If you find that video moderation results returned by Alibaba Cloud Content Moderation do not meet your expectations, you can call an operation to provide feedback. Alibaba Cloud Content Moderation will optimize the algorithm model based on your feedback.

Operation description

Operation: /green/video/feedback

You can call this operation to give feedback on the result of a video moderation task and provide your expected result. For more information about how to construct an HTTP request, see Request structure. You can also select an existing HTTP request. For more information, see SDK overview.

Billing method: This operation is free of charge.

QPS limit

You can send up to 20 requests per second to call this operation by using your Alibaba Cloud account. If you send an excessive number of requests, throttling is implemented, and your business may be affected.

Request parameters

For more information about the common request parameters that must be included in all Content Moderation API requests, see Common parameters.

The request body is a JSON structure. The following table describes the parameters that are contained in the request body.

Parameter Type Required Example Description
taskId String Yes taskId xxx The ID returned by the Content Moderation server, which uniquely identifies the moderation task.
dataId String No dataId xxx The ID of the moderated video, which you specify in the dataId parameter of the moderation request.
url String No http://example.com/d.mp4 The URL of the moderated video, which you specify in the moderation request. If you have not specified the video URL in the moderation request, do not specify this parameter here.
suggestion String No block The moderation result you expect to return. Valid values:
  • pass: The video is normal.
  • block: The video contains violations.
scenes StringArray No ["ad","terrorism"] The scenario of video moderation. Valid values:
  • porn: pornography detection
  • terrorism: terrorist content detection
  • ad: ad violation detection
Note You can specify multiple moderation scenarios. For example, you can specify both porn and terrorism in the scenes parameter to indicate pornography detection and terrorist content detection scenarios.
frames JSONArray Yes The information about captured frames that you consider to be in the detected category. Each element in the JSON array of the frames parameter is a structure. For more information about the structure of each element, see frame.
Table 1. frame
Parameter Type Required Example Description
url String Yes http://example.com/1.jpg The URL of the captured frame.
offset Integer Yes 100 The interval between the start of the video and the captured frame. Unit: seconds.
note String No blabla The description of the captured frame.

Response parameters

For more information about common response parameters that this operation returns, see Common response parameters.

The data parameter in the response body is empty.

Examples

Sample requests
{
  "taskId":"taskId xxx",
  "dataId":"dataId xxx",
  "url":"http://example.com/d.mp4",
  "frames":[
    {
      "url":"http://example.com/1.jpg",
      "offset":100
    },
    {
      "url":"http://example.com/2.jpg",
      "offset":200
    }
  ],
  "suggestion": "block",
  "scenes":[
    "ad",
    "terrorism"
  ],
  "note": "blabla"
}
Sample success responses
{
  "code": 200, 
  "msg": "OK", 
  "requestId": "EE5A1189-4D7B-4C24-AD78-4C1FAA3E7A0C"
}