Patent landscape and key technology interaction roadmap using graph convolutional network – Case of mobile communication technologies beyond 5G. Issue 1 (February 2023)

• Record Type: Journal Article
• Authors: Trappey, Amy J.C.; Wei, Ann Y.E.; Chen, Neil K.T.; Li, Kuo-An; Hung, L.P.; Trappey, Charles V.
• Is Part Of: Journal of informetrics. Volume 17:Issue 1(2023)
• Publication Date: 2023-02
• Subjects: Tech-mining analysis -- Patent analysis -- Keyword extraction -- Graph convolution network (GCN); Library statistics -- Periodicals; Information science -- Statistical methods -- Periodicals; Bibliometrics -- Periodicals; Bibliothèques -- Statistiques -- Périodiques; Sciences de l'information -- Méthodes statistiques -- Périodiques; Bibliométrie -- Périodiques; 020.727
• DOI: 10.1016/j.joi.2022.101354
• Languages: English
• ISSNs: 1751-1577

Abstract

Highlights: Develop tech-mining workflow integrates patent/NPL semantic analyses, topic clustering, and GCN. Propose GCN model for discovering R&D interactions between tech-topics of any domain. The novel tech-mining focuses on the advanced mobile network technologies beyond 5G (B5G) case. B5G patents/NPLs are semantically analyzed to build comprehensive B5G ontology. B5G patent landscape and key technology interactions are generated for advanced R&D strategies. Abstract: Beyond 5G (B5G) in mobile network technologies is the latest communication technology currently under development. B5G is expected to achieve superior capabilities in ultra-high network transmission speed, low latency, low energy consumption, and high coverage, comparing to current 5G network performance. Although B5G is still in the development and implementation stage, there are many patents and non-patent literature depicting B5G innovative technologies and applications. The landscapes of B5G technologies are great references for governments and industries to understand the advances in mobile communication for R&D strategies. Thus, this research focuses on developing a formal tech-mining workflow integrating semantic-based patent and non-patent literature analysis for ontology building, patent technological topic clustering, and graph convolutional network (GCN) modeling for depicting key technology interactions among clusters of sub-domain topics. This research emphasizes the study of B5G patent landscape and key technology interaction roadmap in comprehensive steps as a valuable reference for B5G mobile network R&D, as well as for conducting tech-mining of other technology domains of interests.