主管：中国科学院
主办：中国优选法统筹法与经济数学研究会
　　　中国科学院科技战略咨询研究院
Chinese Journal of Management Science

Chinese Journal of Management Science >

2022 , Vol. 30 >Issue 12: 185 - 197

DOI: https://doi.org/10.16381/j.cnki.issn1003-207x.2021.2628

Articles

Patent Classification Based on multi-dimensional Feature and Graph Convolutional Networks

  • WU Jie ,
  • GUI Liang ,
  • LIU Peng ,
  • SHENG Yong-xiang
Expand
  • School of Economics and Management, Jiangsu University of Science and Technology, Zhen’jiang 212000, China

Received date: 2021-07-31

  Revised date: 2022-04-13

  Online published: 2022-12-20

Fold

Abstract

The shortening of patent examination time and the increase of patent number bring great challenges to patent classification, and using patent automatic classification technology to improve the efficiency of patent classification and shorten the time of patent examination has become an important research topic. An automatic patent classification framework is proposed based on multi-dimensional features and graph convolutional networks. The framework extracts the patent features from the dimensions of patent abstract, citation patent and patent inventor according to document metrology and graph representation learning theory. Secondly, the patent-core word network is constructed by using the dimensionality features of patent abstracts, and the dimensionality features of citation patents and patent inventors are embedded into the patent-core word network as patent number features. The semi-supervised learning of graph convolutional network is used to determine the classification labels of patent nodes in the patent-core word co-occurrence network and complete the task of patent automatic classification. In order to verify the effect of the method, the patent data from the Incopat global patent database are used for experiments. The experimental results show that the patent text information and the patent structured information as the patent features can improve the patent classification accuracy, and the introduction of backward citation patent information can improve the patent classification accuracy. At the same time, the framework proposed in this paper also provides a new solution to the problem of patent automatic classification, and provides support for the implementation of the policy of shortening patent examination time.

Key words： patent; Graph Convolutional Network; multi-dimensional features; backward citation patent; automatic classification

Cite this article

WU Jie , GUI Liang , LIU Peng , SHENG Yong-xiang . Patent Classification Based on multi-dimensional Feature and Graph Convolutional Networks[J]. Chinese Journal of Management Science, 2022 , 30(12) : 185 -197 . DOI: 10.16381/j.cnki.issn1003-207x.2021.2628

