由知識挖掘提升商務(wù)智能應(yīng)用

由知識挖掘提升商務(wù)智能應(yīng)用2024/3/11由知識挖掘提升商務(wù)智能應(yīng)用Outline知識采礦(整合數(shù)據(jù)采礦與文本采礦)與商業(yè)智慧的發(fā)展知識采礦程序、步驟、產(chǎn)出與應(yīng)用如何進(jìn)行數(shù)據(jù)采礦與文本采礦整合知識采礦之技術(shù)發(fā)展評論由知識挖掘提升商務(wù)智能應(yīng)用知識保存價(jià)值減少循環(huán)時(shí)間反應(yīng)時(shí)間重復(fù)投資作業(yè)花費(fèi)會(huì)議時(shí)間外界顧問…等等增加生產(chǎn)力與質(zhì)量企業(yè)知識的轉(zhuǎn)換快且有效的決策課程創(chuàng)新群策群力…等等

企業(yè)知識的保留與轉(zhuǎn)換知識資產(chǎn)的投資精簡與退休人員輪替

生產(chǎn)力能力重復(fù)能量消耗過多的會(huì)議溝通問題組織目標(biāo)

下達(dá)決策可行性快速非正規(guī)由知識挖掘提升商務(wù)智能應(yīng)用為何知識如此迫切?“Thechiefeconomicpriorityfordevelopedcountriesistoraisetheproductivityofknowledge...Thecountrythatdoesthisfirstwilldominatethetwenty-firstcenturyeconomically.”開發(fā)中國家首要經(jīng)濟(jì)目標(biāo)為知識的創(chuàng)造力…誰先掌握誰就統(tǒng)領(lǐng)二十一世紀(jì)的經(jīng)濟(jì)PeterF.Drucker由知識挖掘提升商務(wù)智能應(yīng)用資料

知識形成流程DataWarehouseKnowledgeSelection/cleansingPreprocessingTargetDataPreprocessedDataPatternTransformedData

DataMiningTransformationInterpretation/EvaluationIntegrationRawDataUnderstanding由知識挖掘提升商務(wù)智能應(yīng)用BI結(jié)構(gòu)Monitor&IntegratorCompleteDataWarehouseExtractTransformLoadRefreshmetadataOLAPServer1.ComprehensivePerformanceManagement2.Analysis3.Query4.Reports5.DataminingDataSourcesToolsServeDataMartsOperationalDBsOthersourcesBusinessIntelligence由知識挖掘提升商務(wù)智能應(yīng)用資料采礦/探勘ruleinduction neuralnetworkstreegeneratorsruleinductionsupportvectormachine

regressionCOWEBestimationmaximizationk-meansroughsetsapriori granularcomputingtrendfunctionsruleinduction neuralnetworks CategorizeyourcustomersorclientsClassificationForecastfuturesalesorusagePredictionGroupsimilarcustomersorclientsSegmentationDiscoverproductsthatarepurchasedtogetherAssociationFindpatternsandtrendsovertimeSequence由知識挖掘提升商務(wù)智能應(yīng)用GainingmarketintelligencefromnewsfeedsSreekumarSukumaranandAshishSureka由知識挖掘提升商務(wù)智能應(yīng)用IntegratedBISystemsCompleteDataWarehouseETLStructuralDataDBMSFileSystemXMLEALegacyUnstructuredDataCMSScannedDocumentsEmailETLTexttaggor&AnnotatorIntermediaDataRDBMSXMLSreekumarSukumaranandAshishSureka由知識挖掘提升商務(wù)智能應(yīng)用知識來源與價(jià)值“Onaverage,professionalusersspend11hoursperweeklookingforinformation.Seventy-onepercentsaidtheycouldnotfindwhattheywerelookingfor."

—"InformationManagementSoftware"

LazardFreres&Co.LLC

February2001"Thevolumeofdigitizedinformationwilldoubleeveryyearfrom2000to2005(anincreaseto30timestoday'svolume)."

