{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T23:33:52Z","timestamp":1773099232590,"version":"3.50.1"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2013,4,1]],"date-time":"2013-04-01T00:00:00Z","timestamp":1364774400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Front. Comput. Sci."],"published-print":{"date-parts":[[2013,4]]},"DOI":"10.1007\/s11704-013-3903-7","type":"journal-article","created":{"date-parts":[[2013,4,5]],"date-time":"2013-04-05T20:47:29Z","timestamp":1365194849000},"page":"157-164","source":"Crossref","is-referenced-by-count":225,"title":["Big data challenge: a data management perspective"],"prefix":"10.1007","volume":"7","author":[{"given":"Jinchuan","family":"Chen","sequence":"first","affiliation":[]},{"given":"Yueguo","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Xiaoyong","family":"Du","sequence":"additional","affiliation":[]},{"given":"Cuiping","family":"Li","sequence":"additional","affiliation":[]},{"given":"Jiaheng","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Suyun","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Xuan","family":"Zhou","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2013,4,6]]},"reference":[{"issue":"12","key":"3903_CR1","doi-asserted-by":"crossref","first-page":"2032","DOI":"10.14778\/2367502.2367572","volume":"5","author":"A Labrinidis","year":"2012","unstructured":"Labrinidis A, Jagadish H. Challenges and opportunities with big data. Proceedings of the VLDB Endowment, 2012, 5(12): 2032\u20132033","journal-title":"Proceedings of the VLDB Endowment"},{"issue":"10","key":"3903_CR2","doi-asserted-by":"crossref","first-page":"1411","DOI":"10.1109\/TKDE.2006.152","volume":"18","author":"C Chang","year":"2006","unstructured":"Chang C, Kayed M, Girgis M R, Shaalan K F, others. A survey of web information extraction systems. IEEE Transactions on Knowledge and Data Engineering, 2006, 18(10): 1411\u20131428","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"3903_CR3","first-page":"349","volume-title":"Proceedings of the 2011 International Conference on Management of Data","author":"J Lu","year":"2011","unstructured":"Lu J, Lu Y, Cong G. Reverse spatial and textual K nearest neighbor search. In: Proceedings of the 2011 International Conference on Management of Data. 2011, 349\u2013360"},{"issue":"3","key":"3903_CR4","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1145\/1084805.1084812","volume":"34","author":"Y L Simmhan","year":"2005","unstructured":"Simmhan Y L, Plale B, Gannon D. A survey of data provenance in e-science. ACM Sigmod Record, 2005, 34(3): 31\u201336","journal-title":"ACM Sigmod Record"},{"issue":"5","key":"3903_CR5","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1145\/1230819.1241670","volume":"50","author":"B He","year":"2007","unstructured":"He B, Patel M, Zhang Z, Chang K C C. Accessing the deep web. Communications of the ACM, 2007, 50(5): 94\u2013101","journal-title":"Communications of the ACM"},{"key":"3903_CR6","first-page":"409","volume-title":"Proceedings of the 2012 International Conference on Management of Data","author":"J Lu","year":"2012","unstructured":"Lu J, Senellart P, Lin C, Du X, Wang S, Chen X. Optimal top-k generation of attribute combinations based on ranked lists. In: Proceedings of the 2012 International Conference on Management of Data. 2012, 409\u2013420"},{"key":"3903_CR7","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4419-6045-0","volume-title":"Managing and mining graph data","author":"C C Aggarwal","year":"2010","unstructured":"Aggarwal C C, Wang H. Managing and mining graph data. Springer Publishing Company, Incorporated, 2010"},{"key":"3903_CR8","unstructured":"Oceanbase. http:\/\/oceanbase.taobao.org"},{"key":"3903_CR9","first-page":"731","volume-title":"Proceedings of the 2012 International Conference on Management of Data","author":"V Sikka","year":"2012","unstructured":"Sikka