中國人民大學

何軍，計算機工學博士，數(shù)據(jù)工程與知識工程教育部重點實驗室主要研究人員。長期從事數(shù)據(jù)庫與數(shù)據(jù)挖掘方面的研究，近年主要研究方向為數(shù)據(jù)挖掘、數(shù)據(jù)庫、信息檢索、商務智能、知識工程等，在這個領域積淀了豐富的研究和開發(fā)經(jīng)驗。主持和參加了近十項科研項目，其中包括973項目、國家自然科學基金面上項目、國家自然科學基金重大項目、863項目、社科基金重大項目、微軟研究院IFP 課題等。與國際上多位知名的教授開展合作研究，近年在國際一流學術期刊和學術會議，如ACM Transactions oInformatioSystems (TOIS)、IEEE Transactions oKnowledge and Data Engineering (TKDE)、DecisioSupport Systems (DSS)、InformatioSystems、InformatioSciences、Computational Intelligence、Knowledge and InformatioSystems、Electronic Commerce Research and Applications等上發(fā)表多篇論文，在國際一流學術會議如ACM SIGKDD、IEEE ICDM、SIAM oData Mining (SDM) 、ACM CIKM等發(fā)表論文數(shù)十篇。獲得三次國際會議Best Paper Award獎，獲得5項國家發(fā)明專利授權。目前是ACM、IEEE等國際學術組織會員以及中國計算機學會高級會員。
為本科生、研究生講授包括《數(shù)據(jù)庫概論》、《商務智能》、《數(shù)據(jù)挖掘》、《信息檢索》、《計算廣告學》、《計算機技術前沿》等課程。

電話: 86-10-62514014

E-mail： hejun@ruc.edu.cn

主要研究方向

數(shù)據(jù)/文本挖掘、商務智能、社會網(wǎng)絡分析、社會計算、大數(shù)據(jù)管理與分析、個性化推薦系統(tǒng)、知識發(fā)現(xiàn)的理論與應用研究。

博士研究生將從事的科研工作及對學生的培養(yǎng)要求

1. 有較強的科研能力，能夠熟練閱讀數(shù)據(jù)庫/數(shù)據(jù)挖掘領域的經(jīng)典論文、當前重要國際會議（SIGMOD、VLDB、ICDE、SIGKDD、ICDM、SDM、CIKM）和重要學術期刊論文，寫出高水平的研究綜述，能系統(tǒng)地掌握科學研究的基本方法并撰寫出高水平的學術論文。

2. 積極參加國家科研項目，提高獨立科研能力特別是創(chuàng)新能力，培養(yǎng)團隊合作精神。

3. 有較強的工程能力，能夠進行系統(tǒng)的分析設計和開發(fā)，特別是要通過項目實施，提高設計和實現(xiàn)大型軟件的能力。

目前在研的科研項目：

[1] 國家973項目《海量弱可用信息上知識發(fā)現(xiàn)、演化與服務的理論和技術研究》.項目編號: 2012CB316205

[2] 國家自然科學基金項目《通過社會化媒體挖掘用戶興趣的方法及應用研究》(項目編號：71272029),

[3] 國家自然科學基金重點項目《網(wǎng)絡信息融合與知識服務的理論和方法研究》(項目編號：61033010)

[4] 國家863項目《基于用戶興趣模型的媒體大數(shù)據(jù)內容整合與可視化技術》(項目編號：2014AA015204)

[5] 國家社科基金重大項目《云計算環(huán)境下的信息資源集成與服務研究》（項目編號：12&ZD220）

[6] 國家社科基金重大項目《中華民族偉大復興的社會心理促進機制研究》（項目編號：13&ZD155）

[7] 國家核高基項目:非結構化數(shù)據(jù)管理系統(tǒng)之人大部分，項目編號：2010ZX01042-002-002

近期發(fā)表論文和著作

1.JuHe, H. Liu, Jeffrey Yu, P. Li, W. He, X. Du. Assessing Single-Pair Similarity over Graphs by Aggregating First-Meeting Probabilities. InformatioSystems. Volume 42, June 2014, Pages 107–122.

2.H. Liu, JuHe, D. Zhu, Charles Ling and X. Du. Measuring Similarity Based oLink Information: A Comparative Study. IEEE Transactions oKnowledge and Data Engineering (TKDE). Volume: 25, Issue: 12, 2013, Page(s): 2823–2840.

3.JuHe, H. Liu, Y. Gu, J. Yan, T. Liu. Scalable and Noise Tolerant Web Knowledge Extractiofor Search Task Simplification. DecisioSupport Systems. Volume 56, Pages 156-167. December 2013. (0167-9236).

4.H. Liu, JuHe, T. Wang, W. Song and X. Du. Combining user preferences and user opinions for accurate recommendation. Electronic Commerce Research and Applications. Volume 12, Issue 1, 2013, Pages 14–23.

