|
|
|
| Recommendation of Patent Transaction Based on Attributed Heterogeneous Network Representation Learning |
| He Xijun1, Wu Shuangshuang1, Wu Yuying1, Cai Jiuran1, Pang Ting2,3, Chee Seng Chan2 |
1.School of Economics and Management, Beijing University of Technology, Beijing 100124
2.Department of Artificial Intelligence, Faculty of Computer Science and Information Technology, University of Malaya, Kuala Lumpur 50603
3.Network and Information Center, Xinxiang Medical University, Xinxiang 453000 |
|
|
|
|
Abstract Patent transaction recommendation is an important means of fusing heterogeneous information to facilitate transactions; however, the recommendation results are often affected by the disregard of patent attributes, which represents a research problem. This study proposes a patent transaction recommendation model based on attribute heterogeneous network (AHN) representation learning (AHNRL-PTR), which firstly filters the patent and organizational attributes affecting patent transaction, secondly constructs a patent transaction AHN, then introduces network representation learning in AHN, and finally, uses multidimensional Gaussian distribution and Kullback-Leibler divergence to solve the problems of node representation uncertainty and distance asymmetry between nodes. Finally, an empirical study with the valid invention granted patent data in the Greater Bay Area concluded that: first, compared to the metapath2vec, text-associated DeepWalk (TADW), and variant methods of the AHNRL-PTR model, the AHNRL-PTR model has the highest recommendation accuracy (more than 86%), indicating that fusing organizational and patent attributes and focusing on the solution of the uncertainty and asymmetry problem of node representation can substantially improve recommendation accuracy; second, the values of the non-accurate metrics IntraSim and Popularity of AHNRL-PTR are smaller than those of metapath2vec, AHNvec-PTR, and AHNsy-PTR methods, reflecting the diversity of this method’s recommendation results and its advantage in recommending niche cold patents; third, the organizations are clustered into the following six categories based on IntraSim and Popularity: intermediary, domain backbone, research, community, growth, and professional, which reflect the recommendation results’ interpretability and personalization level. Given the results, this study provides decision support for intelligent recommendation services for patent transactions.
|
|
Received: 09 October 2021
|
|
|
|
1 Wang Q, Du W, Ma J, et al. Recommendation mechanism for patent trading empowered by heterogeneous information networks[J]. International Journal of Electronic Commerce, 2019, 23(2): 147-178.
2 Liu W D, Qiao W B, Liu X. Discovering the realistic paths towards the realization of patent valuation from technical perspectives: defense, implementation or transfer[J]. Neural Computing and Applications, 2021, 33(2): 577-590.
3 何喜军, 董艳波, 武玉英, 等. 基于ERGM的科技主体间专利技术交易机会实证研究[J]. 中国软科学, 2018(3): 184-192.
4 武玉英, 张博闻, 何喜军, 等. 新能源领域专利转让网络中技术供需主体间交易机会预测[J]. 情报杂志, 2018, 37(5): 79-84, 96.
5 Luo Y N, Zhao X B, Zhou J T, et al. A network integration approach for drug-target interaction prediction and computational drug repositioning from heterogeneous information[J]. Nature Communications, 2017, 8(1): Article No.573.
6 Sun Y Z, Han J W, Zhao P X, et al. RankClus: integrating clustering with ranking for heterogeneous information network analysis[C]// Proceedings of the 12th International Conference on Extending Database Technology: Advances in Database Technology. New York: ACM Press, 2009: 565-576.
7 He X J, Dong Y B, Zhen Z, et al. Weighted meta paths and networking embedding for patent technology trade recommendations among subjects[J]. Knowledge-Based Systems, 2019, 184: 104899.
8 Zheng J, Liu J, Shi C, et al. Recommendation in heterogeneous information network via dual similarity regularization[J]. International Journal of Data Science and Analytics, 2017, 3(1): 35-48.
9 La Fond T, Neville J. Randomization tests for distinguishing social influence and homophily effects[C]// Proceedings of the 19th International Conference on World Wide Web. New York: ACM Press, 2010: 601-610.
