KS X ISO IEC 13249-6-2008 Information technology－Database languages－SQL multimedia and application packages－Part 6：Data mining《信息技术 数据库语言 结构化查询语言(SQL)多媒体和应用数据包 第6部分 数据挖掘》.pdf

1、 KSKSKSKSKSKSKSK KSKSKS KSKSK KSKS KSK KS KS X ISO/IEC 13249 6 SQL 6： KS X ISO/IEC 13249 6:2008 2008 11 10 http:/www.kats.go.krKS X ISO/IEC 13249 6:2008 : e- ( ) ( ) () () ( ) : (http:/www.standard.go.kr) ： ： 2003 12 29 ： 2008 11 10 2008-0765 ： e- ： ( 025097262) (http:/www.kats.go.kr). 10 5 , . KS X

2、 ISO/IEC 13249 6:2008 i . iii .1 1 1 2 1 2.1 .1 2.2 Publicly-available specifications .2 3 .2 3.1 .2 3.2 .7 3.3 .8 4 8 4.1 (data mining techniques)8 4.2 (computational patterns).9 4.3 (mapping on user-defined types) 10 5 .14 5.1 DM_RuleModel (DM_RuleModel Type and Routines) 14 5.2 DM_ClusteringModel

3、 (DM_ClusteringModel Type and Routines).17 5.3 DM_RegressionModel (DM_RegressionModel Type and Routines).21 5.4 DM_ClasModel (DM_ClasModel Type and Routines).27 5.5 DM_ClusApplTask (DM_ClusApplTask Type and Routines) 32 5.6 DM_RegTestTask (DM_RegTestTask Type and Routines)37 5.7 DM_RegApplTask (DM_R

4、egApplTask Type and Routines)40 5.8 DM_ClasTestTask (DM_ClasTestTask Type and Routines).45 5.9 DM_ClasApplTask (DM_ClasApplTask Type and Routines) 48 6 53 6.1 DM_ClasSettings (DM_ClasSettings Type and Routines) 53 6.2 DM_ClusSettings (DM_ClusSettings Type and Routines) 61 6.3 DM_RegSettings (DM_RegS

5、ettings Type and Routines)69 6.4 DM_RuleSettings (DM_RuleSettings Type and Routines)75 6.5 DM_ClasBldTask (DM_ClasBldTask Type and Routines) 83 6.6 DM_RuleBldTask (DM_RuleBldTask Type and Routines)87 6.7 DM_RegBldTask (DM_RegBldTask Type and Routines)90 6.8 DM_ClusBldTask (DM_ClusBldTask Type and Ro

6、utines) 94 7 97 7.1 DM_ClusResult (DM_ClusResult Type and Routines)97 7.2 DM_ClasResult (DM_ClasResult Type and Routines)98 7.3 DM_RegResult (DM_RegResult Type and Routines) .100 8 101 8.1 DM_ClasTestResult (DM_ClasTestResult Type and Routines)101 8.2 DM_RegTestResult (DM_RegTestResult Type and Rout

7、ines) .104 KS X ISO/IEC 13249 6:2008 ii 9 105 9.1 DM_LogicalDataSpec (DM_LogicalDataSpec Type and Routines) 105 9.2 DM_MiningData (DM_MiningData Type and Routines) 111 9.3 DM_ApplicationData (DM_ApplicationData Type and Routines) 114 10 .116 11 118 11.1 (requirements for conformance) .118 11.2 (clai

8、ms of conformance)118 A( ) .119 B( ) .120 C( ) 121 KS X ISO/IEC 13249 6:2008 .123 KS X ISO/IEC 13249 6:2008 iii KS X ISO/IEC 13249 6： 2003 . A( ) B( ) C( ) ISO/IEC 13249 “ SQL ” . 1： 2： 3： 5： 6： KS X ISO/IEC 13249 6:2008 SQL 6： Information technology Database languages SQL multimedia and application

9、 packages Part 6： Data mining 2002 1 ISO/IEC 13249 6, Information technology Database languages SQL multimedia and application packages Part 6： Data mining , . 1 . a) KS X ISO/IEC 13249 b) KS X ISO/IEC 13249 6 c) KS X ISO/IEC 13249 6 d) KS X ISO/IEC 13249 6 e) . . , , , . SQL . 2 . . ( .) . 2.1 KS X

10、 ISO/IEC 9075 1, SQL 1： SQL/ KS X ISO/IEC 13249 6:2008 2 ISO/IEC 9075 1： 1999, Information technology Database languages SQL Part 1： Framework (SQL/Framework) KS X ISO/IEC 9075 2, SQL 2： SQL/ ISO/IEC 9075 2： 1999, Information technology Database languages SQL Part 2： Foundation (SQL/Foundation) KS X

