SubmitSmarttagJob-阿里云帮助中心

Submits a smart tagging job.

Operation description

Prerequisites

Before submitting a smart tagging job, you must configure the analysis types in a template. For more information, see CreateCustomTemplate.

Limitations

The smart tagging feature is available only in the China (Beijing), China (Shanghai), and China (Hangzhou) regions.
The default concurrency for the smart tagging pipeline is 2. To request a higher concurrency limit, submit a ticket.
Smart tagging jobs and their results are retained for 180 days, after which they are automatically deleted.

Try it now

Try this API in OpenAPI Explorer, no manual signing needed. Successful calls auto-generate SDK code matching your parameters. Download it with built-in credential security for local usage.

Test

RAM authorization

The table below describes the authorization required to call this API. You can define it in a Resource Access Management (RAM) policy. The table's columns are detailed below:

Action: The actions can be used in the Action element of RAM permission policy statements to grant permissions to perform the operation.
API: The API that you can call to perform the action.
Access level: The predefined level of access granted for each API. Valid values: create, list, get, update, and delete.
Resource type: The type of the resource that supports authorization to perform the action. It indicates if the action supports resource-level permission. The specified resource must be compatible with the action. Otherwise, the policy will be ineffective.
- For APIs with resource-level permissions, required resource types are marked with an asterisk (*). Specify the corresponding Alibaba Cloud Resource Name (ARN) in the Resource element of the policy.
- For APIs without resource-level permissions, it is shown as All Resources. Use an asterisk (*) in the Resource element of the policy.
Condition key: The condition keys defined by the service. The key allows for granular control, applying to either actions alone or actions associated with specific resources. In addition to service-specific condition keys, Alibaba Cloud provides a set of common condition keys applicable across all RAM-supported services.
Dependent action: The dependent actions required to run the action. To complete the action, the RAM user or the RAM role must have the permissions to perform all dependent actions.

Action

Access level

Resource type

Condition key

Dependent action

ice:SubmitSmarttagJob

create

*All Resource

*

None

Request parameters

Parameter	Type	Required	Description	Example
Title	string	No	The video title can contain Chinese characters, English letters, digits, and hyphens (-). It cannot start with a special character and must not exceed 256 bytes.	example-title-****
Content	string	No	The description of the video content can contain Chinese characters, English letters, digits, and hyphens (-). It cannot start with a special character and must not exceed 1 KB.	example content ****
ContentType	string	No	Deprecated.
ContentAddr	string	No	Deprecated.
Params	string	No	Additional request parameters, specified as a JSON string. For example: `{"needAsrData":true, "needOcrData":false}`. `needAsrData`: Specifies whether to include the raw Automatic Speech Recognition (ASR) results in the analysis output. The default is `false`. `needOcrData`: Specifies whether to include the raw Optical Character Recognition (OCR) results in the analysis output. The default is `false`. `needMetaData`: Specifies whether to include metadata in the analysis output. The default is `false`. `nlpParams`: A JSON object that specifies the input parameters for the Natural Language Processing (NLP) operator. If left empty, the operator is not used. For details, see the `nlpParams` table below.	{"needAsrData":true, "needOcrData":false, "nlpParams":{"sourceLanguage":"cn"}}
NotifyUrl	string	No	The callback URL. Only HTTP and HTTPS URLs are supported.	https://example.com/endpoint/aliyun/ai?id=76401125000***
UserData	string	No	Custom data to include in the callback. If you use Message Service (MNS) for callbacks, this data is included in the message. The maximum length is 1 KB.	{“a”:"test"}
Input	object	No	The input file for the job.
Type	string	No	The type of the input media file. Valid values: OSS Media URL	Media
Media	string	No	If you set the `Type` parameter to `OSS`, specify the OSS URL of the media file. Example: `OSS://test-bucket/video/202208/test.mp4`. If you set the `Type` parameter to `Media`, specify the media ID. Example: `c5c62d8f0361337cab312dce8e77dc6d`. If you set the `Type` parameter to `URL`, specify the HTTP or HTTPS URL of the media file. Example: `https://zc-test.oss-cn-shanghai.aliyuncs.com/test/unknowFace.mp4`.	c5c62d8f0361337cab312dce8e77dc6d
TemplateId	string	No	The ID of the template that specifies the analysis algorithms to use.	39f8e0bc005e4f309379701645f4
ScheduleConfig	object	No	The scheduling configurations.
PipelineId	string	No	The ID of the pipeline. Pipelines separate business workloads and bind message notifications. If you do not specify this parameter, the default pipeline is used. The default pipeline has a concurrency of 2. To increase the concurrency, submit a ticket.	acdbfe4323bcfdae
Priority	string	No	The priority of the job. This feature is not yet implemented. You can leave this parameter empty or specify any value.	4
TemplateConfig	string	No	Dynamic parameters for the job, which temporarily override or supplement the base template specified by `TemplateId`. The service merges the dynamic and template parameters to generate the final configuration for the current job and validates it before execution. Merge rules: Values in the request override corresponding values in the template. Fields in the request that do not exist in the template are added to the configuration. Currently supported dynamic fields: `FaceCategoryIds`: A list of face library IDs for recognition, separated by commas (,). You can include both system and custom library IDs. Note: These dynamic parameters affect only the current job and do not modify the template itself.	{"FaceCategoryIds":"custom_face_lib1"}

