基于深度学习的技术机会预测研究——以新能源汽车为例

doi:10.13266/j.issn.0252-3116.2021.19.013

图书情报工作 ›› 2021, Vol. 65 ›› Issue (19): 130-141.DOI: 10.13266/j.issn.0252-3116.2021.19.013

基于深度学习的技术机会预测研究——以新能源汽车为例

桂美增¹, 许学国²

1 浙江财经大学会计学院杭州 310018;
2 上海大学管理学院上海 200444

收稿日期:2021-03-30 修回日期:2021-07-29 出版日期:2021-10-05 发布日期:2021-10-09
通讯作者: 许学国(ORCID:0000-0001-9898-3233),教授,博士,通讯作者,Email:xuxueguo@163.com
作者简介:桂美增(ORCID:0000-0003-4810-8996),讲师,博士。
基金资助:
本文系国家自然科学基金青年项目"关键利益相关者视角下新兴产业创新政策作用机制与仿真优化：以新能源汽车为例"（项目编号：71704101）研究成果之一。

Approach to Technology Opportunity Prediction Based on Deep Learning: Taking the Case of New Energy Vehicles

Gui Meizeng¹, Xu Xueguo²

1 Accounting college, Zhejiang University of Finance and Economics, Hangzhou 310018;
2 School of management, Shanghai University, Shanghai 200444

Received:2021-03-30 Revised:2021-07-29 Online:2021-10-05 Published:2021-10-09

摘要/Abstract

摘要： [目的/意义] 技术机会预测有利于国家和企业管理者识别技术未来的发展方向，从而调整技术发展战略，在技术竞争中占据优势地位。[方法/过程] 提出一种基于深度学习的技术机会预测方法。首先运用AP （affinity propagation）聚类算法实现对技术领域的主题划分。其次运用Doc2Vec算法计算出各技术领域专利文本相似度情况，进而识别出具有发展潜力的技术领域。再次采用生成式拓扑映射（generative topographic mapping，GTM）算法对发展潜力技术领域绘制专利地图，通过GTM逆向映射获得技术机会。最后，构建基于深度学习的链接预测模型，对识别出的技术机会进行链接预测，从而获得高发展概率的技术机会。[结果/结论] 使用新能源汽车专利数据对方法的有效性进行验证，结果显示基于深度学习的链接预测模型的预测准确率、召回率和F1值均优于其他预测模型，并对新能源汽车的技术机会进行预测。

关键词: 技术机会预测, 深度学习, 链接预测, 生成式拓扑映射

Abstract: [Purpose/significance] Technology opportunity prediction helps national and enterprise managers to identify the future direction of technology development, to adjust the development strategy and occupy a favorable posture for technology competition.[Method/process] In this paper, a deep learning-based technology opportunity prediction method was proposed. Firstly, the Affinity Propagation (AP) clustering algorithm was applied to achieve the subject classification of technology fields. Secondly, the Doc2Vec algorithm was used to calculate the similarity of patent texts in each technology area, and then identify the technology areas with development potential. Thirdly, the Generative Topographic Mapping (GTM) algorithm was used to map the patent areas with development potential, and we got the technology opportunities through GTM inverse mapping. Finally, a link prediction model based on deep learning was constructed to predict the links of the identified technology opportunities, to obtain the technology opportunities with high development probability.[Result/conclusion] This paper uses new energy vehicle patent data to verify the effectiveness of the method. The results show that the prediction accuracy, recall and F1 value of the deep learning-based link prediction model outperform other prediction models and predict the technology opportunities for new energy vehicles.

Key words: technology opportunity prediction, deep learning, link prediction, the generative topographic mapping

中图分类号:

C931

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.

Gui Meizeng, Xu Xueguo. Approach to Technology Opportunity Prediction Based on Deep Learning: Taking the Case of New Energy Vehicles[J]. Library and Information Service, 2021, 65(19): 130-141.

