|
|
|
| Research on Industry Emerging Technology Forecast Modeling Based on Knowledge Graph and Deep Neural Networks |
| Wei Mingzhu1, Zheng Rong1,2, Gao Zhihao1, Wang Xiaoyu1 |
1.School of Business and Management, Jilin University, Changchun 130012
2.Information Resources Research Center, Jilin University, Changchun 130012 |
|
|
|
|
Abstract Realizing accurate forecasts of emerging technologies in industry will help advance the layout of industry development, seize the technological commanding heights, and empower high-level technological self-reliance. Based on knowledge graph technology, this research defines the concept, relationship, and attributes of industrial technology patents and constructs an industrial technology patent knowledge graph, focusing on three main characteristics: novelty, social impact, and the fundamental innovation of emerging technologies. Starting from “Novelty-Application Scope-Development Ability” is used to build a complete and quantifiable indicator system for emerging technologies in the industry. Using the complex semantic information of the technology patent knowledge map, map query sentences are mapped to extract the feature values of various indicators, relying on deep neural network algorithms to train a model for predicting emerging technologies in an industry that realizes the accurate prediction of such technologies. Finally, the new energy automobile industry is taken as an example to verify the validity of the model. This research can provide a valuable reference for forecasting emerging technologies in various industries and providing decision support for industrial development.
|
|
Received: 04 January 2022
|
|
|
|
1 全球技术地图. 美国CSIS发布《 2030年全球网络: 发展中经济体和新兴技术》 报告[EB/OL]. (2021-03-30) [2022-10-26]. https://baijiahao.baidu.com/s?id=1695659567092292914&wfr=spider&for=pc.
2 中国科学院科技战略咨询研究院. 欧盟提出工业5.0发展方向及支持措施[EB/OL]. (2021-05-21) [2022-10-26]. http://www.casisd.cn/zkcg/ydkb/kjzcyzxkb/kjzczxkb2021/zczxkb202103/202105/t20210521_6036091.html.
3 中华人民共和国国民经济和社会发展第十四个五年规划和2035年远景目标纲要[EB/OL]. (2021-03-13) [2022-10-26]. http://www.gov.cn/xinwen/2021-03/13/content_5592681.htm.
4 乔治·戴, 保罗·休梅克. 沃顿论新兴技术管理[M]. 石莹, 等译. 北京: 华夏出版社, 2002.
5 周萌, 朱相丽. 新兴技术概念辨析及其识别方法研究进展[J]. 情报理论与实践, 2019, 42(10): 162-169.
6 桂美增, 许学国. 基于深度学习的技术机会预测研究——以新能源汽车为例[J]. 图书情报工作, 2021, 65(19): 130-141.
7 Cho Y Y, Jeong G H, Kim S H. A Delphi technology forecasting approach using a semi-Markov concept[J]. Technological Forecasting and Social Change, 1991, 40(3): 273-287.
8 Lee S, Kim W, Kim Y M, et al. The prioritization and verification of IT emerging technologies using an analytic hierarchy process and cluster analysis[J]. Technological Forecasting and Social Change, 2014, 87: 292-304.
9 Geum Y, Lee S, Yoon B, et al. Identifying and evaluating strategic partners for collaborative R&D: index-based approach using patents and publications[J]. Technovation, 2013, 33(6/7): 211-224.
10 Song B M, Seol H, Park Y. A patent portfolio-based approach for assessing potential R&D partners: an application of the Shapley value[J]. Technological Forecasting and Social Change, 2016, 103: 156-165.
11 Lanjouw J O, Schankerman M. Stylized facts of patent litigation: value, scope and ownership[R]. NBER Working Papers. Cambridge: National Bureau of Economic Research, 1997: No.6297.
12 Narin F, Noma E, Perry R. Patents as indicators of corporate technological strength[J]. Research Policy, 1987, 16(2-4): 143-155.
13 黄鲁成, 卢文光. 基于属性综合评价系统的新兴技术识别研究[J]. 科研管理, 2009, 30(4): 190-194.
