Machine Learning

Why does using a Convolutional Neural Net give users better search results?

“It is the difference between knowing a tomato is a fruit and knowing that a tomato doesn’t belong in a fruit salad.”

“Patent search is more of an art than a science” is a saying in patent industry circles. There are millions of patents worldwide, and accurately searching among terabytes of unstructured natural language and drawing expert level analysis requires a degree of comprehension that existing search technologies are not able to provide. Thus, the art of the search.

There are three common methods of software-driven patent search marketed today, semantic analysis, supervised classifiers, and convolutional neural net training. ClearAccessIP believes that the convolutional neural net is the most powerful method. It can not only enable a hands-free search (no more Booleans!) but type of search that is flexible enough to work consistently and generate insights across industries.

*The most common patent search methodologies in order of their creation and sophistication.

Semantic Analysis

For decades, the most sophisticated patent search methodologies have been keyword or semantic based, yet they do little more than the most simple filter for relevance. Armed with a “bag of words”, this method compares keyword counts and ranks patents based on how many keywords they share. This simple match will inherently lack the context in which those key concepts were used and often creates over-broad, noisy patent lists with unclear review priorities.

Supervised Classifier

Supervised classifier-based systems have entered the market with the promise of more granular patent to technology mappings.

Developing a classifier-based system and taxonomy requires a multi-step process. A model owner starts with a sample of patents and some hypotheses about what they cover. Then, through a tagging process conducted by hand, they begin to organically define a set of classifiers and hierarchy in which those relate. Once a taxonomy has taken shape, each classifier becomes the basis for identifying similar patents across the patent corpus.

There are caveats to this approach. Because humans define every aspect of a taxonomy’s creation, there is inherent bias, such as over-emphasis on certain technical areas or trends. And, because it is a heavy and expensive process to create and maintain a taxonomy, the model owner must be diligent in covering all areas of technology carefully and execute reclassifications and updates in a timely fashion. This requires users to place significant faith in a black-box model.

Convolutional Neural Networks

ClearAccessIP’s Patent Intelligence AI™ provides users with insights to power strategic IP decision-making. ClearAccessIP’s Patent Intelligence AI™ relies on a convolutional neural network (“CNN”), that reads each paragraph and claim of each patent, breaks up the key inventive concept into tokens, and mathematically maps the relationships of overlapping concepts across more than 70 million worldwide filings.

*A portrayal of ClearAccessIP’s neural network.

This mapping finds results based on the process of how an invention works, rather than by searching across the plethora of words used to describe it. Finally, that neural network directly trains on the patent corpus and integrates new filings on a weekly basis, ensuring that users are provided with context rich and always up to date results.

Learn more about how the most advanced patent search on the market can help corporations, small-medium enterprises, universities, law firms, and investors unlock the value of their patent portfolio. Contact us with questions or to schedule a demo today at


Reflections on 2018: A letter from ClearAccessIP CEO Nicole Shanahan


2018 Was a Year of Discovery.

2019 Will be a Year of Change.

Change occurs when the pain of staying the same is worse than the pain (or fear) of change. 2018 was a big year of discovery for ClearAccessIP. We still have more work to do to see through the next wave of change in IP management and transactions.

In January, we scaled ClearAccessIP’s integrated management and patent search platform, a new category for IP related services that puts cloud automation technology at the center of the workflow. Over the past year, we attended numerous industry conferences and met with hundreds of IP professionals and IP-focused organizations. The platform received the broadest possible set of responses, ranging from clinging skepticism to “we need you now.”

We learned that engineering an AI trained on the world’s inventions is no fool’s errand but sure can feel like it at times. As of today, we have exceeded over a hundred machine learning training models. We’ve learned that applying machine learning to a corpus of inventive concepts is more alchemy than science. More grit than moxie. There is no playbook, and our engineering efforts are evolving with the bleeding edge of research in natural language AI, which means we have to be creative and resilient.

2018 was a year overflowing with activity. Between database migrations, feature releases, presentations, and industry events, I realized the importance of taking small moments to reflect on ClearAccessIP’s long-term vision to enable a free marketplace for the exchange of invention assets. It’s no small endeavor, and this year was pivotal to proving that we are on the right track.

The relevance of our mission became especially apparent in regards to U.S. – China trade relations. In June, our Director of Business Development Deepa Krishna spoke at the U.S. – China AI Tech Summit about the transformational impact AI is already having on the legal industry in streamlining workflows, enabling lower transaction costs, and improving access for organizations that today are priced out of needed services. She shared the work we are doing to bridge IP transactions between U.S. and Chinese organizations, helping make it easier for patent buyers and sellers to navigate complex negotiations with the support of our AI platform.


In furtherance of this goal, we supported the development of the The Ocean Tomo Gold Book, a web application that will launch in early 2019 to enable Chinese entities to understand and act on their IP purchasing needs abroad. This effort couldn’t come soon enough as trade tensions between the U.S. and China have escalated and IP has become a sticking point.

We are grateful for all of the big-picture thinkers that have welcomed us into their offices this year to learn more about our vision and technology. To those that can see beyond the daily grind of office actions and foreign filings and think deeply about the significance of this line of work – we raise a glass to you! I personally am inspired by you all and cannot thank you enough for dreaming about the future with us.

Wishing you a happy, healthy and visionary New Year,

Nicole Shanahan

CEO, ClearAccessIP


Patent Portfolio Management, Simplified

At ClearAccessIP, we envision a system where business managers, and innovators work together to create value in the way the patent system intended.

We are the first automation company with a purpose-built solution to strategically manage IP portfolios. With ClearAccessIP, your organization can develop and scale your IP strategy with a level of insight previously not available.

Click on each of the tiles below to read more about how ClearAccessIP unites these services into a seamless workflow.