10 何喜军, 董艳波, 武玉英, 等. 基于异构信息网络嵌入的专利技术主体间交易推荐模型[J]. 情报学报, 2020, 39(1): 57-67.
11 Ji F J, Zhao Z Y, Zhou H, et al. A comparative study on heterogeneous information network embeddings[J]. Journal of Intelligent & Fuzzy Systems, 2020, 39(3): 3463-3473.
12 Wu B, Wen W, Hao Z F, et al. Multi-context aware user-item embedding for recommendation[J]. Neural Networks, 2020, 124: 86-94.
13 Li X, Wu Y, Ester M, et al. Semi-supervised clustering in attributed heterogeneous information networks[C]// Proceedings of the 26th International Conference on World Wide Web. Republic and Canton of Geneva: International World Wide Web Conferences Steering Committee, 2017: 1621-1629.
14 Liu M Y, Liu J, Chen Y H, et al. AHNG: representation learning on attributed heterogeneous network[J]. Information Fusion, 2019, 50: 221-230.
15 Yu G X, Wang Y H, Wang J, et al. Attributed heterogeneous network fusion via collaborative matrix tri-factorization[J]. Information Fusion, 2020, 63: 153-165.
16 Hamilton W L, Ying R, Leskovec J. Representation learning on graphs: methods and applications[J]. Bulletin of the IEEE Computer Society Technical Committee on Data Engineering, 2017, 40: 52-74.
17 Zhang Z, Yang H X, Bu J J, et al. ANRL: attributed network representation learning via deep neural networks[C]// Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence. California: International Joint Conferences on Artificial Intelligence Organization, 2018: 3155-3161.
18 Ding W X, Jing X Y, Yan Z, et al. A survey on data fusion in Internet of Things: towards secure and privacy-preserving fusion[J]. Information Fusion, 2019, 51: 129-144.
19 Shen H J, Huang C, Mao H, et al. To license or sell: a study on the patent transaction modes in China[R]. HKUST IEMS Working Paper, 2018: No.2018-51.
20 Zhang Y, Qian Y, Huang Y, et al. An entropy-based indicator system for measuring the potential of patents in technological innovation: rejecting moderation[J]. Scientometrics, 2017, 111(3): 1925-1946.
21 宋爽, 陈向东. 区域技术差异对专利价值的影响[J]. 科研管理, 2016, 37(9): 68-77.
22 Squicciarini M, Dernis H, Criscuolo C. Measuring patent quality: indicators of technological and economic value[R]. OECD Science, Technology and Industry Working Papers. Paris: OECD Publishing, 2013: No.2013/03.
23 Caviggioli F, Scellato G, Ughetto E. International patent disputes: evidence from oppositions at the European Patent Office[J]. Research Policy, 2013, 42(9): 1634-1646.
24 Bergman K, Graff G D. The global stem cell patent landscape: implications for efficient technology transfer and commercial development[J]. Nature Biotechnology, 2007, 25(4): 419-424.
25 钱坤, 张晓, 黄忠全. 交易情景下专利价值影响因素分析[J]. 科学学研究, 2020, 38(9): 1608-1620.
26 乔永忠, 邓思铭. 创新主体类型对中国专利奖获奖专利运用能力影响研究——以不同地区为视角[J]. 情报学报, 2019, 38(5): 473-481.
27 Bessen J. The value of US patents by owner and patent characteristics[J]. Research Policy, 2008, 37(5): 932-945.
28 Park Y, Yoon J. Application technology opportunity discovery from technology portfolios: use of patent classification and collaborative filtering[J]. Technological Forecasting and Social Change, 2017, 118: 170-183.
29 李文辉, 陈依楠, 江涌芝, 等. 中国经济发达地区高校技术创新溢出研究[J]. 科研管理, 2021, 42(3): 120-130.
30 He X J, Meng X, Dong Y B, et al. Demand identification model of potential technology based on SAO structure semantic analysis: the case of new energy and energy saving fields[J]. Technology in Society, 2019, 58: 101116.
