iOS'te Makine Öğrenimi Kiti ile metnin dilini tanımlama
Koleksiyonlar ile düzeninizi koruyun
İçeriği tercihlerinize göre kaydedin ve kategorilere ayırın.
Bir metin dizesinin dilini tanımlamak için Makine Öğrenimi Kiti'ni kullanabilirsiniz. Şunları yapabilirsiniz:
tüm dizeler için güven puanlarının yanı sıra dizenin en olası
dizenin olası dillerine değineceğiz.
ML Kit, 100'den fazla farklı dildeki metinleri yerel alfabelerinde tanır.
Ayrıca, Latince yazılmış metinler Arapça, Bulgarca, Çince,
Yunanca, Hintçe, Japonca ve Rusça Bkz.
Desteklenen dillerin ve komut dosyalarının tam listesini inceleyin.
Deneyin
Örnek uygulamayı kullanarak
bu API'nin örnek kullanımını inceleyin.
Başlamadan önce
Aşağıdaki ML Kit kapsüllerini Podfile'ınıza ekleyin:
pod 'GoogleMLKit/LanguageID', '8.0.0'
Projenizin kapsüllerini yükledikten veya güncelledikten sonra
.xcworkspace ML Kit, Xcode 12.4 veya sonraki sürümlerde desteklenir.
Dizenin dilini belirleme
Bir dizenin dilini tanımlamak için şunun bir örneğini alın:
LanguageIdentification ve ardından dizeyi
identifyLanguage(for:) yöntemini çağırın.
Örneğin:
Swift
letlanguageId=NaturalLanguage.languageIdentification()languageId.identifyLanguage(for:text){(languageCode,error)inifleterror=error{print("Failed with error: \(error)")return}ifletlanguageCode=languageCode,languageCode!="und"{print("Identified Language: \(languageCode)")}else{print("No language was identified")}}
Objective-C
MLKLanguageIdentification*languageId=[MLKLanguageIdentificationlanguageIdentification];[languageIdidentifyLanguageForText:textcompletion:^(NSString*_NullablelanguageCode,NSError*_Nullableerror){if(error!=nil){NSLog(@"Failed with error: %@",error.localizedDescription);return;}if(![languageCodeisEqualToString:@"und"]){NSLog(@"Identified Language: %@",languageCode);}else{NSLog(@"No language was identified");}}];
Arama başarılı olursa,
BCP-47 dil kodu
metnin dilini belirten tamamlama işleyicisine iletilir. Yanıt hayır ise:
dil güvenli bir şekilde algılandığında und kodu (belirsiz) iletilir.
Varsayılan olarak ML Kit, und olmayan bir değeri yalnızca
güven değeri en az 0,5’tir. Bu eşiği değiştirebilirsiniz
LanguageIdentificationOptions nesnesini
languageIdentification(options:):
Bir dizenin en olası dillerinin güven değerlerini elde etmek için
LanguageIdentification örneğini kullanın ve daha sonra, dizeyi
identifyPossibleLanguages(for:) yöntemini çağırın.
Örneğin:
Swift
letlanguageId=NaturalLanguage.languageIdentification()languageId.identifyPossibleLanguages(for:text){(identifiedLanguages,error)inifleterror=error{print("Failed with error: \(error)")return}guardletidentifiedLanguages=identifiedLanguages,!identifiedLanguages.isEmpty,identifiedLanguages[0].languageCode!="und"else{print("No language was identified")return}print("Identified Languages:\n"+identifiedLanguages.map{String(format:"(%@, %.2f)",$0.languageCode,$0.confidence)}.joined(separator:"\n"))}
Objective-C
MLKLanguageIdentification*languageId=[MLKLanguageIdentificationlanguageIdentification];[languageIdidentifyPossibleLanguagesForText:textcompletion:^(NSArray*_NonnullidentifiedLanguages,NSError*_Nullableerror){if(error!=nil){NSLog(@"Failed with error: %@",error.localizedDescription);return;}if(identifiedLanguages.count==1&&[identifiedLanguages[0].languageCodeisEqualToString:@"und"]){NSLog(@"No language was identified");return;}NSMutableString*outputText=[NSMutableStringstringWithFormat:@"Identified Languages:"];for(MLKIdentifiedLanguage*languageinidentifiedLanguages){[outputTextappendFormat:@"\n(%@, %.2f)",language.languageCode,language.confidence];}NSLog(outputText);}];
Çağrı başarılı olursa IdentifiedLanguage nesnelerinden oluşan bir liste
devamlılık işleyici. Her nesneden dilin BCP-47 kodunu alabilirsiniz
ve dizenin o dilde olduğundan emin olun. Lütfen
bu değerler, tüm dizenin belirtilen
dil; Makine Öğrenimi Kiti, tek bir dizede birden fazla dili tanımlamaz.