References

［1］ 孟猛猛, 雷家骕, 焦捷. 专利质量、知识产权保护与经济高质量发展［J］. 科研管理, 2021, 42(1): 135-145.Meng Mengmeng, Lei Jiasu, Jiao Jie. Patent quality, intellectual property protection and high-quality economic development［J］. Science Research Management, 2021, 42(1): 135-145.
［2］ 杨思思, 戴磊, 郝屹. 专利经济价值度通用评估方法研究［J］. 情报学报, 2018, 37(1): 109-114.Yang Sisi, Dai Lei, Hao Yi. Study on the common evaluation methodology of patented economic value［J］. Journal of the China Society for Scientific and Technical Information, 2018, 37(1): 109-114.
［3］ 毛昊, 刘夏, 党建伟. 对标世界一流专利审查机构的制度经验与改革应对［J］. 中国软科学, 2020(2): 11-25.Mao Hao, Liu Xia, Dang Jianwei. An institutional analysis and critique to CNIPA: lessons from world-class patent offices［J］. China Soft Science, 2020(2): 11-25.
［4］ 尹志锋, 申媛, 刘梦瑶. 专利质量层级、专利管理能力与专利实施水平［J］. 中国科技论坛, 2020(10): 28-37.Yin Zhifeng, Shen Yuan, Liu Mengyao. Patent quality, patent management capacity and patent implementation［J］. Forum on Science and Technology in China, 2020(10): 28-37.
［5］ 胡学钢, 杨恒宇, 林耀进, 等. 基于协同过滤的专利TRIZ分类方法［J］. 情报学报, 2018, 37(5): 512-518.Hu Xuegang, Yang Hengyu, Lin Yaojin, et al. Study on classification of patents collaborative filtering oriented to TRIZ［J］. Journal of the China Society for Scientific and Technical Information, 2018, 37(5): 512-518.
［6］ 包翔, 刘桂锋, 杨国立. 基于多示例学习框架的专利文本分类方法研究［J］. 情报理论与实践, 2018, 41(11): 144-148.Bao Xiang, Liu Guifeng, Yang Guoli. Patent text classification method based on multi-instance learning［J］. Information Studies:Theory & Application, 2018, 41(11): 144-148.
［7］ 佟昕瑀, 赵蕊洁, 路永和. 基于预训练模型的多标签专利分类研究［J］. 数据分析与知识发现, 2022, 6(Z1): 129-137.Tong Xinyu, Zhao Ruijie, Lu Yonghe. Multi-label patent classification with pre-training model［J］. Data Analysis and Knowledge Discovery, 2022, 6(Z1): 129-137.
［8］ 吕璐成, 韩涛, 周健, 等. 基于深度学习的中文专利自动分类方法研究［J］. 图书情报工作, 2020, 64(10): 75-85.Lyu Lucheng, Han Tao, Zhou Jian, et al. Research on the method of Chinese patent automatic classification based on deep learning［J］. Library and Information Service, 2020, 64(10): 75-85.
［9］ 朱雪忠, 徐晨倩. 337调查下的企业专利诉讼策略博弈分析［J］. 科研管理, 2021, 42(6): 112-119.Zhu Xuezhong, Xu Chenqian. The game analysis of enterprise patent litigation strategies under Section 337 Investigation［J］. Science Research Management, 2021, 42(6): 112-119.
［10］ 苏媛, 李广培. 绿色技术创新能力、产品差异化与企业竞争力—基于节能环保产业上市公司的分析［J］. 中国管理科学, 2021, 29(4): 46-56.Su Yuan, Li Guangpei. Green technological innovation ability, product differentiation and enterprise competitiveness: analysis of energy saving and environmental protection industry listed companies［J］. Chinese Journal of Management Science, 2021, 29(4): 46-56.
［11］ 汪明月, 李颖明. 多主体参与的绿色技术创新系统均衡及稳定性［J］. 中国管理科学, 2021, 29(3): 59-70.Wang Mingyue, Li Yingming. Equilibrium and stability of green technology innovation system with multi-agent participation［J］. Chinese Journal of Management Science, 2021, 29(3): 59-70.
［12］ 吴洁, 王建刚, 张运华, 等. 技术创新联盟中知识转移价值增值影响因素的实证研究［J］. 中国管理科学, 2014, 22(S1): 531-538.Wu Jie, Wang Jiangang, Zhang Yunhua, et al. Empirical research on influential factors of knowledge transfer value-added in technology innovation alliance［J］. Chinese Journal of Management Science, 2014, 22(S1): 531-538.
［13］ Chang S B, Lai K K, Chang Shumin. Exploring technology diffusion and classification of business methods: using the Patent Citation Network［J］. Technological forecasting and social change, 2009, 76(1): 107-117.
［14］ Lai K K, Wu S J. Using the patent cocitation approach to establish a new patent classification system［J］. Information processing and management, 2005, 41(2): 313-330.
［15］ Fang Lintao, Zhang Le, Wu Han, et al. Patent2Vec: Multi-view representation learning on patent-graphs for patent classification［J］. World Wide Web, 2021, 24(5): 1791-1812.
［16］ Fall C J, Torcsvari A, Benzineb K, et al. Automated categorization in the international patent classification［C］//Proceedings of ACM SIGIR forum: Association for Computing Machinery, Toronto, Canada, July 28 to August 1, 2003.
［17］ 李程雄, 丁月华, 文贵华. SVM-KNN 组合改进算法在专利文本分类中的应用［J］. 计算机工程与应用, 2006(20): 193-195.Li Chengxiong, Ding Yuehua, Wen Guihua. Application of SVM- KNN combination improvement algorithm on patent text classification［J］. Computer Engineering and Applications, 2006(20): 193-195.
