User demand-driven patent topic classification using machine learning techniques

Fujin Zhu; Xuefeng Wang; Donghua Zhu; Yuqin Liu

doi:10.1142/9789814619998_0108

User demand-driven patent topic classification using machine learning techniques

Fujin Zhu, Xuefeng Wang, Donghua Zhu, Yuqin Liu

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

Traditional patent classification schemes, which are mainly based on either IPC or UPC, are too complicated and general to meet the needs of specific industries. The paper proposes a dynamic classification method, the “user demand-driven patent topic classification”, aiming to a specific industry or technology area. In the paper, classification topics of the method are grouped into technical topic, application topic and application-technical mixed topic. Automatic process of the method using machine learning techniques is presented as well. A case study on the technology area of system on a chip (SoC) is conducted using machine learning techniques, validating the feasibility of the method. The experiment results demonstrate that automatic patent topic classification based on the combination of patents’ metadata and citation information can obtain perfect performance with a greatly simplified document preprocessing.

Original language	English
Title of host publication	Decision Making and Soft Computing - Proceedings of the 11th International FLINS Conference, FLINS 2014
Editors	Ronei Marcos de Moraes, Etienne E. Kerre, Liliane dos Santos Machado, Jie Lu
Publisher	World Scientific Publishing Co. Pte Ltd
Pages	657-663
Number of pages	7
ISBN (Electronic)	9789814619967
DOIs	https://doi.org/10.1142/9789814619998_0108
Publication status	Published - 2014
Event	Decision Making and Soft Computing - 11th International Fuzzy Logic and Intelligent Technologies in Nuclear Science Conference, FLINS 2014 - Joao Pessoa, Paraiba, Brazil Duration: 17 Aug 2014 → 20 Aug 2014

Publication series

Name	Decision Making and Soft Computing - Proceedings of the 11th International FLINS Conference, FLINS 2014

Conference

Conference	Decision Making and Soft Computing - 11th International Fuzzy Logic and Intelligent Technologies in Nuclear Science Conference, FLINS 2014
Country/Territory	Brazil
City	Joao Pessoa, Paraiba
Period	17/08/14 → 20/08/14

Keywords

Document representation
Machine learning
Patent topic classification
SoC
User demand-driven

Access to Document

10.1142/9789814619998_0108

Cite this

Zhu, F., Wang, X., Zhu, D., & Liu, Y. (2014). User demand-driven patent topic classification using machine learning techniques. In R. M. de Moraes, E. E. Kerre, L. dos Santos Machado, & J. Lu (Eds.), Decision Making and Soft Computing - Proceedings of the 11th International FLINS Conference, FLINS 2014 (pp. 657-663). (Decision Making and Soft Computing - Proceedings of the 11th International FLINS Conference, FLINS 2014). World Scientific Publishing Co. Pte Ltd. https://doi.org/10.1142/9789814619998_0108

Zhu, Fujin ; Wang, Xuefeng ; Zhu, Donghua et al. / User demand-driven patent topic classification using machine learning techniques. Decision Making and Soft Computing - Proceedings of the 11th International FLINS Conference, FLINS 2014. editor / Ronei Marcos de Moraes ; Etienne E. Kerre ; Liliane dos Santos Machado ; Jie Lu. World Scientific Publishing Co. Pte Ltd, 2014. pp. 657-663 (Decision Making and Soft Computing - Proceedings of the 11th International FLINS Conference, FLINS 2014).

@inproceedings{9bec4bad2c1d4a5db57a254d51b2f16c,

title = "User demand-driven patent topic classification using machine learning techniques",

abstract = "Traditional patent classification schemes, which are mainly based on either IPC or UPC, are too complicated and general to meet the needs of specific industries. The paper proposes a dynamic classification method, the “user demand-driven patent topic classification”, aiming to a specific industry or technology area. In the paper, classification topics of the method are grouped into technical topic, application topic and application-technical mixed topic. Automatic process of the method using machine learning techniques is presented as well. A case study on the technology area of system on a chip (SoC) is conducted using machine learning techniques, validating the feasibility of the method. The experiment results demonstrate that automatic patent topic classification based on the combination of patents{\textquoteright} metadata and citation information can obtain perfect performance with a greatly simplified document preprocessing.",

keywords = "Document representation, Machine learning, Patent topic classification, SoC, User demand-driven",

author = "Fujin Zhu and Xuefeng Wang and Donghua Zhu and Yuqin Liu",

note = "Publisher Copyright: {\textcopyright} 2014 by World Scientific Publishing Co. Pte. Ltd. All rights reserved.; Decision Making and Soft Computing - 11th International Fuzzy Logic and Intelligent Technologies in Nuclear Science Conference, FLINS 2014 ; Conference date: 17-08-2014 Through 20-08-2014",

year = "2014",

doi = "10.1142/9789814619998_0108",

language = "English",

series = "Decision Making and Soft Computing - Proceedings of the 11th International FLINS Conference, FLINS 2014",

