|
|
|
| Technology Opportunity Identification Based on Dynamic Graph Neural Networks |
| Du Xianjin1,2, Xu Yuxiang1, Che Zifan2, Fu Hong1,3, Wu Gen2 |
1.School of Management, Hefei University of Technology, Hefei 230009
2.High Technology Research and Development Center, National Natural Science Foundation of China, Beijing 100044
3.Second Department, Ministry of Science and Technology, Beijing 100862 |
|
|
|
|
Abstract Technological opportunity identification is a critical driver of innovation. This study proposes a dynamic graph neural network (DGNN)-based identification method to improve the accuracy and timeliness of technological opportunity identification. This approach constructs annual International Patent Classification (IPC) co-occurrence networks and utilizes feature learning to obtain node topological, textual, and hierarchical semantic attributes. These features are then weighted and fused using multimodal fusion methods and attention mechanisms. By training the DGNN model, the long short-term memory network (LSTM) was used to model the evolutionary process of the network structure and node attributes, enabling link prediction for potential future IPC combinations. Technological opportunities were evaluated by combining the centrality metrics with the Louvain algorithm. In the task of identifying technological opportunities in the field of new energy vehicle manufacturing, all the indicators of the model proposed in this paper are significantly better than those of the baseline model. Notably, the AUC value reaches 0.875, and the F1 value reaches 0.823, which are respectively 6.45% and 6.74% higher than those of the second-best model, EvolveGCN. The results reveal technological hotspot trends and development directions and provide actionable references and guidance for innovation practices.
|
|
Received: 01 March 2025
|
|
|
|
1 伊惠芳, 刘细文, 龙艺璇. 技术创新全视角下技术机会发现研究进展[J]. 图书情报工作, 2021, 65(7): 132-142.
2 Song K, Kim K S, Lee S. Discovering new technology opportunities based on patents: text-mining and F-term analysis[J]. Technovation, 2017, 60: 1-14.
3 吴颖文, 纪杨建, 顾新建. 基于专利动态复杂网络的产业共性技术预测[J]. 计算机集成制造系统, 2020, 26(12): 3185-3194.
4 李慧, 孟玮, 徐存真. 基于专利知识流网络的技术融合分析——以石墨烯领域为例[J]. 现代情报, 2021, 41(5): 121-130.
5 许鑫, 李倩, 姚占雷. 基于图神经网络的技术识别链接预测方法研究[J]. 数据分析与知识发现, 2023, 7(6): 15-25.
6 岳俊举, 冯立杰, 冯奕程, 等. 基于多维技术创新地图与关联规则挖掘的技术机会识别方法研究[J]. 情报学报, 2017, 36(8): 798-808.
7 Porter A L, Detampel M J. Technology opportunities analysis[J]. Technological Forecasting and Social Change, 1995, 49(3): 237-255.
8 Hwang M N, Cho M H, Hwang M G, et al. Application of trend detection of technical terms to technology opportunity discovery[C]// Proceedings of the International Conference on U- and E-Service, Science and Technology. Heidelberg: Springer, 2011: 258-262.
9 张金柱, 李溢峰. 专利分类序列和文本语义表示视角下的技术融合预测研究[J]. 情报学报, 2022, 41(6): 609-624.
10 Kim B, Gazzola G, Yang J, et al. Two-phase edge outlier detection method for technology opportunity discovery[J]. Scientometrics, 2017, 113(1): 1-16.
11 Park I, Yoon B. Technological opportunity discovery for technological convergence based on the prediction of technology knowledge flow in a citation network[J]. Journal of Informetrics, 2018, 12(4): 1199-1222.
12 Cho J H, Lee J, Sohn S Y. Predicting future technological convergence patterns based on machine learning using link prediction[J]. Scientometrics, 2021, 126(7): 5413-5429.
13 曹兴, 朱晶莹, 杨春白雪. 新兴技术创新网络“液态化”机理及实证分析[J]. 科研管理, 2022, 43(2): 55-64.
14 Ren H Y, Zhao Y H. Technology opportunity discovery based on constructing, evaluating, and searching knowledge networks[J]. Technovation, 2021, 101: 102196.
15 冯立杰, 王清华, 王金凤, 等. 基于SAO语义分析与多维技术创新地图的技术创新机会识别研究[J]. 科技管理研究, 2022, 42(23): 11-20.
16 Eilers K, Frischkorn J, Eppinger E, et al. Patent-based semantic measurement of one-way and two-way technology convergence: the case of ultraviolet light emitting diodes (UV-LEDs)[J]. Technological Forecasting and Social Change, 2019, 140: 341-353.
17 张晓黎, 匡衡. 基于动态专利嵌入表示的AI产业技术融合预测研究[J]. 数据分析与知识发现, 2025, 9(3): 96-105.
18 Zhou T, Lü L Y, Zhang Y C. Predicting missing links via local information[J]. The European Physical Journal B, 2009, 71(4): 623-630.
19 Yoon B, Magee C L. Exploring technology opportunities by visualizing patent information based on generative topographic mapping and link prediction[J]. Technological Forecasting and Social Change, 2018, 132: 105-117.
