tencent cloud

All product documents
Cloud Infinite
DocumentationCloud InfiniteSDK DocumentationPython SDKContent ModerationText Moderation
Text Moderation
Download PDF
Last updated: 2024-03-01 14:57:12
Text Moderation
Last updated: 2024-03-01 14:57:12
Download PDF

Overview

This document describes how to use the content moderation feature provided by Cloud Infinite (CI). CI fully integrates the processing capabilities with the COS SDK.
Note:
To use the content moderation service, you need to have the permission to use CI:
For root accounts, click here for role authorization.
For sub-accounts, see Authorizing Sub-Accounts to Access CI Services.
This document provides an overview of APIs and SDK code samples for text moderation.
Note:
COS Python SDK v5.1.9.10 or later is required. Earlier versions may contain bugs and need to be upgraded to the latest version when being used.
API
Description
Submits a text moderation job.
Queries the result of a specified text moderation job.

Submitting a Text Moderation Job

Feature description

This API is used to submit a text moderation job. The text moderation feature is async. You can submit a job to moderate your text files, and then use the API for querying text moderation job result to query the moderation results.

Sample code

    """Test the CI's API for moderating text file content"""
    # Create a COS client
    # Recognize a text in COS
    response= client.ci_auditing_text_submit(
        Bucket='bucket',
        DetectType=CiDetectType.PORN | CiDetectType.ADS,
        Key='test.txt'
    )
    print response

Parameter description

The ci_auditing_text_submit function is called. Specific request parameters are as follows:
Parameter
Description
Type
Required
Bucket
Bucket name.
String
Yes
Key
Object name, such as picture.jpg.
String
No
BizType
Unique identifier of the moderation policy. You can configure the scenes you want to moderate on the moderation policy page in the console, such as pornographic, adverting, and illegal information. For configuration guidelines, see Setting Public Moderation Policy. You can get BizType in the console. If BizType is specified, the moderation request will perform moderation based on the scenes configured in the moderation policy. If BizType is not specified, the default moderation policy will be used automatically.
String
No
DetectType
Moderation type. Valid values: CiDetectType.PORN (pornography), CiDetectType.ADS (advertising). You can select multiple types. For example, CiDetectType.PORN | CiDetectType.ADS indicates to moderate the text for pornographic and advertising information. If you need more moderation scenes, use the BizType parameter.
enum
No
Content
When the input content is plain text, the length of the original text cannot exceed 10,000 UTF-8 characters. If the length limit is exceeded, the API will report an error.
String
No
Callback
Callback address, which must start with http:// or https://.
String
No
UserInfo
Business field. For details on parameters that can be passed in, see the UserInfo field in Submitting Text Moderation Job.
Dict
No
DataId
This field will return the original content in the moderation result, which can contain up to 512 bytes. You can use this field to uniquely identify the data to be moderated in your business.
String
No

Response parameters

Calling the ci_auditing_text_submit function will convert the XML returned in the API into a dict value. For specific response parameters, see Submitting Text Moderation Job.

Querying Text Moderation Job Result

Feature description

This API is used to query the result of a specified text moderation job. The text moderation feature is async. You can submit a job to moderate your text files, and then use the API for querying text moderation job result to query the moderation results.

Sample code

    """Test the CI's API for querying moderation job result"""
    # Create a COS client
    # Query the moderation result
    response = client.ci_auditing_text_query(
        Bucket='bucket',
        JobID='v11122zxxxazzz'
    )
    print response

Parameter description

The ci_auditing_text_query function is called. Specific request parameters are as follows:
Parameter
Description
Type
Required
Bucket
Bucket name.
String
Yes
JobID
Moderation job ID.
String
Yes

Response parameters

Calling the ci_auditing_text_query function will convert the XML returned in the API into a dict value. For specific response parameters, see Querying Text Moderation Job Result.
Was this page helpful?
You can also Contact Sales or Submit a Ticket for help.
Yes
No

Feedback

Contact Us

Contact our sales team or business advisors to help your business.

Contact Us
Technical Support

Open a ticket if you're looking for further assistance. Our Ticket is 7x24 available.

Submit a Ticket
7x24 Phone Support
Hong Kong, China
+852 800 906 020 (Toll Free)
United States
+1 844 606 0804 (Toll Free)
United Kingdom
+44 808 196 4551 (Toll Free)
Canada
+1 888 605 7930 (Toll Free)
Australia
+61 1300 986 386 (Toll Free)
EdgeOne hotline
+852 300 80699
More local hotlines coming soon