BestHub
Sign in
iQIYI Technical Product Team
Author

iQIYI Technical Product Team

The technical product team of iQIYI

407
Articles
0
Likes
2.1k
Views
0
Comments
Recent Articles

Latest from iQIYI Technical Product Team

100 recent articles max
iQIYI Technical Product Team
iQIYI Technical Product Team
Dec 5, 2024 · Backend Development

Low-Code Process Engine Architecture and Implementation Using LiteFlow

By adopting LiteFlow’s lightweight low‑code workflow engine with a workbench‑component‑rule architecture, the team replaced repetitive custom code with configurable pipelines, achieving high decoupling, flexible orchestration, reduced development cost, and improved extensibility for complex business processes, while planning a visual backend platform.

Backend DevelopmentComponent ArchitectureLiteFlow
0 likes · 7 min read
Low-Code Process Engine Architecture and Implementation Using LiteFlow
iQIYI Technical Product Team
iQIYI Technical Product Team
Nov 28, 2024 · R&D Management

Advanced Exploration and Practice of Value Delivery in Project Management

At the 12th QECon conference, iQIYI presented a systematic value‑delivery framework that tackles misaligned goals, planning‑execution gaps, and metric deficiencies by using a two‑scenario model for iterative and special projects—defining SMART goals, tight scope control, continuous monitoring, and AI‑driven automation—to accelerate rollout, quantify impact, and guide future integrated, intelligent delivery.

AIMetricsR&D management
0 likes · 15 min read
Advanced Exploration and Practice of Value Delivery in Project Management
iQIYI Technical Product Team
iQIYI Technical Product Team
Nov 21, 2024 · Big Data

Alluxio Integration and Optimization for Multi‑AZ Big Data Analytics at iQIYI

iQIYI integrates Alluxio with its QBFS multi‑AZ unified scheduling system, automatically caching hot tables, applying table‑level policies, page‑level storage and AZ‑aware worker selection, which together cut cross‑zone traffic, halve query latency, achieve up to 20× I/O speedup and a three‑fold overall performance boost.

AlluxioData LakeMulti‑AZ
0 likes · 23 min read
Alluxio Integration and Optimization for Multi‑AZ Big Data Analytics at iQIYI
iQIYI Technical Product Team
iQIYI Technical Product Team
Nov 7, 2024 · Artificial Intelligence

Multimodal Speaker Diarization for Long-Form Video Scripts

iQIYI’s multimodal speaker diarization system splits long‑form video using subtitle timestamps and scene detection, extracts voiceprints with a custom model, hierarchically clusters them, and applies an Activate Speaker Detection algorithm combined with face‑recognition to assign speakers, achieving around 90 % precision and recall and boosting downstream tasks such as summarization, translation, and dubbing.

dialogue recognitioniQIYImultimodal AI
0 likes · 8 min read
Multimodal Speaker Diarization for Long-Form Video Scripts
iQIYI Technical Product Team
iQIYI Technical Product Team
Oct 24, 2024 · Big Data

iQIYI Multi-AZ Unified Scheduling Architecture for Big Data

iQIYI’s Multi‑AZ unified scheduling architecture combines a unified storage layer (QBFS), an abstracted compute scheduler (QBCS), and a federated metadata service (Waggle Dance) to seamlessly route data and jobs across availability zones, cut storage costs up to 65 %, reduce overall big‑data workload expenses by more than 35 %, and lay the groundwork for future hybrid‑cloud expansion.

Big DataCompute SchedulingUnified Storage
0 likes · 15 min read
iQIYI Multi-AZ Unified Scheduling Architecture for Big Data
iQIYI Technical Product Team
iQIYI Technical Product Team
Oct 10, 2024 · Artificial Intelligence

Online Deep Learning (ODL) for Real‑Time Advertising Effectiveness: Challenges and Solutions

iQIYI’s minute‑level online deep‑learning framework overcomes stability, timeliness, compatibility, delayed feedback, catastrophic forgetting, and i.i.d. constraints through high‑availability pipelines, TensorFlow Example serialization, rapid P2P model distribution, flexible scheduling, disaster‑recovery rollbacks, PU‑loss adjustment, and knowledge‑distillation, delivering a 6.2% revenue boost.

AdvertisingCTR predictionDeep Learning
0 likes · 9 min read
Online Deep Learning (ODL) for Real‑Time Advertising Effectiveness: Challenges and Solutions
iQIYI Technical Product Team
iQIYI Technical Product Team
Sep 26, 2024 · Artificial Intelligence

AI-Powered Search in iQIYI: Techniques, Architecture, and Implementation

iQIYI’s AI‑powered search expands beyond title‑only queries by handling fuzzy role, plot, star, award, and semantic searches, using Chain‑of‑Thought‑generated TIPS, Retrieval‑Augmented Generation with sophisticated indexing, chunking, embedding, reranking, and prompt‑engineering to deliver personalized, accurate video recommendations that boost user engagement.

AI SearchEmbeddingQuery Guidance
0 likes · 15 min read
AI-Powered Search in iQIYI: Techniques, Architecture, and Implementation
iQIYI Technical Product Team
iQIYI Technical Product Team
Sep 19, 2024 · Information Security

01 Background Introduction

The article introduces the concept of an egress gateway, explains why iQIYI’s member‑cooperation services require a unified outbound gateway to handle IP‑whitelisting and external access, critiques the limitations of an Nginx proxy, and describes adopting APISIX with security, traffic‑control plugins and a UI‑driven URL translation layer.

APISIXSecurityTraffic Management
0 likes · 13 min read
01 Background Introduction
iQIYI Technical Product Team
iQIYI Technical Product Team
Sep 12, 2024 · Artificial Intelligence

Intelligent Compute Allocation in Advertising: Value Quantification, Elastic Elimination, and Dynamic Optimization

iQIYI’s ad engine team introduced an intelligent compute allocation system that quantifies traffic value and unified compute cost, uses elastic elimination and a dynamic allocation framework to maximize revenue under fixed compute limits, delivering over 30% inventory growth, modest consumption rise, and near‑perfect availability.

OptimizationPID controldynamic allocation
0 likes · 11 min read
Intelligent Compute Allocation in Advertising: Value Quantification, Elastic Elimination, and Dynamic Optimization