1 views collected around this technical thread.
This tutorial walks through building a Python script that fetches a QQ Music QR code, displays it locally, monitors its status, extracts required encrypted parameters from cookies, and completes the login process by repeatedly polling the authentication endpoint to obtain a session.
The article explains that QQ Music desktop client can unexpectedly upload large amounts of data by acting as a PCDN node, but users can easily stop this behavior by disabling the playback acceleration service in the client settings, preserving their upstream bandwidth on both Windows and Mac.
This article presents a comprehensive overview of QQ Music's recall pipeline, detailing business characteristics, challenges such as noisy user behavior and cold‑start, and four major solutions—including knowledge‑graph‑enhanced recall, sequence‑based and multi‑interest modeling, audio‑based recall, and federated learning—along with practical insights and Q&A.
This talk presents the evolution of QQ Music's ranking system, detailing background challenges, user‑perception modeling, multi‑objective and causal learning to mitigate the Matthew effect, long‑tail content support, cross‑domain recommendation, and module personalization for diversified traffic, concluding with future research directions.
This talk details the evolution of QQ Music's ranking system, covering background, user‑perception modeling, pairwise optimization, advanced model architectures, multi‑objective learning with causal inference to mitigate the Matthew effect, cross‑domain recommendation, and module personalization that together boost user engagement and platform traffic.
This article explains why video integration is essential for modern music products, introduces QQ Music's PortrAIt AI vertical video clipping technology, details its technical capabilities and business scenarios such as background videos and video playlists, and outlines current results and future development plans.
This article presents QQ Music’s end‑to‑end solution for data‑driven content understanding, value evaluation, and fine‑grained operation, detailing offline and real‑time pipelines, neural‑network models, a content middle‑platform, parameter services, and a precise delivery system that boost user engagement while preserving experience.
This tutorial walks through using Python's Selenium to automate scrolling and extract QQ Music hot comment data—including user avatars, names, timestamps, and content—then saves the information to CSV and creates a Chinese word cloud for visual analysis.
QQ Music replaced its slow Hive warehouse with a massive ClickHouse cluster, achieving sub‑second to ten‑second query latency on petabyte‑scale data, enabling real‑time analytics for non‑technical users, and following five operational best practices—ZooKeeper planning, idempotent writes, sensible partitions, read‑write separation, and localized joins—while leveraging Tencent Cloud’s managed ClickHouse service.
Android M introduced a dynamic runtime permission model that separates normal and dangerous permissions, requiring apps like QQ Music to implement runtime checks, adapt startup and feature‑triggered requests, use a permission‑guard shell, and handle OEM‑specific fragmentation issues such as sensor, shortcut, and floating‑window permissions.