—"KnowledgeManagementvs.InformationManagement"

GartnerGroup

September2000網(wǎng)絡(luò)訊息新聞報(bào)導(dǎo)專利電子郵件文件…由知識挖掘提升商務(wù)智能應(yīng)用文獻(xiàn)問題出版統(tǒng)計(jì)8TB(書籍),25TB(新聞),20TB(雜志),2TB(期刊)平均每分鐘科學(xué)知識增加2000頁新材料的閱讀須時(shí)5年(24hrs/day)HowCanIKeepUpWiththeLiterature?由知識挖掘提升商務(wù)智能應(yīng)用Evolution“Tostudyhistoryonemustknowinadvancethatoneisattemptingsomethingfundamentallyimpossible,yetnecessaryandhighlyimportant.”FatherJacobus(Hesse'sMagisterLudi)DasGlasperlenspiel(TheGlassBeadGame)由知識挖掘提升商務(wù)智能應(yīng)用文件知識發(fā)掘與管理技術(shù)檢索文件

過濾分類摘要

分群自然語言內(nèi)文分析萃取探勘可視化萃取應(yīng)用探勘應(yīng)用信息存取知識認(rèn)知信息結(jié)構(gòu)由知識挖掘提升商務(wù)智能應(yīng)用知識產(chǎn)生RawtextTermsimilarityDocsimilarityVectorcentroid分群d分類META-DATA/ANNOTATIONddddddddddddddttttttttttttStemming&StopwordsTokenizedtextTermWeightingw11w12…w1nw21w22…w2n……wm1wm2…wmn

t1t2…tn

d1

d2

…dmSentenceselection摘要由知識挖掘提升商務(wù)智能應(yīng)用TextETLtoMiningCallTaker:JamesDate:Aug.30,2002Duration:10min.CustomerID:ADC00123Q:custsyshasstopped

working.A:checkedcustbiosanditneedupdated.…UnstructuredDataStructuredData[CallTaker]James[Date]2002/08/30[Duration]10min.[CustomerID]ADC00123[Noun]Customer[Software]BIOS[Subj...Verb]customersystem..stop[SW..Problem]BIOS..needOriginalDataMetaDataLinguisticAnalysisTaggingDependencyAnalysisNamedEntityExtractionIntentionAnalysisCategoryDictionarySynonymDictionaryCategoryItemVisualization&InteractiveMiningMiningIBMTAKMI(Nasukawa,Nagano,1999)Miningtarget:individualtextMiningunit:>texts>categorylabeleditemsextractedfromtextusingNLP由知識挖掘提升商務(wù)智能應(yīng)用TextisTough其系一個(gè)極不容易表達(dá)的抽象性概念

(AI-Complete)

是許多概念彼此間抽象而復(fù)雜的無盡關(guān)系組合一種名詞可以代表很多不同的概念CELL,IV類似的概念也有很多種方式可以表達(dá)(aliases)spaceship,flyingsaucer,UFO,figmentofimagination概念是很難加以可視化的高維度

其分析構(gòu)面可能高達(dá)成百上千由知識挖掘提升商務(wù)智能應(yīng)用TextMiningisEasy重復(fù)性很高只要一些簡單的算法，就可以從一些極為粗糙的工作中，得到不錯(cuò)的結(jié)果找出重要詞組找到有意義的相關(guān)字從文章中建立摘要主要問題:結(jié)果評估必須定義目標(biāo)及目的由知識挖掘提升商務(wù)智能應(yīng)用TraditionalIR-basedExtractiondocvector1profilevector

docvectorn…scoringscorejudgments

rejecteddocs

accepteddocs

noyesvectorlearningthresholdlearningutilityfunctionOntologyVectorinitializationThresholdinitializationReuseretrievalalgorithmsNewthresholdalgorithmsScore>?threshold

Text-DBLexicons由知識挖掘提升商務(wù)智能應(yīng)用Luhn'sideasItishereproposedthatthefrequencyofwordoccurrenceinanarticlefurnishesausefulmeasurementofwordsignificance.Itisfurtherproposedthattherelativepositionwithinasentenceofwordshavinggivenvaluesofsignificancefurnishausefulmeasurementfordeterminingthesignificanceofsentences.Thesignificancefactorofasentencewillthereforebebasedonacombinationofthesetwomeasurements.由知識挖掘提升商務(wù)智能應(yīng)用信息萃取-Job2

JobTitle:IceCreamGuru

Employer:

