Home  »  II-SDV  »  Programme  »  Monday 5. October 2020

Monday 5. October 2020

Conference starts at 09:00

Patent Analytics Platform at Bayer – turning bits into insights

Patents are one of richest yet most challenging sources to work with when it comes to identifying and analysing scientific innovations and trends. But this requires deep analysis of the scientific content of the complete patent document. We decided to build a patent analytics platform with annotation of all available patents in full-text with terminologies optimized for our needs as key component.  The resulting enriched patent corpus allows us to explore and analyse the scientific content of patents in all areas which are highly relevant to us in an unprecedented way. In this talk we will share with you the goals of the project, the rationale behind the technology choices, the highs and lows along the project and our aspirations for the future.

 

 

 

Early Scientific Intelligence

Learn how

·  text mining is being used to filter and extract information to scale up an otherwise manual surveillance

·  news across 8 different sources are consolidated and distributed via regular newsletters and collected in a database

·  collaborating with two key vendors Linguamatics & Infodesk helped establish an information flow allowing us to process large amounts of information

·  internal social platforms are being used to involve the broader organization in filtering the information

 

The pharma company Novo Nordisk is a strong believer in collaborating with start-ups, biotechs and universities to develop the next state of the art medical treatments. To help connect Novo Nordisk with such organizations the project Early Scientific Intelligence was launched to help create a drone view of potentially interesting companies and projects based on systematic surveillance of at least 8 different information sources. The information is filtered via text mining and human curators to ensure fast processing while keeping the quality high before the selected potential partners are approached.  The data is shared broadly across the research organization with the aim of creating a transparent discussion of the potential value of the collaboration before moving into a more formal screening.  Over time a history of known information on specific companies and projects is built up and visualized via a dashboard.

New Product Introductions: Minesoft, F1000, Biomax

10:30 - 11:15

Exhibition and Networking Break

AI, IoT, Blockchain & Co: How to keep track and take advantage of what’s going on?

New Product Introductions: Deep SEARCH 9, Lighthouse IP, kerntech

12:15 - 14:00

Lunch, Exhibition and Networking

Implementation of new technology within a big pharma company: Finding a way amidst an ever-changing and data-driven environment.

 Pharmaceutical companies have always relied on data to support innovation and drive the business. This concept has remained unchanged, despite the fact that today we get it at the speed of light, in an overwhelming volume, and in a global and mostly unstructured way. In order to continue to derive knowledge and insights from that data to support drug discovery and business strategies, integrating AI tools into work processes and acquiring the required skills to do so has become crucial. Although the need is clear, how to implement these new tools is not straightforward in an era of restructuring, divesting, outsourcing, and budget crunching. This talk will focus on creative ways to overcome some of these barriers within a “big pharma” setting with a specific example demonstrating the application of

Combining Knowledge and Machine Learning for the Analysis of Scientific Documents

New Product Introductions: BizInt, Search Technologies/VantagePoint, CENTREDOC, IPSCREENER

15:40 - 16:25

Exhibition and Networking Break

Bringing AI to SME projects: Addressing customer needs with a flexible set of tools and services

Customers interested in Language Analytics solutions typically approach us with a broad range of business cases and specific business needs. Especially when it comes to the data available for their case and for any AI aspects involved, the variation in data types, data quality and data quantity is, by our experience, quite vast and at the same time so critical for a project's success, that we often start our requirements analysis right there: at the data. At Karakun, our Language Analytics team addresses this in an increasingly flexible way: We select from a set of Language Analytics tools and related services (e.g. data cleansing and data procurement) to meet the business needs at hand with the data available or at least in reach – at reasonable costs. 

The methodology stack ranges from heuristic logic over statistical solutions to neural networks. At the same time, we aim at reducing the amount of data needed for such training, e.g. by integrating state-of-the-art neural technologies into our platform. That way, also SMEs and their specific business cases can benefit from the full range of Language Analytics options. 

To illustrate our approach, we will present an e-Safe solution which allows for semantic document tagging and search in highly secured virtual safes. In addition, our solution provides text-based triggers for complex workflows depending on the safe´s content.

 

In the Age of the Superhuman

Conference ends at 17:15