BestHub
Sign in
Tagged articles
8 articles
Page 1 of 1
Bilibili Tech
Bilibili Tech
Jan 7, 2025 · Cloud Native

Design and Implementation of Bilibili's Large-Scale Recall System

Bilibili’s large‑scale recall system separates online processing into a two‑tier merge service and an index service, supports multi‑channel text, item‑to‑item and vector indexes with real‑time updates, uses horizontal sharding, robust CI/CD, monitoring and degradation mechanisms, and is being extended toward model‑based recall and greater automation.

BilibiliSearch Architecturecloud-native
0 likes · 16 min read
Design and Implementation of Bilibili's Large-Scale Recall System
DataFunTalk
DataFunTalk
Jan 22, 2022 · Artificial Intelligence

Multimodal Content Understanding Techniques in Search Systems

This talk presents Tencent's multimodal content understanding framework for search, covering hierarchical content features, large‑scale ranking, fine‑grained image semantic vectors, video and document analysis, quality detection, duplicate removal, and future directions in AI‑driven search.

AIImage EmbeddingSearch
0 likes · 17 min read
Multimodal Content Understanding Techniques in Search Systems
Kuaishou Tech
Kuaishou Tech
Nov 29, 2021 · Artificial Intelligence

Starry Vector Retrieval Platform: Architecture, Features, and Performance

The article describes the design, challenges, architecture, key features, algorithm optimizations, and future roadmap of Kuaishou's Starry vector retrieval platform, which delivers high‑performance, high‑reliability, and easy‑to‑use large‑scale ANN search for diverse business scenarios.

AI PlatformANNPerformance Optimization
0 likes · 14 min read
Starry Vector Retrieval Platform: Architecture, Features, and Performance
Baidu Geek Talk
Baidu Geek Talk
May 10, 2021 · Industry Insights

How Baidu’s GNOIMI Powers Billion‑Scale Rich Media Retrieval

Baidu’s rich‑media retrieval system combines CNN‑based feature extraction with an Approximate Nearest Neighbor engine called GNOIMI, employing hierarchical clustering, product quantization, and optimized indexing to achieve sub‑millisecond search over billions of images, videos and audio, supporting anti‑spam, recommendation and risk‑control across dozens of services.

ANNGNOIMIHNSW
0 likes · 16 min read
How Baidu’s GNOIMI Powers Billion‑Scale Rich Media Retrieval
Alibaba Cloud Developer
Alibaba Cloud Developer
Mar 4, 2021 · Artificial Intelligence

How Alibaba’s Proxima Engine Revolutionizes Vector Search for AI Applications

Alibaba’s Damo Academy unveils Proxima, a high‑performance vector search engine that powers e‑commerce, video, and payment services, detailing its core capabilities, large‑scale indexing, distributed construction, real‑time updates, and challenges such as algorithm diversity, scalability, and multi‑modal retrieval.

AIAlibaba Proximalarge-scale indexing
0 likes · 17 min read
How Alibaba’s Proxima Engine Revolutionizes Vector Search for AI Applications
Youku Technology
Youku Technology
Jul 9, 2020 · Artificial Intelligence

Multi-level Multi-modal Search Engine and Graph Engine for Billion-scale Video Content

An advanced multi‑level, multi‑modal search and graph engine for Youku processes text, voice, image and video queries across hierarchical video elements, using combined vector and inverted indexes to merge cross‑level and cross‑modal results, while a distributed knowledge‑graph layer enables multimodal graph traversal for billion‑scale video retrieval.

AIgraph enginelarge-scale indexing
0 likes · 12 min read
Multi-level Multi-modal Search Engine and Graph Engine for Billion-scale Video Content
Youku Technology
Youku Technology
Jun 17, 2020 · Industry Insights

How Youku’s Multi‑Modal Search Engine Powers Billion‑Scale Video Retrieval

This article details the design and implementation of Youku’s Multi‑Modal Search Engine (MMS), covering its distributed multi‑level indexing architecture, vector retrieval using Aitheta, cross‑modal query scheduling, graph‑based execution engine, and real‑world applications such as intelligent video search and image‑based series lookup.

Vector RetrievalVideo platformgraph execution engine
0 likes · 10 min read
How Youku’s Multi‑Modal Search Engine Powers Billion‑Scale Video Retrieval
Architecture Digest
Architecture Digest
Nov 15, 2019 · Big Data

Design and Key Technologies of the 360 Search Engine for Billion‑Scale Web Retrieval

This article explains how 360 Search handles billions of daily crawls and hundred‑billion‑scale indexing by describing its overall architecture, core modules such as offline indexing and online retrieval, query analysis, relevance scoring, and the engineering techniques that enable efficient large‑scale web search.

information retrievallarge-scale indexingranking
0 likes · 22 min read
Design and Key Technologies of the 360 Search Engine for Billion‑Scale Web Retrieval