Helsinki, September 6, 2022
IPRally Technologies, the AI patent research and intelligence company, today announces the launch of an AI-based custom patent classifier. With the launch, IPRally adds additional strategic capabilities to their product, suitable for projects like portfolio segmentation, benchmarking and competitive intelligence.
Based on the same technology as IPRally's patent search engine, the classifier uses graph neural networks (GNNs) to classify patent data according to customer-specific categories. It provides immediate insights by letting organizations combine their accumulated intelligence with the tested and proven power of IPRally's AI. The classifier can be set up, calibrated and applied by the end-user in minutes, and does not require large data sets to train.
“Companies are spending disproportionate amounts of resources on cleaning, categorizing and making sense of patent information. With the launch of IPRally’s classifier, we can rely on AI for this. And the good thing is that the whole organization can benefit from it. Also non-patent experts will be able to search using their own terminology, without being turned off by complex search methods like boolean. The hundreds of hours of manual data processing that has been spent in landscaping or benchmarking projects can now be spent elsewhere”, said Andreas Cehlinder, CCO at IPRally.
“The graph neural network technology has proven to be excellent for patent research. Now we use the same technology to classify data, not in a general way but trained with the customers’ historical or project-specific data. The classifier allows you to look at the patent space through your own lens, in the way that you are used to and that makes sense in your context and for your organization”, said Sakari Arvela, CEO and Co-founder at IPRally.
“The last year of beta-testing of IPRally’s custom classifier has proven that it works very well also with a small amount of internal training data. This opens many possibilities to combine internal and public data with a high level of automatization in our patent risk management, innovation and R&D processes. We just carried out a benchmark study and concluded that none of the traditional providers have anything near the AI-capabilities of IPRally”, said Ville Lähteinen, Patent portfolio manager at KONE, who has beta-tested the custom classifier.
IPRally Technologies is a Finnish software company founded in 2018, with the long-term goal of making technical knowledge universally accessible and usable. IPRally provides explainable AI for patent research and intelligence via an intuitive web platform, enabling intellectual property and R&D professionals to spend less resources on admin and make better decisions. The services are utilized by technology corporations, patent law firms, academic institutions and public patent offices.
Sakari Arvela, CEO and Co-founder
Andreas Cehlinder. CCO,
Download product sheet
Register for the introduction webinar
(To be broadcasted on September 29, 14:00 CET and 18:00 CET)
Is your organization willing to be in the IPR frontline? Get in touch to book a demo or take a sneak peek of the future of patent AI as we see it.