What matters in patent claims: structural and semantic-based feature extraction and embedding optimization

Xinyu Tong (), Linrong Zeng () and Yonghe Lu ()
Additional contact information
Xinyu Tong: Sun Yat-sen University, School of Information Management
Linrong Zeng: Sun Yat-sen University, School of Information Management
Yonghe Lu: Sun Yat-sen University, School of Artificial Intelligence

Scientometrics, 2025, vol. 130, issue 10, No 15, 5665 pages

Abstract: Abstract This study introduces HI-ICD-AugCCE, a hybrid framework that integrates structural and semantic analysis of patent claims using deep learning techniques. By assigning importance weights to individual claims based on hierarchical position and information density, the framework effectively captures the core technical content within patent texts. It further employs an unsupervised contrastive learning model enhanced with data augmentation, enabling accurate similarity evaluation even in the absence of labeled data. Experiments demonstrate that HI-ICD-AugCCE achieves a Spearman correlation of 0.812, representing a 6.98% improvement over baselines. The results highlight the framework’s effectiveness in enhancing the semantic precision and scalability of patent similarity assessment.

Keywords: Patent analysis; Semantic similarity; Unsupervised learning; Contrastive learning (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s11192-025-05427-7 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:10:d:10.1007_s11192-025-05427-7

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

DOI: 10.1007/s11192-025-05427-7

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 ().