［18］ 贾杉杉, 刘畅, 孙连英, 等. 基于多特征多分类器集成的专利自动分类研究［J］. 数据分析与知识发现, 2017, 1(8): 76-84.Jia Shanshan, Liu Chang, Sun Lianying, et al. Patent classification based on multi-feature and multi-classifier integration［J］. Data Analysis and Knowledge Discovery, 2017, 1(8): 76-84.
［19］ Hu Jie, Li Shaobo, Yao Yong, et al. Patent keyword extraction algorithm based on distributed representation for patent classification［J］. Entropy, 2018, 20(2): 104.
［20］ Xia Bing, Li Baoan, Lv Xueqiang. Research on patent document classification based on deep learning［C］//Proceedings of 2nd International Conference on Artificial Intelligence and Industrial Engineering, Beijing, China, November 20-21, 2016.
［21］ Hu Jie, Li Shaobo, Hu Jianjun, et al. A hierarchical feature extraction model for multi-label mechanical patent classification［J］. Sustainability, 2018, 10(1): 219.
［22］ Risch J, Krestel R. Domain-specific word embeddings for patent classification［J］. Data Technologies and Applications, 2019, 53(1): 108- 122.
［23］ 胡杰, 李少波, 于丽娅, 等. 基于卷积神经网络与随机森林算法的专利文本分类模型［J］. 科学技术与工程, 2018, 18(6): 268-272.Hu Jie, Li Shaobo, Yu Liya, et al. A patent classification model based on convolutional neural networks and rand forest［J］. Science Technology and Engineering, 2018, 18(6): 268-272.
［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): 215-220.Ma Jianhong, Wang Ruiyang, Yao Shuang, et al. Patent classification method based on depth learning［J］. Computer Engineering, 2018, 44(10): 209-214.
［25］ Li Shaobo, Hu Jie, Cui Yuxin, et al. Deep Patent:Patent classification with convolutional neural networks and word embedding［J］. Scientometrics, 2018, 117(2): 721-744.
［26］ Roudsari A H, Afshar J, Lee C C, et al. Multi-label patent classification using attention-aware deep learning model［C］// Proceedings of 2020 IEEE International Conference on Big Data and Smart Computing, Busan, Korea, February 19-22, 2020.
［27］ Tang Pingjie, Jiang Meng, Xia Bryan, et al. Multi-label patent categorization with non-local attention-based graph convolutional network［C］// Proceedings of the AAAI Conference on Artificial Intelligence, New York, USA, February 7-12, 2020.
［28］ 余本功, 张培行. 基于双通道特征融合的WPOS-GRU专利分类方法［J］. 计算机应用研究, 2020, 37(3): 655-658.Yu Bengong, Zhang Peihang. WPOS-GRU patent classification method based on two-channel feature fusion［J］. Application Research of Computers, 2020, 37(3): 655-658.
［29］ 吴洁, 桂亮, 刘鹏. 基于图卷积网络的高质量专利自动识别方案研究［J］. 情报杂志, 2022, 41(1): 88-95+124.Wu Jie, Gui Liang, Liu Peng. Indicator and textual features-based patent evaluation with graph convolutional networks［J］. Journal of Intelligence, 2022, 41(1): 88-95+124.
［30］ 宋艳辉, 邱均平. 发明人专利文献耦合与发明人德温特分类号耦合比较研究——以非专利实施主体为例［J］. 情报学报, 2021, 40(4): 364-374.Song Yanhui, Qiu Junping. A comparative study of inventor bibliographic-patent coupling and inventor-patent-classification-coupling—non-practicing entities as an example［J］. Journal of the China Society for Scientific and Technical Information, 2021, 40(4): 364-374.
［31］ 赵阳, 文庭孝. 专利引证动机分析［J］. 情报理论与实践, 2017, 40(7): 28-32+16.Zhao Yang, Wen Tingxiao. Motivation analysis of patent citation［J］. Information Studies:Theory & Application, 2017, 40(7): 28-32+16.
［32］ 张娴, 方曙, 王春华. 专利引证视角下的技术演化研究综述［J］. 科学学与科学技术管理, 2016, 37(3): 58-67.Zhang Xian, Fang Shu, Wang Chunhua. Review on technology evolution research from patent citation perspective［J］. Science of Science and Management of S.& T., 2016, 37(3): 58-67.
［33］ Kipf T N, Welling M. Semi-supervised classification with graph convolutional networks［C］//Proceedings of International Conference On Learning Representations (ICLR),Toulon, France, April 24-26,2017.
［34］ Yao Liang, Mao Chengsheng, Luo Yuan. Graph convolutional networks for text classification［C］ //Proceedings of Association for the Advancement of Artificial Intelligence Conference on Artificial Intelligence(AAAI),Hawaii, USA, January 27 to February 1, 2019.
［35］ Wu Shu, Tang Yuyuan, Zhu Yanqiao, et al. Session-based recommendation with braph neural networks［C］//Proceedings of Association for the Advancement of Artificial Intelligence Conference on Artificial Intelligence(AAAI), Hawaii, USA, January 27 to February 1, 2019.
Options
Outlines

/

〈 〉