This article presents Beike's experience building a large‑scale graph database platform, covering the need for graph databases, technology selection between JanusGraph and Dgraph, detailed architecture, data ingestion pipelines, query interfaces, performance benchmarks, and future roadmap.
Facing billions of video entities and edges, Youku’s engineering team replaced traditional relational stores with a graph‑based knowledge platform, leveraging Alibaba’s Blink streaming engine and Lindorm to enable real‑time, incremental updates, unified UDF logic, and scalable feature computation for search and recommendation.
This article explains how Weibo's advertising platform leverages content understanding—covering system architecture, problems caused by insufficient comprehension, the construction of NLP and vision capabilities, content‑based ad strategies, and a celebrity‑brand knowledge graph—to improve ad relevance and ROI.
This article reviews the factors influencing search results, explains why query expansion is crucial for improving recall, surveys various sources of expansion terms, describes probabilistic and translation‑based models, and offers practical recommendations for building effective, data‑driven query expansion pipelines.
In this article, Wang Zhe addresses fifteen common questions about recommendation systems, covering topics such as building cross‑domain knowledge, the role of deep reinforcement learning, handling sparse or low‑sample data, offline‑online evaluation, knowledge graphs, graph neural networks, model interpretability, large‑scale ID embedding, and career advice for engineers.
The article explains how Beike Real Estate constructs an industry knowledge graph by integrating internal and external data, outlines the technical framework and data processing steps, and demonstrates its AI-driven applications such as intelligent Q&A, recommendation, and decision support for the real‑estate market.
This article outlines Baidu's large‑scale knowledge graph applications in AI, detailing the need for multimodal semantic understanding, challenges in text and video comprehension, and the technical solutions including entity annotation, conceptization, knowledge networks, and multimodal fusion for enhanced search, recommendation, and visual question answering.
Alibaba’s AliCoCo, a large‑scale e‑commerce cognitive concept net, models user needs as graph nodes, linking concepts, primitives, taxonomy and items, and leverages advanced NLP, BiLSTM‑CRF, projection learning and knowledge‑enhanced models to boost search relevance, recommendation diversity, and overall user experience.
This article explores how integrating unstructured business data into structured knowledge graphs and applying graph neural networks can overcome deep‑learning bottlenecks in NLP, dramatically improving HS‑code product classification accuracy from around 60% to over 75% through richer reasoning and multimodal knowledge.
This article presents a comprehensive overview of 360's voice interaction platform, detailing dialogue system fundamentals, platform architecture, and core technologies such as semantic understanding, dialog management, and question answering, all driven by deep learning and multimodal innovations.
Personalized recommendation systems, essential for modern internet platforms, can be enhanced by knowledge graphs which provide auxiliary information to improve accuracy, diversity, and explainability, with various methods such as embedding-based (DKN, MKR), path-based, and hybrid approaches like RippleNet and KGCN.
The article reviews recent deep‑learning breakthroughs in personalized content recommendation, covering news and e‑commerce systems, JD Digits' multi‑dimensional user behavior prediction models, knowledge‑graph meta‑learning, and the impact of multimodal AI on future recommendation technologies.
The talk explains how Beike Real Estate constructs a large‑scale relationship graph from billions of user, house, and agent interactions, quantifies edge strengths, builds homogeneous and heterogeneous sub‑graphs, derives graph capabilities such as node influence, embedding, similarity and relation prediction, and finally deploys these capabilities in multi‑degree queries, house‑similarity recommendations and B‑side agent assistance, achieving measurable CTR improvements.
This article presents the 2019 GOPS Global Operations Conference talk by Gong Cheng, detailing how intelligent monitoring leverages multi‑dimensional anomaly detection, machine‑learning‑based alert merging, knowledge‑graph construction, and root‑cause analysis to automate and improve large‑scale IT operations.
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.
The article details how Beike's Agent Cooperation Network employs a multi‑layered risk control framework built on large‑scale knowledge graphs, graph mining, and machine‑learning techniques to detect fake listings, malicious competition, and other threats across both online and offline real‑estate scenarios.
This comprehensive report analyzes the evolution of knowledge graphs, reviews achievements of the first half, and examines the challenges and opportunities of the emerging second half, highlighting shifts from large‑scale simple applications to complex, expert‑driven scenarios, and outlining strategies for representation, acquisition, and application in the era of big data and AI.