ML Kit varsayılan olarak yalnızca en az şu güven değerine sahip dilleri döndürür:
0,01. Bu eşiği, Müşteri Eşleştirme için
languageIdentification(options:) öğesine LanguageIdentificationOptions nesne eklendi:
[[["Anlaması kolay","easyToUnderstand","thumb-up"],["Sorunumu çözdü","solvedMyProblem","thumb-up"],["Diğer","otherUp","thumb-up"]],[["İhtiyacım olan bilgiler yok","missingTheInformationINeed","thumb-down"],["Çok karmaşık / çok fazla adım var","tooComplicatedTooManySteps","thumb-down"],["Güncel değil","outOfDate","thumb-down"],["Çeviri sorunu","translationIssue","thumb-down"],["Örnek veya kod sorunu","samplesCodeIssue","thumb-down"],["Diğer","otherDown","thumb-down"]],["Son güncelleme tarihi: 2025-09-04 UTC."],[[["\u003cp\u003eML Kit can identify the language of a string of text and provide confidence scores for all possible languages, supporting over 100 languages.\u003c/p\u003e\n"],["\u003cp\u003eYou can get the most likely language of a string using the \u003ccode\u003eidentifyLanguage(for:)\u003c/code\u003e method or get confidence values for possible languages using the \u003ccode\u003eidentifyPossibleLanguages(for:)\u003c/code\u003e method.\u003c/p\u003e\n"],["\u003cp\u003eAdjust the confidence threshold for language identification by passing a \u003ccode\u003eLanguageIdentificationOptions\u003c/code\u003e object to \u003ccode\u003elanguageIdentification(options:)\u003c/code\u003e.\u003c/p\u003e\n"],["\u003cp\u003eTo use ML Kit for language identification, include the \u003ccode\u003eGoogleMLKit/LanguageID\u003c/code\u003e pod in your Podfile and ensure your Xcode version is 12.4 or greater.\u003c/p\u003e\n"]]],["ML Kit can identify the language of text strings, supporting over 100 languages and romanized text for select languages. To use it, add the `GoogleMLKit/LanguageID` pod to your project. The `identifyLanguage(for:)` method returns the most likely language code, or \"und\" if undetermined. The method `identifyPossibleLanguages(for:)` provides confidence scores for multiple potential languages. Both methods allow setting a confidence threshold, with the default at 0.5 and 0.01 respectively.\n"],null,["You can use ML Kit to identify the language of a string of text. You can\nget the string's most likely language as well as confidence scores for all of the\nstring's possible languages.\n\nML Kit recognizes text in more than 100 different languages in their native scripts.\nIn addition, romanized text can be recognized for Arabic, Bulgarian, Chinese,\nGreek, Hindi, Japanese, and Russian. See the\n[complete list](/ml-kit/language/identification/langid-support) of supported languages and scripts.\n\n\u003cbr /\u003e\n\n| **Note:** ML Kit iOS APIs only run on 64-bit devices. If you build your app with 32-bit support, check the device's architecture before using this API.\n\nTry it out\n\n- Play around with [the sample app](https://github.com/googlesamples/mlkit/tree/master/ios/quickstarts/languageid) to see an example usage of this API.\n\nBefore you begin\n\n1. Include the following ML Kit pods in your Podfile: \n\n ```\n pod 'GoogleMLKit/LanguageID', '8.0.0'\n ```\n2. After you install or update your project's Pods, open your Xcode project using its `.xcworkspace`. ML Kit is supported in Xcode version 12.4 or greater.\n\nIdentify the language of a string\n\nTo identify the language of a string, get an instance of\n`LanguageIdentification`, and then pass the string to the\n`identifyLanguage(for:)` method.\n\nFor example: \n\nSwift \n\n```swift\nlet languageId = NaturalLanguage.languageIdentification()\n\nlanguageId.identifyLanguage(for: text) { (languageCode, error) in\n if let error = error {\n print(\"Failed with error: \\(error)\")\n return\n }\n if let languageCode = languageCode, languageCode != \"und\" {\n print(\"Identified Language: \\(languageCode)\")\n } else {\n print(\"No language was identified\")\n }\n}\n```\n\nObjective-C \n\n```objective-c\nMLKLanguageIdentification *languageId = [MLKLanguageIdentification languageIdentification];\n\n[languageId identifyLanguageForText:text\n completion:^(NSString * _Nullable languageCode,\n NSError * _Nullable error) {\n if (error != nil) {\n NSLog(@\"Failed with error: %@\", error.localizedDescription);\n return;\n }\n if (![languageCode isEqualToString:@\"und\"] ) {\n NSLog(@\"Identified Language: %@\", languageCode);\n } else {\n NSLog(@\"No language was identified\");\n }\n }];\n```\n\nIf the call succeeds, a\n[BCP-47 language code](//en.wikipedia.org/wiki/IETF_language_tag) is\npassed to the completion handler, indicating the language of the text. If no\nlanguage could be confidently detected, the code `und` (undetermined) is passed.