Help Center> Natural Language Processing> API Reference> NLP APIs> LU APIs> Intent Understanding
View PDF

Intent Understanding

Introduction

This API is used to identify user's intent in content related to weather, time, news, joke, translation, note, alarm and music. It identifies a specific domain from user's questions and statements and extracts entities contained in the domain.

For details about endpoints, see Endpoints.

Calling NLP APIs will incur fees. NLP packages are classified into the basic and domain-specific editions. When purchasing a package, view the APIs supported by the basic package and domain-specific packages in the Natural Language Processing Price Calculator.

URI

  • URI format 
    POST /v1/{project_id}/nlu/semantic-parser
  • Parameter description
Table 1 URI parameters

Parameter

Mandatory

Description

project_id

Yes

Project ID. For details about how to obtain the project ID, see Obtaining a Project ID.

Request

Table 2 describes the request parameters.

Table 2 Request parameters

Parameter

Type

Mandatory

Description

text

String

Yes

Text list to be analyzed. The text is encoded using UTF-8 and the value contains a maximum of 32 characters. If the value exceeds 32 characters, only the first 32 characters are detected.

lang

String

No

Supported language type. Currently, only Chinese is supported. The default value is zh.

Response

Table 3 Response parameters

Parameter

Type

Description

result

Result object

Intent information returned when the API is successfully called.

This parameter is not included when the API fails to be called.

For details, see Table 4.

error_code

String

Error code returned when the API fails to be called.

The parameter is not included when the API call succeeds.

error_msg

String

Error message returned when the API fails to be called.

The parameter is not included when the API call succeeds.
Table 4 Data structure description of result

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

Array of slot

Data structure of slots. For details, see Table 5.
Table 5 Data structure description of slots

Parameter

Type

Description

word

String

Entity text

tag

String

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

weather: date, time, location

time: location, timezone

news: genre

joke: genre

translation: content

notification: content, date, time, singer

alarm: date, time

music: singer, song, content

offset

Integer

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

length

Integer

Length of an entity text

normalized_word

String

Synonym or other normalized word. The default value is the original word.

Examples

  • Example request 
    POST https://{endpoint}/v1/{project_id}/nlu/semantic-parser

Request Header: 
    Content-Type: application/json 
    X-Auth-Token:MIINRwYJKoZIhvcNAQcCoIINODCCDTQCAQExDTALBglghkgBZQMEAgEwgguVBgkqhkiG... 

Request Body: 
    {          
           "text":"Text for analysis",
        "lang":"zh" 
    }
  • Example response
    • Successful example response 
      {
    "result": {
        "confidence": 1,
        "label": "music",
        "slots": [
            {
                "length": 3,
                "normalized_word": "word-1",
                "offset": 3,
                "tag": "singer",
                "word": "word-1",
            },
            {
                "length": 3,
                "normalized_word": "word-2",
                "offset": 7,
                "tag": "song",
                "word": "word-2"
            }
        ],
        "text": "Response"
    }
}
    • Failed example response 
      {
    "error_code": "NLP.0101",
    "error_msg": "Authentication failed. Please verify the token"
}

Status Code

For details about status codes, see Status Code.

Error Code

For details about error codes, see Error Code.

Parent topic: LU APIs