V, F\u00e4rber F, Lehner W, Cha S K, Peh T, Bornh\u00f6vd C. Efficient transaction processing in SAP HANA database: the end of a column store myth. In: Proceedings of the 2012 International Conference on Management of Data. 2012, 731\u2013742"},{"key":"3903_CR10","unstructured":"Neo4j. http:\/\/neo4j.org"},{"key":"3903_CR11","first-page":"135","volume-title":"Proceedings of the 2010 International Conference on Management of data","author":"G Malewicz","year":"2010","unstructured":"Malewicz G, Austern M H, Bik A J, Dehnert J C, Horn I, Leiser N, Czajkowski G. Pregel: a system for large-scale graph processing. In: Proceedings of the 2010 International Conference on Management of data. 2010, 135\u2013146"},{"key":"3903_CR12","volume-title":"Proceedings of the 4th Biennial Conference on Innovative Data Systems Research","author":"A Doan","year":"2009","unstructured":"Doan A, Naughton J F, Baid A, Chai X, Chen F, Chen T, Chu E, DeRose P, Gao B J, Gokhale C, Huang J, Shen W, Vuong B Q. The case for a structured approach to managing unstructured data. In: Proceedings of the 4th Biennial Conference on Innovative Data Systems Research. 2009"},{"key":"3903_CR13","doi-asserted-by":"crossref","first-page":"847","DOI":"10.1145\/1376616.1376701","volume-title":"Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data","author":"S R Jeffery","year":"2008","unstructured":"Jeffery S R, Franklin M J, Halevy A Y. Pay-as-you-go user feedback for dataspace systems. In: Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data. 2008, 847\u2013860"},{"key":"3903_CR14","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1145\/1559845.1559857","volume-title":"Proceedings of the 35th SIGMOD International Conference on Management of Data","author":"X Chai","year":"2009","unstructured":"Chai X, Vuong B Q, Doan A, Naughton J F. Efficiently incorporating user feedback into information extraction and integration programs. In: Proceedings of the 35th SIGMOD International Conference on Management of Data. 2009, 87\u2013100"},{"key":"3903_CR15","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1145\/1807167.1807211","volume-title":"Proceedings of the 2010 ACM SIGMOD International Conference on Management of data","author":"P P Talukdar","year":"2010","unstructured":"Talukdar P P, Ives Z G, Pereira F. Automatically incorporating new sources in keyword search-based data integration. In: Proceedings of the 2010 ACM SIGMOD International Conference on Management of data. 2010, 387\u2013398"},{"issue":"5","key":"3903_CR16","doi-asserted-by":"crossref","first-page":"279","DOI":"10.14778\/1952376.1952378","volume":"4","author":"M Yakout","year":"2011","unstructured":"Yakout M, Elmagarmid A K, Neville J, Ouzzani M, Ilyas I F. Guided data repair. Proceedings of the VLDB Endowment, 2011, 4(5): 279\u2013289","journal-title":"Proceedings of the VLDB Endowment"},{"issue":"11","key":"3903_CR17","doi-asserted-by":"crossref","first-page":"1483","DOI":"10.14778\/2350229.2350263","volume":"5","author":"J Wang","year":"2012","unstructured":"Wang J, Kraska T, Franklin M J, Feng J. CrowdER: crowdsourcing entity resolution. Proceedings of the VLDB Endowment, 2012, 5(11): 1483\u20131494","journal-title":"Proceedings of the VLDB Endowment"},{"key":"3903_CR18","first-page":"9","volume-title":"Proceedings of the 32nd International Conference on Very Large Data Bases","author":"A Halevy","year":"2006","unstructured":"Halevy A, Rajaraman A, Ordille J. Data integration: the teenage years. In: Proceedings of the 32nd International Conference on Very Large Data Bases. 