|
|
|
| A Deep Learning Approach for Identification of Potentially Disruptive Technologies by Integrating Patent Data and Social Media |
| Feng Lijie1,2, Qin Hao1,3, Wang Jinfeng4, Liu Peng1,3, Wu Xuan1,3, Zhang Zhixin1,3 |
1.School of Management, Zhengzhou University, Zhengzhou 450001
2.Logistics Engineering College, Shanghai Maritime University, Shanghai 201306
3.Henan Innovation Method Engineering Technology Research Center, Zhengzhou 450001
4.China Institute of FTZ Supply Chain, Shanghai Maritime University, Shanghai 201306 |
|
|
|
|
Abstract In promoting social progress and economic development, prompt and accurate identification of potentially disruptive technologies is critical for enhancing enterprise competitiveness and driving industrial transformation. This study proposes a method for the early identification of potentially disruptive technologies by integrating patent and social media data, as an important supplement to existing research theories and methods. First, the relevant patent data in the field were retrieved and divided. Second, based on the characteristics of disruptive technologies, indicators related to disruptive technologies were selected to construct an indicator system and calculate the technological impact. Third, Bi-LSTM was employed to train the relationship between patent indicators and technological impact, whereby candidate disruptive technologies were predicted and combined with BERTopic to extract technology topics. Social topics were extracted from social media data through BERTopic modeling and evaluated for attention and sentiment tendencies. Subsequently, using semantic similarity, the social topics were matched and mapped to technology topics for classification, to identify potentially disruptive technologies. The application of this identification method is illustrated in medical robots. The results demonstrated that the Bi-LSTM model achieves above 90% accuracy, precision, recall, and F1-score metrics, outperforming other models. Potentially disruptive technologies in the field of medical robotics can be classified into high attention-positive attitude, low attention-positive attitude, and low attention-negative attitude. The potentially disruptive technologies identified in medical robotics can provide valuable references for national development policies and relevant industry arrangements.
|
|
Received: 17 May 2023
|
|
|
|
1 Lee P C. Investigating long-term technological competitiveness: originality, generality, and longevity[J]. IEEE Transactions on Engineering Management, 2024, 71: 20-42.
2 Kemeny T, Petralia S, Storper M. Disruptive innovation and spatial inequality[J/OL]. Regional Studies, (2022-07-20). https://doi.org/10.1080/00343404.2022.2076824.
3 Liu X W, Wang X Z, Lyu L C, et al. Identifying disruptive technologies by integrating multi-source data[J]. Scientometrics, 2022, 127(9): 5325-5351.
4 孙永福, 王礼恒, 孙棕檀, 等. 引发产业变革的颠覆性技术内涵与遴选研究[J]. 中国工程科学, 2017, 19(5): 9-16.
5 Zhang Y, Robinson D K R, Porter A L, et al. Technology roadmapping for competitive technical intelligence[J]. Technological Forecasting and Social Change, 2016, 110: 175-186.
6 Guo J F, Pan J F, Guo J X, et al. Measurement framework for assessing disruptive innovations[J]. Technological Forecasting and Social Change, 2019, 139: 250-265.
7 于光辉, 宁钟, 李昊夫. 基于专利和Bass模型的颠覆性技术识别方法研究[J]. 科学学研究, 2021, 39(8): 1467-1473, 1536.
8 Cheng Y, Huang L C, Ramlogan R, et al. Forecasting of potential impacts of disruptive technology in promising technological areas: Elaborating the SIRS epidemic model in RFID technology[J]. Technological Forecasting and Social Change, 2017, 117: 170-183.
9 陈育新, 卢俊, 韩毅. 基于专利文献的颠覆性技术识别研究——以人工智能为例[J]. 情报学报, 2022, 41(11): 1124-1133.
10 李乾瑞, 郭俊芳, 黄颖, 等. 基于专利计量的颠覆性技术识别方法研究[J]. 科学学研究, 2021, 39(7): 1166-1175.
11 Dotsika F, Watkins A. Identifying potentially disruptive trends by means of keyword network analysis[J]. Technological Forecasting and Social Change, 2017, 119: 114-127.
