您好,欢迎访问三七文档
当前位置:首页 > 商业/管理/HR > 企业财务 > 数据挖掘在税务管理的应用
合肥工业大学硕士学位论文数据挖掘在税务管理的应用姓名:贾虎申请学位级别:硕士专业:工商管理指导教师:赵惠芳2010-12CTAISApplicationofdataminingintaxadministrationABSTRACTAlongwithdatawarehousetechnologyfastdevelopment,manycorporations,governmentandfinancedepartmentsusethistechnologyinbroaddomain.Atthesametime,taxdepartmentofourcountryaccumulateagreatdealoftaxationdatathroughincessantbuildinginformationsystemsonkindsofplat.Howtoutilizethesedatasufficientlyandprovideefficientservicesforrevenuers,isabigproblemtoberesolvedimminently.Thisarticlemainlyintroducesthebasetheoryofdatawarehousefirstly.Itproposesadesignprojectcombiningrequirementsofrevenuersfortheframeworkoftaxdatawarehouse,andconfirmstheemphasesofdesignwork.Secondly,putforwardawayhowtocreatetax—datawarehousewhichusesChinataxationadministrationinformationsysterm(CTAIS)asdatasourceinvirtueoftechniqueindatawarehouseAfterstudieddeepCTAISandofferedaquiteall-sidedviewofprocessofdatawarehouseomstruction.IntheresearchofDMtechnique,thepaperdiscussthefunction,classification,task,methodsandtechniqueofdatamining.PutforwardthebasicprocedureandmainstepsaboutapplicationofDMintaxadministrationsystem.wediscussedthedetectofabstractofmistakeoftaxadministratorsystemthroughthetechnologyofcluster.wecanfindtheabnormalthingsinthetaxfactorsandtheruleofit,wecanpromoteourablityofmanagermentandmonitorinthetaxmanagermentKeywords:TaxDataWarehouseTaxDataTopicdatamining2-1………………………………………………………64-1……………………………………………144-2……………………………………………154-3………………………………………………164-4………………………………………164-5…………………………………………………………294-6…………………………………………………………304-7………………………………………………………………314-8…………………………………………………………324-9……………………………………………………………345-1………………………………………………………………405-1415-242201012132010121320101213462010121311.11.1.180client/serverbrowser/server2[1]1.1.21.(CTAISv1.1)2.3.oracle4.1.1.31.3,2.12---3441.212OLAP352.1OLAP[5][6][5][6]2.2123(6)2.31[6]2ETLExtraction-Transformation-Loading[6]3[6]4OLAP[6]5[6]112-12-172.41.:[5]2.:COBOLMVSJCLUNIXSQL[5]3.[5]informationdirectory4.EISOLAP5.DataMartssubjectarea[5]6.7.Web82.5OLTPOLAPOLTPon-linetransactionprocessingOLAPOn-LineAnalyticalProcessing[6]OLTPOLTP1.2.3.OLTP()4.,OLAPOLAP1.2.OLAP;3.OLAPOLTPOLAPOLTPOLAPDBADBE-R//9/DB100MBGB100GBTB2.6[2][3][4]1classificationABCdecisiontreediscriminantanalysisartificialneuralnetworkmemory-basedreasoning2estimationLogistic3prediction4affinitygrouping5clusteringclusters10k-meansagglomeration2.7113.11OLTPOLAPOLAP2OLTPOLAPW.H.Inmon[7]ABCDEABC3.213412OLTPOLAP2345/133.3144.114-14-12(CTAIS)3[9]4154.214-2OLAP[10]CTAISETLETL4-2216ETLETLINFODIBO