The Content Moderation service for Video Moderation 2.0 includes a pre-configured general policy. This policy is based on extensive experience in content administration and common standards across various industries. If the default configuration does not meet your business needs, you can customize the policy. This topic describes how to adjust threat detection policies for video moderation.
Scenarios
You can use the console for Video Moderation 2.0 to customize detection rules and scope, query detection results, and view usage statistics.
The first time you use the service, log on to the Content Moderation console to view the default detection policy configuration for video moderation.
Scenario | Description |
You can adjust video moderation policies based on your business needs or common industry practices. You can adjust the following detection policies:
For example, if you want to scan video frames only for serious violations at a frequency of one frame every 2 seconds, you can adjust the image detection rules in the console. | |
Set different threat detection policies for multiple business operations | If you have multiple business operations that use the same service but require different threat detection policies, you can copy the service. For example, you have three business operations (A, B, and C) that all use the video file moderation (videoDetection_global) service, but each operation has different standards. You can copy the videoDetection_global service in the console to create videoDetection_global_01 and videoDetection_global_02. Then, you can set different threat detection policies for these three services to meet the requirements of each business operation. |
To view and analyze the details of recently moderated videos, you can view or search for them on the result query page. | |
To view statistics on recent video moderation usage, you can use the usage statistics page. |
Activate the service
Go to the Content Moderation 2.0 page to activate the Video Moderation 2.0 service.
Before you activate the Video Moderation 2.0 service, ensure that you understand the billing rules for Video Moderation 2.0. For more information, see Introduction and billing for Video Moderation Enhanced Edition 2.0.
Adjust threat detection policies for video moderation
You can adjust the detection scope and result return method to meet your business requirements based on your needs or common industry practices.
In the navigation pane on the left, choose .
On the Rules page, find the video file moderation(videoDetection_global) service and click Settings in the Actions column.
On the Rules page for the video file moderation ( videoDetection_global ) service, adjust the configurations as needed.
Example: To take 1,000 snapshots for each video, scan the frames for serious violations, scan the audio for violations, and return all detection results, perform the following steps:
For Image Snapshot Method, select Fixed Total Number of Snapshots, enter 1000 for the total number of snapshots, and select General Baseline Detection for Image Moderation Rule.
For more information about image moderation rules, see Introduction to Image Moderation 2.0 and its billing.
Turn on the Moderate Audio switch and select Audio and Video Media Moderation.
Select Return All Results.
Click Save to save the new detection rule.
The new rule takes effect in about 2 to 5 minutes.
Set different threat detection policies for multiple business operations
You can copy a service and set different threat detection policies for each copy to meet the different moderation needs of your business operations.
Log on to the Content Moderation console.
In the navigation pane on the left, choose .
On the Rules page, copy the service for which you want to set different detection policies.
In the service list, find the video moderation service (videoDetection_global) and click the Copy button in the Actions column.
In the Copy Service dialog box, enter a Service Name and Service Description.
Click OK. After the service is created, find the new service videoDetection_global_01. Then, click Settings in the Actions column and adjust the Rules as needed.
The new service ( videoDetection_global_01 ) can be called 1 to 2 minutes after it is created. You can create multiple copies of a service and adjust the rules for each to meet your different threat detection needs.
Query detailed results of video moderation
You can query the detailed moderation results for specific videos by taskId, dataId, service, image label, voice label, or video threat.
Log on to the Content Moderation console.
In the navigation pane on the left, choose .
On the Detection Results page, set query conditions to find detection results.
To search for all records that have hit labels in their frames, set the query condition to Image Label is not equal to nonLabel. You can enter multiple labels separated by commas (,).
NoteBy default, results are displayed in reverse chronological order, and a maximum of 50,000 records are shown. The Content Moderation console provides query results from the last 30 days. You must store the data or logs from each API operation call if you want to perform data analysis and statistics over a longer period.
Find the target result and click Details in the Actions column to view detailed video moderation information.
Find the target result and click Audio and Image Results in the Actions column to view the detailed moderation results for the video frames and audio.
The Screen review results tab displays the snapshot of each frame and the labels that were hit by each snapshot.
The Voice Audit Results tab displays the speech-to-text results and the labels that were hit.
NoteThe voice moderation results are displayed only if you enable voice moderation for videos in the settings.
View statistics on recent video moderation usage
You can view statistics on recent video moderation usage to help you decide on further moderation or administration measures for specific video content.
Log on to the Content Moderation console.
In the navigation pane on the left, choose .
On the Dashboards page, you can select a time range to query or export usage data.
Query usage: You can view usage statistics by day or by month. The statistical data is stored for one year. You can query data from a period of up to two months. You can query data by Alibaba Cloud account, RAM user, or service.
The curve chart shows statistics on the number of video moderation service tasks (number of videos).
The column chart shows statistics on the usage of image and voice moderation services (number of moderated video snapshots and duration of moderated video audio in minutes).
Export usage: Click the
icon to export usage data by day or by month. The exported report is in Excel format and includes only data with usage records.Name
Description
Unit
Account UID
The UID of the account for which the data is exported.
None
service
Video moderation service
Video image moderation service
Video voice moderation service
None
Usage
Total number of calls.
Count
Date
The date of the statistics.
Day/Month
View video moderation threat statistics: This section displays statistics for high, medium, low, and no threats, along with threat trends and distribution for the selected time range.
Threat Level Distribution: Displays the number and percentage of high, medium, low, and no threats for the selected time range.
Threat Trend Statistics: Displays the threat trend by day or month for the selected time range.
Threat Distribution Statistics: Displays threat statistics for video frames and audio. You can view the top 5 threats and their percentage of all threats.