12 马永红, 孔令凯, 林超然, 等. 基于异构数据的颠覆性技术识别研究——以智能制造装备领域为例[J]. 现代情报, 2022, 42(7): 92-104.
13 谭晓, 西桂权, 苏娜, 等. 科学—技术—项目联动视角下颠覆性技术识别研究[J]. 情报杂志, 2023, 42(2): 82-91.
14 吕璐成, 赵萍, 姜山, 等. 基于候选技术辅助生成和多源数据评估的颠覆性技术识别方法研究[J]. 情报理论与实践, 2023, 46(6): 136-144.
15 程鹏, 梁艳, 柳卸林, 等. 突破性产品创新群的实现机制——基于应用场景视角[J]. 科学学与科学技术管理, 2022, 43(12): 76-93.
16 陈稳, 陈伟. 基于计量指标多变量LSTM模型的新兴主题热度预测研究[J]. 数据分析与知识发现, 2022, 6(10): 35-45.
17 刘惠, 刘振宇, 郏维强, 等. 深度学习在装备剩余使用寿命预测技术中的研究现状与挑战[J]. 计算机集成制造系统, 2021, 27(1): 34-52.
18 文井辉, 伍荣森, 李帅永, 等. 基于DRSN和优化BiLSTM的轴承剩余寿命预测方法[J/OL]. 计算机集成制造系统, (2022-08-26) [2024-01-15]. http://kns.cnki.net/kcms/detail/11.5946.TP.20220826.1702.002.html.
19 Khine W L K, Aung N T T. Applying deep learning approach to targeted aspect-based sentiment analysis for restaurant domain[C]// Proceedings of the 2019 International Conference on Advanced Information Technologies. IEEE, 2019: 206-211.
20 Zhang K, Lin K Y, Wang J F, et al. UNISON framework for user requirement elicitation and classification of smart product-service system[J]. Advanced Engineering Informatics, 2023, 57: 101996.
21 李刚, 孟坤, 贺帅, 等. 考虑特征耦合的Bi-LSTM变压器故障诊断方法[J]. 中国电力, 2023, 56(3): 100-108, 117.
22 Ali F, Ali A, Imran M, et al. Traffic accident detection and condition analysis based on social networking data[J]. Accident Analysis & Prevention, 2021, 151: 105973.
23 Ali F, El-Sappagh S, Riazul Islam S M, et al. An intelligent healthcare monitoring framework using wearable sensors and social networking data[J]. Future Generation Computer Systems, 2021, 114: 23-43.
24 马建红, 王瑞杨, 姚爽, 等. 基于深度学习的专利分类方法[J]. 计算机工程, 2018, 44(10): 209-214.
25 周波, 冷伏海. 演绎逻辑与归纳逻辑视角下的颠覆性技术识别方法研究述评[J]. 情报学报, 2022, 41(9): 980-990.
26 王金凤, 仵轩, 冯立杰, 等. 用户偏好-制造商偏好双重视阈下的产品创新机会识别路径研究[J/OL]. 计算机集成制造系统, (2023-01-17) [2023-05-08]. https://kns.cnki.net/kcms/detail//11.5946.TP.20230117.0949.001.html
27 冯立杰, 秦浩, 张珂, 等. 基于离群专利和多维技术创新地图的技术机会识别路径研究[J]. 情报理论与实践, 2023, 46(9): 79-86.
28 赵爽, 周桂君. 中华哲学典籍海外读者评价的影响因素研究——以《易经》英译本为例[J]. 现代情报, 2023, 43(3): 64-72, 147.
29 张清慧, 陈谊, 武彩霞. 基于词表示模型的领域文献数据可视分析方法[J]. 图学学报, 2022, 43(4): 685-694.
30 杨思洛, 吴丽娟. 基于BERTopic模型的国外信息资源管理研究进展分析[J]. 情报理论与实践, 2024, 47(2): 189-197.
31 陈育新, 李健, 韩毅. 核心—边缘理论视角下的颠覆性技术识别研究[J]. 情报理论与实践, 2022, 45(8): 121-129.
32 单晓红, 韩晟熙, 刘晓燕. 基于技术主题演化的颠覆性技术识别研究[J]. 情报理论与实践, 2023, 46(8): 113-123.