JobCategory:Travel/Hospitality

JobFunction:FoodServices

JobLocation:UpperMidwestContactPhone:800-488-2611

DateExtracted:January8,2001

Source:/jobs_midwest.html

OtherCompanyJobs:-Job1由知識挖掘提升商務(wù)智能應(yīng)用InformationExtractionGiven:SourceoftextualdocumentsWelldefinedlimitedquery(textbased)Find:SentenceswithrelevantinformationExtracttherelevantinformationandignorenon-relevantinformation(important!)LinkrelatedinformationandoutputinapredeterminedformatAdvisoryProgrammer-Oracle(Austin,TX)ResponseCode:1008-0074-97-iexc-jcnResponsibilities:ThisisanexcitingopportunitywithSiemensWirelessTerminals;astart-upventurefullycapitalizedbyaGlobalLeaderinAdvancedTechnologies.Qualifiedcandidateswill:Responsibleforassistingwithrequirementsdefinition,analysis,designandimplementationthatmeetobjectives,codesdifficultandsophisticatedroutines.Developsprojectplans,schedulesandcostdata.Developtestplansandimplementphysicaldesignofdatabases.Developshellscriptsforadministrativeandbackgroundtasks,storedproceduresandtriggers.UsingOraclesDesigner2000,assistwithDataModelmaintenanceandassistwithapplicationsdevelopmentusingOracleForms.Qualifications:BSCS,BSMISorcloselyrelatedfieldorrelatedequivalentknowledgenormallyobtainedthroughtechnicaleducationprograms.5-8yearsofprofessionalexperienceindevelopment,systemdesignanalysis,programming,installationusingOracledevelopment…由知識挖掘提升商務(wù)智能應(yīng)用AutomaticPattern-LearningSystemsPros:PortableacrossdomainsTendtohavebroadcoverageRobustinthefaceofdegradedinput.AutomaticallyfindappropriatestatisticalpatternsSystemknowledgenotneededbythosewhosupplythedomainknowledge.Cons:Annotatedtrainingdata,andlotsofit,isneeded.Isn’tnecessarilybetterorcheaperthanhand-builtsol’nExamples:

Riloffetal.,AutoSlog,SoderlandWHISK(UMass);Mooneyetal.Rapier(UTexas);Ciravegna(Sheffield)Learnlexicon-syntacticpatternsfromtemplatesTrainerDecoderModelLanguageInputAnswersAnswersLanguageInput由知識挖掘提升商務(wù)智能應(yīng)用TextAnalysisSpectrumEntityExtractionTargetedFactsandEventsClassificationClusteringConceptIdentificationWhatisthisdocumentabout?Whodidwhattowhomwhenwhere,etc.由知識挖掘提升商務(wù)智能應(yīng)用Whyisgettingdimensionaldatasohard?HankboughtplasticexplosivesfromHenryin Tucsonyesterday.NamedEntityExtractionPeople,Weapons,Vehicles,DatesNEREngineHankHenryPlasticexplosivesTucson11/01/07FrameNet由知識挖掘提升商務(wù)智能應(yīng)用NameExtractionviaMMsTextSpeechRecognitionExtractorSpeechEntities

NEModelsLocationsPersonsOrganizationsThedelegation,whichincludedthecommanderoftheU.N.troopsinBosnia,Lt.Gen.SirMichaelRose,wenttotheSerbstrongholdofPale,nearSarajevo,fortalkswithBosnianSerbleaderRadovanKaradzic.TrainingProgramtrainingsentencesanswersThedelegation,whichincludedthecommanderoftheU.N.

troopsinBosnia,Lt.Gen.SirMichaelRose,wenttotheSerbstrongholdofPale,nearSarajevo,fortalkswithBosnianSerbleader

RadovanKaradzic.AneasybutsuccessfulHMMapplication:Priorto1997-nolearningapproachcompetitivewithhand-builtrulesystemsSince1997-Statisticalapproaches(BBN(Bikeletal.1997),NYU,MITRE,CMU/JustSystems)achievestate-of-the-artperformance由知識挖掘提升商務(wù)智能應(yīng)用NER由知識挖掘提升商務(wù)智能應(yīng)用數(shù)據(jù)庫探勘作業(yè)流程決策參考決策建議自動(dòng)分群自動(dòng)／專家分類事件關(guān)連分析文檔庫知識本體論推論圖知識地圖由知識挖掘提升商務(wù)智能應(yīng)用概念分群documentDocumentCollection{sun}{beach}Frequenttermset:{surf}{fun}{sun,beach}clusterC1C2C4C5C3Clustering:{C1,C2,C4,C5}.ClusteringDescription:{surf,sun,beach,fun}.由知識挖掘提升商務(wù)智能應(yīng)用Anopheles由知識挖掘提升商務(wù)智能應(yīng)用FeedbackasModelInterpolationConceptCDocumentDResultsFeedbackDocsF={d1,d2,…,dn}GenerativemodelDivergenceminimization=0Nofeedback=1Fullfeedback由知識挖掘提升商務(wù)智能應(yīng)用非單調(diào)性資料(Heterogeneous)TDRTDRTDRTDRTDR成千成萬的歷史紀(jì)錄巨量分析文件分群1000解決方案個(gè)案庫由知識挖掘提升商務(wù)智能應(yīng)用Mooter科學(xué)人雜志3月號由知識挖掘提升商務(wù)智能應(yīng)用文件數(shù)據(jù)分群由知識挖掘提升商務(wù)智能應(yīng)用AnnotationandTaggingOnNovember16,2005,IBMannouncedithadacquired

