tencent cloud

Text Moderation System
Text Moderation System (TMS) uses the deep learning technology to recognize content in text that may be offensive, unsafe, or inappropriate. It allows you to configure dictionaries to detect custom texts.
Text Moderation System
Features
Pornographic Recognition

Accurately recognizes pornographic words and their variants such as split words and homographs. Its machine learning model has a good resistance to interference.

Ad Detection

Recognizes the content of spam ads, including malicious, fraud, and prostitution ads, and supports identifying different ad variants such as symbols, icons, and stickers.

Scenarios

Recognizes inappropriate content in user posts and comments on social media platforms.

Communities and Forums

Recognizes on-screen comments and user reviews in videos and live streams to identify inappropriate content in real time.

Live Streaming

Detects inappropriate text contents in e-commerce scenarios.

E-commerce
Pricing

TMS is billed in a pay-as-you-go manner. For more details, see Purchase Guide.

FAQs
Which languages can TMS detect?

Currently, TMS can detect and recognize porn, ads, and spam in Chinese and English text. It also allows you to configure custom dictionaries to recognize custom non-compliant text.

Does TMS support manual moderation? How do I access it?

Yes, and a separate manual moderation API needs to be accessed. You can submit a ticket to get the access documentation.

I don’t see the data I want in the TMS console.

Please check the following:

  • Make sure the currently logged-in account is the account that called the API.
  • The console data is displayed at the account level, which means that you can only see the data under the currently logged in account, no matter it’s a root account or a sub-account.
  • The console displays the T+1 day data; that is, you can only view the data of a day in the console on the next day.