31 Zhou S, Bu J J, Zhang Z, et al. Cross multi-type objects clustering in attributed heterogeneous information network[J]. Knowledge-Based Systems, 2020, 194: 105458.
32 Lozares C, Verd J M, Cruz I, et al. Homophily and heterophily in personal networks. From mutual acquaintance to relationship intensity[J]. Quality & Quantity, 2014, 48(5): 2657-2670.[Li nkOut]
33 Cheng H, Gan B Q, Zhang C. Research on personalized recommendation method based on social impact theory[J]. Journal of Physics: Conference Series, 2021, 1848(1): 012128.
34 La Fond T, Neville J. Randomization tests for distinguishing social influence and homophily effects[C]// Proceedings of the 19th International Conference on World Wide Web. New York: ACM Press, 2010: 601-610.
35 Zhang J W, Xia C Y, Zhang C W, et al. BL-MNE: emerging heterogeneous social network embedding through broad learning with aligned autoencoder[C]// Proceedings of the 2017 IEEE International Conference on Data Mining. IEEE, 2017: 605-614.
36 Huang X, Li J D, Hu X. Label informed attributed network embedding[C]// Proceedings of the Tenth ACM International Conference on Web Search and Data Mining. New York: ACM Press, 2017: 731-739.
37 Cen Y K, Zou X, Zhang J W, et al. Representation learning for attributed multiplex heterogeneous network[C]// Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. New York: ACM Press, 2019: 1358-1368.
38 Brochier R. Representation learning for recommender systems with application to the scientific literature[C]// Proceedings of the 2019 World Wide Web Conference. New York: ACM Press, 2019: 12-16.
39 Zhao J, Liu X D, Yan Q B, et al. Automatically predicting cyber attack preference with attributed heterogeneous attention networks and transductive learning[J]. Computers & Security, 2021, 102: 102152.
40 Zhang D K, Yin J, Zhu X Q, et al. Network representation learning: a survey[J]. IEEE Transactions on Big Data, 2020, 6(1): 3-28.
41 Perozzi B, Al-Rfou R, Skiena S. DeepWalk: online learning of social representations[C]// Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM Press, 2014: 701-710.
42 Chuan C H, Agres K, Herremans D. From context to concept: exploring semantic relationships in music with word2vec[J]. Neural Computing and Applications, 2020, 32(4): 1023-1036.
43 Dong Y X, Chawla N V, Swami A. metapath2vec: scalable representation learning for heterogeneous networks[C]// Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM Press, 2017: 135-144.
44 Duan Z H, Wang Y Y, Ye W H, et al. Connecting latent relationships over heterogeneous attributed network for recommendation[J/OL]. Applied Intelligence, (2022-03-21). https://doi.org/10.1007/s10489-022-03340-7.
45 Zhang Y M, Fan Y J, Ye Y F, et al. Key player identification in underground forums over attributed heterogeneous information network embedding framework[C]// Proceedings of the 28th ACM International Conference on Information and Knowledge Management. New York: ACM Press, 2019: 549-558.
46 Zhang Y M, Fan Y J, Song W, et al. Your style your identity: leveraging writing and photography styles for drug trafficker identification in darknet markets over attributed heterogeneous information network[C]// Proceedings of the World Wide Web Conference. New York: ACM Press, 2019: 3448-3454.
47 Jiang J Y, Yang D Q, Xiao Y H, et al. Convolutional Gaussian embeddings for personalized recommendation with uncertainty[C]// Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence. California: International Joint Conferences on Artificial Intelligence Organization, 2019: 2642-2648.
48 Bojchevski A, Günnemann S. Deep Gaussian embedding of attributed graphs: unsupervised inductive learning via ranking[OL]. (2017-07-13). https://arxiv.org/pdf/1707.03815v2.pdf.
49 Zhu D Y, Cui P, Wang D X, et al. Deep variational network embedding in Wasserstein space[C]// Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. New York: ACM Press, 2018: 2827-2836.
50 Bouhlel N, Dziri A. Kullback-Leibler divergence between multivariate generalized Gaussian distributions[J]. IEEE Signal Processing Letters, 2019, 26(7): 1021-1025.
