Help Center> Natural Language Processing> SDK Reference> Using the LU SDK> Calling LU APIs> Intent Understanding
View PDF

Intent Understanding

  • Example request 
    //You are advised to construct and use the client in a singleton pattern to avoid frequent object creation.
NluClient client = new NluClient (AuthMode.AKSK,authInfo);

IntentReq req = new IntentReq();
req.setText("Text for analysis");

//Supported language of the text. zh indicates Chinese. Only Chinese is currently supported.
req.setLang("zh");

try {
    IntentResp resp = client.getIntent(req);
} catch (NlpException e) {
    //A failure is thrown as an exception. For details about exceptions, see section "Exceptions". The client automatically processes exceptions.
}·
  • Table 1 describes IntentReq parameters.
    Table 1 IntentReq parameters

    Parameter

    Mandatory

    Type

    Description

    text

    Yes

    String

    Text to be analyzed. The text is encoded using UTF-8 and the value contains a maximum of 400 characters. If the value exceeds 400 characters, only the first 400 characters are detected.

    lang

    No

    String

    Supported language type. Currently, only Chinese is supported. The default value is zh.
  • Table 2 describes IntentResp parameters.
    Table 2 IntentResp parameters

    Parameter

    Type

    Description

    result

    IntentResult

    Encapsulated object of the returned result
  • Table 3 describes the data structure description of the IntentResult field.
    Table 3 Data structure description of the IntentResult field

    Parameter

    Type

    Description

    text

    String

    Text to be analyzed.

    label

    String

    Intent label of the text to be analyzed. Labels are classified into the following types:

    weather, time, news, joke, translation, notification, alarm, music, and others.

    confidence

    Float

    Confidence level of a label

    slots

    List of Slot

    Entity text list of the sentence to be analyzed. For details about the slot data structure, see Table 4.
    Table 4 Data structure description of the Slot field

    Parameter

    Type

    Description

    word

    String

    Entity text to be analyzed

    tag

    String

    Entity type. Entity types supported by each intent category are:

    weather: date, time, and location

    time: location and timezone

    news: genre

    joke: genre

    translation: content

    notification: content, date, time, and singer

    alarm: date and time

    music: singer, song, and content

    offset

    Integer

    Starting position of the entity text in the text to be analyzed

    length

    Integer

    Entity text length

    normalizedWord

    String

    Synonym or other normalized word. The default value is the original word text.
Parent topic: Calling LU APIs