The talk presents JD's end‑to‑end semantic search recall pipeline, covering multi‑stage retrieval, a dual‑tower embedding model with multi‑head attention, a heterogeneous graph neural network for low‑frequency items, automatic synonym generation via transformer models, and a joint training approach that integrates product quantization directly into the model to improve accuracy and efficiency.
Xianyu search recall stage upgraded from simple text matching to semantic vector retrieval using DSSM with Electra‑Small, query graph attention, and behavior‑based I2I, adding structured attributes and OCR tags, improving AUC to 0.824 and HitRate@10 to 90.1%, boosting purchase metrics by up to 4%.
The article outlines five major trends—neural-network-enhanced search, semantic search, document understanding, image and voice search, and knowledge graphs—that are transforming enterprise use of unstructured data by leveraging AI to deliver precise, context-aware answers and insights.
This article walks through building a large‑scale semantic search system on the English Wikipedia using the Weaviate vector database, GraphQL queries, and pre‑trained Sentence‑BERT and BERT Q&A models, covering dataset preparation, schema design, import pipelines, query examples, and production deployment strategies.
This article provides a comprehensive overview of knowledge graphs and entity linking, covering their definitions, practical uses in question answering, search and recommendation, the standard pipeline of mention detection, candidate generation and scoring, challenges such as scalability and multilinguality, and recent research advances including dual‑encoder, RELIC, deep retrieval, and multilingual BERT‑based models, followed by a discussion of modern knowledge‑graph construction methods.
WanFang upgraded its academic paper retrieval system by adopting PaddleNLP’s Chinese pre‑trained Sentence‑BERT models, using weakly supervised SimCSE data and Milvus vector indexing, compressing the transformer for TensorRT‑accelerated inference, achieving 70% better matching quality and 2600 QPS latency‑optimized performance.
The article explains why traditional text‑based search engines like ElasticSearch struggle with modern multimodal data, introduces vector databases that store implicit semantic embeddings, and proposes a generalized search architecture that decouples data‑to‑vector mapping from the engine while leveraging clustering or graph indexes for similarity search.
This article details Zhihu Search's engineering solutions for long‑tail query challenges, covering historical development, term weighting, synonym expansion, query rewriting with reinforcement learning, and semantic recall using BERT‑based models, while also outlining future research directions such as GAN‑based rewriting and lightweight pre‑training.
This article presents a comprehensive overview of 58 Search's multi‑stage retrieval system, compares term‑match and semantic matching, details the design, training, and optimization of interactive, dual‑tower, and semi‑interactive BERT‑based semantic models, and discusses their practical deployment in ranking and recall stages.
This article explains how financial institutions can leverage large amounts of structured and unstructured data to build and apply financial knowledge graphs, covering AI key technologies, schema design, data extraction, graph construction, storage solutions, and real-world use cases such as intelligent tagging, recommendation, policy analysis, and executive relationship mining.
This article explains how financial institutions can leverage massive structured and unstructured data by building a financial knowledge graph, detailing AI core technologies, schema design, extraction methods, storage solutions, and a range of practical applications such as intelligent tagging, recommendation, policy analysis, and executive relationship mining.
This article explores the challenges of enterprise knowledge management and presents a comprehensive OpenIE-based approach for building vertical domain knowledge graphs, covering data extraction, SPO triple generation, case studies, and applications such as chatbots, semantic search, and intelligent QA.
The article presents an in‑depth overview of Xiaomi's knowledge graph, describing its evolution, core technologies such as entity linking, knowledge fusion and concept mining, and illustrating how it powers diverse AI‑driven services like smart Q&A, virtual assistants, e‑commerce and financial applications.
This article explains how keyword matching in search advertising works, outlines the challenges of semantic gaps, matching‑mode determination and scalability, and describes data‑driven synonym transformation techniques—including rule‑based, sequence‑to‑sequence, metric‑space and graph‑based models—to improve recall, efficiency, and robustness.
The article outlines how advances in neural networks, semantic search, document understanding, image and voice search, and knowledge graphs are transforming enterprise search of unstructured data, enabling more accurate, context‑aware answers and new business use cases across organizations.
iQIYI Douya’s emoji search evolved from ElasticSearch to a pure Lucene implementation and added semantic vector retrieval, enabling fast, scalable, and more accurate text‑based search of AI‑generated images for small‑to‑medium businesses by combining custom tokenization, dense embeddings, and hybrid ranking.
This article presents JD's e‑commerce search system, detailing the semantic vector retrieval and product ranking pipelines, the two‑tower deep learning architecture, attention‑based personalization, negative sampling strategies, training optimizations, and real‑world performance gains achieved in production.
The OpenKG initiative, together with dozens of university and industry partners, has released a series of open‑source COVID‑19 knowledge graphs—including encyclopedia, research, clinical, hero, hotspot‑event, and upcoming prevention and resource graphs—detailing their data sources, scale, schema designs, and potential AI‑driven applications such as semantic search and intelligent question answering.
This article outlines the evolution of knowledge graphs, describes typical enterprise application scenarios, compares graph database options such as Neo4j, Cayley and Dgraph, and presents a six‑step methodology for building, storing, and applying knowledge graphs in large‑scale business environments.
This article explains what a tourism knowledge graph is, discusses its architecture, construction methods, practical applications such as QA and recommendation, and explores future directions integrating knowledge graphs with deep learning and multi‑domain fusion.
Meituan Brain builds a massive multi‑modal knowledge graph of billions of entities and triples across food, entertainment, and travel, using advanced extraction, validation, fusion, and reasoning techniques to empower search, recommendation, merchant tools, and fraud detection while addressing scalability and schema‑evolution challenges.
This article examines the evolution of search, defines multimedia content retrieval, explores user scenarios such as voice, image, and video input, and details key AI techniques—including OCR, face recognition, and content knowledge graphs—that enable semantic understanding and ranking of video content.
This article examines the distinctive features of tourism-domain knowledge graphs, outlines methods for constructing them from internal and external data sources, and explores their practical applications such as question‑answering bots, personalized recommendation, and advanced search within the online travel sector.
This article details the evolution, architecture, and practical applications of knowledge graphs at Beike Real Estate, covering their historical background, five‑view advantages, data pipelines, ontology construction, intelligent search, recommendation, and chatbot integration, while also discussing challenges and future directions.
Meituan leverages deep‑learning models such as Word2Vec, DSSM, and LSTM‑based encoders within its ClickNet framework to compute text similarity and rank results, integrating rich business features like user location and merchant rating, thereby surpassing traditional TF‑IDF, BM25, and XGBoost approaches and boosting click‑through rates and revenue.
Google Research unveiled “Talk to Books,” a semantic‑experience that lets users type statements or questions and receive full‑sentence matches from books, showcasing how AI trained on billions of conversational pairs can understand meaning beyond simple keyword matching.
Alibaba’s search team outlines how deep learning transforms e‑commerce search and recommendation, detailing system infrastructure, AI‑driven features like intelligent interaction, semantic search, personalized matching, performance optimizations, multi‑agent learning, and future plans for unified user and query representations.
This article presents a knowledge‑graph‑driven question answering system, detailing its three‑layer architecture, semantic search and disambiguation techniques, verb‑semantic templates, deep‑learning models, experimental results, and current challenges in data quality and model integration.