a file thumbnail image brings a screen with AI's interpretation of the content of the file:

Flowcharts are described in flowchart description language (Mermaid) for accurate information representation:

Images are described in plain language:

The results are reviewable using IPRally's standard and AI assisted review features: