在研究问题复杂程度不断提高、交叉学科蓬勃发展的背景下，科研团队已成为学术研究的基本单位。科研团队面临着引进科研人员的需求，以保持和提升其学术竞争力。然而，科研团队本身时间有限，获取和处理数据的能力也有限，因此需要依靠图书馆等科研服务机构提供科研人员推荐服务。为了帮助科研服务机构实现高水平的科研团队成员推荐服务，本研究从数据和模型两个方面展开研究。数据和模型相辅相成，高效的模型需要依赖高质量的数据进行训练，而优秀的模型结构则能使数据发挥更大的作用。

本研究在数据方面提出了两个主要方法。首先，本研究提出了一种多源异构科研人员和团队数据处理方法，以扩宽数据的来源，提高数据的数量和完整性。本研究将图书馆、科研人员社交网站以及学校（科研机构）管理系统作为科研人员和团队数据的来源。通过采集、清洗和融合来自多个来源的数据，并利用知识图谱和图数据库进行表示和存储。其次，本研究提出了一种科研团队画像构建方法，通过挖掘基础数据中的潜在属性和信息，提升科研团队和成员数据的质量和多样性，为模型的训练和使用提供支持。科研团队画像方法还可以帮助科研服务机构直观了解科研团队的基本情况和特点，以更好地为科研团队提供服务。

本研究在模型方面引入自注意力机制和神经协同过滤技术，提出为科研团队推荐科研人员的深度学习组推荐模型——科研团队成员推荐模型（Member Recommendation for Scientific Research Teams，MRST）。该模型首先运用自注意力机制从科研团队成员属性信息和交互信息中学习科研团队的语义表示，然后利用神经协同过滤技术学习科研团队和科研人员之间的非线性关系，最终得到科研团队和科研人员之间的契合程度作为推荐的依据。图书馆、科研人员社交网站、学校（科研机构）管理系统多个来源的丰富数据可以训练出高效的模型，高效的模型和推荐策略可以为科研团队推荐合适的科研人员，满足科研团队的需求。本研究提出的科研团队成员推荐模型（MRST）在公共数据集上与基线模型进行了对比实验，实验结果表明，科研团队成员推荐模型（MRST）在推荐正确率和F1值上相较于表现最好的对比模型提升了10.22%和10.25%，在实际推荐场景中具有更优秀的表现。ROC曲线的对比实验中，科研团队成员推荐模型（MRST）的AUC值高于所有的对比模型，体现了科研团队成员推荐模型（MRST）的优越性。

本研究从数据角度提出了多源异构科研人员和团队数据处理方法，以扩展数据来源，并提出了科研团队画像构建方法来挖掘科研团队和成员的潜在属性和信息，为模型的训练和使用提供支持。从模型角度，本研究提出了基于自注意力机制和神经协同过滤技术的深度学习组推荐模型，用于为科研团队推荐科研人员，并提出多种推荐策略以提升推荐效果。这些方法有助于图书馆等科研服务机构提升对科研团队的服务水平，满足科研团队引进科研人员以提升科研竞争力的需求。同时，推荐服务的实现也提升了图书馆等科研服务机构自身的数字化和智慧化水平。

In the context of increasing complexity of research problems and the thriving development of interdisciplinary studies, research teams have become the fundamental unit of academic research. Research teams often face the need to recruit researcher to maintain and enhance their academic competitiveness. However, research teams themselves have limited time and limited capabilities in data acquisition and processing, which necessitate research services such as libraries to provide researcher recommendation services. To assist research services, such as libraries, in achieving high-quality researcher recommendation services, this study conducts research from two aspects: data and models. Data and models are complementary, as efficient models require high-quality data for training, and data needs excellent model structures to be effective.

 

In terms of data, this study proposes a method for processing multi-source and heterogeneous researcher and team data to broaden the sources of data and improve the quantity and completeness of the data.This study proposes using libraries, social networking websites for researcher, and school (research institution) management systems as sources of researcher and team data. Data from multiple sources are collected, cleaned, and integrated, and represented and stored using knowledge graphs and graph databases. Furthermore, this study proposes a research team profiling method that extracts latent attributes and information of research teams and members from basic data, thereby enhancing the quality and diversity of research team and member data, and providing support for model training and utilization. Research team profiling method also helps research service institutions to intuitively understand the basic situation and characteristics of research teams, thus better serving research teams.

 

In terms of models, this study introduces self-attention mechanisms and neural collaborative filtering techniques, and proposes a deep learning group recommendation model to recommend researcher for research teams, called Member Recommendation for Scientific Research Teams (MRST).This model first uses self-attention mechanisms to learn the semantic representation of research teams from attribute information and interaction information of team members, and then uses neural collaborative filtering techniques to learn the nonlinear relationship between research teams and researcher, ultimately obtaining the compatibility between research teams and researcher as the basis for recommendation. The rich data from multiple sources such as libraries, social networking websites for researcher, and school (research institution) management systems can train an efficient model, and the efficient model and recommendation strategy can recommend suitable researcher for research teams, meeting their needs. The proposed Member Recommendation for Scientific Research Teams (MRST) model is compared with baseline models on public datasets, and the experimental results show that the MRST model has improved the recommendation accuracy and F1 score by 10.22% and 10.25%, respectively, compared to the best performing baseline model, demonstrating superior performance in practical recommendation scenarios. In the comparison experiment of ROC curves, the AUC value of the MRST model is higher than that of all the baseline models, highlighting the superiority of the MRST model in researcher recommendation.

 

This study proposes a data-driven approach to expand data sources for processing heterogeneous researcher and team data, and introduces a research team profiling method to extract latent attributes and information of research teams and members, providing support for model training and utilization. From a modeling perspective, this study proposes a deep learning group recommendation model to recommend researcher for research teams based on self-attention mechanism and neural collaborative filtering techniques, and presents various recommendation strategies to improve recommendation effectiveness. The methods proposed in this study contribute to enhancing the service level of research service organizations such as libraries, in meeting the needs of research teams for recruiting researcher to enhance their research competitiveness. The implementation of recommendation services also enhances the digitalization and intelligence level of research service organizations such as libraries in the process.

[1]初景利, 段美珍. 从智能图书馆到智慧图书馆[J].国家图书馆学刊,2019,28(01):3-9.
[2]刘昱甫. 多源异构数据组织与管理[J]. 科学与信息化,2021(5):18.
[3]Wu J, Li M, Zhao E, et al. Can multi-source heterogeneous data improve the forecasting performance of tourist arrivals amid COVID-19? Mixed-data sampling approach[J]. Tourism Management, 2023, 98: 104759.
[4]WANG J, LI G, YU J X, et al. Entity matching: How similar is similar[J]. Proceedings of the VLDB Endowment, 2011, 4(10): 622-633.
[5]GE X, YANG Y, PENG L, et al. Spatio-temporal knowledge graph based forest fire prediction with multi source heterogeneous data[J]. Remote Sensing, 2022, 14(14): 3496.
[6]CHAI L, XU H, LUO Z, et al. A multi-source heterogeneous data analytic method for future price fluctuation prediction[J]. Neurocomputing, 2020, 418: 11-20.
[7]MENG T, JING X, YAN Z, et al. A survey on machine learning for data fusion[J]. Information Fusion, 2020, 57: 115-129.
[8]DAS S, GC P S, DOAN A H, et al. Falcon: Scaling up hands-off crowdsourced entity matching to build cloud services[C]//Proceedings of the 2017 ACM International Conference on Management of Data. 2017: 1431-1446.
[9]ZHANG L, XIE Y, XIDAO L, et al. Multi-source heterogeneous data fusion[C]//2018 International conference on artificial intelligence and big data (ICAIBD). IEEE, 2018: 47-51.
[10]LU W, TAO C, LI H, et al. A unified deep learning framework for urban functional zone extraction based on multi-source heterogeneous data[J]. Remote Sensing of Environment, 2022, 270: 112830.
[11]李叶叶, 李贺, 沈旺,等. 基于多源异构数据挖掘的在线评论知识图谱构建[J]. 情报科学, 2022, 40(2):10.
[12]林丹琼. 面向科研人员的多数据源命名实体消歧方法研究[D]. 北京林业大学, 2019.
[13]李肖俊, 邵必林. 多源异构数据情境中学术知识图谱模型构建研究[J]. 现代情报, 2020, 40(6):10.
[14]莫君兰, 窦永香, 开庆. 基于多源异构数据的科研团队画像的构建[J].情报理论与实践,2020,43(09):100-106.
[15]COPPER A. The inmates are running the asylum: why high-tech products drive us crazy and how to restore the sanity[J]. SAMS. TSBN: 0-67231-649-8, 1999.
[16]KRISMAYER T, SCHEDL M, KNEES P, et al. Prediction of user demographics from music listening habits[C]//Proceedings of the 15th International Workshop on Content-Based Multimedia Indexing. 2017: 1-7
[17]CULOTTA A, RAVI N K, CUTLER J. Predicting Twitter user demographics using distant supervision from website traffic data[J]. Journal of Artificial Intelligence Research, 2016, 55: 389-408.
[18]DHELIM S, AUNG N, NING H. Mining user interest based on personality-aware hybrid filtering in social networks[J]. Knowledge-Based Systems, 2020, 206: 106227.
[19]ZENG H, WU S. User image and precision marketing on account of big data in Weibo[J]. Modern Economic Information, 2016, 16: 306-308.
[20]XING L, SONG Z, MA Q. User interest model based on hybrid behaviors interest rate[J]. Application Research of Computers, 2016, 33(3): 661-665.
[21]HUANG W, XU S, WU J, et al. The profile construction of the mobile user[J]. J. Mod. Inf, 2016, 10.
[22]刘行兵, 翟亚超, 柴斌,等. 基于AHP模型的协同创新科研团队画像的构建[J]. 科技管理研究,2021,41(19):136-140.
[23]XU M, LIANG M, XUE Z, et al. Research on accurate stereo portrait generation algorithm of scientific research team[J]. arXiv preprint arXiv:2204.05807, 2022.
[24]张玉洁, 杜雨露, 孟祥武. 组推荐系统及其应用研究[J].计算机学报,2016,39(04):745-764.
[25]GARCIA I, PAJARES S, SEBASTIA L, et al. Preference elicitation techniques for group recommender systems[J]. Information Sciences, 2012, 189: 155-175.
[26]CARVALHO L A M C, MACEDO H T. Users' satisfaction in recommendation systems for groups: an approach based on noncooperative games[C]//Proceedings of the 22nd International Conference on World Wide Web. 2013: 951-958.
[27]LIU X, TIAN Y, YE M, et al. Exploring personal impact for group recommendation[C]//Proceedings of the 21st ACM international conference on Information and knowledge management. 2012: 674-683.
[28]YUAN Q, CONG G, LIN C Y. COM: a generative model for group recommendation[C]//Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining. 2014: 163-172.
[29]张纯金, 郭盛辉, 纪淑娟, 等. 基于多属性评分隐表征学习的群组推荐算法[J]. 数据分析与知识发现, 2020, 4(12): 120-135.
[30]CAO D, HE X, MIAO L, et al. Attentive group recommendation[C]//The 41st International ACM SIGIR conference on research & development in information retrieval. 2018: 645-654.
[31]CAO D, HE X, MIAO L, et al. Social-enhanced attentive group recommendation[J]. IEEE Transactions on Knowledge and Data Engineering, 2019, 33(3): 1195-1209.
[32]WANG H, LI Y, FRIMPONG F. Group recommendation via self-attention and collaborative metric learning model[J]. IEEE Access, 2019, 7: 164844-164855.
[33]刘浩翰, 任洪润, 贺怀清. 一种基于自注意力机制的组推荐方法[J].计算机应用研究,2020,37(12):3572-3577.
[34]张耀坤, 吴瑞, 宗金星. 基于SD的学术社交网络科研协同行为演化博弈分析[J].现代情报, 2022, 42(7): 68-80.
[35]熊回香, 杨雪萍, 蒋武轩,等. 基于学术能力及合作关系网络的学者推荐研究[J].情报科学,2019,37(05):71-78.
[36]熊回香, 李晓敏, 杜瑾. 基于学术关键词与共被引的学者推荐研究[J].情报学报,2021,40(07):725-733.
[37]陈卫静, 郑颖. 基于作者关键词耦合的潜在合作关系挖掘[J].情报杂志, 2013, 32(5): 127-131.
[38]张金柱, 韩涛, 王小梅. 作者-关键词二分网络中的合著关系预测研究[J]. 图书情报工作, 2016, 60(21): 74-80.
[39]BLEI D M, NG A Y, JORDAN M I. Latent dirichlet allocation[J]. Journal of machine Learning research, 2003, 3(Jan): 993-1022.
[40]刘萍, 郑凯伦, 邹德安. 基于LDA模型的科研合作推荐研究[J]. 情报理论与实践, 2015, 38(9): 79-85.
[41]蒲姗姗. 基于知识互补的科研合作专家推荐模型研究[J]. 情报理论与实践, 2018, 41(8): 96-101.
[42]TANG J, WU S, SUN J, et al. Cross-domain collaboration recommendation[C]//Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining. 2012: 1285-1293.
[43]李仲, 韩红旗, 吴广印, 等. 基于文本稀疏分布式表征的学术合作推荐[J]. 情报科学, 2019, 37(6): 113-118.
[44]余传明, 林奥琛, 钟韵辞, 等. 基于网络表示学习的科研合作推荐研究[J].情报学报,2019,38(05):500-511.
[45]林原, 刘海峰, 王海龙, 等. 基于表示学习的学者间潜在合作机会挖掘[J]. 情报杂志, 2019, 38(5): 65-70.
[46]XU Y, ZHOU D, MA J. Scholar-friend recommendation in online academic communities: an approach based on heterogeneous network[J]. Decision Support Systems, 2019, 119: 1-13.
[47]LI P, LI T, WANG X, et al. Scholar recommendation based on high-order propagation of knowledge graphs[J]. International Journal on Semantic Web and Information Systems (IJSWIS), 2022, 18(1): 1-19.
[48]TAZZINI G, MONTELISCIANI G, GABELLONI D, et al. A structured team building method for collaborative crowdsourcing[C]//2013 International Conference on Engineering, Technology and Innovation (ICE) & IEEE International Technology Management Conference. IEEE, 2013: 1-11.
[49]LI L, TONG H, CAO N, et al. Replacing the irreplaceable: Fast algorithms for team member recommendation[C]//Proceedings of the 24th International Conference on World Wide Web. 2015: 636-646.
[50]DATTA A, TAN TECK YONG J, VENTRESQUE A. T-RecS: team recommendation system through expertise and cohesiveness[C]//Proceedings of the 20th international conference companion on World wide web. 2011: 201-204.
[51]BROCCO M, GROH G, FORSTER F. A meta model for team recommendations[C]//Social Informatics: Second International Conference, SocInfo 2010, Laxenburg, Austria, October 27-29, 2010. Proceedings 2. Springer Berlin Heidelberg, 2010: 35-50.
[52]ASIKIN Y A, BROCCO M, WOERNDL W. Case-based team recommendation[C]//Social Informatics: Second International Conference, SocInfo 2010, Laxenburg, Austria, October 27-29, 2010. Proceedings 2. Springer Berlin Heidelberg, 2010: 1-18.
[53]BROCCO M, GROH G, KERN C. On the influence of social factors on team recommendations[C]//2010 IEEE 26th International Conference on Data Engineering Workshops (ICDEW 2010). IEEE, 2010: 270-277.
[54]MACHADO L, STEFANIDIS K. Fair team recommendations for multidisciplinary projects[C]//IEEE/WIC/ACM International Conference on Web Intelligence. 2019: 293-297.
[55]TWYMAN M, NEWMAN D A, DECHURCH L, et al. Teammate invitation networks: The roles of recommender systems and prior collaboration in team assembly[J]. Social networks, 2022, 68: 84-96.
[56]EL-ASHMAWI W H, ALI A F, TAWHID M A. An improved particle swarm optimization with a new swap operator for team formation problem[J]. Journal of Industrial Engineering International, 2019, 15: 53-71.
[57]TUAROB S, ASSAVAKAMHAENGHAN N, TANAPHANTARUK W, et al. Automatic team recommendation for collaborative software development[J]. Empirical Software Engineering, 2021, 26(4): 64.
[58]LIU H, QIAO M, GREENIA D, et al. A machine learning approach to combining individual strength and team features for team recommendation[C]//2014 13th International Conference on Machine Learning and Applications. IEEE, 2014: 213-218.
[59]GOYAL P, SAPIENZA A, FERRARA E. Recommending teammates with deep neural networks[M]//Proceedings of the 29th on Hypertext and Social Media. 2018: 57-61.
[60]SAPIENZA A, GOYAL P, FERRARA E. Deep neural networks for optimal team composition[J]. Frontiers in big Data, 2019, 2: 14.
[61]杨鑫俊. 基于表达学习的科研项目团队推荐系统的研究与实现[D].北京：北京邮电大学,2019.