Collation,aprivatelyheldcompanybasedinRedwoodCity,Californiaforundisclosedamount.DateAcquiringOrganizationAcquisitionEventAcquiredOrganizationPlaceAmountTextAnnotatorDateOrganizationPlaceAmountNov.16IBMRedwoodCity,CAUndisclosedOutputtoRDBMSXMLoutputOn<Date>November16,2005</Date>,<ACQUIRINGORG>IBM</ACQUIRINGORG>announcedithad<ACQUISITIONEVENT>acquired</ACQUISITIONEVENT><ACQUIREDORG>Collation</ACQUIREDORG>,aprivatelyheldcompanybasedin<PLACE>RedwoodCity,California</PLACE>for<AMOUNT>undisclosed</AMOUNT>amount.由知識挖掘提升商務(wù)智能應(yīng)用LinguisticConceptExtraction

fromCustomerServiceRecords

Bagof“Words”extractionCstmrIDCustomerYellowIncHappyNotSwitchCellPhoneExpressionsextractionCstmrIDCustomerYellowIncswitchCellPhoneNothappyNamedEntitiesextractionCustomerCRMtermCstmr?YellowInc

TelcoCompanyCellPhoneTelcoTermNothappySwitchEvents/SentimentExtractionCustomer(cstmr)

cellphone

unhappy(Negative)Switchto(NegativePredicate)yellowinc(Competition)CombinedWithstructureddataDecisionMakingChurnerSpecialOfferKnowledgeInferenceInformationExtractionInformationRetrieval由知識挖掘提升商務(wù)智能應(yīng)用ExtractingInformationFromTextStructuringknowledgefromtexttagging,compounds,grammaticalanalysis,ontologicalinterpretation,regularexpressions,patterrecognitionTextDatabaseOntologyMinimalrecursionsemanticsrepresentations[DeepThoughtEUproject]由知識挖掘提升商務(wù)智能應(yīng)用KnowledgeConstructionWanttoextractprominentconcepts/relationsfromtexttagging,compounds,NPrecognition,termfrequencies,

stopwords,languageidentification[Brasethvik&Gulla,DKE,38/1,2001]Domaindoc.coll.OntologyStatistical&linguisticanalysesManuallabor由知識挖掘提升商務(wù)智能應(yīng)用PatternsConstructionTaipeiTokyoNewYorkRepositoryTagging&annotationCDWKnowledgeRepositoryOrstructureddataPatterns由知識挖掘提升商務(wù)智能應(yīng)用PatternsExplorerWebBrowserHarddiskWindowsXPDesktopcomputerHarddisksize40GBProductsLaptopcomputersOperatingSystemLinuxMacintoshisacrashesInstalledfromhttp://...由知識挖掘提升商務(wù)智能應(yīng)用人、事、時(shí)、地、物元資料participatein人物性質(zhì)ConceptualObjectsPhysicalEntitiesTemporalEntities應(yīng)用affector/refertoreferto/refinereferto/identifielocationatwithin地點(diǎn)時(shí)間由知識挖掘提升商務(wù)智能應(yīng)用資源索引人物事件物件Derivedknowledgedata(e.g.RDF)ThesauriextentCRMentitiesOntologyexpansionSourcesandmetadata(XML/RDF)Backgroundknowledge/AuthoritiesCIDOCCRMorDC由知識挖掘提升商務(wù)智能應(yīng)用ConceptLatticeC1:(D1,?)C2:({d1,d2,d4},{t1,t6})C3:({d3,d4},{t4})C4:({d1,d2},{t1,t3,t5,t6})C5:({d4},{t1,t4,t6})C6:({d3},{t2,t4})C7:(?,T1)TheformalconceptC4hastwoownterms{t3,t5}andtwoinheritedterms{t1,t6}Giventhecontext(D1,T1)whereD1={d1,d2,d3,d4}&T1={t1,t2,t3,t4,t5,t6}