publisher = "World Scientific Publishing Co. Pte Ltd",

pages = "657--663",

editor = "{de Moraes}, {Ronei Marcos} and Kerre, {Etienne E.} and {dos Santos Machado}, Liliane and Jie Lu",

booktitle = "Decision Making and Soft Computing - Proceedings of the 11th International FLINS Conference, FLINS 2014",

address = "Singapore",

}

Zhu, F, Wang, X, Zhu, D & Liu, Y 2014, User demand-driven patent topic classification using machine learning techniques. in RM de Moraes, EE Kerre, L dos Santos Machado & J Lu (eds), Decision Making and Soft Computing - Proceedings of the 11th International FLINS Conference, FLINS 2014. Decision Making and Soft Computing - Proceedings of the 11th International FLINS Conference, FLINS 2014, World Scientific Publishing Co. Pte Ltd, pp. 657-663, Decision Making and Soft Computing - 11th International Fuzzy Logic and Intelligent Technologies in Nuclear Science Conference, FLINS 2014, Joao Pessoa, Paraiba, Brazil, 17/08/14. https://doi.org/10.1142/9789814619998_0108

User demand-driven patent topic classification using machine learning techniques. / Zhu, Fujin; Wang, Xuefeng; Zhu, Donghua et al.
Decision Making and Soft Computing - Proceedings of the 11th International FLINS Conference, FLINS 2014. ed. / Ronei Marcos de Moraes; Etienne E. Kerre; Liliane dos Santos Machado; Jie Lu. World Scientific Publishing Co. Pte Ltd, 2014. p. 657-663 (Decision Making and Soft Computing - Proceedings of the 11th International FLINS Conference, FLINS 2014).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - User demand-driven patent topic classification using machine learning techniques

AU - Zhu, Fujin

AU - Wang, Xuefeng

AU - Zhu, Donghua

AU - Liu, Yuqin

PY - 2014

Y1 - 2014

N2 - Traditional patent classification schemes, which are mainly based on either IPC or UPC, are too complicated and general to meet the needs of specific industries. The paper proposes a dynamic classification method, the “user demand-driven patent topic classification”, aiming to a specific industry or technology area. In the paper, classification topics of the method are grouped into technical topic, application topic and application-technical mixed topic. Automatic process of the method using machine learning techniques is presented as well. A case study on the technology area of system on a chip (SoC) is conducted using machine learning techniques, validating the feasibility of the method. The experiment results demonstrate that automatic patent topic classification based on the combination of patents’ metadata and citation information can obtain perfect performance with a greatly simplified document preprocessing.

AB - Traditional patent classification schemes, which are mainly based on either IPC or UPC, are too complicated and general to meet the needs of specific industries. The paper proposes a dynamic classification method, the “user demand-driven patent topic classification”, aiming to a specific industry or technology area. In the paper, classification topics of the method are grouped into technical topic, application topic and application-technical mixed topic. Automatic process of the method using machine learning techniques is presented as well. A case study on the technology area of system on a chip (SoC) is conducted using machine learning techniques, validating the feasibility of the method. The experiment results demonstrate that automatic patent topic classification based on the combination of patents’ metadata and citation information can obtain perfect performance with a greatly simplified document preprocessing.

KW - Document representation

KW - Machine learning

KW - Patent topic classification

KW - SoC

KW - User demand-driven

UR - http://www.scopus.com/inward/record.url?scp=85037376766&partnerID=8YFLogxK

U2 - 10.1142/9789814619998_0108

DO - 10.1142/9789814619998_0108

M3 - Conference contribution

AN - SCOPUS:85037376766

T3 - Decision Making and Soft Computing - Proceedings of the 11th International FLINS Conference, FLINS 2014

SP - 657

EP - 663

BT - Decision Making and Soft Computing - Proceedings of the 11th International FLINS Conference, FLINS 2014

A2 - de Moraes, Ronei Marcos

A2 - Kerre, Etienne E.

A2 - dos Santos Machado, Liliane

A2 - Lu, Jie

PB - World Scientific Publishing Co. Pte Ltd

T2 - Decision Making and Soft Computing - 11th International Fuzzy Logic and Intelligent Technologies in Nuclear Science Conference, FLINS 2014

Y2 - 17 August 2014 through 20 August 2014

ER -

Zhu F, Wang X, Zhu D, Liu Y. User demand-driven patent topic classification using machine learning techniques. In de Moraes RM, Kerre EE, dos Santos Machado L, Lu J, editors, Decision Making and Soft Computing - Proceedings of the 11th International FLINS Conference, FLINS 2014. World Scientific Publishing Co. Pte Ltd. 2014. p. 657-663. (Decision Making and Soft Computing - Proceedings of the 11th International FLINS Conference, FLINS 2014). doi: 10.1142/9789814619998_0108

User demand-driven patent topic classification using machine learning techniques

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this