Technology forecasting using topic-based patent analysis

Gab Jo Kim, Sang Sung Park, Dong Sik Jang

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

The number of patents with critical information related to various technologies is increasing by the day. This trend has led corporations and countries to consider patent analysis as an important element in their analysis methodology for research and development. The present study seeks to determine and forecast vacant technology with considerable development potential through an analysis of patents. In order to identify a vacant technology cluster, the unstructured patent documents need to be structured into groups of similar technologies by using k-means clustering. Furthermore, silhouette width, Davies-Bouldin Index (DBI), and Pseudo F are used for enhancing reliability of determining the optimal number of clusters. From each technology cluster, a generative topic model, latent Dirichlet allocation (LDA), is adopted to extract latent topics specifically for examination of technologies. Renewable energy patents from the United States Patent and Trademark Office (USPTO) are analyzed for the case study, which verifies the proposed methodology.

Original languageEnglish
Pages (from-to)265-270
Number of pages6
JournalJournal of Scientific and Industrial Research
Volume74
Issue number5
Publication statusPublished - 2015 May 1

Fingerprint

Trademarks
Industry

Keywords

  • K-means clustering
  • Latent dirichlet allocation
  • Patent analysis
  • Technology cluster

ASJC Scopus subject areas

  • General

Cite this

Technology forecasting using topic-based patent analysis. / Kim, Gab Jo; Park, Sang Sung; Jang, Dong Sik.

In: Journal of Scientific and Industrial Research, Vol. 74, No. 5, 01.05.2015, p. 265-270.

Research output: Contribution to journalArticle

@article{e91778dfd8344daaaa9526c12edf2b92,
title = "Technology forecasting using topic-based patent analysis",
abstract = "The number of patents with critical information related to various technologies is increasing by the day. This trend has led corporations and countries to consider patent analysis as an important element in their analysis methodology for research and development. The present study seeks to determine and forecast vacant technology with considerable development potential through an analysis of patents. In order to identify a vacant technology cluster, the unstructured patent documents need to be structured into groups of similar technologies by using k-means clustering. Furthermore, silhouette width, Davies-Bouldin Index (DBI), and Pseudo F are used for enhancing reliability of determining the optimal number of clusters. From each technology cluster, a generative topic model, latent Dirichlet allocation (LDA), is adopted to extract latent topics specifically for examination of technologies. Renewable energy patents from the United States Patent and Trademark Office (USPTO) are analyzed for the case study, which verifies the proposed methodology.",
keywords = "K-means clustering, Latent dirichlet allocation, Patent analysis, Technology cluster",
author = "Kim, {Gab Jo} and Park, {Sang Sung} and Jang, {Dong Sik}",
year = "2015",
month = "5",
day = "1",
language = "English",
volume = "74",
pages = "265--270",
journal = "Journal of Scientific and Industrial Research",
issn = "0022-4456",
publisher = "National Institute of Science Communication and Information Resources (NISCAIR)",
number = "5",

}

TY - JOUR

T1 - Technology forecasting using topic-based patent analysis

AU - Kim, Gab Jo

AU - Park, Sang Sung

AU - Jang, Dong Sik

PY - 2015/5/1

Y1 - 2015/5/1

N2 - The number of patents with critical information related to various technologies is increasing by the day. This trend has led corporations and countries to consider patent analysis as an important element in their analysis methodology for research and development. The present study seeks to determine and forecast vacant technology with considerable development potential through an analysis of patents. In order to identify a vacant technology cluster, the unstructured patent documents need to be structured into groups of similar technologies by using k-means clustering. Furthermore, silhouette width, Davies-Bouldin Index (DBI), and Pseudo F are used for enhancing reliability of determining the optimal number of clusters. From each technology cluster, a generative topic model, latent Dirichlet allocation (LDA), is adopted to extract latent topics specifically for examination of technologies. Renewable energy patents from the United States Patent and Trademark Office (USPTO) are analyzed for the case study, which verifies the proposed methodology.

AB - The number of patents with critical information related to various technologies is increasing by the day. This trend has led corporations and countries to consider patent analysis as an important element in their analysis methodology for research and development. The present study seeks to determine and forecast vacant technology with considerable development potential through an analysis of patents. In order to identify a vacant technology cluster, the unstructured patent documents need to be structured into groups of similar technologies by using k-means clustering. Furthermore, silhouette width, Davies-Bouldin Index (DBI), and Pseudo F are used for enhancing reliability of determining the optimal number of clusters. From each technology cluster, a generative topic model, latent Dirichlet allocation (LDA), is adopted to extract latent topics specifically for examination of technologies. Renewable energy patents from the United States Patent and Trademark Office (USPTO) are analyzed for the case study, which verifies the proposed methodology.

KW - K-means clustering

KW - Latent dirichlet allocation

KW - Patent analysis

KW - Technology cluster

UR - http://www.scopus.com/inward/record.url?scp=84928984684&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84928984684&partnerID=8YFLogxK

M3 - Article

VL - 74

SP - 265

EP - 270

JO - Journal of Scientific and Industrial Research

JF - Journal of Scientific and Industrial Research

SN - 0022-4456

IS - 5

ER -