IPRally logo

Frequently asked questions

A quick guide to the IPRally way


Q: What’s the point of IPRally in a nutshell?

A: We want to harness the vast amounts of human patent intelligence stored in public databases to serve the whole IPR field. Put simply, to build a virtual patent professional learning from real-world professionals with the latest machine learning technologies.

Q: What do you mean by human patent intelligence and real-world patent professionals?

A: Each year, thousands of patent attorneys use millions of hours for defining inventions in natural language (i.e. drafting patent applications). Each year, thousands of patent examiners in e.g. the USPTO and EPO spend millions of hours for examining the outputs of patent attorneys (i.e. finding novelty bars for the patent applications). In this process, an enormous amount of data is formed that we can learn from to assist both in defining and examining upcoming inventions.

Q: How do you differ from other AI-based or so-called semantic patent searches?

A: To our knowledge, our search is the only one that utilises real patent examination data to train the AI to find most relevant results. In fact, "utilise" is too mild a word, since the search is heavily based on this data. In addition to that, we use a technical graph-based approach, which reflects “patent attorney thinking”, allows for detail-level information handling and is efficient for neural networks to process. Our search UI is also very different from all existing ones, bringing a whole new dimension to the search, i.e. technical relations between features.

Q: How does IPRally differ from traditional keyword-based searches?

A: Keyword searches are excellent when you know beforehand what you are looking for or have the expertise and time to make complex search strategies with synonyms and Boolean logic and so on. Plus the time to go through hundreds of documents manually. We want to give less weight to exact keywords and focus more on their technical relationships, that is, the core technical concept which is of interest. Understanding the synonyms and context is built-in.

Q: What is the main advantage of your approach?

A: Our AI can actually learn the logic of patenting. By logic we mean the core concepts of novelty and inventive step. In addition to that, we can really take into account very detailed technical information of patents, which is not possible in rough similarity searches, for example.

Q: What are the limits of your approach?

A: We honestly do not know yet. We only know that we have certainly not found the technical limits yet and that no search product can ever produce only 100% relevant hits. One fundamental limitation is of course the office action data we use: even human-made novelty evaluations sometimes go wrong. However, if some publication is in every case likely to come up during prosecution as a novelty bar, wouldn't it be a good search hit anyway?

Q: How will the user benefit from all that?

A: The user will be presented with technically more relevant search hits and is able to make quicker and better IPR decisions, be it in protecting own inventions or coping with competitors' patents. We are also working on summarizing and visualizing the key content of the relevant hits, reducing the manual workload even further.

Q: Which kinds of companies and users can use the product?

A: For some companies, immaterial property is their key asset. For some others, patents are just one of the inevitable boring things that need to be taken care of in order to stay in the competition. We want to serve them all, bringing not only a productivity boost but also a pinch of joy to the traditionally tedious IPR work. Our design prociple from day one has been to keep the product as simple as possible so that an every engineer or researcher, whoever develops or innovates, can use it, yet powerful enough for patent professionals to achieve their goals quicker.

Q: How are you going to improve the product in the future?

A: The most active development areas in our approach currently are accurate graphification of the patent documents, domain-specific embedding of patent terminology and tuning the learning capability of neural network algorithms to the maximum. In all these areas, we have had several breakthroughs during the past months and have a lot of development ideas for the future. We will also constantly be adding new patent data and new and higher-quality training data. In addition, there are quite a few related product ideas that just wait to see the daylight. And last but not least, we will listen to our users wishes and implement features that serve as many customers as possible.

Q: You speak quite openly about your technology. Why's that?

A: There is quite a lot of hype around AI these days. We feel and know that our approach is in the very heart of machine learning and AI is not just a buzzword. Solving a difficult problem in a complex domain with real-world data is something that inspires us and attracts a lot of interest around. We also want to make clear that the machine learning and NLP technology is moving fast and the journey has just begun. The real transformation of the way patents are being made, found and evaluated is still to be seen.

Q: How do you spell "IPRally" and where does the name come from?

A: We like to say I-P-Rally. But we do not mind if you call us your IPR ally, since that's what we really want to be. Rally stands both for speed and change. And speed of change too. Things that people do not typically associate with the patent process but we see inevitable.

Curious to hear more about our solution?

Is your organization willing to be in the IPR frontline? Get in touch to get a demo or take a sneak peek of the future of patent AI as we see it.

I would like to