Rt1t2t3t4t5t6d1101011

d2101011d3010100d4100101Table:TheinputrelationR=documents

keywordsHasseDiagram由知識挖掘提升商務(wù)智能應(yīng)用P14performedP11participatedinP94hascreatedE31Document“YaltaAgreement”E7Activity“CrimeaConference”E65CreationEvent*E38ImageP86fallswithinP7tookplaceatP67isreferredtobyE52Time-SpanFebruary1945P81ongoingthroughoutP82atsometimewithinE39ActorE39ActorE39ActorE53Place7012124E52Time-Span11-2-1945ExplicitEvents,ObjectIdentity,Symmetry由知識挖掘提升商務(wù)智能應(yīng)用RulesExtractionTheformalconceptC4makesitpossiblethefollowingrulesR1:t3

t1

t6R2:t5

t1

t6R3:t3

t5TheinterpretationoftheR1andR2:Theuseoftermst3ort5isalwaysassociatedwiththatoftermst1andt6TheruleR3expressmutualequivalenceoftheterms{t3,t5}:Allthedocumentswhichhavethetermt3alsohavethet5term.由知識挖掘提升商務(wù)智能應(yīng)用文獻(xiàn)知識群組專家與決策由知識挖掘提升商務(wù)智能應(yīng)用知識呈現(xiàn)由知識挖掘提升商務(wù)智能應(yīng)用實(shí)時(shí)性分群Real-timeIndexMetadataofSearchingResults由知識挖掘提升商務(wù)智能應(yīng)用公文性資料由知識挖掘提升商務(wù)智能應(yīng)用中低收入戶補(bǔ)助因果圖--失依兒童各縣市福利，信托基金的成立所在各縣市失依兒童狀態(tài)各縣市政府，社會(huì)局等介入對單親家庭的補(bǔ)助之災(zāi)后重建及經(jīng)費(fèi)相關(guān)使用災(zāi)后重建基金由知識挖掘提升商務(wù)智能應(yīng)用規(guī)則由知識挖掘提升商務(wù)智能應(yīng)用Clustering由知識挖掘提升商務(wù)智能應(yīng)用范例很適合用機(jī)洗香味好聞去污力強(qiáng)洗衣省力氣味清香能去除99種污漬洗得特別干凈香味好聞白襪子洗得最干凈氣味很香不傷手能夠很好的去除污漬衣服不易褪色洗衣不費(fèi)力能去除99種污漬用量少洗得干凈對皮膚刺激少洗各種污漬都很干凈洗得干凈價(jià)格適當(dāng)洗衣服的效果較好氣味不錯(cuò)一直使用該品牌洗好的衣物更白氣味好聞廣告印象深洗得干凈易漂清不太傷手洗得干凈用量少洗得干凈用量比別的牌子少廣告大洗得干凈用量少質(zhì)量好用量少洗得干凈包裝好廣告多，吸引人香味好聞洗的干凈、白宣傳好，廣告有趣很多人都說好由知識挖掘提升商務(wù)智能應(yīng)用由知識挖掘提升商務(wù)智能應(yīng)用知識脈絡(luò)由知識挖掘提升商務(wù)智能應(yīng)用知識地圖由知識挖掘提升商務(wù)智能應(yīng)用事件追蹤由知識挖掘提升商務(wù)智能應(yīng)用信息檢索由知識挖掘提升商務(wù)智能應(yīng)用知識概念由知識挖掘提升商務(wù)智能應(yīng)用Kuhn’sDescriptiveProjectImmatureScienceNormalScienceAnomaliesCrisisRevolution由知識挖掘提升商務(wù)智能應(yīng)用Evolutionarytheoryisevolving由知識挖掘提升商務(wù)智能應(yīng)用TasksinNewsDetectionNewsFeedsDetectionSegmentationOn-LineRetroTracking由知識挖掘提升商務(wù)智能應(yīng)用MightbeRelevantUSSColeOctober12,2000世貿(mào)中心五角大廈2001年九月11日

