Позадина
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."
Дефиниција
Thedomainknowledgebasepossessedbyearlyartificialintelligenceorknowledgeengineeringsystemsisanotherkindofknowledgebase.Inotherwords,domainknowledgebaseandcommonsenseknowledgebasearethetwobasictypesofknowledgebasepossessedbyintelligentcomputersystem.Thefieldofcomputersciencegenerallybelievesthatdomainknowledgebasesandcommonsenseknowledgebasesarethebottleneckproblemsofartificialintelligenceorknowledgeengineeringtechnology.Fromfocusingonthedomainknowledgeofexpertsintheearlydaystonowfocusingoncommonsenseknowledgeatthesametime,thisisanadvancementinartificialintelligenceorknowledgeengineeringtechnology.Duetothecontinuousmaturityofcomputerhardwareandsoftware,databasesandevendatawarehousesandtheirhuman-computerinteractioninterfacetechnologies,peopleneedtodevelopvariousmedium-scaledomainknowledgebasesandlarge-scalecommonsensesystemsrequiredforthedevelopmentofvariousexpertsystemsinthe21stcentury.Alarge-scalecommonsenseknowledgebasehasthebasicconditions.
Листофцоммонсенсецонтент
Theinformationinthecommonsenseknowledgebasemayincludebutisnotlimitedtothefollowing:
ЦлассандонтологиИндивидуал
Материалофпартсандобјецтс
Објецтаттрибутес (суцхасцолорандсизе)
Функција и сврха објекта
Локација и дистрибуција објекта
Тхелоцатионофацтионсанддевентс
Тимеофацтионсанддевентс
Предуслови за радње и догађаје
Утицај фактора и догађаја (пост-услови)
Тхесубјецтандобјецтофтхеацтион
Тхебехавиортхедевице
Застарелост ситуације или скрипта
Хуманригхтсгоалсанднеедс
Емоција
Планандстратеги
Сторитхеме
Контекст
ПопуларЕкамплес
ВордНет, база знања здравог разума у стилу речника.
(Великог)ЦоммонСенсеКновледгеБасе(Циц),која је цоммонсенсекбазе знања великих размера слично енциклопедији.
MindCollection,itisaknowledgebaseofcommonsenseinvolvingnaturallanguageprocessing.
TheSemanticWeb,whichisafuturenetworkwithbothadomainknowledgebaseandacommonsenseknowledgebase.
ОпенМиндЦоммонСенсе
Басицформалонтологи
Генералформализедонтологи
Цонцептнетворк
Тхинкингдотмап
Онтологија
Горњи или горњи ниво лонтологије
Цоммонсенсереасонинг
Смер развоја
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.
