We apply advanced Natural Language Processing tools to examine a neglected part of the content of patents- namely, the users of inventions. After a formal definition of users we develop a complex methodology, based on supervised algorithms, to identify and clean the occurrences in which the description of the inventions include a reference to actual or potential users. A total number of 76.857 users was used as the knowledge base. Preliminary applications of the methodology deliver extremely rich information, but also exhibit noise from generic description of users. Further classification work has been done in order to discriminate between generic and specific descriptions of users and deliver highly informative sets of occurrences. After a review of the literature on the role of users for technological innovation the paper will discuss the potential of the methodology to address some of the open issues.

Mapping users in patents. Steps towards a new methodology and the definition of a research agenda

Andrea Bonaccorsi;Filippo Chiarello;Gualtiero Fantoni;D'AMICO, LAURA
2017

Abstract

We apply advanced Natural Language Processing tools to examine a neglected part of the content of patents- namely, the users of inventions. After a formal definition of users we develop a complex methodology, based on supervised algorithms, to identify and clean the occurrences in which the description of the inventions include a reference to actual or potential users. A total number of 76.857 users was used as the knowledge base. Preliminary applications of the methodology deliver extremely rich information, but also exhibit noise from generic description of users. Further classification work has been done in order to discriminate between generic and specific descriptions of users and deliver highly informative sets of occurrences. After a review of the literature on the role of users for technological innovation the paper will discuss the potential of the methodology to address some of the open issues.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11568/952792
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact