|
|
|
| Multisource Data Fusion and Emerging Frontier Technology Topic Detection Based on Graph Neural Networks |
| Tian Xuecan1, Wang Li2,3 |
1.School of Information Management, Wuhan University, Wuhan 430072
2.National Science Library, Chinese Academy of Sciences, Beijing 100190
3.Department of Information Resources Management, School of Economics and Management, University of Chinese Academy of Sciences, Beijing 100190 |
|
|
|
|
Abstract Against the backdrop of rapid technological advancements and profound shifts in the innovation landscape, an efficient detection of emerging frontier technologies through fine-grained traceable semantic unit-level data fusion has a significant practical value. In this paper, a multisource data fusion and emerging frontier technology detection framework based on graph neural networks is proposed, refining the granularity of data fusion and technology detection from both semantic and structural feature perspectives. The framework constructs three indicator sets, novelty, growth, and attention, centered around the core characteristics of emerging technologies, embedding these indicator values as node attributes into technology cooccurrence networks to enrich the semantic features of single-source networks. Alternatively, by leveraging the strengths of graph attention networks in capturing structural features, it achieves feature-level multisource data fusion, enhancing both granularity and interpretability of the fusion process. Using the field of quantum sensing as an empirical case study, experimental results demonstrate that the proposed method enables an efficient multisource data fusion through node alignment operations, with correctly predicted entity pairs appearing within the top one to three positions of the result list on average. The refined fusion of multisource data not only improves the granularity of emerging frontier technology detection but also effectively reduces misjudgment risks, validating the framework’s potential to enhance the accuracy and interpretability of emerging frontier technology detection.
|
|
Received: 23 July 2025
|
|
|
|
1 孔德婧, 董放, 陈子婧, 等. 离群专利视角下的新兴技术预测——基于BERT模型和深度神经网络[J]. 图书情报工作, 2021, 65(17): 131-141.
2 廖鹏飞, 李明鑫, 万锋. 基于长尾关键词的领域新兴前沿探寻模型构建研究[J]. 情报杂志, 2020, 39(3): 51-55.
3 中国科学院科技战略咨询研究院, 中国科学院文献情报中心, 科睿唯安. 2023研究前沿[R/OL]. (2023-11-28) [2025-05-13]. http://www.casisd.cn/zkcg/zxcg/202311/P020240105542012235470.pdf.
4 余玉刚, 郑圣明, 李建平, 等. 管理科学与工程学科“十四五”重点前沿领域的顶层布局与具体内容: 面向基础科学理论与国家重大需求[J]. 中国管理科学, 2022, 30(5): 1-8.
5 颉靖, 张睿健. 美军网信前沿重点领域科技创新与军事应用研究[J]. 中国电子科学研究院学报, 2021, 16(10): 1006-1011.
6 王达. 日本第11次技术预见方法及经验解析[J]. 今日科苑, 2020(1): 10-15.
7 秦琴琴, 乜勇. 基于词频分析和可视化共词网络图的国内创客研究热点分析[J]. 现代教育技术, 2016, 26(1): 113-119.
8 杨选辉, 杜心雨, 蔡志强. 基于突变检测与共词分析的深阅读新兴趋势分析[J]. 图书馆建设, 2018(5): 48-53.
9 马红鸽, 莫正晖. 人工智能对劳动力供给的影响问题研究——基于CiteSpace科学知识图谱(2010—2020)[J]. 重庆理工大学学报(社会科学), 2022, 36(4): 118-132.
10 Li M N, Chu Y Q. Explore the research front of a specific research theme based on a novel technique of enhanced co-word analysis[J]. Journal of Information Science, 2017, 43(6): 725-741.
11 徐畅, 管开轩, 宋昱晓, 等. 文献计量视角下全球人工智能领域研究态势与热点分析[J]. 科技促进发展, 2021, 17(11): 1968-1977.
12 Shibata N, Kajikawa Y, Takeda Y, et al. Detecting emerging research fronts based on topological measures in citation networks of scientific publications[J]. Technovation, 2008, 28(11): 758-775.
13 Lu L Y Y, Liu J S. A novel approach to identify research fronts of tourism literature[C]// Proceedings of the 2015 Portland International Conference on Management of Engineering and Technology. Piscataway: IEEE, 2015: 2211-2217.
14 Morris S A, Yen G, Wu Z, et al. Time line visualization of research fronts[J]. Journal of the American Society for Information Science and Technology, 2003, 54(5): 413-422.
15 Liu J S, Lu L Y Y, Lu W M. Research fronts in data envelopment analysis[J]. Omega, 2016, 58: 33-45.
16 Zhang L, Gl?nzel W, Ye F Y. The dynamic evolution of core documents: an experimental study based on h-related literature (2005-2013)[J]. Scientometrics, 2016, 106(1): 369-381.
17 周云泽, 闵超. 基于LDA模型与共享语义空间的新兴技术识别——以自动驾驶汽车为例[J]. 数据分析与知识发现, 2022, 6(2-3): 55-66.
18 刘自强, 岳丽欣, 方曙. 基于主题扩散演化滞后的研究前沿趋势预测方法研究[J]. 情报理论与实践, 2023, 46(6): 145-154.
19 陈斌, 马静. 基于HLDA-IDF模型的网络文本主题挖掘研究[J]. 情报理论与实践, 2017, 40(10): 117-122, 144.
20 林晗, 汤珊红, 高强, 等. 基于改进HLDA的前沿主题挖掘方法研究[J]. 情报理论与实践, 2022, 45(11): 188-194.
