Console operations

Use cases

When your business encounters the following scenarios, you can use the Alibaba Cloud Document Moderation Enhanced Edition console to customize detection rules and the detection scope, query detection results, and gather statistics on the detection volume.

When using the service for the first time, log on to the AI Guardrails console to view the initial detection policy for Document Moderation.

Use case	Description
Adjust threat detection policies	You can adjust the document detection policy based on industry standards or your business needs. You can modify the following settings: Image Moderation Rule Text Moderation Rule Document page limit For example, to detect only red-line violations in document images, you can adjust the Image Moderation Rule in the AI Guardrails console.
Set different policies for multiple businesses	If you manage multiple businesses that use the same service but require different threat detection policies, you can copy the service to create a unique policy for each business. For example, if you have three businesses (A, B, and C) that all use the General Document Moderation (document_detection) service but have different standards, you can copy the document_detection service to create document_detection_01 and document_detection_02. You can then set different threat detection policies for these three services to meet your business needs.
Transfer and store document screenshots	If you want to store document screenshots for an extended period, you can configure the service to transfer the screenshots to your OSS bucket. Note By default, the system temporarily stores document screenshots for 30 minutes and returns a temporary URL in the API response.
Query detailed detection results	To review and analyze recently moderated documents, use the Result Query page to view or search for results.
Get usage statistics	To track recent document moderation volumes, use the Usage Statistics page.

Activate the service

Go to the Content Moderation Enhanced Edition page to activate the Document Moderation Enhanced Edition service.

Adjust threat detection policies

Adjust the detection scope and result handling to meet your business requirements.

1. Log on to the AI Guardrails console.

2. In the left-side navigation pane, choose Machine Moderation Enhanced Edition > Document Moderation > Rules.

3. On the Rules page, find the General Document Moderation (document_detection) service and click Settings in the Actions column.

4. On the rule configuration page for the General Document Moderation service, adjust the configuration as needed.

   1. You can set the document page limit to a value from 1 to 1,000.

   2. For document pages, the default Image Moderation Rule is Common Baseline Detection. For more information about image moderation rules, see Introduction to Image Moderation Enhanced Edition.

   3. For text pages, the default Text Moderation Rule is PGC General Material Detection. For more information about text moderation rules, see Introduction to Text Moderation Enhanced Edition.

Set different policies for multiple businesses

Create distinct threat detection policies for different business scenarios by copying a service.

1. Log on to the AI Guardrails console.

2. In the left-side navigation pane, choose Machine Moderation Enhanced Edition > Document Moderation > Rules.

3. On the Rules page, copy the service for which you want to set different detection policies.

   1. In the service list, find the General Document Moderation service (document_detection) and click Copy in the Actions column.

   2. In the Copy Service dialog box, enter the Service Name and Service Remarks.

   3. Click OK. After the service is created, find the new service (for example, document_detection_01), click Settings in the Actions column, and adjust the rule configuration as needed.

   4. The new service (document_detection_01) is ready for use in 1 to 2 minutes. You can copy multiple services and adjust the rules for each to create customized threat detection policies.

Transfer and store document screenshots

You can save screenshots from moderated documents to your OSS bucket for long-term evidence storage.

1. Log on to the AI Guardrails console.

2. In the left-side navigation pane, choose Machine Moderation Enhanced Edition > Document Moderation > Rules.

3. On the Rules page, find the service that you want to configure, and click Settings in the Actions column. This example uses the General Document Moderation (document_detection) service.

4. On the rule configuration page for the General Document Moderation (document_detection) service, click the Result Handling Configuration tab.

   Example: To transfer all screenshots to the test folder in an OSS bucket, configure the settings as follows:

   1. Turn on the Transfer to OSS switch. If you are enabling this for the first time, you must grant OSS authorization. Select a Bucket for Transfer, enter a Transfer Directory, and set the Access URL Validity Period and Transfer Scope.

   2. Click Save to apply the transfer configuration.

      The updated detection rules take effect in approximately 2 to 5 minutes.

Query detailed detection results

You can query detailed detection results for documents by Task ID, Data ID, image label, or text label.

1. Log on to the AI Guardrails console.

2. In the left-side navigation pane, choose Machine Moderation Enhanced Edition > Document Moderation > Detection Results.

3. On the Result Query page, enter your query conditions to search for detection results.

   To search for all records with hit labels, set the query condition to Image Label not equal to nonLabel. You can specify multiple labels, separated by commas (,).

   Note

   By default, results are displayed in reverse chronological order, with a maximum of 50,000 records shown. The AI Guardrails console provides query results for the last 30 days. We recommend that you store the data or logs from each API response for long-term analysis.

   1. For a specific result, click Details in the Actions column to view its detailed moderation information.

   2. For a specific result, click Document Page Results in the Actions column to view the detailed moderation results for the images and text on each document page.

Usage statistics

View recent document moderation volumes to plan further moderation or governance actions.

1. Log on to the AI Guardrails console.

2. In the left-side navigation pane, choose Machine Moderation Enhanced Edition > Document Moderation > Dashboards.

3. On the Usage Statistics page, select a time range to query or export usage data.

   1. Threat statistics: Displays statistics for high, medium, and low-threat counts, items with no threats, as well as threat trends and distribution for the selected time period.

   2. Query usage: View daily and monthly usage statistics. The statistical data is stored for one year, and a single query can span up to two months.

   3. Export usage: Click the icon to export usage data by day or month. The exported report is in Excel format and includes data only for periods with API calls.