The Hulu AI team’s ICLR‑2020 paper introduces a consciousness‑prior‑driven graph neural network that dynamically prunes message‑passing subgraphs, achieving state‑of‑the‑art results on large‑scale knowledge‑graph completion tasks while improving interpretability and computational efficiency.
The article reports on Beike Zhaofang's knowledge‑graph technology conference, detailing how relationship graphs are applied to risk control, the four‑layer graph architecture, the use of Spark GraphX, JanusGraph and DGraph, and broader industry‑graph applications in real‑estate AI solutions.
This article surveys recent advances in recommendation system technology, covering the evolution from a two‑stage recall‑ranking pipeline to a four‑stage architecture, and detailing emerging trends in model‑based recall, user‑behavior sequence modeling, knowledge‑graph integration, graph neural networks, advanced ranking models, multi‑objective optimization, multimodal fusion, and listwise re‑ranking.
This article presents an in‑depth overview of Alibaba's Xiaomì conversational AI system, describing how structured knowledge—including FAQs, phrase‑based knowledge, knowledge graphs, and machine‑read documents—is organized into a two‑level schema and applied to knowledge‑based QA (KBQA) and event‑based QA (EBQA) with detailed model pipelines, ranking, type inference, and recommendation techniques, while also discussing practical challenges and future directions.
This article reviews the principles, techniques, and challenges of automatically building knowledge graphs, covering logical modeling, latent‑space analysis, human‑computer interaction, ontology support, and practical pipelines, and illustrates their use in network behavior analysis, intelligent Q&A, and recommendation systems.
This article explains how query understanding (QP) transforms user search queries into structured semantic blocks and intent categories using rule‑based NLP, entity recognition, and post‑processing, and describes its taxonomy, implementation details, and practical impact on search engine results.
This presentation reviews recent progress in spoken and multimodal dialogue systems, covering X‑driven architectures, task‑oriented and open‑domain approaches, NLU/DM integration, FAQ, KB/KG‑driven methods, document‑driven dialogue, and outlines remaining challenges and future research directions.
This article presents a comprehensive case study of how 58.com built a personalized recommendation system for its large‑scale recruitment platform, covering business background, data challenges, user modeling, recall strategies, ranking pipelines, system architecture, experimental infrastructure, and future research directions.
This article describes the development of MT‑BERT, a BERT‑based language model pre‑trained on Meituan‑Dianping business data, its distributed mixed‑precision training pipeline, domain adaptation, knowledge‑graph integration, model compression techniques, and the wide range of downstream NLP applications achieved in the platform.
This article details how 58.com constructed a large‑scale personalized recommendation platform for its recruitment business, covering business background, user intent modeling, knowledge‑graph and NER techniques, user profiling, multi‑stage recall strategies, ranking model pipelines, serving infrastructure, AB testing, and future research directions.
MT‑BERT at Meituan‑Dianping combines mixed‑precision, domain‑adapted continual pre‑training, knowledge‑graph‑aware masking, and extensive compression techniques to produce fast, accurate BERT models that power fine‑grained sentiment analysis, intent classification, recommendation reasoning, and other NLP tasks across the platform.
This talk presents how Meituan leverages knowledge‑graph QA (KBQA) across restricted and complex smart‑interaction scenarios, compares semantic‑parsing and information‑retrieval approaches, introduces three‑layer concept nodes to handle entity explosion and non‑connected queries, and outlines architectural refinements for multi‑turn dialogue integration.
This article summarizes the keynote on intelligent operations presented at the 13th GOPS Global Operations Conference, covering multi‑dimensional anomaly detection, smart alarm aggregation, the construction of an operations knowledge graph, and AI‑driven root‑cause analysis techniques for large‑scale server environments.
The article details 360's AIOps deployment, covering external speaker insights, internal architecture, data collection pipelines, AI models for resource recycling, alarm reduction, and correlation, as well as visualization dashboards, labeling platforms, and self‑healing mechanisms, illustrating a comprehensive AI‑driven operations framework.
This talk analyzes the technical and practical challenges of current chatbots, introduces the next‑generation paradigm of virtual life, and details how AI technologies such as speech, vision, NLP, and knowledge graphs can be combined with multimodal interaction to create more intelligent and engaging conversational agents.
This article explores how AI is used in iQIYI's video advertising pipeline to analyze video content, generate and recommend ad placement points, create scene‑aware ad creatives, build a video knowledge graph, and support various ad formats, ultimately improving ad relevance and revenue.
This lecture explores how machine learning can generate individualized learning pathways for students by building knowledge dependency graphs, defining optimization goals, and leveraging historical data to rank candidate routes, while reflecting on data, model, business, and demand challenges in AI-driven education.