21 余传明, 原赛, 朱星宇, 等. 基于深度学习的热点事件主题表示研究[J]. 数据分析与知识发现, 2020, 4(4): 1-14.
22 吕鲲, 项旻昊, 靖继鹏. 基于LDA2Vec和DTM模型的颠覆性技术主题识别研究——以能源科技领域为例[J]. 图书情报工作, 2023, 67(12): 89-102.
23 Jiang J R, Ying F L, Dhuny R. Unveiling technological evolution with a patent-based dynamic topic modeling framework: a case study of advanced 6G technologies[J]. Applied Sciences, 2025, 15(7): 3783.
24 曹树金, 曹茹烨. 基于研究主题和引文分析的信息资源管理学科发展探究[J]. 信息资源管理学报, 2023, 13(2): 12-29.
25 Zheng X L, Wu Q, Luo X Y, et al. Analyzing the evolutionary trajectory of technological themes based on the BERTopic model: a case study in the field of artificial intelligence[J]. PLoS One, 2025, 20(6): e0324933.
26 Xu H Y, Winnink J, Yue Z H, et al. Multidimensional scientometric indicators for the detection of emerging research topics[J]. Technological Forecasting and Social Change, 2021, 163: 120490.
27 Zhang B, Yu X, Zhang R Z. Emerging technology identification based on a dynamic framework: a lifecycle evolution perspective[J]. Technology Analysis & Strategic Management, 2024, 36(2): 378-392.
28 李涛民. 基于LDA模型的科学基金主题分析[D]. 西安: 西安电子科技大学, 2018.
29 谢秀芳, 张晓林. 针对科技路线图的文本挖掘研究: 集成分析及可视化[J]. 数据分析与知识发现, 2017, 1(1): 16-25.
30 张维冲, 王芳, 赵洪. 多源信息融合用于新兴技术发展趋势识别——以区块链为例[J]. 情报学报, 2019, 38(11): 1166-1176.
31 张浩. 数据融合视角下技术预测方法研究[D]. 长春: 吉林大学, 2019.
32 刘博文, 白如江, 周彦廷, 等. 基金项目数据和论文数据融合视角下科学研究前沿主题识别——以碳纳米管领域为例[J]. 数据分析与知识发现, 2019, 3(8): 114-122.
33 Shen Y C, Wang M Y, Yang Y C. Discovering the potential opportunities of scientific advancement and technological innovation: a case study of smart health monitoring technology[J]. Technological Forecasting and Social Change, 2020, 160: 120225.
34 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.
35 黄衍标, 罗广岳, 何铭金. BP神经网络在巡逻机器人多传感器数据融合中的应用[J]. 传感技术学报, 2016, 29(12): 1936-1940.
36 Luo Y, Xiao F S, Zhao H. Hierarchical contextualized representation for named entity recognition[C]// Proceedings of the 34th AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2020: 8441-8448.
37 刘耀, 张越, 叶璐. 融合篇章结构的文本知识网络构建[J]. 图书情报工作, 2021, 65(21): 118-130.
38 杨春霞, 李锐, 秦家鹏. 一种粒度融合的新闻文本主题分类模型[J]. 小型微型计算机系统, 2020, 41(11): 2256-2259.
39 Situ Z, Wang Q, Teng S, et al. Improving urban flood prediction using LSTM-DeepLabv3+ and Bayesian optimization with spatiotemporal feature fusion[J]. Journal of Hydrology, 2024, 630: 130743.
40 连芷萱, 王芳, 康佳, 等. 基于图神经网络和粒子群算法的技术预测模型[J]. 情报学报, 2023, 42(4): 420-435.
41 Yuan G, Fan X M, Xiao Y, et al. FME-GCN: a multi-source heterogeneous data fusion approach for high-accuracy traffic flow prediction[J]. IEEE Access, 2025, 13: 181100-181115.
42 杨冠灿, 行佳鑫, 鲁国轩, 等. 基于图神经网络的细粒度技术会聚预测方法研究[J]. 信息资源管理学报, 2023, 13(2): 95-107.
43 李慧, 胡吉霞. 一种基于图卷积自编码模型的多维度学科知识网络融合方法[J]. 图书情报工作, 2020, 64(18): 114-125.
44 Wang X, Wang Y T, Yang J, et al. The survey on multi-source data fusion in cyber-physical-social systems: foundational infrastructure for industrial metaverses and industries 5.0[J]. Information Fusion, 2024, 107: 102321.
45 Katsurai M, Ono S. TrendNets: mapping emerging research trends from dynamic co-word networks via sparse representation[J]. Scientometrics, 2019, 121(3): 1583-1598.
46 李彤, 肖锋, 张文娟, 等. 基于深度学习的压缩感知图像重构算法综述[J]. 微电子学与计算机, 2022, 39(12): 1-12.
47 黄璐, 朱一鹤, 张嶷. 基于加权网络链路预测的新兴技术主题识别研究[J]. 情报学报, 2019, 38(4): 335-341.
48 Cao Y X, Liu Z Y, Li C J, et al. Multi-channel graph neural network for entity alignment[C]// Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Stroudsburg: Association for Computational Linguistics, 2019: 1452-1461.
49 邓启平, 陈卫静, 张玲玲, 等. 基于多维特征测度的人工智能领域研究前沿分析[J]. 情报杂志, 2020, 39(3): 56-62.
50 Sun Z Q, Hu W, Zhang Q H, et al. Bootstrapping entity alignment with knowledge graph embedding[C]// Proceedings of the 27th International Joint Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2018: 4396-4402. |
|
|
|