参考文献

[1] OLSSON O. Technological opportunity and growth[J]. Journal of economic growth, 2005, 10(1):31-53.
[2] LEE J, KIM C, SHIN J. Technology opportunity discovery to R&D planning:key technological performance analysis[EB/OL].[2021-01-06]. https://doi.org/10.1016/j.techfore.2017.03.011.
[3] SCHWARTZ P. Technological innovation opportunities[J]. Computers and people, 1974, 23(5):33.
[4] PORTER A L, DETAMPEL M J. Technology opportunities analysis[J]. Technological forecasting and social change, 1995, 49(3):237-255.
[5] 潘东华,徐珂珂. 基于共词分析的技术机会分析[J]. 科研管理, 2014, 35(4):12-19.
[6] SON C, SUH Y, JEON J, et al. Development of a GTM-based patent map for identifying patent vacuums[J]. Expert systems with applications, 2012, 39(3):2489-2500.
[7] WOO H G, YEOM J, LEE C. Screening early stage ideas in technology development processes:a text mining and k-nearest neighbours approach using patent information[J]. Technology analysis and strategic management, 2019, 31(5):532-545.
[8] CHANG S H. Technical trends of artificial intelligence in standard-essential patents[J]. Data technologies and applications, 2021, 55(1):97-117.
[9] LI S Y, ZHANG X, XU H Y, et al. Measuring strategic technological strength:patent portfolio model[EB/OL].[2021-01-06]. https://doi.org/10.1016/j.techfore.2020.120119.
[10] TANG Y, LOU X M, CHEN Z F, et al. A study on dynamic patterns of technology convergence with IPC co-occurrence-based analysis:the case of 3D printing[J]. Sustainability, 2020, 12(7):1-26.
[11] JI Y K, ZHU X Z, ZHAO T W, et al. Revealing technology innovation, competition and cooperation of self-driving vehicles from patent perspective[EB/OL].[2021-01-06]. https://doi.org/10.1109/ACCESS.2020.3042019.
[12] WANG M Y, FANG S C, CHANG Y H. Exploring technological opportunities by mining the gaps between science and technology:microalgal biofuels[EB/OL].[2021-01-16].https://doi.org/10.1016/j.techfore.2014.07.008.
[13] MUSYUNI P, AGGARWAL G, NAGPAL M, et al. A case study:analysis of patents on coronaviruses and covid-19 for technological assessment and future research[J]. Current pharmaceutical design, 2021, 27(3):423-439.
[14] FENG L J, NIU Y X, LIU Z F, et al. Discovering technology opportunity by keyword-based patent analysis:a hybrid approach of morphology analysis and usit[J]. Sustainability, 2020, 12(1):1-35.
[15] ZHOU X, HUANG L, ZHANG Y, et al. A hybrid approach to detecting technological recombination based on text mining and patent network analysis[J]. Scientometrics, 2019, 121(2):699-737.
[16] GERKEN J M, MOEHRLE M G. A new instrument for technology monitoring:novelty in patents measured by semantic patent analysis[J]. Scientometrics, 2012, 91(3):645-670.
[17] LEE S, YOON B, PARK Y. An approach to discovering new technology opportunities:keyword-based patent map approach[J]. Technovation, 2009, 29(6):481-497.
[18] CHOI J, HWANG Y S. Patent keyword network analysis for improving technology development efficiency[EB/OL].[2021-01-06]. https://doi.org/10.1016/j.techfore.2013.07.004.
[19] 吴菲菲,米兰,黄鲁成. 以技术标准为导向的企业研发方向识别与评估[J]. 科学学研究, 2018, 36(10):1837-1847.
[20] 许学国,桂美增.基于GTM逆向映射的技术创新机会识别——以新能源汽车为例[J].情报理论与实践,2021,44(6):146-153,198.
[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] LIBEN D, KLEINBERG J. The link prediction problem for social networks[J]. Journal of the American Society for Information Science and technology, 2007, 58(7):1019-1031.
[23] LEE C, KANG B, SHIN J. Novelty focused patent mapping for technology opportunity analysis[EB/OL].[2021-01-06]. https://doi.org/10.1016/j.techfore.2014.05.010.
[24] LESKOVEC J, HUTTENLOCHER D, KLEINBERG J. Predicting positive and negative links in online social networks[C]//Proceedings of the 19th international conference on world wide web. New York:ACM Press, 2010:641-650.
[25] 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.
[26] ZHOU M, WANG B, GUO S D, et al. Multi-objective prediction intervals for wind power forecast based on deep neural networks[EB/OL].[2021-01-06]. https://doi.org/10.1016/j.ins.2020.10.034.
[27] CHEN J, ZHANG J, XU X, et al. E-LSTM-D:a deep learning framework for dynamic network link prediction[J]. IEEE transactions on systems man cybernetics-systems, 2021, 51(6):3699-3712.