5.H. Liu, JuHe, Y. Gu, H. Xiong and X. Du. Detecting and Tracking Topics and Events from Web Search Logs. ACM Transactions oInformatioSystems (TOIS). Volume 30 Issue 4, 2012. No. 21.

6.J. Cui, H. Liu, P. Li, JuHe, X. Du, P. Wang. TagClus: a Random Walk-Based Method for Tag Clustering. Knowledge and InformatioSystems. Volume 27, Issue 2 (2011), Page 193–225.

7. JuHe, H. Liu, B. Hu, X. Du and P. Wang. Selecting Effective Features and Relations for Efficient Multi-relational Classification. Computational Intelligence. Volume 26, Number 3, 2010.

8. H. Liu, X. Wang, JuHe, J. Han, D. Xin, Zheng Shao. Top-dowmining of frequent closed patterns from very high dimensional data. InformatioSciences, 15 March 2009.Volume 179, Issue 7, Pages 899–924.

國際會議論文選列（Refereed Proceedings with high impact）

1.N. Xu. H. Liu, JuHe and X. Du. Selecting a Representative Set of Diverse Quality Reviews Automatically. SIAM International conference oData Mining (SDM2014). April 24-26, 2014, Philadelphia, Pennsylvania, USA.

2.Y. Li, T. Liu, H. Liu, JuHe and X. Du. Predicting Microblog User's Age based oText Information. The 14th International Conference oWeb InformatioSystem Engineering (WISE 2013), Nanjing, China, 2013, Pages 510-515. (Best Challenge Paper Award).

3.T. Wang, H. Liu, JuHe and X. Du. Mining User Interests from informatioSharing Behaviors iSocial Media. The 17th Pacific-Asia Conference oKnowledge Discovery and Data Mining (PAKDD). April 14–17, 2013, Gold Coast, Australia. (Acceptance Rates: 59/344=17%).

4.X. Jiang, H. Liu, JuHe, X. Du. Effectively Grouping Named Entities from Click-Through Data into Clusters of Generated Keywords. The 16th 2Pacific Asia Conference oInformatioSystems (PACIS). July 11–15, 2012, Vientnam.

5.J. Cui, H. Liu, J. Yan, J. He, at el. Multi-view random walk framework for search task discovery from click-through log. Iproceedings of the 20th ACM Conference oInformatioand Knowledge Management (CIKM). Glasgow, UK. 2011. (Acceptance Rate: 20%).

6.Y. Gu, J. Yan, H. Liu, JuHe, L. Ji, N. Liu, Z. Chen. Extract Knowledge from Semi-structured WebSites for Search Task Simplification. Iproceedings of the 20th ACM Conference oInformatioand Knowledge Management (CIKM). Glasgow, UK. 2011. (Acceptance Rate: 20%)

7.P. Li, Jeffrey Yu, H. Liu, JuHe, X. Du. Ranking Individuals and Groups by Influence Propagation. The Pacific-Asia Conference oKnowledge Discovery and Data Mining (PAKDD). Shenzhen, China. May, 2011. (Acceptance rate: 9.7%).

8.P. Li, H. Liu, Jeffrey Yu, JuHe, X. Du. Fast Single-Pair SimRank Computation. SIAM International conference oData Mining (SDM2010). April 29–May 1, 2010. Columbus, Ohio. pp. 571–582. (Best paper award) (Acceptance rate: 82/351=23.36%).

9. H. Liu, H. Yan, W. Li, W. Wei, JuHe, X. Du. CRO: a System for Online Review Structurization. The 14th ACM SIGKDD International Conference oKnowledge Discovery and Data Mining (SIGKDD), 2008, Las Vegas, USA. p1085–1088. (DEMO).

10. Y. Cai, G. Cong, X. Jia, H. Liu, JuHe, J. Lu and X. Du. Efficient Algorithms for Computing Link-based Similarity iReal World Networks. IEEE International Conference oData Mining (ICDM). Miami, FL, December 6-9, 2009, IEEE Computer Society Press. (Acceptance rate: 139/786=17.68%).

11. P. Li, Y. Cai, H. Liu, JuHe and X. Du. Exploiting the Block Structure of Link Graph for Efficient Similarity Computation. The 13th Pacific-Asia Conference oKnowledge Discovery and Data Mining (PAKDD), Bangkok, Thailand. April 27-30, 2009. (Acceptance Rate: 39/338=11.54%).

15. J. Cui, Pei Li, H. Liu, JuHe, X. Du. A Neighborhood Search Method for Link-Based Tag Clustering. The International Conference oAdvanced Data Mining and Applications (ADMA), August, 2009. Beijing, China. p.91-103. (Best research paper award) (Acceptance rate: 39/322=12%).