This article explains the motivation, challenges, architecture, and algorithms behind building a large‑scale cognitive concept graph for search, detailing data construction, concept mining, fusion, confidence scoring, hierarchical structuring, validation, service algorithms, platform access, and real‑world applications such as intent recognition and entity recommendation.
The article surveys the evolution and core components of knowledge graphs—from early Linked Data concepts to modern semantic networks—detailing the end‑to‑end pipeline of data acquisition, cleaning, extraction, and fusion, and showcases Tencent Cloud’s Merak framework and encyclopedia KG, highlighting model choices, performance benchmarks, and real‑world applications such as recommendation and intelligent Q&A.
This report explains how Alibaba uses knowledge graph construction, semantic parsing, and structured answer generation to overcome knowledge management and language understanding challenges in next‑generation intelligent customer service, delivering efficient reuse, precise comprehension, and fine‑grained management of knowledge.
This article introduces KOBE, a knowledge‑based personalized text generation system that leverages Transformer architecture, attribute fusion, and external knowledge graphs to produce fluent, domain‑aware recommendation reasons for e‑commerce products, with a case study on the Spring Festival cloud theme.
CrossE introduces an explicit crossover interaction mechanism for knowledge graph embedding, learning both general and interaction-specific representations of entities and relations, which improves link prediction accuracy and provides interpretable explanations, as demonstrated on benchmark datasets WN18, FB15k, and FB15k-237.
At SIGIR 2019 in Paris, Alipay presented two AI research papers—one applying reinforcement learning to predict user intent in customer‑service bots and another introducing the unsupervised QUEST method that builds noisy quasi‑knowledge graphs for answering complex multi‑document questions.
This article reviews the evolution, architecture, and key technical challenges of general‑domain conversational QA systems, describing Alibaba UC’s search background, dialogue bot types, data pipelines, and advanced methods such as transfer learning, few‑shot learning, and multi‑dimensional dialogue management.
This article introduces the "Kelu Fang" product, which leverages knowledge graph, NLU, and ranking technologies to enhance real‑estate search by adding commute‑based filtering and a local view of surrounding facilities, and discusses its architecture, implementation details, and future improvement directions.
This article presents a comprehensive overview of Alibaba's large entertainment division research on multimodal video analysis, covering intelligent video asset management, automated cover creation with personalized distribution, video knowledge graph construction, multimodal search techniques, and future directions in AI-driven media processing.
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 the concept of a marketing data middle platform, its origins, the expectations of advertisers, how it differs from traditional data warehouses, the technical challenges of data governance, analysis and real‑time output, the role of knowledge graphs, system architecture, data sources, and the three main forms—Data Lake, CDP and DMP—offering a comprehensive overview for marketers and data professionals.
In an interview, JD data platform leader Li Wei discusses how dynamic balance between business demands and technical improvement, knowledge computing, and AI-driven product quality control can drive innovation, enhance user experience, and shape future R&D management strategies.
This article explains how Alibaba’s Search & Recommendation team constructs a large‑scale e‑commerce concept graph—defining e‑commerce concepts, mining them from queries and titles, building an ontology, linking concepts to entities, and applying the graph to improve personalized search and recommendation.
This article reviews Alibaba’s year‑long Knowledge Engine program, detailing its five‑module architecture, major technical breakthroughs such as automatic ontology building and deep‑learning alignment, and two flagship research works: adversarial learning for crowdsourced NER and an iterative rule‑and‑embedding reasoning framework.
The article explores how chatbots require personalized dense knowledge graphs, dynamic temporal graphs, subjective emotion modeling, integration with external services, and multimodal media support, while also promoting a new NLP book and a related giveaway for readers.
ManishRai Jain recounts his journey from Google’s single‑process Graphd, built for Freebase, to creating Dgraph, a distributed graph‑database that shards SPO triples by predicate, avoids fan‑out broadcasts, and supports deep traversals, illustrating the technical evolution and design choices behind modern scalable graph systems.
The Meituan‑Dianping search team progressed its core ranking from linear, FM and GBDT models to a knowledge‑graph‑enhanced deep‑learning architecture, culminating in the listwise LambdaDNN network that directly optimizes NDCG, supported by extensive feature engineering, distributed TensorFlow training, and the Athena diagnostic system.
