MEASURING PATENT NOVELTY USING NATURAL LANGUAGE PROCESSING

Ali Yassine; Carlo Lipizzi

doi:10.1017/pds.2023.261

MEASURING PATENT NOVELTY USING NATURAL LANGUAGE PROCESSING

Research output: Contribution to journal › Conference article › peer-review

1 Scopus citations

Abstract

This paper develops a novelty measure for patents. We devise a text-based novelty measure using natural language processing (NLP) techniques. The proposed method is applied on patents that belong to a common category, which represents a subset of patents under a specific patent class. We then extract the novelty-value profile of those patents and discuss a use case for product design and development (i.e., extracting patent novelty and predicting inventive value).

Original language	English
Pages (from-to)	2605-2614
Number of pages	10
Journal	Proceedings of the Design Society
Volume	3
DOIs	https://doi.org/10.1017/pds.2023.261
State	Published - 2023
Event	24th International Conference on Engineering Design, ICED 2023 - Bordeaux, France Duration: 24 Jul 2023 → 28 Jul 2023

Keywords

Machine learning
New product development
Open source design

Access to Document

10.1017/pds.2023.261

Cite this

@article{c4cc8fd6e4574e1eae335091dad2d48b,

title = "MEASURING PATENT NOVELTY USING NATURAL LANGUAGE PROCESSING",

abstract = "This paper develops a novelty measure for patents. We devise a text-based novelty measure using natural language processing (NLP) techniques. The proposed method is applied on patents that belong to a common category, which represents a subset of patents under a specific patent class. We then extract the novelty-value profile of those patents and discuss a use case for product design and development (i.e., extracting patent novelty and predicting inventive value).",

keywords = "Machine learning, New product development, Open source design",

author = "Ali Yassine and Carlo Lipizzi",

note = "Publisher Copyright: {\textcopyright} The Author(s), 2023. Published by Cambridge University Press.; 24th International Conference on Engineering Design, ICED 2023 ; Conference date: 24-07-2023 Through 28-07-2023",

year = "2023",

doi = "10.1017/pds.2023.261",

language = "English",

volume = "3",

pages = "2605--2614",

}

TY - JOUR

T1 - MEASURING PATENT NOVELTY USING NATURAL LANGUAGE PROCESSING

AU - Yassine, Ali

AU - Lipizzi, Carlo

N1 - Publisher Copyright: © The Author(s), 2023. Published by Cambridge University Press.

PY - 2023

Y1 - 2023

N2 - This paper develops a novelty measure for patents. We devise a text-based novelty measure using natural language processing (NLP) techniques. The proposed method is applied on patents that belong to a common category, which represents a subset of patents under a specific patent class. We then extract the novelty-value profile of those patents and discuss a use case for product design and development (i.e., extracting patent novelty and predicting inventive value).

AB - This paper develops a novelty measure for patents. We devise a text-based novelty measure using natural language processing (NLP) techniques. The proposed method is applied on patents that belong to a common category, which represents a subset of patents under a specific patent class. We then extract the novelty-value profile of those patents and discuss a use case for product design and development (i.e., extracting patent novelty and predicting inventive value).

KW - Machine learning

KW - New product development

KW - Open source design

UR - https://www.scopus.com/pages/publications/85165514989

UR - https://www.scopus.com/pages/publications/85165514989#tab=citedBy

U2 - 10.1017/pds.2023.261

DO - 10.1017/pds.2023.261

M3 - Conference article

AN - SCOPUS:85165514989

VL - 3

SP - 2605

EP - 2614

JO - Proceedings of the Design Society

JF - Proceedings of the Design Society

T2 - 24th International Conference on Engineering Design, ICED 2023

Y2 - 24 July 2023 through 28 July 2023

ER -

MEASURING PATENT NOVELTY USING NATURAL LANGUAGE PROCESSING

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this