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
|
摘要
[目的/意义]在专利转让网络中,通过挖掘供需主体信息及网络结构对交易机会的预测,有助于提升专利的转化效率。[方法/过程]以新能源领域为例,采集2012-2016年专利转让数据,构建专利技术交易加权有向网络。在转让数据统计分析与网络结构研究基础上,计算并筛选网络节点结构相似度指标,利用LDA主题模型结合余弦相似度方法计算节点内容相似性指标,通过熵权法将结构与内容指标融合,预测网络中专利技术供需主体间交易机会及专利技术流动方向。[结果/结论]结果表明:RA相比其他9个结构指标其预测精度更高,将RA与内容相似性指标融合后,预测精度略有上升,预测结果相比单一结构指标,更全面的挖掘出可能发生交易的供需主体对,结果更具多样化和合理性,在实践中更具有辅助决策的价值。
[Purpose/Significance]In the patent transfer network,the prediction of transaction opportunities can help improve the efficiency of patent transformation by mining the information of supply and demand entities and the network structure.[Method/Process]Taking the newenergy field as an example,the patent technology transaction weighted and directed networks are constructed based on the patent transfer information collected from 2012 to 2016. On the basis of the statistical analysis of transfer data and the research on the structure of the networks,we calculate and select the structural similarity index of network nudes,combining the topic model of Latent Dirichlet Allocation(LDA) and the method of cosine similarity to confirm the nude content similarity index. We use the entropy method to carry out the structure and content similarity fusion to achieve the link prediction of inter-subject technical transaction opportunity and direction.[Result/Conclusion]The results showthat: RA can get the best prediction accuracy compared with other 9 structural similarity indexes; the prediction accuracy is slightly increased after the fusion of RA and the content index; compared to the single structure index,the supply and demand subjects making a pair likely to trade with each other identified are more comprehensive,the prediction results are more diversified and reasonable and are more valuable in decision support practice.
[Purpose/Significance]In the patent transfer network,the prediction of transaction opportunities can help improve the efficiency of patent transformation by mining the information of supply and demand entities and the network structure.[Method/Process]Taking the newenergy field as an example,the patent technology transaction weighted and directed networks are constructed based on the patent transfer information collected from 2012 to 2016. On the basis of the statistical analysis of transfer data and the research on the structure of the networks,we calculate and select the structural similarity index of network nudes,combining the topic model of Latent Dirichlet Allocation(LDA) and the method of cosine similarity to confirm the nude content similarity index. We use the entropy method to carry out the structure and content similarity fusion to achieve the link prediction of inter-subject technical transaction opportunity and direction.[Result/Conclusion]The results showthat: RA can get the best prediction accuracy compared with other 9 structural similarity indexes; the prediction accuracy is slightly increased after the fusion of RA and the content index; compared to the single structure index,the supply and demand subjects making a pair likely to trade with each other identified are more comprehensive,the prediction results are more diversified and reasonable and are more valuable in decision support practice.
引文
[1]马荣康,刘凤朝.基于专利许可的新能源技术转移网络演变特征研究[J].科学学与科学技术管理,2017,38(6):65-76.
[2]刘雪凤,郑友德,蔡祖国.我国新能源技术知识产权战略的构建[J].科学学与科学技术管理,2011,32(10):13-20.
[3]Lv L,Zhou T.Link prediction in complex networks:A survey[J].Physical A:Statistical Mechanics and its Applications,2011,390(6):1150-1170.
[4]Kossinets G.Effects of missing data in social networks[J].Social Netw orks,2006,28(3):247-268.
[5]Aamic L A,Adar E.Friends and neighbors on the web[J].Social Netw orks,2003,25(3):211-230.
[6]Zhou T,Lv L,Zhang Y C.Predicting missing links via local information[J].The European Physical Journal B-Condensed M atter and Complex Systems,2009,71(4):623-630.
[7]Barabsi A L,Albert R.Emergence of scalling in random netw orks[J].Science,1999,286(5439):509-512.
[8]Jaccard P.Etude comparative de la distribution florale dans une portion des Alpes et des Jura[J].Bulletin of the Torrey Botanical Club,1901,37:547.
[9]Leicht E A,Holme P,Newman M E J.Vertex similarity in netw orks[J].Physical Review E,2006,73(2):026120.
[10]Salton G,Mc Mill M J.Introduction to Modern Information Retrieval[M].Auckland:M c Graw-Hill,1983.
[11]Srensen T.A method of establishing groups of equal amplitude in plant sociology based on similarity of species content and its application to analyses of the vegetation on Danish commons[J].Biologiske Skrifter,1948,5(4):1-34.
[12]Ravase E,Somera A L,Mongru D A,et al.Hierarchical organization of modularity in metabolic netw orks[J].Science.2002,297(5586):1551-1555.
[13]Lv L,Jin C H,Zhou T.Similarity index based on local paths for link prediction of complex netw orks[J].Physical Review E,2009,80(4):046122.