The article examines why natural language understanding is intrinsically difficult, outlines four core linguistic challenges, proposes a neural‑symbolic integration framework with three design principles, introduces the Object‑Oriented Neural Programming (OONP) architecture, and showcases real‑world applications in public security, legal document analysis, and financial fraud detection.
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.
The talk outlines how Beike built a real‑estate conversational AI platform, covering the market need for dialogue systems, the five technical challenges, data‑driven intent and slot extraction, model choices such as FastText and Bi‑LSTM‑CRF, a three‑layer system architecture, multi‑intent handling, and future directions like 4D viewing and an internal AI dialogue platform.
This article presents a comprehensive overview of financial knowledge graphs, covering their historical evolution, theoretical foundations, technical stack, implementation steps, and real‑world case studies in banking, regulatory technology, and securities, while highlighting community resources for AI and big‑data practitioners.
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.
The AI Challenger 2018 competition, co‑hosted by Innovation Workshop, Sogou, Meituan‑Dianping and Meitu, provides over ten new datasets, more than ten research and industry tracks, and prizes exceeding 3 million RMB, with Meituan‑Dianping debuting as organizer on fine‑grained sentiment analysis and autonomous‑driving perception tracks, and launching a technical salon offering live courses such as the October 24 session on knowledge graphs and Meitu’s AI brain.
This article outlines how Alibaba engineers apply AI, image processing, natural language processing, and knowledge‑graph techniques to automate and secure the handling of complex, image‑heavy trade documents, dramatically improving efficiency, reducing risk, and enabling scalable, low‑cost solutions for SMEs in international commerce.
This article explains the challenges of traditional human‑centric IT operations, introduces a quantitative unmanned‑operations rating method, describes how AIOps (AI for IT Operations) provides the perception‑decision‑action loop, and showcases intelligent fault detection and knowledge‑graph techniques that together enable a path toward fully autonomous operations.
During the CCF Multimedia Committee’s visit to iQIYI, senior researchers and professors presented cutting‑edge AI, knowledge‑graph‑driven content distribution, image‑text sentiment matching, and intelligent multimedia transmission technologies, while interactive tours of studios and labs deepened academia‑industry collaboration and highlighted iQIYI’s innovative multimedia ecosystem.
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 explains how a knowledge graph for second‑hand e‑commerce is built—from data extraction and entity, attribute, and relation mining to ontology construction, entity alignment, and graph integration—and describes how the resulting graph supports personalized recommendation, search optimization, and statistical or regression‑based pricing models.
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.
This article explains Alibaba’s end‑to‑end approach to constructing an e‑commerce knowledge graph—detailing the background, challenges, data‑structuring methods, schema design, modular architecture, and deployment pipeline that enable deep user‑intent understanding across complex shopping scenarios.
Alibaba, together with top Chinese universities and research institutes, unveiled the Cangjingge Knowledge Engine project, detailing its massive data assets, five‑module architecture, large‑scale knowledge construction techniques, and initial deployments in safety and tourism knowledge graphs to boost AI applications.
This article explains what graph databases are, traces their evolution from early navigational models to modern distributed systems, highlights their core concepts and advantages over relational databases, showcases typical application scenarios, and provides a comparative overview of popular open‑source graph database engines to guide technology selection.
JD.com describes its AI-powered image automation pipeline—including intelligent cutout, layout learning, and batch synthesis—along with a large-scale product knowledge graph that enables applications such as the JIMI customer service robot and the Li Bai writing assistant for global e-commerce.
This article explains the fundamentals of knowledge graphs, compares top‑down and bottom‑up construction methods, describes data types, storage options, logical and technical architectures, and walks through the iterative steps of information extraction, knowledge fusion, processing, updating, and real‑world applications.
Alibaba’s knowledge graph leverages massive product data, NLP, semantic reasoning, and machine‑learning inference to detect and block counterfeit, infringing, or unsafe items in real time, providing millisecond‑level responses, self‑learning capabilities, and explainable decisions across e‑commerce platforms, thereby protecting intellectual property and consumer rights.
This article explains the origins of knowledge graphs, introduces the leading graph databases Neo4j and OrientDB, demonstrates their Java client usage, and compares their features to help developers select the most suitable technology for constructing effective knowledge graph solutions.
This article details Alibaba’s Shenma Search intelligent dialogue system, covering its content taxonomy, platform architecture, TaskBot/QABot/ChatBot engines, knowledge‑graph infrastructure, production pipelines, and performance metrics that enable AI‑driven information services across devices like Tmall Genie.