14 宋欣娜, 郭颖, 席笑文. 基于专利文献的多指标新兴技术识别研究[J]. 情报杂志, 2020, 39(6): 76-81, 88.
15 马瑞敏, 尉心渊. 技术领域细分视角下核心专利预测研究[J]. 情报学报, 2017, 36(12): 1279-1289.
16 Fujita K, Kajikawa Y, Mori J, et al. Detecting research fronts using different types of weighted citation networks[J]. Journal of Engineering and Technology Management, 2014, 32: 129-146.
17 曹艺文, 许海云, 武华维, 等. 基于引文曲线拟合的新兴技术主题的突破性预测——以干细胞领域为例[J]. 图书情报工作, 2020, 64(5): 100-113.
18 罗建, 蔡丽君, 史敏. 基于专利的两阶段新兴技术识别研究——以图像识别技术为例[J]. 情报科学, 2019, 37(12): 57-62.
19 董放, 刘宇飞, 周源. 基于LDA-SVM论文摘要多分类新兴技术预测[J]. 情报杂志, 2017, 36(7): 40-45, 133.
20 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.
21 翟东升, 刘鹤, 张杰, 等. 一种基于链路预测的技术机会挖掘方法[J]. 情报学报, 2016, 35(10): 1090-1100.
22 王燕鹏, 韩涛, 陈芳. 融合文献知识聚类和复杂网络的关键技术识别方法研究[J]. 图书情报工作, 2020, 64(16): 105-113.
23 Kong D J, Zhou Y, Liu Y F, et al. Using the data mining method to assess the innovation gap: a case of industrial robotics in a catching-up country[J]. Technological Forecasting and Social Change, 2017, 119: 80-97.
24 李冰, 丁堃, 孙晓玲. 企业潜在技术合作伙伴及竞争者预测研究——以燃料电池技术为例[J]. 情报学报, 2021, 40(10): 1043-1051.
25 Song K, Kim K, Lee S. Identifying promising technologies using patents: a retrospective feature analysis and a prospective needs analysis on outlier patents[J]. Technological Forecasting and Social Change, 2018, 128: 118-132.
26 张洋, 林宇航, 侯剑华. 基于融合数据和生命周期的技术预测方法: 以病毒核酸检测技术为例[J]. 情报学报, 2021, 40(5): 462-470.
27 王玏, 吴新年. 新兴技术识别方法研究综述[J]. 图书情报工作, 2020, 64(4): 125-135.
28 魏明珠, 郑荣, 杨竞雄. 基于深度学习的图像检索研究进展[J]. 情报科学, 2021, 39(5): 184-192.
29 李永卉, 周树斌, 周宇婷, 等. 基于图数据库Neo4j的宋代镇江诗词知识图谱构建研究[J]. 大学图书馆学报, 2021, 39(2): 52-61.
30 王红, 张青青, 蔡伟伟, 等. 基于Neo4j的领域本体存储方法研究[J]. 计算机应用研究, 2017, 34(8): 2404-2407.
31 康杰华, 罗章璇. 基于图形数据库Neo4j的RDF数据存储研究[J]. 信息技术, 2015, 39(6): 115-117.
32 Gartner中国. Gartner发布2021年新兴技术成熟度曲线[EB/OL]. (2021-08-26) [2022-10-26]. https://jishuin.proginn.com/p/763bfbd64100.
33 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.
34 汪江桦, 冷伏海, 汤建国. 基于专利的新兴技术未来产业影响力评价研究[J]. 情报杂志, 2014, 33(5): 44-48.
35 Joung J, Kim K. Monitoring emerging technologies for technology planning using technical keyword based analysis from patent data[J]. Technological Forecasting and Social Change, 2017, 114: 281-292.
36 汪涛, 王璐玮, 张晗. 中国城市新兴技术的双元创新路径与发生机制——以生物医药技术为例[J]. 科技进步与对策, 2022, 39(6): 29-39.
37 Porter A L, Garner J, Carley S F, et al. Emergence scoring to identify frontier R&D topics and key players[J]. Technological Forecasting and Social Change, 2019, 146: 628-643. |
|
|
|