[14]Katz L.A new status index derived from sociometric index[J].Psychometrika,1953,18(1):39-43.
[15]Leicht E A,Holme P,Newman M E.Vertex similarity in networks[J].Physical Review E Statistical Nonlinear&Soft Matter Physics,2005,73(2):026120.
[16]Klein D J,Randic M.Resistance distance[J].Journal of Mathematical Chemistry,1993,12(1):81-95.
[17]Brin S,Page L.The anatomy of a large-scale hypertextual web search engine[J].Computer netw orks and ISDN systems,1998,30(1):107-117.
[18]Liu W P,Lv L.Link prediction based on local random walk[J].Europhysics Letters,2010,89(5):58007
[19]Jeh G,Widom J.SimRank:A measure of structural-context similarity[C].Proceedings of ACM SIGKDD 2002.New York:ACM Press,2002:538-543.
[20]Murata T,Moriyasu S.Link prediction of social networks based on w eighted proximity measures[C]//Web Intelligence,IEEE/WIC/ACM International Conference on.IEEE,2007:85-88.
[21]Lv L,Zhou T.Link prediction in weighted networks:The role of w eak ties[J].Epl,2010,89(1):18001.
[22]Papadimitriou A,Symeonidis P,Manolopoulos Y.Fast and accurate link prediction in social netw orking systems[J].Journal of Systems&Softw are,2012,85(9):2119-2132.
[23]郭景峰,刘苗苗,罗旭.加权网络中基于多路径节点相似性的链接预测[J].浙江大学学报(工学版),2016,50(7):1347-1352.
[24]Aiello L M,Petkos G,Martin C,et al.Sensing trending topics in tw itter[J].IEEE Transactions on M ultimedia,2013,15(6):1268-1282.
[25]Brzozowski M J,Romero D M.Who should I follow?Recommending people in directed social netw orks[C]//International Conference on Weblogs and Social M edia,Barcelona,Catalonia,Spain,July.DBLP,2011.
[26]Zhang Q M,LüL,Wang W Q,et al.Correction:Potential theory for directed netw orks[J].Plos One,2013,8(2):e55437.
[27]张军,夏昊翔.基于粗糙相似度的有向网络链路预测[J].系统工程,2015(11):146-152.
[28]吴梦蝶,唐雁.基于主题模型的有向社交网络链接预测方法[J].西南大学学报(自然科学版),2014,36(1):152-158.
[29]He Yulin,Liu J N K,Hu Yan-xing,et al.OWA operator based link prediction ensemble for social netw ork[J].Expert Systems w ith Applications,2015,42(1):21-50.
[30]Schifanella R,Barrat A,Cattuto C.Folks in folksonomies:Social link prediction from shared metadata[C].Acm International Conference on Web Search&Data M ining,2010:271-280.
[31]Wu M,Tang Y.Topic model based link prediction for directed social netw ork[J].Journal of Computational Information Systems.2014,10(11):4765-4774.
[32]张玉峰,王志芳.基于内容相似性的论坛用户社会网络挖掘[J].情报杂志,2010,29(8):125-130.
[33]翟东升,刘鹤,张杰,等.一种基于链路预测的技术机会挖掘算法[J].情报学报,2016,35(10):1090-1100.
[34]Shibata N,Kajikawa Y,Sakata I.Link prediction in citation netw orks[J].Journal of the American society for Information Science and Technology,2012,63(1):78-85.
[35]Niladri Sett,Sanasam Ranbir Singh,Sukumar Nandi.Influence of edge w eight on node proximity based link prediction methods:An empirical analysis[J].Neurocomputing,2016,172:71-83.
[36]Griffiths T L,Steyvers M,Blei D M,et al.Integrating topics and syntax[C]//International Conference on Neural Information Processing Systems.M IT Press,2004:537-544.
[37]任海英,于立婷,黄鲁成.基于链接预测的科学研究机会发现方法研究[J].情报杂志,2016,35(10):53-58.
[38]刘宏鲲,吕琳媛,周涛.利用链路预测推断网络演化机制[J].中国科学:物理学力学天文学,2011(7):816-823.
[2]刘雪凤,郑友德,蔡祖国.我国新能源技术知识产权战略的构建[J].科学学与科学技术管理,2011,32(10):13-20.
[3]Lv L,Zhou T.Link prediction in complex networks:A survey[J].Physical A:Statistical Mechanics and its Applications,2011,390(6):1150-1170.
[4]Kossinets G.Effects of missing data in social networks[J].Social Netw orks,2006,28(3):247-268.
[5]Aamic L A,Adar E.Friends and neighbors on the web[J].Social Netw orks,2003,25(3):211-230.
[6]Zhou T,Lv L,Zhang Y C.Predicting missing links via local information[J].The European Physical Journal B-Condensed M atter and Complex Systems,2009,71(4):623-630.
[7]Barabsi A L,Albert R.Emergence of scalling in random netw orks[J].Science,1999,286(5439):509-512.
