Tausta
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."
Määritelmä
Thedomainknowledgebasepossessedbyearlyartificialintelligenceorknowledgeengineeringsystemsisanotherkindofknowledgebase.Inotherwords,domainknowledgebaseandcommonsenseknowledgebasearethetwobasictypesofknowledgebasepossessedbyintelligentcomputersystem.Thefieldofcomputersciencegenerallybelievesthatdomainknowledgebasesandcommonsenseknowledgebasesarethebottleneckproblemsofartificialintelligenceorknowledgeengineeringtechnology.Fromfocusingonthedomainknowledgeofexpertsintheearlydaystonowfocusingoncommonsenseknowledgeatthesametime,thisisanadvancementinartificialintelligenceorknowledgeengineeringtechnology.Duetothecontinuousmaturityofcomputerhardwareandsoftware,databasesandevendatawarehousesandtheirhuman-computerinteractioninterfacetechnologies,peopleneedtodevelopvariousmedium-scaledomainknowledgebasesandlarge-scalecommonsensesystemsrequiredforthedevelopmentofvariousexpertsystemsinthe21stcentury.Alarge-scalecommonsenseknowledgebasehasthebasicconditions.
Luettelo yleismaailmallisesta sisällöstä
Theinformationinthecommonsenseknowledgebasemayincludebutisnotlimitedtothefollowing:
Classanddontologia Yksilö
Materiaali osista ja esineistä
Objektin määritteet (kuten väri ja koko)
Objektin toiminta ja tarkoitus
Objektin sijainti ja jakelu
Toimintojen ja tapahtumien sijainti
Toimien ja tapahtumien aika
Toimien ja tapahtumien edellytykset
Toimien ja tapahtumien vaikutukset (jälkiolosuhteet)
toiminnan aihe ja kohde
laitteen käyttäytyminen
Tilanteen tai käsikirjoituksen vanhentuminen
Ihmisoikeustavoitteet ja tarpeet
Tunne
Suunnittelu ja strategia
Tarinateema
Konteksti
Suosittuja esimerkkejä
WordNet, joka on sanakirjatyylinen tietopohja.
(Laaja mittakaava)CommonSenseKnowledgeBase(Cyc),joka on laajamittaista yleistietokantaa, joka on samankaltainen kuin encyclopedia.
MindCollection,itisaknowledgebaseofcommonsenseinvolvingnaturallanguageprocessing.
TheSemanticWeb,whichisafuturenetworkwithbothadomainknowledgebaseandacommonsenseknowledgebase.
OpenMindCommonSense
Perusformalontologia
Yleinen formalisoitudontologia
Käsiteverkko
Ajattelupistekartta
Ontologia
Ylemmän tason tasontologia
yleistä järkeä
Kehityksen suunta
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.
