Abnormal comment processing method, computer device and storage medium

By clustering and sorting song comments, abnormal comments can be identified and processed, solving the problem that existing technologies cannot effectively identify duplicate and advertising comments, and improving processing efficiency.

CN116484045BActive Publication Date: 2026-06-12TENCENT MUSIC ENTERTAINMENT TECH (SHENZHEN) CO LTD
View PDF 1 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
TENCENT MUSIC ENTERTAINMENT TECH (SHENZHEN) CO LTD
Filing Date
2023-04-18
Publication Date
2026-06-12

AI Technical Summary

⚠Technical Problem

Existing methods for handling abnormal comments based on plain text content recognition cannot effectively identify and process duplicate comments and advertising comments with identical or similar content. As a result, a large number of abnormal comments still exist in the comment section, requiring manual review and reducing processing efficiency.

⚗Method used

By clustering the comments to be detected for a song, a comment set is generated, and the comments are sorted according to the clustering information and song type, with abnormal comments being processed first.

🎯Benefits of technology

By using clustering and ranking methods, malicious comments, duplicate comments, or advertising comments can be efficiently identified and processed, reducing the need for manual review of the comment section and improving the efficiency of handling abnormal comments.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116484045B_ABST
    Figure CN116484045B_ABST
Patent Text Reader

Abstract

The application relates to an abnormal comment processing method, computer equipment and a storage medium. The method comprises the following steps: performing clustering processing on a to-be-detected comment of a song to obtain a comment set corresponding to the song; confirming comment aggregation information of the comment set corresponding to the song, confirming comment aggregation information of the song according to the comment aggregation information of the comment set corresponding to the song; the comment aggregation information of the comment set is used for representing the overall aggregation degree of the comments in the comment set; sorting the songs according to the comment aggregation information of the songs and the song types of the songs; and performing corresponding abnormal comment processing on the sorted songs. The method can improve the efficiency of abnormal comment processing.
Need to check novelty before this filing date? Find Prior Art