[8]Jaccard P.Etude comparative de la distribution florale dans une portion des Alpes et des Jura[J].Bulletin of the Torrey Botanical Club,1901,37:547.
[9]Leicht E A,Holme P,Newman M E J.Vertex similarity in netw orks[J].Physical Review E,2006,73(2):026120.
[10]Salton G,Mc Mill M J.Introduction to Modern Information Retrieval[M].Auckland:M c Graw-Hill,1983.
[11]Srensen T.A method of establishing groups of equal amplitude in plant sociology based on similarity of species content and its application to analyses of the vegetation on Danish commons[J].Biologiske Skrifter,1948,5(4):1-34.
[12]Ravase E,Somera A L,Mongru D A,et al.Hierarchical organization of modularity in metabolic netw orks[J].Science.2002,297(5586):1551-1555.
[13]Lv L,Jin C H,Zhou T.Similarity index based on local paths for link prediction of complex netw orks[J].Physical Review E,2009,80(4):046122.
[14]Katz L.A new status index derived from sociometric index[J].Psychometrika,1953,18(1):39-43.
[15]Leicht E A,Holme P,Newman M E.Vertex similarity in networks[J].Physical Review E Statistical Nonlinear&Soft Matter Physics,2005,73(2):026120.
[16]Klein D J,Randic M.Resistance distance[J].Journal of Mathematical Chemistry,1993,12(1):81-95.
[17]Brin S,Page L.The anatomy of a large-scale hypertextual web search engine[J].Computer netw orks and ISDN systems,1998,30(1):107-117.
[18]Liu W P,Lv L.Link prediction based on local random walk[J].Europhysics Letters,2010,89(5):58007
[19]Jeh G,Widom J.SimRank:A measure of structural-context similarity[C].Proceedings of ACM SIGKDD 2002.New York:ACM Press,2002:538-543.
[20]Murata T,Moriyasu S.Link prediction of social networks based on w eighted proximity measures[C]//Web Intelligence,IEEE/WIC/ACM International Conference on.IEEE,2007:85-88.
[21]Lv L,Zhou T.Link prediction in weighted networks:The role of w eak ties[J].Epl,2010,89(1):18001.
[22]Papadimitriou A,Symeonidis P,Manolopoulos Y.Fast and accurate link prediction in social netw orking systems[J].Journal of Systems&Softw are,2012,85(9):2119-2132.
[23]郭景峰,刘苗苗,罗旭.加权网络中基于多路径节点相似性的链接预测[J].浙江大学学报(工学版),2016,50(7):1347-1352.
[24]Aiello L M,Petkos G,Martin C,et al.Sensing trending topics in tw itter[J].IEEE Transactions on M ultimedia,2013,15(6):1268-1282.
[25]Brzozowski M J,Romero D M.Who should I follow?Recommending people in directed social netw orks[C]//International Conference on Weblogs and Social M edia,Barcelona,Catalonia,Spain,July.DBLP,2011.
[26]Zhang Q M,LüL,Wang W Q,et al.Correction:Potential theory for directed netw orks[J].Plos One,2013,8(2):e55437.
[27]张军,夏昊翔.基于粗糙相似度的有向网络链路预测[J].系统工程,2015(11):146-152.
[28]吴梦蝶,唐雁.基于主题模型的有向社交网络链接预测方法[J].西南大学学报(自然科学版),2014,36(1):152-158.
[29]He Yulin,Liu J N K,Hu Yan-xing,et al.OWA operator based link prediction ensemble for social netw ork[J].Expert Systems w ith Applications,2015,42(1):21-50.
[30]Schifanella R,Barrat A,Cattuto C.Folks in folksonomies:Social link prediction from shared metadata[C].Acm International Conference on Web Search&Data M ining,2010:271-280.
[31]Wu M,Tang Y.Topic model based link prediction for directed social netw ork[J].Journal of Computational Information Systems.2014,10(11):4765-4774.
[32]张玉峰,王志芳.基于内容相似性的论坛用户社会网络挖掘[J].情报杂志,2010,29(8):125-130.
[33]翟东升,刘鹤,张杰,等.一种基于链路预测的技术机会挖掘算法[J].情报学报,2016,35(10):1090-1100.
[34]Shibata N,Kajikawa Y,Sakata I.Link prediction in citation netw orks[J].Journal of the American society for Information Science and Technology,2012,63(1):78-85.
[35]Niladri Sett,Sanasam Ranbir Singh,Sukumar Nandi.Influence of edge w eight on node proximity based link prediction methods:An empirical analysis[J].Neurocomputing,2016,172:71-83.
[36]Griffiths T L,Steyvers M,Blei D M,et al.Integrating topics and syntax[C]//International Conference on Neural Information Processing Systems.M IT Press,2004:537-544.
[37]任海英,于立婷,黄鲁成.基于链接预测的科学研究机会发现方法研究[J].情报杂志,2016,35(10):53-58.
[38]刘宏鲲,吕琳媛,周涛.利用链路预测推断网络演化机制[J].中国科学:物理学力学天文学,2011(7):816-823.