33 Zhou Y, Dong F, Liu Y F, et al. A deep learning framework to early identify emerging technologies in large-scale outlier patents: an empirical study of CNC machine tool[J]. Scientometrics, 2021, 126(2): 969-994.
34 Callaert J, Grouwels J, van Looy B. Delineating the scientific footprint in technology: identifying scientific publications within non-patent references[J]. Scientometrics, 2012, 91(2): 383-398.
35 衣春波, 赵文华, 邓璐芗, 等. 基于专利信息的技术创新策源评价指标体系构建与应用[J]. 情报杂志, 2021, 40(2): 55-62.
36 罗素平, 寇翠翠, 金金, 等. 基于离群专利的颠覆性技术预测——以中药专利为例[J]. 情报理论与实践, 2019, 42(7): 165-170.
37 康旭东, 贾汐玥, 邓乐乐, 等. 基于全代引证网络的高影响力专利知识扩散特征研究[J]. 图书情报工作, 2022, 66(22): 83-94.
38 黄鲁成, 刘春文, 吴菲菲, 等. 基于NPCIA的核心技术识别模型及应用研究[J]. 科学学研究, 2020, 38(11): 1998-2007.
39 Zhang D T, Tang P. Forecasting European Union allowances futures: the role of technical indicators[J]. Energy, 2023, 270: 126916.
40 王康, 陈悦. 基于异质性专利的颠覆性技术早期识别研究[J]. 科学学研究, 2023, 41(8): 1364-1375.
41 Chui C K, Lin S B, Zhang B, et al. Realization of spatial sparseness by deep ReLU nets with massive data[J]. IEEE Transactions on Neural Networks and Learning Systems, 2022, 33(1): 229-243.
42 Yang B C, Sun X C, Shi Q H, et al. Prediction of early prognosis after traumatic brain injury by multifactor model[J]. CNS Neuroscience & Therapeutics, 2022, 28(12): 2044-2052.
43 Coccia M. Theories and laws of scientific development[R]. ID 3568913. Rochester: Social Science Research Network, 2020.
44 王超, 马铭, 李思思, 等. Altmetrics视角下颠覆性技术的社会影响力探测研究[J]. 情报理论与实践, 2022, 45(1): 93-104.
45 Yu S B, Eisenman D, Han Z Q. Temporal dynamics of public emotions during the COVID-19 pandemic at the epicenter of the outbreak: sentiment analysis of Weibo posts from Wuhan[J]. Journal of Medical Internet Research, 2021, 23(3): e27078.
46 王超, 马铭, 王海燕, 等. 生命周期视角下颠覆性技术的扩散特征研究[J]. 情报学报, 2022, 41(8): 845-859.
47 王康, 陈悦, 宋超, 等. 颠覆性技术: 概念辨析与特征分析[J]. 科学学研究, 2022, 40(11): 1937-1946.
48 苏成, 赵志耘, 赵筱媛, 等. 颠覆性技术新阐释: 概念、内涵及特征[J]. 情报学报, 2021, 40(12): 1253-1262.
49 赵志耘, 潘云涛, 苏成, 等. 颠覆性技术感知响应系统框架研究[J]. 情报学报, 2021, 40(12): 1245-1252.
50 Wang J F, Zhang Z X, Feng L J, et al. Development of technology opportunity analysis based on technology landscape by extending technology elements with BERT and TRIZ[J]. Technological Forecasting and Social Change, 2023, 191: 122481.
51 Nwosu A C, Sturgeon B, McGlinchey T, et al. Robotic technology for palliative and supportive care: strengths, weaknesses, opportunities and threats[J]. Palliative Medicine, 2019, 33(8): 1106-1113.
52 任佳妮, 张薇, 杨阳, 等. “人工智能+医疗”新兴技术识别研究——以医疗机器人为例[J]. 情报杂志, 2021, 40(12): 45-50.
53 叶佳慧, 许鑫. 医疗机器人领域科技发展水平现状与研究热点[J]. 中华医学图书情报杂志, 2022, 31(7): 41-49.
54 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.
55 Thompson K A, Dickenson E R V. Using machine learning classification to detect simulated increases of de facto reuse and urban stormwater surges in surface water[J]. Water Research, 2021, 204: 117556. |
|
|
|