[28] RUI L, ZHU Y, GAO Z, et al. CLPM:a cooperative link prediction model for industrial internet of things using partitioned stacked denoising autoencoder[J]. IEEE transactions on industrial informatics, 2021, 17(5):3620-3629.
[29] YOON B, MAGEE C L. Exploring technology opportunities by visualizing patent information based on generative topographic mapping and link prediction[EB/OL].[2021-01-06]. https://doi.org/10.1016/j.techfore.2018.01.019.
[30] OH S, CHOI J, KO N, et al. Predicting product development directions for new product planning using patent classification-based link prediction[J]. Scientometrics, 2020, 125(3):1833-1876.
[31] 许学国,桂美增. 基于深度学习的技术预测方法——以机器人技术为例[J]. 情报杂志, 2020, 39(8):53-62.
[32] DHELIM S, NING H, AUNG N. Compath:user interest mining in heterogeneous signed social networks for internet of people[J]. IEEE Internet of things journal, 2021, 8(8):7024-7035.
[33] KIM M, PARK Y, YOON J. Generating patent development maps for technology monitoring using semantic patent-topic analysis[EB/OL].[2021-01-06]. https://doi.org/10.1016/j.cie.2016.06.006.
[34] FREY B J, DUECK D. Clustering by passing messages between data points[J]. Science, 2007, 315(5814):972-976.
[35] TAHERI S, BOUYER A. Community detection in social networks using affinity propagation with adaptive similarity matrix[J]. Big data, 2020, 8(3):189-202.
[36] GUAN R, SHI X, MARCHESE M, et al. Text clustering with seeds affinity propagation[J]. IEEE transactions on knowledge and data engineering, 2010, 23(4):627-637.
[37] 国显达,那日萨,高欢,等. 基于Gaussian LDA的在线评论主题挖掘研究[J]. 情报学报, 2020, 39(6):630-639.
[38] YANG Y, DORN C. Affinity propagation clustering of full-field, high-spatial-dimensional measurements for robust output-only modal identification:a proof-of-concept study[EB/OL].[2021-02-06]. https://doi.org/10.1016/j.jsv.2020.115473.
[39] 李勇敢. 技术领域维度下相对技术关联度研究——以德温特专利数据库共类分析为例[J]. 科技进步与对策, 2017, 34(7):146-153.
[40] LE Q, MIKOLOV T. Distributed representations of sentences and documents[C]//Proceedings of the 31st international conference on machine learning. New York:PMLR, 2014:1188-1196.
[41] FENG S. The proximity of ideas:an analysis of patent text using machine learning[J]. Plos one, 2020, 15(7):1-19.
[42] LU Y, XIONG X, ZHANG W, et al. Research on classification and similarity of patent citation based on deep learning[J]. Scientometrics, 2020, 123(2):813-837.
[43] KIM D, SEO D, CHO S, et al. Multi-co-training for document classification using various document representations:TF-IDF, LDA, and doc2vec[EB/OL].[2021-02-06]. https://doi.org/10.1016/j.ins.2018.10.006
[44] TRAPPEY A J C, CHEN P P J, TRAPPEY V C, et al. A machine learning approach for solar power technology review and patent evolution analysis[J]. Applied sciences-basel, 2019, 9(7):1-25.
[45] BISHOP C M, SVENSEN M, WILLIAMS C K I. GTM:the generative topographic mapping[J]. Neural computation, 1998, 10(1):215-234.
[46] 孙冰,徐晓菲,苏晓. 技术扩散主路径及核心企业的识别研究——以手机芯片专利引文网络为例[J]. 情报学报, 2019, 38(2):201-208.
[47] 柴庆凤,翟东升,蔡力伟,等. 基于专利网络链接模型的技术链接机会预测方法研究[J]. 情报理论与实践, 2020, 43(12):111-119.
[48] LEE C, KWON O, KIM M, et al. Early identification of emerging technologies:a machine learning approach using multiple patent indicators[EB/OL].[2021-01-06]. https://doi.org/10.1016/j.techfore.2017.10.002.
[49] SOHRABI M K, ROSHANI R. Frequent itemset mining using cellular learning automata[EB/OL].[2021-01-06]. https://doi.org/10.1016/j.chb.2016.11.036.
[50] ALI S H. Miner for oaccr:case of medical data analysis in knowledge discovery[C]//2012 6th international conference on sciences of electronics, technologies of information and telecommunications (setit). Sousse:IEEE, 2012:962-975.
[51] DA COSTA M, DOS SANTOS L, SCHAEFER J, et al. Industry 4.0 technologies basic network identification[J]. Scientometrics, 2019, 121(2):977-994.
[52] 贾军,魏洁云. 新兴产业核心技术早期识别方法与应用研究[J]. 科学学研究, 2018, 36(7):1206-1214.
[53] 吴菲菲,陈明,黄鲁成. 基于GTM的3D生物打印专利技术空白点识别[J]. 情报杂志, 2015, 34(3):58-64.
[54] 郭本海,陆文茜,王涵,等. 基于关键技术链的新能源汽车产业政策分解及政策效力测度[J]. 中国人口·资源与环境, 2019, 29(8):76-86.
[55] MARTINO J P. A review of selected recent advances in technological forecasting[J]. Technological forecasting and social change, 2003, 70(8):719-733.