51 Noh H, Lee S. What constitutes a promising technology in the era of open innovation? An investigation of patent potential from multiple perspectives[J]. Technological Forecasting and Social Change, 2020, 157: 120046.
52 Li W. Analyzing the protection scope limit for biosequence patent claims in China[J]. Nature Biotechnology, 2018, 36(9): 811-813.
53 Ko N, Jeong B, Seo W, et al. A transferability evaluation model for intellectual property[J]. Computers & Industrial Engineering, 2019, 131: 344-355.
54 Lee C Y, Kwon O, Kim M, et al. Early identification of emerging technologies: a machine learning approach using multiple patent indicators[J]. Technological Forecasting and Social Change, 2018, 127: 291-303.
55 Messeni Petruzzelli A, Rotolo D, Albino V. Determinants of patent citations in biotechnology: an analysis of patent influence across the industrial and organizational boundaries[J]. Technological Forecasting and Social Change, 2015, 91: 208-221.
56 Jaffe A B, de Rassenfosse G. Patent citation data in social science research: overview and best practices[J]. Journal of the Association for Information Science and Technology, 2017, 68(6): 1360-1374.
57 Tong T W, Zhang K, He Z L, et al. What determines the duration of patent examination in China? An outcome-specific duration analysis of invention patent applications at SIPO[J]. Research Policy, 2018, 47(3): 583-591.
58 Chen J, Chen J L, Zhao S, et al. Exploiting word embedding for heterogeneous topic model towards patent recommendation[J]. Scientometrics, 2020, 125(3): 2091-2108.
59 Choi J, Jeong B, Yoon J, et al. A novel approach to evaluating the business potential of intellectual properties: a machine learning-based predictive analysis of patent lifetime[J]. Computers & Industrial Engineering, 2020, 145: 106544.
60 刘业政, 吴锋, 孙见山, 等. 基于群偏好与用户偏好协同演化的群推荐方法[J]. 系统工程理论与实践, 2021, 41(3): 537-553.
61 Chen L J, Zhang Z K, Liu J H, et al. A vertex similarity index for better personalized recommendation[J]. Physica A: Statistical Mechanics and Its Applications, 2017, 466: 607-615.
62 Landin A, Suárez-García E, Valcarce D. When diversity met accuracy: a story of recommender systems[J]. Proceedings, 2018, 2(18): 1178.
63 何喜军, 吴爽爽, 才久然, 等. 中美湾区科技主体间专利转让网络结构演化对比研究[J]. 科学学与科学技术管理, 2021, 42(11): 77-95.
64 何喜军, 吴爽爽, 武玉英, 等. 专利转让网络中结构洞占据者识别及角色演化——粤港澳大湾区的实证研究[J]. 科学学与科学技术管理, 2022, 43(4): 75-94.
65 孙震. 我国个人专利维持之谜——市场摩擦的证据[J]. 科研管理, 2019, 40(3): 179-187.
66 刘凤朝, 肖站旗, 马荣康. 多维邻近性对技术交易网络的动态影响研究[J]. 科学学研究, 2018, 36(12): 2205-2214.
67 Yang C, Liu Z Y, Zhao D L, et al. Network representation learning with rich text information[C]// Proceedings of the 24th International Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2015: 2111-2117.
68 Cai B, Huang Y S. Personalised recommendation algorithm based on covariance[J]. The Journal of Engineering, 2020, 2020(13): 577-583.
69 Chan D M, Rao R, Huang F, et al. GPU accelerated t-distributed stochastic neighbor embedding[J]. Journal of Parallel and Distributed Computing, 2019, 131: 1-13.
70 Liao L Z, He X N, Zhang H W, et al. Attributed social network embedding[J]. IEEE Transactions on Knowledge and Data Engineering, 2018, 30(12): 2257-2270.
71 Syakur M A, Khotimah B K, Rochman E M S, et al. Integration K-means clustering method and elbow method for identification of the best customer profile cluster[J]. IOP Conference Series: Materials Science and Engineering, 2018, 336: 012017. |
|
|
|
