Clarifying the path to patent intelligence automation

AI is transforming the world of patent intelligence—but with transformation comes confusion. In this article, Sakari Arvela, CEO and Co-Founder of IPRally, shares his perspective on how to bring clarity to the discussion around patent intelligence automation. By distinguishing between retrieval and analysis AI, he outlines a practical path toward trust, transparency, and meaningful adoption of AI in the IP industry.

In the last months, I've spoken at various industry events about patent intelligence automation. After some self-reflection, I've learned that I need to recalibrate how I talk about the topic and patent AI in general.

At an IP law firm event, with almost 100 patent attorneys and corporate IP managers present, I asked how many of them had used ChatGPT Deep Research or other similar agentic generative AI products. I saw only one or two hands raised in the audience, even though such products had been there for six months or so at that point. Discussions at drinks revealed that many were not using even simpler AI products.

Six months feels like an eternity when you are deep in the AI space yourself and when your job is to adopt new technologies fast in the product you are building, and in your own work, too. Make no mistake, I don't blame the audience for not having used them. I just realized that I'm in a bubble and need to take that better into account.

On the other hand, at a few other events, even those focused on IP information, I've come to realize that there is a lot of confusion about AI. It varies from healthy skepticism to full swing overuse of LLMs for jobs that are not within their capabilities. Even many software vendors stir it either with overpromises or problem-centric approaches, sometimes even false information. I can understand someone new to it may be confused.

Little first-hand experience combined with incoherent information does not help in building trust in and adopting new technologies. 

At the end of the day only getting a job done is what matters. To get there, there needs to be both education on AI fundamentals, as well as transparent solutions whose value and readiness level in action can be easily tested.

For advanced AI-based patent searching and analysis, one needs two types of AIs: document retrieval AI and content analysis AI. The former finds relevant sources of information, the latter processes it into digestible form. In automated systems, these are done linearly or in a more iterative or agentic manner, but both parts are still present.

The dominant technology for retrieval AI are so-called embeddings. Basically converting texts, images or sound into long lists of numbers, i.e. vectors using an AI model trained for this purpose. Similar content results in close-by vectors. Vectors are mathematically easy to compare. Embeddings are in a way fingerprints of the original long documents. Good embeddings tailored for the patent domain lead to accurate patent search results.

LLMs have shown their power in content analysis, and the progress in the last year has been rapid. When used for information extraction from individual documents, the risk of hallucinations is also low. But each model has its own character and performance, and complex and nuanced IP tasks, like analyzing infringement, are still imperfect. Also high-level system prompts and specific task prompts matter a lot.

Thus, the remaining key questions are: What information does the retrieval AI have access to? What is its hit rate and noise rate? How reliable is the LLM in the task in question?

We see excellent progress over time with retrieval AI, meaning that the risk of missing relevant documents is going down. Regarding content analysis, on our platform we see over 1 million patents being analyzed in-depth each month, with LLM based patent review features. The users keep coming back, which is the best proof of value.

While almost no one disputes that AI will play a big role in IP in the future, one still hears a lot of talk about the dangers and risks of AI, without showing solutions on how to overcome those. When the above split between retrieval and analysis is understood, it is easier to address risks, envision solutions and form an idea of whether a solution would be fit for a purpose.

We believe the most effective approach is to offer new AI in digestible chunks, providing so-called AI Assistants around our retrieval AI. This allows the users to test not only the search part, but also the AI Assistant in isolation and build trust in future full automation that leverages the same technology.

As an example, one can optimize novel search queries from diverse invention materials, make prior art searches, automatically create meaningful prior art review prompts, and finally use AI analysis and filtering to narrow down the results to just a few of the highest relevance, and use AI reasoning to double check the analysis.

This way, the paradigm shifts from a vague "is AI good enough for X" to more tangible "by improving this part of the pipeline, I would be able to do X with a confidence level Y". 

As the pipeline gets more mature, proving the value of AI gets easier. Complexity gives way to clarity, and trust grows, moving us closer to the reality of patent intelligence automation.

If you found this blog post insightful, there's more to come on related topics. I look forward to seeing you at IP Service World on Monday 24th November, during the 11:20 session for my presentation, "Automated patent search: Today and beyond". Don't miss the opportunity to dive deeper into how AI is automating patent workflows.