1、黑龍江大學(xué)碩士學(xué)位論文基于實體聚類的網(wǎng)絡(luò)信息檢索處理姓名：高鑌申請學(xué)位級別：碩士專業(yè)：計算機(jī)應(yīng)用技術(shù)指導(dǎo)教師：韓習(xí)武20090508黑龍江大學(xué)碩士學(xué)位論文AbstractAsthecontinualdevelopmentandapplicationofcomputingtechnologythequantityofdigitizedtextdocumentsunceasinglygrowsandthedevelopmentofIntem

2、etintensifiedtheinflationofdigitaltextSearchenginehasbecomeamaintoolforpeopletogetinformationSearchenginehasdevelopedveryfastandbeenusedwidelybutithasmanydisadvantagesandisinconvenientinpracticeSoutilizingtheclusteringan

3、alysistechnologytosimplifytherepresentationofmasstextdatareorganizetheresultsfromsearchengines，speeduptheinformationretrievalandrecommendcustomizedinformationwouldbepromisingapplicationsTherealemanyresearchesonthecluster

4、ingmethodusedinsearchengines，butclusteringmethodhasitsowndisadvantagesandonlyalittlehasbeenusedintheactualapplicationThispaperdemonstratesthatclusteringmethodcouldbeallauxiliaryfunctioninwebinformationretrievalThecluster

5、ingmethodwillreorganizethewebsearchresultsfortheusersBasedonthepropertiesofinformationretrievalthispaperproposesatwostagefastclusteringstrategyofwebsearchresultpagesInwebsearchresultclustering，HAC(HierarchicalAgglomerati

6、veClustering)andKmeansareusuallyusedButeachofthemhastheirownfaultsThispaperadvancesatwo—stageclusteringmethodInthefirststage，weclusterthetopicsbyHAC，andinthesecondstage，weclusterthetopicsandabstractsbyK—meanswiththeiniti

7、alclustercentersfromthefirststageclusteringtogetareasonableclusteringresultBecausethetopicsalealwaysshorttherunningtimeofHACisgreatlyshorterThismethodwillmakethetimeconditionofwebsearchbesatisfiedwellandgetabettercluster

8、ingresuRThemaincontributionofthisthesisisthatclusteringmethodisregardedastheauxiliaryfunctionininformationretrievalclearandanewimplementmethodhasbeenproposedKeywords：searchengine，clusteringmethod，afastclusteringstategyof