Global Patent Explorer

Award-winning Shiny App for patent statistics


Paul Simmering


July 1, 2018

Freeelance work for Aalborg University, commissioned by Assoc. Prof. Daniel S. Hain and Assoc. Prof. Roman Jurowetzki. The Shiny App visualizes the results of a paper on natural language processing on patent texts:

D.S. Hain, R. Jurowetzki, T. Buchmann, P. Wolf (2018), A Vector Worth a Thousand Counts: A Temporal Semantic Similarity Approach to Patent Impact Prediction. Available at

The app’s code is available on Github.

This tool lets users map and visualize inventive and innovative activity around the globe. The explorer relies on a series of novel indicators that combine insights from large-scale natural language processing and established patent analysis techniques and provide insights about dimensions such as technological originality or future orientation. Users can explore the dataset on country or city level, select time-ranges and technologies. The app features rich visualizations including a world map, network plots that show relations between countries and cities, and customizable statistical plots.

The app is a winner of the first IPSDM (Intellectual property statistics for descision makers) “Big Data Analytics” Challenge (2018) by the European Union Intellectual Property Office.

I also presented the app at the GOR 2019 conference. You can find the slides here.

Tech stack: R, Shiny