[62]洪少文, 汤庸, 袁成哲, 等. 基于社交网络的虚拟团队成员推荐模型[J].广西大学学报(自然科学版),2014,39(05):1109-1115.
[63]袁成哲, 曾碧卿, 汤庸, 等. 面向学术社交网络的多维度团队推荐模型[J].计算机科学与探索,2016,10(02):201-209.
[64]刘成山, 赵捧未, 窦永香. 数字图书馆及其实现技术[J].情报科学,2002(12):1319-1321+1335.
[65]初景利, 任娇菡, 王译晗. 从数字图书馆到智慧图书馆[J].大学图书馆学报,2022,40(02):52-58.
[66]严栋. 基于物联网的智慧图书馆[J].图书馆学刊,2010,32(07):8-10.
[67]任萍萍. 5G技术驱动下的智慧图书馆应用场景与智慧平台模型构建[J].情报理论与实践,2020,43(07):95-102.
[68]陈廉芳, 常志卫. 美国一流高校图书馆科研支持服务调查与启示[J].现代情报,2019,39(04):108-114.
[69]汪圳, 刘成山, 秦春秀. 基于科研情境的数字图书馆知识推荐研究[J].情报理论与实践,2018,41(12):139-143+138.
[70]王元卓, 靳小龙, 程学旗. 网络大数据:现状与展望[J].计算机学报,2013,36(06):1125-1138.
[71]李学龙, 龚海刚. 大数据系统综述[J].中国科学:信息科学,2015,45(01):1-44.
[72]夏靖波, 韦泽鲲, 付凯, 等. 云计算中Hadoop技术研究与应用综述[J].计算机科学,2016,43(11):6-11+48.
[73]YANG R, YU F R, SI P, et al. Integrated blockchain and edge computing systems: A survey, some research issues and challenges[J]. IEEE Communications Surveys & Tutorials, 2019, 21(2): 1508-1532.
[74]ZHOU H, SUN G, FU S, et al. A big data mining approach of PSO-based BP neural network for financial risk management with IoT[J]. IEEE Access, 2019, 7: 154035-154043.
[75]YANG J, LI Y, LIU Q, et al. Brief introduction of medical database and data mining technology in big data era[J]. Journal of Evidence‐Based Medicine, 2020, 13(1): 57-69.
[76]FIORE S, ELIA D, PIRES C E, et al. An integrated big and fast data analytics platform for smart urban transportation management[J]. IEEE Access, 2019, 7: 117652-117677.
[77]孙忠富, 杜克明, 郑飞翔, 等. 大数据在智慧农业中研究与应用展望[J].中国农业科技导报,2013,15(06):63-71.
[78]彭小圣, 邓迪元, 程时杰, 等. 面向智能电网应用的电力大数据关键技术[J].中国电机工程学报,2015,35(03):503-511.
[79]洪亮, 周莉娜, 陈珑绮. 大数据驱动的图书馆智慧信息服务体系构建研究[J].图书与情报,2018,No.180(02):8-15+23.
[80]黄恒琪, 于娟, 廖晓, 等. 知识图谱研究综述[J].计算机系统应用,2019,28(06):1-12.
[81]GRUBER T R. A translation approach to portable ontology specifications[J]. Knowledge acquisition, 1993, 5(2): 199-220.
[82]AL-MOSLMI T, OCAÑA M G, OPDAHL A L, et al. Named entity extraction for knowledge graphs: A literature overview[J]. IEEE Access, 2020, 8: 32862-32881.
[83]SMIRNOVA A, CUDRÉ-MAUROUX P. Relation extraction using distant supervision: A survey[J]. ACM Computing Surveys (CSUR), 2018, 51(5): 1-35.
[84]KUMAR S. A survey of deep learning methods for relation extraction[J]. arXiv preprint arXiv:1705.03645, 2017.
[85]庄传志, 靳小龙, 朱伟建， 等. 基于深度学习的关系抽取研究综述［J］.中文信息学报，2019，33（12）：1-18.
[86]王昊奋, 漆桂林, 陈华钧. 知识图谱：方法，实践与应用［M］. 北京：电子工业出版社，2019.
[87]HAO Y, ZHANG Y, LIU K, et al. An end-to-end model for question answering over knowledge base with cross-attention combining global knowledge[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2017: 221-231.
[88]常亮, 张伟涛, 古天龙, 等. 知识图谱的推荐系统综述[J].智能系统学报,2019,14(02):207-216.
