Classifying patents based on their semantic content

Antonin Bergeaud, Yoann Potiron, Juste Raimbault

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

In this paper, we extend some usual techniques of classification resulting from a large-scale data-mining and network approach. This new technology, which in particular is designed to be suitable to big data, is used to construct an open consolidated database from raw data on 4 million patents taken from the US patent office from 1976 onward. To build the pattern network, not only do we look at each patent title, but we also examine their full abstract and extract the relevant keywords accordingly. We refer to this classification as semantic approach in contrast with the more common technological approach which consists in taking the topology when considering US Patent office technological classes. Moreover, we document that both approaches have highly different topological measures and strong statistical evidence that they feature a different model. This suggests that our method is a useful tool to extract endogenous information.

Original languageEnglish
Article numbere0176310
JournalPLoS One
Volume12
Issue number4
DOIs
Publication statusPublished - 2017 Apr 1

Fingerprint

Patents
patents
Semantics
Data Mining
Data mining
Topology
Databases
Technology
topology
extracts
methodology
Big data

ASJC Scopus subject areas

  • Medicine(all)
  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)

Cite this

Classifying patents based on their semantic content. / Bergeaud, Antonin; Potiron, Yoann; Raimbault, Juste.

In: PLoS One, Vol. 12, No. 4, e0176310, 01.04.2017.

Research output: Contribution to journalArticle

Bergeaud, Antonin ; Potiron, Yoann ; Raimbault, Juste. / Classifying patents based on their semantic content. In: PLoS One. 2017 ; Vol. 12, No. 4.
@article{4181e8ad8b1c4e9a92ccdd06fb5568d8,
title = "Classifying patents based on their semantic content",
abstract = "In this paper, we extend some usual techniques of classification resulting from a large-scale data-mining and network approach. This new technology, which in particular is designed to be suitable to big data, is used to construct an open consolidated database from raw data on 4 million patents taken from the US patent office from 1976 onward. To build the pattern network, not only do we look at each patent title, but we also examine their full abstract and extract the relevant keywords accordingly. We refer to this classification as semantic approach in contrast with the more common technological approach which consists in taking the topology when considering US Patent office technological classes. Moreover, we document that both approaches have highly different topological measures and strong statistical evidence that they feature a different model. This suggests that our method is a useful tool to extract endogenous information.",
author = "Antonin Bergeaud and Yoann Potiron and Juste Raimbault",
year = "2017",
month = "4",
day = "1",
doi = "10.1371/journal.pone.0176310",
language = "English",
volume = "12",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "4",

}

TY - JOUR

T1 - Classifying patents based on their semantic content

AU - Bergeaud, Antonin

AU - Potiron, Yoann

AU - Raimbault, Juste

PY - 2017/4/1

Y1 - 2017/4/1

N2 - In this paper, we extend some usual techniques of classification resulting from a large-scale data-mining and network approach. This new technology, which in particular is designed to be suitable to big data, is used to construct an open consolidated database from raw data on 4 million patents taken from the US patent office from 1976 onward. To build the pattern network, not only do we look at each patent title, but we also examine their full abstract and extract the relevant keywords accordingly. We refer to this classification as semantic approach in contrast with the more common technological approach which consists in taking the topology when considering US Patent office technological classes. Moreover, we document that both approaches have highly different topological measures and strong statistical evidence that they feature a different model. This suggests that our method is a useful tool to extract endogenous information.

AB - In this paper, we extend some usual techniques of classification resulting from a large-scale data-mining and network approach. This new technology, which in particular is designed to be suitable to big data, is used to construct an open consolidated database from raw data on 4 million patents taken from the US patent office from 1976 onward. To build the pattern network, not only do we look at each patent title, but we also examine their full abstract and extract the relevant keywords accordingly. We refer to this classification as semantic approach in contrast with the more common technological approach which consists in taking the topology when considering US Patent office technological classes. Moreover, we document that both approaches have highly different topological measures and strong statistical evidence that they feature a different model. This suggests that our method is a useful tool to extract endogenous information.

UR - http://www.scopus.com/inward/record.url?scp=85018166764&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85018166764&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0176310

DO - 10.1371/journal.pone.0176310

M3 - Article

C2 - 28445550

AN - SCOPUS:85018166764

VL - 12

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 4

M1 - e0176310

ER -