2006, 9\u201316"},{"key":"3903_CR19","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1145\/1807167.1807176","volume-title":"Proceedings of the 2010 ACM SIGMOD International Conference on Management of Data","author":"H Chen","year":"2010","unstructured":"Chen H, Ku W S, Wang H, Sun M T. Leveraging spatio-temporal redundancy for RFID data cleansing. In: Proceedings of the 2010 ACM SIGMOD International Conference on Management of Data. 2010, 51\u201362"},{"key":"3903_CR20","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1145\/1807167.1807213","volume-title":"Proceedings of the 2010 ACM SIGMOD International Conference on Management of Data","author":"H A Mahmoud","year":"2010","unstructured":"Mahmoud H A, Aboulnaga A. Schema clustering and retrieval for multi-domain pay-as-you-go data integration systems. In: Proceedings of the 2010 ACM SIGMOD International Conference on Management of Data. 2010, 411\u2013422"},{"key":"3903_CR21","first-page":"807","volume-title":"Proceedings of the 2012 International Conference on Management of Data","author":"K Morton","year":"2012","unstructured":"Morton K, Bunker R, Mackinlay J, Morton R, Stolte C. Dynamic workload driven data integration in tableau. In: Proceedings of the 2012 International Conference on Management of Data. 2012, 807\u2013816"},{"issue":"1\u20132","key":"3903_CR22","doi-asserted-by":"crossref","first-page":"1080","DOI":"10.14778\/1920841.1920976","volume":"3","author":"P Agrawal","year":"2010","unstructured":"Agrawal P, Sarma A D, Ullman J, Widom J. Foundations of uncertaindata integration. Proceedings of the VLDB Endowment, 2010, 3(1\u20132): 1080\u20131090","journal-title":"Proceedings of the VLDB Endowment"},{"key":"3903_CR23","doi-asserted-by":"crossref","first-page":"861","DOI":"10.1145\/1376616.1376702","volume-title":"Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data","author":"A Sarma Das","year":"2008","unstructured":"Das Sarma A, Dong X, Halevy A. Bootstrapping pay-as-you-go data integration systems. In: Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data. 2008, 861\u2013874"},{"issue":"3","key":"3903_CR24","doi-asserted-by":"crossref","first-page":"157","DOI":"10.14778\/2078331.2078332","volume":"5","author":"F M Suchanek","year":"2011","unstructured":"Suchanek F M, Abiteboul S, Senellart P. PARIS: probabilistic alignment of relations, instances, and schema. Proceedings of the VLDB Endowment, 2011, 5(3): 157\u2013168","journal-title":"Proceedings of the VLDB Endowment"},{"issue":"1","key":"3903_CR25","doi-asserted-by":"crossref","first-page":"736","DOI":"10.14778\/1453856.1453936","volume":"1","author":"J Huang","year":"2008","unstructured":"Huang J, Chen T, Doan A, Naughton J F. On the provenance of nonanswers to queries over extracted data. Proceedings of the VLDB Endowment, 2008, 1(1): 736\u2013747","journal-title":"Proceedings of the VLDB Endowment"},{"issue":"1\u20132","key":"3903_CR26","doi-asserted-by":"crossref","first-page":"429","DOI":"10.14778\/1920841.1920898","volume":"3","author":"E Ioannou","year":"2010","unstructured":"Ioannou E, Nejdl W, Nieder\u00e9e C, Velegrakis Y. On-the-fly entity-aware query processing in the presence of linkage. Proceedings of the VLDB Endowment, 2010, 3(1\u20132): 429\u2013438","journal-title":"Proceedings of the VLDB Endowment"},{"key":"3903_CR27","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1145\/1559845.1559869","volume-title":"Proceedings of the 35th SIGMOD International Conference on Management of Data","author":"Z Chen","year":"2009","unstructured":"Chen Z, Kalashnikov D V, Mehrotra S. Exploiting context analysis for combining multiple entity resolution systems. In: Proceedings of the 35th SIGMOD International Conference on Management of Data. 2009, 207\u2013218"},{"key":"3903_CR28","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1145\/1559845.1559870","volume-title":"Proceedings of the 35th SIGMOD International Conference on Management of Data","author":"S E Whang","year":"2009","unstructured":"Whang S E, Menestrina D, Koutrika G, Theobald M, Garcia-Molina H. Entity resolution with iterative blocking. In: Proceedings of the 35th SIGMOD International Conference on Management of