This article reviews the evolution from rule‑based DeepDive methods to deep‑learning approaches such as PCNNs and attention‑enhanced models for relation extraction, presents experimental results on the NYT dataset, discusses practical challenges in large‑scale deployment, and outlines future research directions.
This article explains how Alibaba’s Shenma Search team builds and refines a large‑scale knowledge graph using open information extraction, detailing relation‑extraction techniques, distant supervision challenges, and the DeepDive system’s architecture, custom Chinese NLP pipeline, iterative improvements, and empirical results across millions of triples.
In 2017 Alibaba's AliMe chatbot platform expanded from a single‑company solution to a multilingual, multi‑channel AI service, introducing platform‑level SaaS/PaaS capabilities, a seven‑layer front‑end architecture, modular back‑end design, advanced intent recognition, knowledge‑graph‑driven product management, reinforcement‑learning‑based recommendation, and machine‑reading comprehension for enterprise and consumer use cases.
The December 20 Knowledge Graph symposium in Hangzhou, organized by Alibaba and the Chinese Society of Computational Linguistics, gathered leading Chinese scholars who discussed the pivotal role of massive knowledge graphs in AI, natural language processing, knowledge engineering, reasoning, and data‑driven intelligence.
He Xiaofeng, JD Mall Infrastructure chief architect, discusses his role in building a real‑time computing platform, applying streaming frameworks, machine learning, and knowledge‑graph techniques to product data mining, improve search accuracy, and outline future research directions.
This article presents a comprehensive overview of Alibaba’s intelligent chatbot “Ali Xiaomi”, covering industry context, e‑commerce deployment, NLU architecture, intent‑matching layers, deep‑learning‑based intent classification, reinforcement‑learning‑driven recommendation, knowledge‑graph‑enhanced services, and hybrid retrieval‑generation dialogue models, with future outlooks for AI‑driven interaction.
At the 2nd China Big Data International Summit 2017, JD’s chief architect presented how machine‑learning techniques are applied across e‑commerce to improve product data quality, ensure compliance, resolve image‑text mismatches, automate category identification, restructure titles, and build a multi‑dimensional product knowledge graph.
Alibaba’s massive product knowledge graph combines billions of triples, AI‑driven inference, and semantic reasoning to enable millisecond‑level, explainable detection of illegal or counterfeit items across its e‑commerce ecosystem, improving platform governance and consumer experience.
This article examines the construction, reasoning, and large‑scale applications of knowledge graphs, discussing graph building techniques, storage solutions, deep‑learning‑based entity extraction, inference models such as TransR and RESCAL, and how these graphs enhance search, recommendation, and other AI systems.
The article examines the evolution of integration architectures, identifies persistent data‑search, adaptation, and system‑linkage challenges, and proposes AI‑driven solutions such as knowledge‑graph self‑service and deep‑learning UI automation, illustrating how intelligent integration can reshape software development pipelines.
Alibaba's senior algorithm expert Yang Hongxia explains how the company fuses massive, heterogeneous data sources into a unified platform, builds automated tag‑production pipelines and large‑scale distributed knowledge graphs, and applies these technologies to drive smarter business decisions and AI‑enabled services.
The article explains how web crawlers (spiders) collect data for knowledge graphs, covering core tasks, major challenges, crawler features, new‑link expansion, storage design, link‑selection scheduling strategies, and the role of large‑scale data mining and machine learning in optimizing crawl efficiency.
Alibaba’s ‘Ali Xiaomi’ chatbot leverages a layered architecture that integrates intent recognition, multi‑type matching, knowledge‑graph‑based entity management, deep reinforcement learning, and hybrid retrieval‑generation models to deliver high‑accuracy, scalable conversational services across e‑commerce, customer support, and intelligent recommendation scenarios.
This article outlines a detailed lesson plan for teaching function parity and monotonicity, analyzes teaching difficulties, proposes a knowledge‑graph model for instructional sequencing, and discusses time‑budget constraints to optimize student understanding.
Last month Ctrip Technology Center hosted a deep‑learning meetup featuring academic and industry experts from UCL, Fudan, Southeast University, Nanjing University, Huawei, Sogou and others, who presented real‑world applications of deep learning in travel, advertising, natural language processing, computer vision, and knowledge graphs.
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.
The talk reviews the history and concepts of knowledge graphs, explains logical and statistical reasoning methods—including rule‑based and representation‑learning approaches—and demonstrates how these techniques can be applied to build an intelligent robot that assists students in solving high‑school exam problems.