LocationAden,YemenDateOctober12,2000

11:18am(UTC+3)Attack

typesuicidebombingDeaths19(includingthe2perpetrators)Injured39Perpetrator(s)al-Qaeda,carriedoutbyIbrahimal-ThawrandAbdullahal-Misawa由知識挖掘提升商務(wù)智能應(yīng)用911事件可預(yù)防FBI明尼蘇達(dá)干員

ZacariasMoussaoui個(gè)人計(jì)算機(jī)FBI鳳凰城備忘錄(GeorgeWill)Dr.Bhandari(VirtualGold,Inc)資料探勘可預(yù)防911悲劇由知識挖掘提升商務(wù)智能應(yīng)用恐怖份子由知識挖掘提升商務(wù)智能應(yīng)用911恐怖份子網(wǎng)絡(luò)由知識挖掘提升商務(wù)智能應(yīng)用911恐怖份子網(wǎng)絡(luò)由知識挖掘提升商務(wù)智能應(yīng)用赤軍旅(RedArmyFaction)威脅HorstHerold(德國聯(lián)邦警察總長)建立數(shù)據(jù)探勘之信息網(wǎng)Germany’sBundeskriminalamt1972數(shù)據(jù)源房屋銷售、能源公司…成果RolfHeissler(RAF成員)結(jié)果Ｈerold遭報(bào)導(dǎo)違反人權(quán)退休1986修改犯罪條例911三個(gè)飛行員系來自Hamburg由知識挖掘提升商務(wù)智能應(yīng)用疫病警示及通報(bào)系統(tǒng)世界衛(wèi)生組織多年前即建立了「疫病警示及通報(bào)系統(tǒng)」（EpidemicAlertandResponse）。由于一些國家可能基于經(jīng)濟(jì)沖擊的考慮，可能淡化有關(guān)疫情的報(bào)導(dǎo)，世界衛(wèi)生組織的這套系統(tǒng)特別裝置了一套軟件，可以由各國媒體的網(wǎng)站上抓取相關(guān)資料并由二十位專家分析這些資料中的信息。由知識挖掘提升商務(wù)智能應(yīng)用HighW由知識挖掘提升商務(wù)智能應(yīng)用信息與知識–Amazon數(shù)字相機(jī)銷售由知識挖掘提升商務(wù)智能應(yīng)用新聞事件–華盛頓時(shí)報(bào)由知識挖掘提升商務(wù)智能應(yīng)用美國家衛(wèi)生院NIH熱門研究ProposalsbyFunding/DateacrossIRGsandActivityTypes由知識挖掘提升商務(wù)智能應(yīng)用疾病診療指引

Athena/EON-Stanford由知識挖掘提升商務(wù)智能應(yīng)用Athena臨床指引R.D.Shankar,etal.2001由知識挖掘提升商務(wù)智能應(yīng)用高血壓臨床指引

AthenaHypertensionGuidelineA.Advani,etal.2003由知識挖掘提升商務(wù)智能應(yīng)用由知識挖掘提升商務(wù)智能應(yīng)用受災(zāi)戶(金融輔助政策)由知識挖掘提升商務(wù)智能應(yīng)用貸款(受災(zāi)戶、臨時(shí)住宅)由知識挖掘提升商務(wù)智能應(yīng)用GenerativeDiscriminative重建家園專案金融機(jī)構(gòu)貸款震災(zāi)重建暫行條例受災(zāi)戶房屋利息損毀災(zāi)戶objectmethodObject:attributeObject:attributeObject:attributeObject:conditionObject:attributeObject:Attribute(condition)Object:attributeSpecifyGeneralize由知識挖掘提升商務(wù)智能應(yīng)用IntegratingDistributedKnowledgeAdaptiveknowledgeinfrastructureisinplaceKnowledgeresourcesidentifiedandsharedappropriatelyTimelyknowledgegetstotherightpersontomakedecisionsIntelligenttoolsforauthoringthrougharchivingCohesiveknowledgedevelopmentbetweenJPL,itspartners,andcustomersInstrumentdesignissemi-automaticbasedonknowledgerepositoriesMissionsoftwareauto-instantiatesbasedonuniquemissionparametersKMprincipalsarepartofLabcultureandsupportedbylayeredCOTSproductsRemotedatamanagementallowsspacecrafttoself-commandKnowledgegatheredanyplacefromhand-helddevicesusingstandardformatsoninterplanetaryInternetExpertsystemsonspacecraftanalyzeanduploaddataAutonomousagentsoperateacrossexistingsensor