Field identification and opportunity discovery of photovoltaics technology: deep transfer learning method

Ruilian Han, Lu An (), Wei Zhou and Gang Li
Additional contact information
Ruilian Han: Wuhan University
Lu An: Wuhan University
Wei Zhou: Wuhan University
Gang Li: Wuhan University

Scientometrics, 2025, vol. 130, issue 8, No 5, 4283-4307

Abstract: Abstract The advancement of technology relies on scientific and accurate identification of potential opportunities within the field. This study presents a novel method for discovering technology opportunities by combining multi-source data sources and utilizing the word-embedding model, the topic model, and deep transfer learning. The process involves identifying technology fields using sentence vectors that incorporate external semantic knowledge, which addresses the limitations of previous models that only consider word co-occurrence relationships. Real-time Google search data is also integrated to ensure the results are up-to-date. The proposed method was applied to photovoltaics technology and demonstrated impressive performance in enhancing topic coherence and predictive accuracy. The findings indicate that solar cell devices and materials, such as polymer materials and flexible photovoltaic devices, are the most promising technology opportunities based on multi-source data analysis.

Keywords: Technology opportunity discovery; Deep transfer learning; Generative pretrained transformer; Technology field identification; Link prediction; Photovoltaics technology (search for similar items in EconPapers)
Date: 2025
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s11192-025-05394-z Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:scient:v:130:y:2025:i:8:d:10.1007_s11192-025-05394-z

Ordering information: This journal article can be ordered from
http://www.springer.com/economics/journal/11192

DOI: 10.1007/s11192-025-05394-z

Access Statistics for this article

Scientometrics is currently edited by Wolfgang Glänzel

More articles in Scientometrics from Springer, Akadémiai Kiadó
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().