EPO ACADEMIC RESEARCH PROGRAMME

Session at EPIP 2022

Chairs: Yann Ménière, Chief Economist, EPO, and Xavier Seuba, Director European Patent Academy and EQE, EPO

Summary: Three grant recipients from 2019 and 2020 present their final and interim results of their research projects done with the support of the EPO under the Academic Research Programme.

From patents to trademarks: towards a concordance map
By Carolina Castaldi, Professor Utrecht University
Presented by Milad Abbasiharofteh

The aim of this project is to link patent to trademark data by mapping patent classes (IPC codes) to trademark classes (Nice codes and the keywords in the detailed goods and services descriptors). The main scientific objective of this project is threefold: 1. to develop a concordance map between patent and trademark classes, 2. to validate it extensively using complementary data sources and alternative techniques, and 3. to illustrate its use for cleantech patents. By focusing on classification systems, we aim at capturing the qualities of technological and market specialisation patterns. In this respect, the envisioned concordance map would allow to tackle three types of research questions.

Understanding the business value of SMEs’ patent portfolio: an artificial intelligence-based approach
By Alberto Di Minin, Professor Sant’Anna School of Advanced Studies
Presented by Antonio Crupi

The project’s primary goal is to assess and forecast the commercial value of SMEs’ patents measuring the proximity between their portfolio and their business model. With the use of artificial intelligence methodologies, the project aims to: 1. identify the closeness of firms’ business model developments from their technological footprint (patents) 2. predict the success likelihood of a specific business model applied to a given patent and 3. suggest alternative business models more in line with the patent portfolio characteristics. The project relies on original and relatively rare data regarding company business models disclosed directly by SMEs extracted from funding applications, submitted during the period 2014 to 2019, to the Horizon 2020 SME Instrument (SMEi) programme.

Linking patents to scientific publications through in-text reference mining
By Jian Wang, Ass. Professor Leiden University
Presented by Jian Wang

The project will create a public database linking patents to scientific publications, using a high-performing text mining method to extract patent in-text references. As a result, it will make it possible for researchers to analyse the impact of scientific research on industry innovation.