Pozadí
Intheresearchofartificialintelligence,commonsenseknowledgeisthefactscollectedandtheinformationthatanordinarypersonpredicts.Theproblemofcommonsenseknowledgeisanongoingprojectthatbelongstothefieldofknowledgeexpression(abranchofartificialintelligence).Itaimstocreateaknowledgebaseofcommonsense:adatabasecontainingallthegeneralknowledgethatmostpeoplehave.Itisexpressedinsuchawaythatitcanusenaturallanguageinartificialintelligenceprogramsormakeinferencesabouttheordinaryworld.Suchadatabaseisakindofontology,themostcommonofwhichistheso-calledupper-levelontology.
Thisquestionisconsideredthemostdifficult,becausethebreadthofartificialintelligenceresearchanddetailedcommonsenseknowledgeishuge.Anytaskthatrequirescommonsenseknowledgeisconsideredtobeaccomplishedbyartificialintelligence:alotofworktobedone,andwhatapersondoesnothave,itrequiresamachinetoshowtheintelligenceofaperson.Thesetasksincludemachinetranslation,objectrecognition,textmining,andmanyotherproblems.Toperformthesetasksperfectly,themachinesimplyknowswhatthetextistalkingaboutandtheobjectisvisible.Thisisimpossibleunlessthemachineisfamiliarwiththesameconceptsasanordinaryperson.
Someexpertsbelievethat"common-senseknowledgeprocessingisthecoreproblemofartificialknowledgeresearch."Someexpertsbelievethat"howtoeffectivelyacquiretheknowledgeofexpertsinthefieldhasalwaysbeenaprobleminartificialintelligence."
Definice
Thedomainknowledgebasepossessedbyearlyartificialintelligenceorknowledgeengineeringsystemsisanotherkindofknowledgebase.Inotherwords,domainknowledgebaseandcommonsenseknowledgebasearethetwobasictypesofknowledgebasepossessedbyintelligentcomputersystem.Thefieldofcomputersciencegenerallybelievesthatdomainknowledgebasesandcommonsenseknowledgebasesarethebottleneckproblemsofartificialintelligenceorknowledgeengineeringtechnology.Fromfocusingonthedomainknowledgeofexpertsintheearlydaystonowfocusingoncommonsenseknowledgeatthesametime,thisisanadvancementinartificialintelligenceorknowledgeengineeringtechnology.Duetothecontinuousmaturityofcomputerhardwareandsoftware,databasesandevendatawarehousesandtheirhuman-computerinteractioninterfacetechnologies,peopleneedtodevelopvariousmedium-scaledomainknowledgebasesandlarge-scalecommonsensesystemsrequiredforthedevelopmentofvariousexpertsystemsinthe21stcentury.Alarge-scalecommonsenseknowledgebasehasthebasicconditions.
Seznam běžného obsahu
Theinformationinthecommonsenseknowledgebasemayincludebutisnotlimitedtothefollowing:
TřídaandontologieIndividuum
Materiál částí a předmětů
Objektové atributy (jako barva a velikost)
Funkce a účel objektu
Umístění a rozmístění objektu
Umístění frakcí a událostí
Časové frakce a události
Předpoklady pro akceaudálosti
Dopady a události (post-podmínky)
Předmět a předmět jednání
Chování zařízení
Zastarání situace nebo scénáře
Lidskoprávní cíle a potřeby
Emoce
Plán a strategie
Téma příběhu
Kontext
Populární příklady
WordNet, což je znalostní základna zdravého rozumu ve stylu slovníku.
(Velká)Báze znalostí běžného rozumu(Cyc), což je základna obecných znalostí ve velkém měřítku podobná encyklopedii.
MindCollection,itisaknowledgebaseofcommonsenseinvolvingnaturallanguageprocessing.
TheSemanticWeb,whichisafuturenetworkwithbothadomainknowledgebaseandacommonsenseknowledgebase.
OpenMindCommonSense
Základní formalontologie
Obecná formalizovaná dentologie
Koncepční síť
Thinkingdotmap
Ontologie
Ontologie vyšších nebo vyšších úrovní
Uvažování zdravým rozumem
Směr vývoje
Practicallyresearchtheontologystructureandoperatingmechanismofalarge-scalecommonsenseknowledgebaseforintelligentagents.Intheinternationalartificialintelligencecommunity,ithasalwaysbeenrecognizedthattheprocessingofcommonsenseknowledgeisthecoreproblemofartificialintelligence.Theso-calledcommonsenseisrelativetoprofessionalknowledge.Professionalknowledgeiswidelyusedinvariousexpertsystemsandapplicationsoftware.Althoughtheprofessionalknowledgeaccumulatedbyhumanbeingsisvast,butcomparedwithcommonsense,professionalknowledgeisonlyalittlewitch’sopinion.Greatwitch.McCarthyoncepointedout:Lackofcommonsenseisamajorweaknessofthecurrentexpertsystem.Averyimportantresearchdirectionofcommonsenseproblemsisthemathematicalmodelofcommonsenseandcommonsenseprocessing,whichinvolvesvariousrepresentationsofcommonsense(first-orderlogic,productionsystems,semanticnetworks,neuralnetworks,etc.),aswellasvariouscommonsenseprocessingPrinciples(deduction,induction,qualitativereasoning,fuzzyreasoning,non-monotonicreasoning,sub-consistentreasoning,etc.),especiallynon-monotonicreasoningandnon-monotoniclogic,arespecificallyproposedforthestudyofnon-monotonicityincommonsensereasoning.AboutcommonsenseproblemsVarioustheoreticalstudieshavegreatlypromotedtheprogressofcommonsensereasoning,someofwhichhavebeguntodevelopinpracticalaspects,suchastheuseofnon-monotonicreasoningfortruthmaintenance.However,thesestudiesarestilltheoreticalstudiesintermsoftheirmainaspects.Thelackof"heavyweight"applicationsismainlyduetothewide,vagueandcomplexcharacteristicsofcommonsenseanditsreasoning.Forexample,Sowacomparescommonsenseto"knowledgesoup".CaoCungenlikenscommonsensetoacloudofknowledge.Thestudyofnon-monotoniclogiconlycapturesthefeatureofnon-monotonicityincommon-sensereasoning.Infact,therearemanyvariouscharacteristicsincommon-sensereasoningthatneedtobestudiedextensively.
