Заден план
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."
Определение
Thedomainknowledgebasepossessedbyearlyartificialintelligenceorknowledgeengineeringsystemsisanotherkindofknowledgebase.Inotherwords,domainknowledgebaseandcommonsenseknowledgebasearethetwobasictypesofknowledgebasepossessedbyintelligentcomputersystem.Thefieldofcomputersciencegenerallybelievesthatdomainknowledgebasesandcommonsenseknowledgebasesarethebottleneckproblemsofartificialintelligenceorknowledgeengineeringtechnology.Fromfocusingonthedomainknowledgeofexpertsintheearlydaystonowfocusingoncommonsenseknowledgeatthesametime,thisisanadvancementinartificialintelligenceorknowledgeengineeringtechnology.Duetothecontinuousmaturityofcomputerhardwareandsoftware,databasesandevendatawarehousesandtheirhuman-computerinteractioninterfacetechnologies,peopleneedtodevelopvariousmedium-scaledomainknowledgebasesandlarge-scalecommonsensesystemsrequiredforthedevelopmentofvariousexpertsystemsinthe21stcentury.Alarge-scalecommonsenseknowledgebasehasthebasicconditions.
Списък на здравословно съдържание
Theinformationinthecommonsenseknowledgebasemayincludebutisnotlimitedtothefollowing:
КласнадонтологияИндивидуален
Материал на части и обекти
Атрибути на обект (като цвят и размер)
Функцията и предназначението на обекта
Разположението и разпределението на обекта
Местоположението на фракциите и събитията
Време на фракции и събития
Предпоставки за действия и събития
Въздействието на факторите и събитията (следусловия)
Субектът и субектът на действието
Поведението на устройството
Остаряването на ситуацията или сценария
Цели и потребности на правата на човека
Емоция
План и стратегия
Тема на историята
Контекст
Популярни примери
WordNet, която е база от знания в речников стил на здравия разум.
(Мащабна) база знания Commonsense (Cyc), която е широкомащабна база знания Commonsense, подобна на енциклопедия.
MindCollection,itisaknowledgebaseofcommonsenseinvolvingnaturallanguageprocessing.
TheSemanticWeb,whichisafuturenetworkwithbothadomainknowledgebaseandacommonsenseknowledgebase.
OpenMindCommonSense
Основиформалонтология
Обща формализиранадонтология
Концептуална мрежа
Thinkingdotmap
Онтология
Горно или горно ниво-ниво
Здрав разум
Посока на развитие
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.
