PTNS: patent citation trajectory prediction based on temporal network snapshots

• Published in: Scientific reports Vol. 14; no. 1; pp. 24034 - 15
• Main Authors: Ding, Mingli, Yu, Wangke, Zeng, Tingyu, Wang, Shuhua
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 14.10.2024; Nature Publishing Group; Nature Portfolio
• Subjects: 639/705/1046; 639/705/531; 704/844/2787; Citations; Graph representations; Humanities and Social Sciences; Innovations; Intellectual property; Long short-term memory; Machine learning; multidisciplinary; Network snapshots; Neural networks; Patent citation; Prediction models; Principal components analysis; Science; Science (multidisciplinary); Semantics; Technological change; Temporal variations; Time series; Trajectory prediction; Trajectory prediction; Patent citation; Network snapshots; Time series
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-024-75913-0

With the rapid development of science and technology, the pace of development in the knowledge economy is accelerating. Intellectual property, especially patents, is a strategic resource for technological innovation and a crucial support for building an innovative country. Therefore, it is particularly important to predict patents with high value and strong impact from the numerous and uneven-quality patents. However, patent citation behavior involves many uncertainties, and it is difficult to capture its temporal variations effectively. Therefore, this paper proposes a patent citation trajectory prediction model (PTNS) based on temporal network snapshots. It adopts relational graph convolutional networks (R-GCN) to learn the complex relationships among multiple attributes of patents and utilizes bidirectional long short-term memory networks (BiLSTM) to aggregate the temporal evolution differences of patents. Subsequently, principal component analysis (PCA) is used to explore the evolution characteristics of patent citations in depth, thereby capturing the aging effect and the ‘sleeping beauty’ phenomenon. Compared with other baselines, the PTNS performs well. In predicting new, grown, and random patents, the RMSLE decreases by approximately 0.04, 0.14, and 0.18 respectively, while the MALE decreases by approximately 0.04, 0.12, and 0.16 respectively.