11、 ISO/IEC 9075 4, SQL 4： SQL/ ISO/IEC 9075 4： 1999, Information technology Database languages SQL Part 4： Persistent Stored Modules(SQL/PSM) KS X ISO/IEC 13249 1, SQL 1： ISO/IEC 13249 1： 2000, Information technology Database languages SQL multimedia and application packages Part 1： Framework 2.2 Publ

12、icly-available specifications Extensible Markup Language(XML) 1.0(Second Edition). 2 October 2000, http： /www.w3.org/TR/REC xml Predictive Model Markup Language(PMML) 1.1, http： /www.dmg.org/pmml v1 1.htm 3 3.1 . 3.1.1 KS X ISO/IEC 13249 1 KS X ISO/IEC 13249 1 . 3.1.2 . 3.1.2.1 (active field) . 3.1.

13、2.2 (application phase) ( ) 3.1.2.3 (association rule) ( ) , . KS X ISO/IEC 13249 6:2008 3 3.1.2.4 (association rule support) “X Y Z .” X Y, Z 100 . 3.1.2.5 (categorical field type) . . 3.1.2.6 (class label) . . . 3.1.2.7 (classification cost rate) . . 3.1.2.8 (classification error) . 3.1.2.9 (class

14、ification model) 3.1.2.10 (data mining application task) , 3.1.2.11 (data mining classification) “ ” “ ” . KS X ISO/IEC 13249 6:2008 4 3.1.2.12 (data mining cluster) “ ” “ ” . 3.1.2.13 (data mining clustering) ( .) “ ” “ ” “ ” . 3.1.2.14 (data mining data) . 3.1.2.15 (data mining data type) . ( ) .

15、. 3.1.2.16 (data mining model) . 1 ( ) . 2 “ ” “ ” “ ” . 3.1.2.17 (data mining regression) , . 1 . 2 “ ” “ ” . KS X ISO/IEC 13249 6:2008 5 3.1.2.18 (data mining run) . , , . , . 3.1.2.19 (data mining segmentation) 3.1.2.20 (data mining settings) “ ” “ ” “ ” . 3.1.2.21 (data mining task) , “ ” “ ” “

16、” . 3.1.2.22 (data mining technique) 4 ( / , , ). 3.1.2.23 (data mining test result) 1 . 2 “ ” “ ” . 3.1.2.24 (data mining test task) 3.1.2.25 (data warehouse) KS X ISO/IEC 13249 6:2008 6 3.1.2.26 (export) 3.1.2.27 (import) 3.1.2.28 (input field) 3.1.2.29 (input row) . 3.1.2.30 (logical data specifi

17、cation) . 3.1.2.31 (logical field) (DM_LogicalDataSpec) 3.1.2.32 (logical field type) “ ” “ ” . 3.1.2.33 (numerical field type) . 3.1.2.34 (predicted value) . KS X ISO/IEC 13249 6:2008 7 3.1.2.35 (regression model) 3.1.2.36 (rule confidence) “X Y Z .” X Y, Z X Y 100 . 3.1.2.37 (similarity scale) 50

18、% . 3.1.2.38 (source table) . . 3.1.2.39 (target field) . . . 3.1.2.40 (testing phase) , , 3.1.2.41 (training data) 3.1.2.42 (training phase) . 3.1.2.43 (validation phase) , , , . 3.2 KS X ISO/IEC 13249 6:2008 8 3.2.1 KS X ISO/IEC 13249 1 KS X ISO/IEC 13249 1 . 3.2.2 , SQL “DM_” . SQL . “appl” “appl

19、ication” “bld” “Build” “clas” “classification” “clus” “clustering” “conf” “confidence” “dataSpec” “Logical Data Specification” “def” “define” “exp” “export” “fld” “field” “imp” “import” “mdlSpec” “Model Data Specification” “num” “number of” “outp” “Output” “pred” “predicted” “Prediction” “reg” “regr

20、ession” “sim” “similarity” “spec” “Specification” “trn” “training” “val” “validation” 3.3 KS X ISO/IEC 13249 1 . 4 4.1 (data mining techniques) . ( ) . . 4 . a) (the search for association rules) ( ) , . X Y , N % Z . b) / (clustering/segmentation) KS X ISO/IEC 13249 6:2008 9 . . . c) (classification) , . . d) (regression) . . . 4.2 (computational patterns) 3 ( , ). . 4.2.1 (training phase) . . 1 . . . 4.2.2 (application phase) , . . . . KS X ISO/IEC 13249 6:2008 10 2 . . 4.2.3 (testing phase) . . . . . 3 4.3 (mapping on user-defined types) 4.3.1 (target application) . . . .