基于深度学习的技术机会预测研究——以新能源汽车为例

Approach to Technology Opportunity Prediction Based on Deep Learning: Taking the Case of New Energy Vehicles

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	孙蒙鸽, 王燕鹏, 韩涛, 刘盼盼. 新兴技术的多指标量化识别研究——基于向量表征方法的探索[J]. 图书情报工作, 2022, 66(3): 130-139.
[2]	步一, 黄圣智, 黄永, 陆伟. 学者研究主题演化的时空测度:速度、覆盖度和迂回度[J]. 图书情报工作, 2022, 66(24): 84-91.
[3]	胡雅敏, 吴晓燕, 廖兴滨, 钱杨舸, 陈方. 融合深度学习和链路预测的细粒度技术预测研究——以合成生物技术为例[J]. 图书情报工作, 2022, 66(24): 92-103.
[4]	张卫, 王昊, 李晓敏, Song Min. 数字人文视角下古诗意象知识抽取及其文化图式构建研究[J]. 图书情报工作, 2022, 66(24): 104-117.
[5]	袁义国, 李斌, 冯敏萱, 贺胜, 王东波. 基于深度学习的古籍文本自动断句与标点一体化研究[J]. 图书情报工作, 2022, 66(22): 134-141.
[6]	袁毅, 陶鑫琪, 李瑾萱, 刘娅娴, 汪晓芸, 景香玉. 基于招聘文本实体挖掘的人才供需分析——以人工智能领域为例[J]. 图书情报工作, 2022, 66(14): 101-118.
[7]	韩普, 顾亮. 基于混合深度学习的中文医学实体抽取研究[J]. 图书情报工作, 2022, 66(14): 119-127.
[8]	周潇, 许银彪, 史益. 基于深度学习与语义挖掘的技术创新组合识别与追踪[J]. 图书情报工作, 2022, 66(10): 33-44.
[9]	李娜, 姜恩波, 朱一真, 刘婷. 政策工具自动识别方法与实证研究[J]. 图书情报工作, 2021, 65(7): 115-122.
[10]	杜悦, 王东波, 江川, 徐润华, 李斌, 许超, 徐晨飞. 数字人文下的典籍深度学习实体自动识别模型构建及应用研究[J]. 图书情报工作, 2021, 65(3): 100-108.
[11]	孔德婧, 董放, 陈子婧, 刘宇涵, 周源. 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.
[12]	钱力, 刘细文, 张智雄, 刘会洲. AI+智慧知识服务生态体系研究设计与应用实践——以中国科学院文献情报中心智慧服务平台建设为例[J]. 图书情报工作, 2021, 65(15): 78-90.
[13]	雷兵, 刘小, 钟镇. 基于题录信息的领域学术文献细粒度分类方法研究[J]. 图书情报工作, 2021, 65(14): 128-137.
[14]	孙冉, 安璐. 异质信息网络嵌入视角下公安微博传播预测研究[J]. 图书情报工作, 2020, 64(21): 67-76.
[15]	林泽斐, 欧石燕. 融合结构与文本特征的知识图谱关系预测方法研究[J]. 图书情报工作, 2020, 64(21): 99-110.