Content Security Management
The entry point for Content Security Management is as follows:
Sensitive Words Management
The Sensitive Words Management feature helps users effectively control platform content, ensuring compliance, healthiness, and alignment with internal company policies or community management standards. By defining sensitive words, the system can intelligently identify and intercept them during content generation, display, or storage stages, preventing the spread of sensitive information.
Feature Highlights
- Supports batch import and export, making it easy to centrally manage a large number of sensitive words
- Flexible status control, allowing each sensitive word to be enabled or disabled individually
- Supports description information, making it convenient to record the background and purpose of sensitive word settings
- Import template validation mechanism, preventing format errors or duplicate entries during import
Add Sensitive Words
Users can manually add one or more sensitive words. The steps are as follows:
- Navigate to:
Content Security Management > Sensitive Words > New
- In the pop-up window, fill in the following information:
- Sensitive Word: e.g.,
terror
- Enable Status: select
Enable
orDisable
- Description (optional): supplementary explanation for adding the sensitive word
- Sensitive Word: e.g.,
- Click Save. The sensitive word will take effect immediately or be kept for later use (depending on the enable status)
Download Import Template
To facilitate batch management of sensitive words, the system provides a unified import template. The steps are as follows:
- Navigate to:
Content Security Management > Sensitive Words > Download Template
- The system will automatically download an Excel file, with the default name:
敏感词导入模板.xlsx
- Open the template file and fill in the following fields:
敏感词
(required)是否启用
(Yes / No)描述
(optional)
- After completing the form, save the file for later import
Import Sensitive Words
After preparing the sensitive words template, you can proceed with batch import:
- Navigate to:
Content Security Management > Sensitive Words > Import
- Click the upload area, or drag and drop the template file to upload
- The system will automatically validate the content (field completeness, format, duplicates, etc.)
- After a successful import, an "Upload Successful" prompt will be displayed, and the newly added sensitive words will appear in the list
⚠️ It is recommended to test with a small batch first to ensure the format is correct before importing in bulk
Export Sensitive Words
It is supported to export all sensitive words on the current platform as an Excel file. The steps are as follows:
- Navigate to:
Content Security Management > Sensitive Words > Export
- After clicking export, the system will automatically download a
.xlsx
file, with the default name:敏感词报表.xlsx
- The report includes the sensitive word itself, enable status, and description information, making it easy for archiving and sharing
Content Review Model
Confidence usually refers to the degree of certainty a model or system has in its prediction results.
In the context of content review models, confidence threshold setting is an important feature that allows users to define the minimum confidence level a model must reach before marking content as a specific category (such as spam, inappropriate content, etc.). This helps reduce the number of false positives or false negatives, depending on how the threshold is set.
For example, if the confidence threshold is set to 0.8
, the model will only mark content as inappropriate when it is at least 80% confident in its prediction. This helps ensure that only cases where the model is very certain will be acted upon.