Author

Bilibili Tech

Provides introductions and tutorials on Bilibili-related technologies.

396

Articles

Likes

1.2k

Views

Comments

Latest from Bilibili Tech

100 recent articles max

Bilibili Tech

Nov 26, 2024 · Big Data

Bilibili’s Iceberg‑Based Streaming‑Batch Integration: Architecture, Optimizations, and Practices

Bilibili migrated its massive user‑behavior, commercial AI training, and database synchronization pipelines from Hive and Kafka to an Iceberg‑based streaming‑batch architecture, using Flink and the Magnus optimizer to achieve minute‑level freshness, reduce CPU and memory usage by about 20‑22 %, save roughly 3.55 M CNY annually, and dramatically improve query latency and join performance.

BatchData integrationFlink

0 likes · 20 min read

Bilibili’s Iceberg‑Based Streaming‑Batch Integration: Architecture, Optimizations, and Practices

Bilibili Tech

Nov 26, 2024 · Artificial Intelligence

DNTextSpotter: Arbitrary-Shaped Scene Text Spotting via Improved Denoising Training

DNTextSpotter is an arbitrary-shaped scene text spotting model using the DETR architecture with an improved denoising training scheme that adds noise to Bézier control points and employs mask‑sliding character queries, achieving significant benchmark gains without extra inference cost and enabling robust text recognition in challenging environments.

DETRarbitrary-shaped textdenoising training

0 likes · 13 min read

DNTextSpotter: Arbitrary-Shaped Scene Text Spotting via Improved Denoising Training

Bilibili Tech

Nov 22, 2024 · Product Management

Crowdsourced Testing Platform for Bilibili: Background, Challenges, Risks, and Management

Bilibili launched a crowdsourced testing platform that mobilizes its engaged head‑users to run product tests across diverse devices, addressing limited professional resources and scenario mismatches, while mitigating information leakage, security, and compliance risks through confidentiality agreements, whitelist access, and an intelligent management mini‑program that tracks recruitment, feedback quality, and incentives.

crowdsourced testingplatform architecturerisk management

0 likes · 18 min read

Crowdsourced Testing Platform for Bilibili: Background, Challenges, Risks, and Management

Bilibili Tech

Nov 19, 2024 · Operations

Building a Lightweight Disaster‑Recovery Drill System at Bilibili: Architecture, Practices, and Lessons

Bilibili’s infrastructure team created a lightweight, multi‑layered disaster‑recovery drill platform—combining an atomic fault library, scenario catalogs, chaos‑experiment orchestration, real‑time observation, and a product‑level interface—backed by standardized governance and CI‑integrated automation, cutting drill preparation from weeks to days and boosting weekly resilience testing across the organization.

disaster recoveryhigh availabilitysite reliability

0 likes · 39 min read

Building a Lightweight Disaster‑Recovery Drill System at Bilibili: Architecture, Practices, and Lessons

Bilibili Tech

Nov 19, 2024 · Backend Development

Evolution and Design of Bilibili Customer Service Seat Scheduling System

The article traces Bilibili’s customer‑service seat scheduling system from its initial balanced‑distribution algorithm and Redis‑based priority queues for live chat and ticket handling, through fairness‑focused saturation limits and virtual‑queue mechanisms, to planned dynamic tuning and expertise‑aware routing for future scalability.

Customer ServiceLoad BalancingRedis

0 likes · 23 min read

Evolution and Design of Bilibili Customer Service Seat Scheduling System

Bilibili Tech

Nov 15, 2024 · Operations

B站直播团队S14赛事保障实践

The Bilibili live‑streaming team’s S14 tournament support showcases how systematic business‑scenario analysis, precise resource forecasting, accelerated fault‑drill and stress‑test workflows, and optimized tooling can deliver stable, low‑cost performance for massive, high‑concurrency events like the 2024 League of Legends World Championship.

InfrastructureTechnical Case Studyevent support

0 likes · 13 min read

Bilibili Tech

Nov 12, 2024 · Big Data

Scalable Tag System Architecture and Optimization

The rebuilt tag system introduces a three‑layer architecture, standard pipelines, Iceberg‑backed storage and custom ClickHouse sharding, a DSL for crowd selection, and a stateless online service, achieving 99.9% success, sub‑5 ms latency, and supporting thousands of tags across dozens of business scenarios while planning real‑time processing and automated lifecycle management.

ClickHouseIcebergOnline Service

0 likes · 23 min read

Scalable Tag System Architecture and Optimization

Bilibili Tech

Nov 8, 2024 · Artificial Intelligence

AI-Powered Game Recognition for League of Legends Live Streaming on Bilibili

Bilibili’s AI‑driven game‑recognition system extracts real‑time LoL events through OCR, hero detection and hot‑spot tagging, generating high‑energy timestamps and interactive overlays that let viewers jump to key moments and view detailed statistics, enhancing spectator engagement and analytical capabilities across major esports tournaments.

AIGame RecognitionOCR

0 likes · 14 min read

AI-Powered Game Recognition for League of Legends Live Streaming on Bilibili

Bilibili Tech

Nov 5, 2024 · Artificial Intelligence

Bilibili's In-House Role-Playing Large Language Model: Architecture, Training Stages, Evaluation, and Demonstrations

Bilibili’s in‑house role‑playing large language model, built on the Index architecture and refined through pre‑training, supervised fine‑tuning, and preference optimization (PPO and DPO), achieved top scores on the Chinese CharacterEval benchmark, surpassing rivals while incorporating safety alignment and showcasing consistent, personality‑driven dialogue examples.

Content SafetySupervised Fine‑Tuningevaluation benchmark

0 likes · 13 min read

Bilibili's In-House Role-Playing Large Language Model: Architecture, Training Stages, Evaluation, and Demonstrations

Bilibili Tech

Nov 1, 2024 · Big Data

Magnus: Intelligent Data Optimization Service for Iceberg Tables in Bilibili's Lakehouse Platform

Magnus is Bilibili’s self‑developed intelligent service that continuously optimizes Iceberg tables by scheduling snapshot expiration, orphan‑file cleanup, manifest rewriting, and multi‑dimensional data optimizations—including small‑file merging, sorting, distribution, and index creation—while automatically recommending configurations from real‑time query logs, delivering over 99.9% task success and up to 30% scan‑data reduction.

IcebergIntelligent RecommendationOptimization

0 likes · 15 min read

Magnus: Intelligent Data Optimization Service for Iceberg Tables in Bilibili's Lakehouse Platform