nlpParams

Feature	Parameter	Type	Required	Description	Example
	nlpParams	object	Yes	Contains all parameters related to NLP processing. This parameter is required if the analysis types in the template include NLP. Otherwise, the job fails.	{"sourceLanguage":"cn"}
Transcription	sourceLanguage	string	Yes	The source language model for transcription. Valid values: `cn` (Chinese), `en` (English), `yue` (Cantonese), `fspk` (mixed Chinese and English), and `ja` (Japanese). If the audio contains multiple languages, you can set this parameter to `multilingual` to recognize text in each language. Use this parameter with `languageHints`. Only 16 kHz audio is supported.	"cn"
	languageHints	list[string]	No	Specifies the languages to recognize when `sourceLanguage` is set to `multilingual`. Valid values (multiple can be selected): `cn` (Chinese), `en` (English), `yue` (Cantonese), `ja` (Japanese), `ko` (Korean), `de` (German), `fr` (French), and `ru` (Russian). This parameter restricts the scope of language detection and prevents misidentification of irrelevant languages. It takes effect only when `sourceLanguage` is set to `multilingual`.	['cn', 'en', 'yue']
	transcriptionModel	string	No	Specifies the transcription model to use. Valid value: `fun-asr`. This model must be used with `sourceLanguage` set to `multilingual`.	fun-asr
	diarizationEnabled	boolean	No	Specifies whether to enable speaker diarization. The default is `false`.	true
	speakerCount	integer	No	Configures the speaker count for speaker diarization. `0`: The number of speakers is automatically detected. `2`: Diarizes the audio for two speakers.	2
Hotword	phraseId	string	No	The ID of the hotword vocabulary.	ce9c2a34b6d847bf92a77d0a196f***
PPT extraction and summarization	pptExtractionEnabled	boolean	No	Specifies whether to enable PPT extraction and summarization. If enabled, the service extracts PPT slides from the video and generates a summary. The default is `false`.	true
Summarization	summarizationEnabled	boolean	No	Specifies whether to enable summarization. If enabled, the service can generate a full-text summary, speaker summary, and other results.	true
	summarizationTypes	string	No	When summarization is enabled, you must specify the desired summarization types. Valid values: `Paragraph` (full-text summary), `Conversational` (speaker summary), `QuestionsAnswering` (Q&A summary), and `MindMap` (mind map).	"Paragraph,Conversational,QuestionsAnswering,MindMap"
Translation	translationEnabled	boolean	No	Specifies whether to enable translation.	true
	targetLanguages	string	No	The target languages for translation. This parameter is required if translation is enabled. Valid values: `cn` (Chinese), `en` (English), `yue` (Cantonese), and `fspk` (mixed Chinese and English).	"en,cn"
Chapter detection	autoChaptersEnabled	boolean	No	Specifies whether to enable automatic chapter generation. The output includes chapter titles and summaries.	true
Meeting assistance	meetingAssistanceEnabled	boolean	No	Specifies whether to enable the meeting assistance feature. The output includes categories, keywords, key sentences, and action items.	true

Response elements

Element	Type	Description	Example
	object
RequestId	string	The request ID.	****11-DB8D-4A9A-875B-275798****
JobId	string	The ID of the smart tagging job. Save this ID for subsequent API calls.	**d80e4e4044975745c14b**

Examples

Success response

JSON format

{
  "RequestId": "******11-DB8D-4A9A-875B-275798******",
  "JobId": "****d80e4e4044975745c14b****"
}

Error codes

See Error Codes for a complete list.

Release notes

See Release Notes for a complete list.