[89]GONG F, WANG M, WANG H, et al. SMR: medical knowledge graph embedding for safe medicine recommendation[J]. Big Data Research, 2021, 23: 100174.
[90]DONG X, GABRILOVICH E, HEITZ G, et al. Knowledge vault: A web-scale approach to probabilistic knowledge fusion[C]//Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining. 2014: 601-610.
[91]AMATO G, STRACCIA U. User profile modeling and applications to digital libraries[C]//Research and Advanced Technology for Digital Libraries: Third European Conference, ECDL’99 Paris, France, September 22–24, 1999 Proceedings. Berlin, Heidelberg: Springer Berlin Heidelberg, 1999: 184-197.
[92]MAZHARI S, FAKHRAHMAD S M, SADEGHBEYGI H. A user-profile-based friendship recommendation solution in social networks[J]. Journal of Information Science, 2015, 41(3): 284-295.
[93]曾鸿, 吴苏倪. 基于微博的大数据用户画像与精准营销[J].现代经济信息,2016(16):306-308.
[94]许鹏程, 毕强, 张晗等.数据驱动下数字图书馆用户画像模型构建[J].图书情报工作,2019,63(03):30-37.
[95]范晓玉, 窦永香, 赵捧未, 等. 融合多源数据的科研人员画像构建方法研究[J].图书情报工作,2018,62(15):31-40.
[96]王东, 李青, 张志刚, 等. 科研人员画像构建方法研究[J].情报学报,2022,41(08):812-821.
[97]赵海信. 高校科研团队建设的研究[J].科技进步与对策,2007,No.204(08):188-189.
[98]RAMOS-VILLAGRASA P J, MARQUES-QUINTEIRO P, NAVARRO J, et al. Teams as complex adaptive systems: Reviewing 17 years of research[J]. Small Group Research, 2018, 49(2): 135-176.
[99]BEYERLEIN M, HAN S J, PRASAD A. A multilevel model of collaboration and creativity[J]. Team creativity and innovation, 2018: 195-224.
[100]刘君良, 李晓光. 个性化推荐系统技术进展[J].计算机科学,2020,47(07):47-55.
[101]周惠宏, 柳益君, 张尉青, 等. 推荐技术在电子商务中的运用综述[J].计算机应用研究,2004(01):8-12.
[102]LIU H, HE J, WANG T, et al. Combining user preferences and user opinions for accurate recommendation[J]. Electronic Commerce Research and Applications, 2013, 12(1): 14-23.
[103]VERBERT K, MANOUSELIS N, OCHOA X, et al. Context-aware recommender systems for learning: a survey and future challenges[J]. IEEE transactions on learning technologies, 2012, 5(4): 318-335.
[104]MOONEY R J, ROY L. Content-based book recommending using learning for text categorization[C]//Proceedings of the fifth ACM conference on Digital libraries. 2000: 195-204.
[105]BREESE J S, HECKERMAN D, KADIE C. Empirical analysis of predictive algorithms for collaborative filtering[J]. arXiv preprint arXiv:1301.7363, 2013.
[106]BALABANOVIĆ M, SHOHAM Y. Fab: content-based, collaborative recommendation[J]. Communications of the ACM, 1997, 40(3): 66-72.
[107]GOLDBERG D, NICHOLS D, OKI B M, et al. Using collaborative filtering to weave an information tapestry[J]. Communications of the ACM, 1992, 35(12): 61-70.
[108]MNIH A, SALAKHUTDINOV R R. Probabilistic matrix factorization[J]. Advances in neural information processing systems, 2007, 20.
[109]SONG Y, ELKAHKY A M, HE X. Multi-rate deep learning for temporal recommendation[C]//Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval. 2016: 909-912.
[110]HE X, LIAO L, ZHANG H, et al. Neural collaborative filtering[C]//Proceedings of the 26th international conference on world wide web. 2017: 173-182.
[111]ZHANG S, YAO L, SUN A, et al. Deep learning based recommender system: A survey and new perspectives[J]. ACM computing surveys (CSUR), 2019, 52(1): 1-38.
[112]高芬, 苏依拉, 牛向华, 等. 基于Transformer的蒙汉神经机器翻译研究［J］. 计算机应用与软件，2020，37（2）：141-146+225.
[113]申翔翔, 侯新文, 尹传环. 深度强化学习中状态注意力机制的研究［J］. 智能系统学报，2020，15（2）：317-322.