20 金可怡, 周立军, 杨静. 基于SAO结构的颠覆性技术关联机会发现路径研究[J]. 情报杂志, 2024, 43(9): 84-91, 111.
21 Perozzi B, Al-Rfou R, Skiena S. DeepWalk: online learning of social representations[C]// Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM Press, 2014: 701-710.
22 Grover A, Leskovec J. Node2Vec: scalable feature learning for networks[C]// Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM Press, 2016: 855-864.
23 Kipf T N, Welling M. Semi-supervised classification with graph convolutional networks[OL]. (2017-02-22). https://arxiv.org/pdf/1609.02907.
24 Veli?kovi? P, Cucurull G, Casanova A, et al. Graph attention networks[C]// Proceedings of the 6th International Conference on Learning Representations. Appleton: ICLR, 2018: 1-12.
25 Hamilton W L, Ying R, Leskovec J. Inductive representation learning on large graphs[C]// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook: Curran Associates, 2017: 1025-1035.
26 冯宁, 郭晟楠, 宋超, 等. 面向交通流量预测的多组件时空图卷积网络[J]. 软件学报, 2019, 30(3): 759-769.
27 刘非凡, 张爽, 罗双玲, 等. 基于深度图神经网络方法的领域知识结构探测[J]. 情报学报, 2021, 40(11): 1209-1220.
28 谢小东, 吴洁, 盛永祥, 等. 基于图卷积网络的发明人跨领域合作伙伴识别方法[J]. 情报杂志, 2024, 43(4): 175-183, 167.
29 施国良, 张丽丽, 张笑笑, 等. 基于专利数据的产业链视角下企业合作目标预测研究——以新能源汽车产业为例[J]. 情报理论与实践, 2024, 47(8): 120-128.
30 谢小东, 吴洁, 盛永祥, 等. 基于动态图卷积网络的发明人潜在合作伙伴识别方法研究[J]. 数据分析与知识发现, 2025, 9(3): 83-95.
31 Pareja A, Domeniconi G, Chen J, et al. EvolveGCN: evolving graph convolutional networks for dynamic graphs[C]// Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2020: 5363-5370.
32 Sankar A, Wu Y H, Gou L, et al. DySAT: deep neural representation learning on dynamic graphs via self-attention networks[C]// Proceedings of the 13th International Conference on Web Search and Data Mining. New York: ACM Press, 2020: 519-527.
33 Goyal P, Kamra N, He X R, et al. DynGEM: deep embedding method for dynamic graphs[OL]. (2018-05-29). https://arxiv.org/pdf/1805.11273.
34 Xu D, Ruan C W, Korpeoglu E, et al. Inductive representation learning on temporal graphs[OL]. (2020-02-19). https://arxiv.org/pdf/2002.07962.
35 Wang Q R, Guo B, Ouyang Y, et al. Spatial community-informed evolving graphs for demand prediction[C]// Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases. Cham: Springer, 2021: 440-456.
36 Le Q, Mikolov T. Distributed representations of sentences and documents[J]. Proceedings of Machine Learning Research., 2014, 32(2): 1188-1196.
37 慎金花, 陈红艺, 张更平, 等. 基于层次分类器的专利文本分类模型研究[J]. 情报杂志, 2023, 42(8): 157-163, 68.
38 何俊, 张彩庆, 李小珍, 等. 面向深度学习的多模态融合技术研究综述[J]. 计算机工程, 2020, 46(5): 1-11.
39 Cai Z G, Zhou Y, Xu Y, et al. Patent analysis for identifying core technology and forecasting promising technology in medical imaging equipment[J]. IEEE Transactions on Engineering Management, 2024, 71: 14375-14386.
40 Yan E J, Ding Y. Applying centrality measures to impact analysis: a coauthorship network analysis[J]. Journal of the American Society for Information Science and Technology, 2009, 60(10): 2107-2118.
41 陈文杰, 曲建升. 基于超链路预测的多元技术机会发现研究[J]. 情报学报, 2025, 44(7): 892-902.
42 万校基, 赖静, 牟莹禧, 等. 基于矩阵画像和Louvain社区发现算法的关键核心技术识别研究[J]. 情报学报, 2025, 44(7): 903-914.
43 黄山, 陈洲玲. 基于专利计量和技术生命周期预测的新能源汽车全产业链技术竞争态势研究[J]. 中国科技论坛, 2023(10): 62-73.
44 Zhao K, Guo C J, Cheng Y Y, et al. Multiple time series forecasting with dynamic graph modeling[J]. Proceedings of the VLDB Endowment, 2023, 17(4): 753-765.
45 纪亚琨, 余翔, 张奔, 等. 专利网络视角下的潜在颠覆性技术识别——以自动驾驶领域为例[J]. 情报杂志, 2022, 41(12): 46-50, 139.
46 Sun B X, Kolesnikov S, Goldstein A, et al. A dynamic approach for identifying technological breakthroughs with an application in solar photovoltaics[J]. Technological Forecasting and Social Change, 2021, 165: 120534. |
|
|
|
