SubmitVideoCognitionJob

Updated at:

Submits a video understanding task.

Operation description

This operation is an asynchronous operation. After you submit a task, a task ID is returned. The task is not completed immediately and is queued for asynchronous execution in the background. The final result is delivered through a callback notification. You can also query the task status by calling the Query intelligent content understanding tasks operation.

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:SubmitVideoCognitionJob

create

*All Resource

*

None None

Request parameters

Parameter

Type

Required

Description

Example

Title

string

No

The video title. The title supports Chinese characters, English letters, digits, and hyphens (-). It cannot start with a special character and cannot exceed 256 bytes in length.

example-title-****

Params

string

No

The additional request parameters, represented as a JSON string. This parameter supports additional parameters for operators such as natural language processing, shot detection, custom tagging, and action recognition.

{ "nlpParams": { "sourceLanguage": "cn", "diarizationEnabled": true, "speakerCount": 2, "summarizationEnabled": true, "summarizationTypes": "Paragraph,Conversational,QuestionsAnswering,MindMap", "translationEnabled": true, "targetLanguages": "en", "autoChaptersEnabled": true, "meetingAssistanceEnabled": true } }

UserData

string

No

The user-defined data. The data is returned as-is when the result is retrieved. The length cannot exceed 1,024 bytes.

{"test":1}

Input

object

No

The input media structure.

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, such as OSS://test-bucket/video/202208/test.mp4.

If the Type parameter is set to Media, specify the mediaId, such as c5c62d8f0361337cab312dce8e77dc6d.

If the Type parameter is set to URL, specify the HTTP URL, such as https://zc-test.oss-cn-shanghai.aliyuncs.com/test/unknowFace.mp4.

c5c62d8f03613************c6d

TemplateId

string

No

The template ID used to specify the analysis algorithm. For template-related operations, refer to Create a custom template and Smart tagging template.

39f8e0bc00***************

TemplateConfig

string

No

nlpParams description

FeatureNameTypeRequiredDescriptionExample
nlpParamsobjectYesThis parameter contains all parameters related to NLP processing. It is required when the template analysis type includes NLP. Otherwise, the task fails.{"sourceLanguage":"cn"}
TranscriptionsourceLanguagestringYesThe source language model used for transcription. Valid values: cn (Chinese), en (English), yue (Cantonese), and fspk (free speech in Chinese and English)."cn"
diarizationEnabledbooleanNoSpecifies whether to enable the speaker diarization feature. Default value: false.true
speakerCountintegerNoThe speaker diarization parameter. If you do not set this parameter, speaker roles are not distinguished. 0: The number of speakers is unspecified. 2: The number of speakers is two.2
SummarizationsummarizationEnabledbooleanNoSpecifies whether to enable the summarization feature. If enabled, results such as full-text summaries and speaker summaries can be generated.true
summarizationTypesstringNoThe 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"
TranslationtranslationEnabledbooleanNoSpecifies whether to enable the translation feature.true
targetLanguagesstringNoThe 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 recognitionautoChaptersEnabledbooleanNoSpecifies whether to enable the chapter overview feature. The result includes chapter titles and chapter summaries.true
Intelligent meeting minutesmeetingAssistanceEnabledbooleanNoSpecifies whether to enable the meeting assistance feature. The result includes 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 task ID.

****20b48fb04483915d4f2cd8ac****

Examples

Success response

JSON format

{
  "RequestId": "******11-DB8D-4A9A-875B-275798******",
  "JobId": "****20b48fb04483915d4f2cd8ac****"
}

Error codes

See Error Codes for a complete list.

Release notes

See Release Notes for a complete list.