[114]BAHDANAU D, CHO K, BENGIO Y. Neural machine translation by jointly learning to align and translate[J]. arXiv preprint arXiv:1409.0473, 2014.
[115]TSOTSOS J K, CULHANE S M, WAI W Y K, et al. Modeling visual attention via selective tuning[J]. Artificial intelligence, 1995, 78(1-2): 507-545.
[116]MNIH V, HEESS N, GRAVES A. Recurrent models of visual attention[J]. Advances in neural information processing systems, 2014, 27.
[117]BAHDANAU D, CHO K, BENGIO Y. Neural machine translation by jointly learning to align and translate[J]. arXiv preprint arXiv:1409.0473, 2014.
[118]CHO K, VAN MERRIËNBOER B, BAHDANAU D, et al. On the properties of neural machine translation: Encoder-decoder approaches[J]. arXiv preprint arXiv:1409.1259, 2014.
[119]HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural computation, 1997, 9(8): 1735-1780.
[120]CHOROWSKI J K, BAHDANAU D, SERDYUK D, et al. Attention-based models for speech recognition[J]. Advances in neural information processing systems, 2015, 28.
[121]TANG D, QIN B, LIU T. Aspect level sentiment classification with deep memory network[J]. arXiv preprint arXiv:1605.08900, 2016.
[122]LUONG M T, PHAM H, MANNING C D. Effective approaches to attention-based neural machine translation[J]. arXiv preprint arXiv:1508.04025, 2015.
[123]WANG L, CAO Z, DE MELO G, et al. Relation classification via multi-level attention cnns[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2016: 1298-1307.
[124]LU J, YANG J, BATRA D, et al. Hierarchical question-image co-attention for visual question answering[J]. Advances in neural information processing systems, 2016, 29.
[125]VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[J]. Advances in neural information processing systems, 2017, 30.
[126]DEVLIN J, CHANG M W, LEE K, et al. Bert: Pre-training of deep bidirectional transformers for language understanding[J]. arXiv preprint arXiv:1810.04805, 2018.
[127]RADFORD A, NARASIMHAN K, SALIMANS T, et al. Improving language understanding by generative pre-training[J]. 2018.
[128]RADFORD A, WU J, CHILD R, et al. Language models are unsupervised multitask learners[J]. OpenAI blog, 2019, 1(8): 9.
[129]BROWN T, MANN B, RYDER N, et al. Language models are few-shot learners[J]. Advances in neural information processing systems, 2020, 33: 1877-1901.
[130]HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 7132-7141.
[131]ZHOU Y, XU J, CAO J, et al. Hybrid attention networks for Chinese short text classification[J]. Computación y Sistemas, 2017, 21(4): 759-769.
[132]ZHANG S, TAY Y, YAO L, et al. Next item recommendation with self-attention[J]. arXiv preprint arXiv:1808.06414, 2018.
[133]李玉海,朱泽,夏红玉. 图书馆智慧服务中的数据获取[J]. 图书情报工作,2019,63(01):30-35.
[134]庞弘燊, 方曙, 杨波, 等. 科研团队合作紧密度的分析研究——以大连理工大学WISE实验室为例[J].图书情报工作,2011,55(04):28-32+99
[135]WATTS D J, STROGATZ S H. Collective dynamics of ‘small-world’networks[J]. nature, 1998, 393(6684): 440-442.
[136]SVIDER P F, CHOUDHRY Z A, CHOUDHRY O J, et al. The use of the h‐index in academic otolaryngology[J]. The Laryngoscope, 2013, 123(1): 103-106.
[137]DE BRÉBISSON A, SIMON É, AUVOLAT A, et al. Artificial neural networks applied to taxi destination prediction[J]. arXiv preprint arXiv:1508.00021, 2015.
[138]GROVER A, LESKOVEC J. node2vec: Scalable feature learning for networks[C]//Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining. 2016: 855-864.
[139]ZHANG S, TAY Y, YAO L, et al. Next item recommendation with self-attentive metric learning[C]//Thirty-Third AAAI Conference on Artificial Intelligence. 2019, 9.
[140]XU Q, QIU L, LIN R, et al. An improved community detection algorithm via fusing topology and attribute information[C]//2021 IEEE 24th International Conference on Computer Supported Cooperative Work in Design (CSCWD). IEEE, 2021: 1069-1074.