SubmitSmarttagJob-Intelligent Media Services(IMS)-阿里云帮助中心

Submits a smart tagging job.

Operation description

Before you begin

To submit a smart tagging job by calling this operation, you must first configure the analysis type by using a template. For more information, see CreateCustomTemplate.

Limits

The smart tagging feature is available only in the China (Beijing), China (Shanghai), and China (Hangzhou) regions.
The default concurrency of smart tagging pipelines is 2. If you require a higher concurrency, submit a ticket to contact Alibaba Cloud technical support for evaluation and configuration.
Smart tagging jobs and related results are retained for 180 days and are automatically deleted after the retention period expires.

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. It supports Chinese characters, English letters, digits, and hyphens (-). It cannot start with a special character and can be up to 256 bytes in length.	example-title-****
Content	string	No	The description of the video content. It supports Chinese characters, English letters, digits, and hyphens (-). It cannot start with a special character and can be up to 1 KB in length.	example content ****
ContentType	string	No	[Deprecated] This parameter is deprecated.	This parameter is deprecated
ContentAddr	string	No	[Deprecated] This parameter is deprecated.	This parameter is deprecated
Params	string	No	The additional request parameters, represented as a JSON string. Example: {"needAsrData":true, "needOcrData":false}. Field descriptions: needAsrData: a Boolean value that specifies whether to include the original ASR results in the analysis results. Default value: false. Set the value to true to include the original ASR results. needOcrData: a Boolean value that specifies whether to include the original OCR results in the analysis results. Default value: false. Set the value to true to include the original OCR results. needMetaData: a Boolean value that specifies whether to include metadata in the analysis results. Default value: false. Set the value to true to include metadata. nlpParams: a JSON object that specifies the input parameters for the NLP operator. Default value: empty (the NLP operator is not used). For more information, see the supplementary description of request parameters below.	{"needAsrData":true, "needOcrData":false, "nlpParams":{"sourceLanguage":"cn"}}
NotifyUrl	string	No	The callback URL. Only HTTP and HTTPS are supported.	https://example.com/endpoint/aliyun/ai?id=76401125000***
UserData	string	No	The custom data that is returned in an MNS callback. It can be up to 1 KB in length. For more information about how to configure an MNS callback queue, see the relevant documentation.	{“a”:"test"}
Input	object	No	input
Type	string	No	The media type. Valid values: OSS Media URL	Media
Media	string	No	If the Type parameter is set to OSS, specify the OSS address. Example: OSS://test-bucket/video/202208/test.mp4. If the Type parameter is set to Media, specify the media ID. Example: c5c62d8f0361337cab312dce8e77dc6d. If the Type parameter is set to URL, specify the HTTP URL. Example: https://zc-test.oss-cn-shanghai.aliyuncs.com/test/unknowFace.mp4.	c5c62d8f0361337cab312dce8e77dc6d
TemplateId	string	No	The ID of the template that is used to specify the analysis algorithm.	39f8e0bc005e4f309379701645f4
ScheduleConfig	object	No	scheduleConfig
PipelineId	string	No	The ID of the pipeline, which is used to distinguish business scenarios and bind message notifications. If this parameter is not configured, the default pipeline is used. The default concurrency of the default pipeline is 2. To increase the concurrency, submit a ticket.	acdbfe4323bcfdae
Priority	string	No	The priority. This parameter is not implemented. You can leave it empty or specify an arbitrary value.	4
TemplateConfig	string	No	The template parameters that are dynamically passed when the job is started. These parameters are used to temporarily override or supplement the configured parameters in the template specified by TemplateId. The server merges these parameters with the original template parameters by field to generate the final template configuration for the current job, and validates the configuration before execution. Merge rules: If a field already exists in the template, the value provided by the caller overrides the template value (caller takes precedence). If a field does not exist in the template, it is appended as a new field. Supported dynamic fields: FaceCategoryIds: the list of face library IDs that participate in recognition (separated by commas, which can include system library IDs and custom library IDs). Precautions: This configuration affects only the execution of the current job and does not modify the template itself.	{"FaceCategoryIds":"custom_face_lib1"}

nlpParams description

Feature	Name	Type	Required	Description	Example value
	nlpParams	object	Yes	This parameter contains all NLP processing-related parameters. It is required when the template analysis type includes NLP. Otherwise, the node fails.	{"sourceLanguage":"cn"}
Transcription	sourceLanguage	string	Yes	The source language model used for transcription. Valid values: cn (Chinese), en (English), yue (Cantonese), fspk (free speech in Chinese and English), and ja (Japanese). If the audio contains multiple languages, you can set this parameter to multilingual to recognize the text in the corresponding languages. This parameter is used in conjunction with Input.LanguageHints. Only 16 kHz audio is supported.	"cn"
	languageHints	list[string]	No	The list of languages for speech recognition when the multilingual model is specified. Valid values (multiple values allowed): cn (Chinese), en (English), yue (Cantonese), ja (Japanese), ko (Korean), de (German), fr (French), and ru (Russian). When the audio contains multiple languages that need to be recognized, this parameter is used to limit the language categories and avoid misrecognizing irrelevant languages. This parameter takes effect only when Input.SourceLanguage is set to multilingual.	['cn', 'en', 'yue']
	transcriptionModel	string	No	The name of the transcription model to be used. Valid value: fun-asr. This value must be used in conjunction with sourceLanguage=multilingual.	fun-asr
	diarizationEnabled	boolean	No	Specifies whether to enable speaker diarization. Default value: false.	true
	speakerCount	integer	No	Settings for speaker diarization parameters. If not set: speaker roles are not distinguished. 0: the number of speakers is unknown. 2: the number of speakers is 2.	2
Hotwords	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, PPT frames are extracted from the video file and corresponding summaries are generated. Default value: false.	true
Summarization	summarizationEnabled	boolean	No	Specifies whether to enable the summarization feature. If enabled, full-text summaries and speaker summaries can be generated.	true
	summarizationTypes	string	No	The expected summary types when the summarization feature is enabled. 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 the translation feature.	true
	targetLanguages	string	No	The target languages when the translation feature is enabled. Valid values: cn (Chinese), en (English), yue (Cantonese), and fspk (free speech in Chinese and English).	"en,cn"
Chapter recognition	autoChaptersEnabled	boolean	No	Specifies whether to enable the chapter overview feature. The results include chapter titles and chapter summaries.	true
Smart meeting minutes	meetingAssistanceEnabled	boolean	No	Specifies whether to enable the meeting assistance feature. The results include categories, keywords, key sentences, and to-do 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. We recommend that you save this ID for use in 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.