4-3(1)CTAIS(2)(3)3.34-417CTAISOracleSqlserver4(1)(2)(3)5(1)55(2)dataaboutdataTechnicalMetadataBusinessMetadata(3)18(4)(5)1234(6)12(7)1194.34.3.1[9-12]1.2.3.4.20552.9716.5636.3948.946.4511.911.890.15214.3.21()24.3.3ETLCTAISETLsql/****************//**//****************/22/*1--*//*1.1--*//*1.1.1--*//*1.1.2--*//*1.1.3--SQL*/--(5013)selectsubstr(b.nsr_swjg_dm,1,5)swjg,b.nsrsbhfrom(selectrz_nsrsbhnsrsbhfromrz_fpdkl_mx@fwskwhererz_yf=1745--2009.01andrz_yf=1763--2010.03andrz_fs=5--groupbyrz_nsrsbh)a,dj_nsrxxbwherea.nsrsbh=b.nsrsbh/*--()(14896)selectsubstr(b.nsr_swjg_dm,1,5)swjg,b.nsrsbhfromhtjs.wsrz_qy_khxx@fwska,dj_nsrxxbwherea.nsrsbh=b.nsrsbh--*/union--selectsubstr(b.nsr_swjg_dm,1,5)swjg,b.nsrsbhfrom(selectdistinctnsrsbhfromsb_sbxxwherelrrq=to_date('20090101','YYYYMMDD')andlrrqto_date('20100331','YYYYMMDD')andlrr_dmin('13401999999','13402009990','13403009900','13404060002','13405000100','13406000068','13407008888','13408009996','13410009997','13411008888','13412009990','13416000990','13422009991','13424999999','13425009993','13426009998','13429009995')--)a,dj_nsrxxbwherea.nsrsbh=b.nsrsbhandb.djzclx_dmnotin('410','420','430')--union--()23selectsubstr(b.nsr_swjg_dm,1,5)swjg,b.nsrsbhfrom(selectdistinctnsrsbhfromsb_sbxxwherelrrq=to_date('20090101','YYYYMMDD')andlrrqto_date('20100331','YYYYMMDD')andlrr_dm='00000000000'--)a,dj_nsrxxbwherea.nsrsbh=b.nsrsbhandb.djzclx_dmnotin('410','420','430')--/*1.2--*//*1.2.1--*//*1.2.2--*//*1.2.3--SQL*/selectsubstr(b.nsr_swjg_dm,1,5)swjg,b.nsrsbhfrom(selectdistinctnsrsbhfromsb_sbxxwherelrrq=to_date('20090101','YYYYMMDD')andlrrqto_date('20100331','YYYYMMDD'))a,dj_nsrxxbwherea.nsrsbh=b.nsrsbhandb.djzclx_dmnotin('410','420','430')--/*2--*//*3--*/1./*4--*/1./*++*/selecta.,b.,c.,d.from(selectnvl(count(distincta.nsrsbh),0)asfromv3429_dj_nsrxxawhereexists(select1fromv3429_dj_nsrzt_bgbwhereb.nsrzt_dm'50'anda.nsrsbh=b.nsrsbhandb.yxq_q=to_date('&','yyyymmdd')24and(b.YXQ_Z=to_date('&','yyyymmdd')orb.YXQ_Zisnull)))a,(selectnvl(count(distincta.nsrsbh),0)asfromv3429_dj_nsrxxawherea.DJZCLX_DMnotin('410','420','430')andexists(select1fromv3429_dj_nsrzt_bgbwhereb.nsrzt_dm'50'anda.nsrsbh=b.nsrsbhandb.yxq_q=to_date('&','yyyymmdd')and(b.YXQ_Z=to_date('&','yyyymmdd')orb.YXQ_Zisnull)))b,(selectnvl(count(distincta.nsrsbh),0)asfromv3429_dj_nsrxxawherea.DJZCLX_DMin('410','420','430')andexists(select1fromv3429_dj_nsrzt_bgbwhereb.nsrzt_dm'50'anda.nsrsbh=b.nsrsbhandb.yxq_q=to_date('&','yyyymmdd')and(b.YXQ_Z=to_date('&','yyyymmdd')orb.YXQ_Zisnull))
本文标题:数据挖掘在税务管理的应用
链接地址:https://www.777doc.com/doc-1188748 .html