Technology opportunity discovery based on patent analysis: a hybrid approach of subject-action-object and generative topographic mapping

An incomplete understanding of the technical details in a firm's technology selection can lead to a failure in the process of the technology opportunity discovery (TOD) and cause a series of R&D problems. This study proposes an approach for the automated TOD by combining the subject-section...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Technology analysis & strategic management Ročník 36; číslo 9; s. 2070 - 2083
Hlavní autoři: Wang, Jinfeng, Ding, Zhaoye, Liu, Zhenfeng, Feng, Lijie
Médium: Journal Article
Jazyk:angličtina
Vydáno: Abingdon Routledge 01.09.2024
Taylor & Francis Ltd
Témata:
ISSN:0953-7325, 1465-3990
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:An incomplete understanding of the technical details in a firm's technology selection can lead to a failure in the process of the technology opportunity discovery (TOD) and cause a series of R&D problems. This study proposes an approach for the automated TOD by combining the subject-section-object (SAO) and the generative topographic mapping (GTM), which concentrates on the role of the semantic information in TOD process. First, the semantic information of the technology components in a target field is extracted and the topics of different semantic structures are defined. Second, the GTM-based patent map is established to discover technology opportunities based on a vector matrix composed of patents and topics. Finally, the degree of semantic similarity is applied to measure the technology novelty and to identify promising technology opportunities. The case of the coal-bed methane extraction technology demonstrates that the automated approach based on the semantic information can help understand the concrete details of technology opportunities and improve the accuracy of TOD.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0953-7325
1465-3990
DOI:10.1080/09537325.2022.2126306