\n\nBy default, ML Kit returns a non-`und` value only when it identifies the\nlanguage with a confidence value of at least 0.5. You can change this threshold\nby passing a `LanguageIdentificationOptions` object to\n`languageIdentification(options:)`: \n\nSwift \n\n```swift\nlet options = LanguageIdentificationOptions(confidenceThreshold: 0.4)\nlet languageId = NaturalLanguage.languageIdentification(options: options)\n```\n\nObjective-C \n\n```objective-c\nMLKLanguageIdentificationOptions *options =\n [[MLKLanguageIdentificationOptions alloc] initWithConfidenceThreshold:0.4];\nMLKLanguageIdentification *languageId =\n [MLKLanguageIdentification languageIdentificationWithOptions:options];\n```\n\nGet the possible languages of a string\n\nTo get the confidence values of a string's most likely languages, get an\ninstance of `LanguageIdentification` and then pass the string to the\n`identifyPossibleLanguages(for:)` method.\n\nFor example: \n\nSwift \n\n```swift\nlet languageId = NaturalLanguage.languageIdentification()\n\nlanguageId.identifyPossibleLanguages(for: text) { (identifiedLanguages, error) in\n if let error = error {\n print(\"Failed with error: \\(error)\")\n return\n }\n guard let identifiedLanguages = identifiedLanguages,\n !identifiedLanguages.isEmpty,\n identifiedLanguages[0].languageCode != \"und\"\n else {\n print(\"No language was identified\")\n return\n }\n\n print(\"Identified Languages:\\n\" +\n identifiedLanguages.map {\n String(format: \"(%@, %.2f)\", $0.languageCode, $0.confidence)\n }.joined(separator: \"\\n\"))\n}\n```\n\nObjective-C \n\n```objective-c\nMLKLanguageIdentification *languageId = [MLKLanguageIdentification languageIdentification];\n\n[languageId identifyPossibleLanguagesForText:text\n completion:^(NSArray * _Nonnull identifiedLanguages,\n NSError * _Nullable error) {\n if (error != nil) {\n NSLog(@\"Failed with error: %@\", error.localizedDescription);\n return;\n }\n if (identifiedLanguages.count == 1\n && [identifiedLanguages[0].languageCode isEqualToString:@\"und\"] ) {\n NSLog(@\"No language was identified\");\n return;\n }\n NSMutableString *outputText = [NSMutableString stringWithFormat:@\"Identified Languages:\"];\n for (MLKIdentifiedLanguage *language in identifiedLanguages) {\n [outputText appendFormat:@\"\\n(%@, %.2f)\", language.languageCode, language.confidence];\n }\n NSLog(outputText);\n}];\n```\n\nIf the call succeeds, a list of `IdentifiedLanguage` objects is passed to the\ncontinuation handler. From each object, you can get the language's BCP-47 code\nand the confidence that the string is in that language. Note that\nthese values indicate the confidence that the entire string is in the given\nlanguage; ML Kit doesn't identify multiple languages in a single string.\n\nBy default, ML Kit returns only languages with confidence values of at least\n0.01. You can change this threshold by passing a\n`LanguageIdentificationOptions` object to `languageIdentification(options:)`: \n\nSwift \n\n```swift\nlet options = LanguageIdentificationOptions(confidenceThreshold: 0.4)\nlet languageId = NaturalLanguage.languageIdentification(options: options)\n```\n\nObjective-C \n\n```objective-c\nMLKLanguageIdentificationOptions *options =\n [[MLKLanguageIdentificationOptions alloc] initWithConfidenceThreshold:0.4];\nMLKLanguageIdentification *languageId =\n [MLKLanguageIdentification languageIdentificationWithOptions:options];\n```\n\nIf no language meets this threshold, the list has one item, with the value\n`und`."]]