Classifying patents based on their semantic content.

Antonin Bergeaud,Yoann Potiron,Juste Raimbault,Zhong-Ke Gao

doi:10.1371/journal.pone.0176310

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.

Highlights

Innovation and technological change have been described by many scholars as the main drivers of economic growth as in [1] and [2]. [3] advertised the use of patents as an economic indicator and as a good proxy for innovation
Most of the statistics derived from the patent databases relied on a few key features: the identity of the inventor, the type and identity of the rights owner, the citations made by the patent to prior art and the technological classes assigned by the patent office post patent’s content review
We present some key features of our resulting semantic classification showing both complementary and differences with the technological classification

Summary

Introduction

Innovation and technological change have been described by many scholars as the main drivers of economic growth as in [1] and [2]. [3] advertised the use of patents as an economic indicator and as a good proxy for innovation. Most of the statistics derived from the patent databases relied on a few key features: the identity of the inventor, the type and identity of the rights owner, the citations made by the patent to prior art and the technological classes assigned by the patent office post patent’s content review. Combining this information is relevant when trying to capture the diffusion of knowledge and the interaction between technological fields as studied in [5]. The USPTO reviews all the previous patents so as to create a consistent classification

Objectives

Results

Conclusion