Data. 2009, 219\u2013232"},{"issue":"1","key":"3903_CR29","doi-asserted-by":"crossref","first-page":"407","DOI":"10.14778\/1687627.1687674","volume":"2","author":"W Fan","year":"2009","unstructured":"Fan W, Jia X, Li J, Ma S. Reasoning about record matching rules. Proceedings of the VLDB Endowment, 2009, 2(1): 407\u2013418","journal-title":"Proceedings of the VLDB Endowment"},{"key":"3903_CR30","first-page":"44","volume-title":"Proceedings of the 5th International Joint Conference on INC, IMS and IDC","author":"B P Rimal","year":"2009","unstructured":"Rimal B P, Choi E, Lumb I. A taxonomy and survey of cloud computing systems. In: Proceedings of the 5th International Joint Conference on INC, IMS and IDC. 2009, 44\u201351"},{"issue":"1","key":"3903_CR31","doi-asserted-by":"crossref","first-page":"598","DOI":"10.14778\/1453856.1453922","volume":"1","author":"M K Aguilera","year":"2008","unstructured":"Aguilera M K, Golab W, Shah M A. A practical scalable distributed b-tree. Proceedings of the VLDB Endowment, 2008, 1(1): 598\u2013609","journal-title":"Proceedings of the VLDB Endowment"},{"key":"3903_CR32","first-page":"661","volume-title":"Proceedings of the 31st International Conference on Very Large Data Bases","author":"H V Jagadish","year":"2005","unstructured":"Jagadish H V, Ooi B C, Vu Q H. BATON: a balanced tree structure for peer-to-peer networks. In: Proceedings of the 31st International Conference on Very Large Data Bases. 2005, 661\u2013672"},{"key":"3903_CR33","first-page":"1","volume-title":"Bulletin of the IEEE Computer Society Technical Committee on Data Engineering","author":"S Wu","year":"2009","unstructured":"Wu S, Wu K L. An indexing framework for efficient retrieval on the cloud. In: Bulletin of the IEEE Computer Society Technical Committee on Data Engineering. 2009, 1\u20138"},{"key":"3903_CR34","first-page":"987","volume-title":"Proceedings of the 2010 International Conference on Management of Data","author":"S Das","year":"2010","unstructured":"Das S, Sismanis Y, Beyer K S, Gemulla R, Haas P J, McPherson J. Ricardo: integrating R and Hadoop. In: Proceedings of the 2010 International Conference on Management of Data. 2010, 987\u2013998"},{"key":"3903_CR35","doi-asserted-by":"crossref","first-page":"296","DOI":"10.1109\/ICDMW.2009.34","volume-title":"Proceedings of the 2009 IEEE International Conference on Data Mining Workshops","author":"D Wegener","year":"2009","unstructured":"Wegener D, Mock M, Adranale D, Wrobel S. Toolkit-based high-performance data mining of large data on MapReduce clusters. In: Proceedings of the 2009 IEEE International Conference on Data Mining Workshops. 2009, 296\u2013301"},{"key":"3903_CR36","first-page":"281","volume-title":"Proceedings of the 2006 Conference Advances in Neural Information Processing Systems","author":"C T Chu","year":"2007","unstructured":"Chu C T, Kim S K, Lin Y A, Yu Y Y, Bradski G, Ng A Y, Olukotun K. Map-reduce for machine learning on multicore. In: Proceedings of the 2006 Conference Advances in Neural Information Processing Systems. 2007, 281\u2013288"}],"container-title":["Frontiers of Computer Science"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11704-013-3903-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11704-013-3903-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11704-013-3903-7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T21:01:18Z","timestamp":1559422878000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11704-013-3903-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,4]]},"references-count":36,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2013,4]]}},"alternative-id":["3903"],"URL":"https:\/\/doi.org\/10.1007\/s11704-013-3903-7","relation":{},"ISSN":["2095-2228","2095-2236"],"issn-type":[{"value":"2095-2228","type":"print"},{"value":"2095-2236","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,4]]}}}