BestHub
Sign in
Tagged articles

business semantics

18 articles · Page 1 of 1
Data Bricklaying Diary
Data Bricklaying Diary
Sep 21, 2026 · R&D Management

Ontology Review Exposes Governance Conflicts: Customer & Revenue Disputes

The article explains how ontology reviews surface business governance conflicts over definitions like 'customer' and 'revenue,' and provides a framework to distinguish identity, roles, granularity, facts, and rules; assign confirmation authority by domain, cross-domain, and management levels; implement decisions via versioned decision cards; and validate through concrete test cases rather than forced unification.

business semanticscross-domain governancecustomer master data
0 likes · 22 min read
Ontology Review Exposes Governance Conflicts: Customer & Revenue Disputes
DataFunTalk
DataFunTalk
Sep 11, 2026 · Big Data

Ant Group's Financial Data Ontology: Automating Business Semantics with LangGraph

Ant Group solves inconsistent business definitions across thousands of tables by building a financial data knowledge ontology using a six-node LangGraph state machine that automates schema perception, entity resolution, and conflict marking without forced merging, enabling a three-layer retrieval architecture that cuts cross-opportunity identification from days to hours and achieves 85% anomaly analysis accuracy.

Automated Ontology ConstructionFinancial Data OntologyLangGraph
0 likes · 4 min read
Ant Group's Financial Data Ontology: Automating Business Semantics with LangGraph
Digital Deification
Digital Deification
Sep 9, 2026 · R&D Management

Business Semantics Is the Baseline, Ontology the Ceiling: Why FDEs Must Master Both

This article argues that Field Delivery Engineers (FDEs) who lack business semantics understanding become mere button-pushers, while ontology thinking separates executors from solution architects, using concrete factory and multi-system integration examples to show how semantic misalignment causes rework and endless arguments.

FDEbusiness semanticsdata modeling
0 likes · 11 min read
Business Semantics Is the Baseline, Ontology the Ceiling: Why FDEs Must Master Both
Digital Deification
Digital Deification
Sep 1, 2026 · Industry Insights

GB/T 48000.3: Three Shifts for Enterprise Knowledge Modeling from Documents to Actionable Ontologies

The article interprets China's GB/T 48000.3 ontology modeling standard, highlighting its core principle of separating knowledge content from representation, and derives three enterprise digitalization shifts: moving from document chunks to business information units, from retrieval to constraint validation, and from answer generation to action-driven knowledge modeling.

GB/T 48000.3action-driven AIbusiness semantics
0 likes · 7 min read
GB/T 48000.3: Three Shifts for Enterprise Knowledge Modeling from Documents to Actionable Ontologies
Data Bricklaying Diary
Data Bricklaying Diary
Aug 30, 2026 · Industry Insights

Palantir Ontology Isn't Just Schema Design — It's a Runtime Semantic Platform

The article argues Palantir Ontology's primitives aren't novel, but its value comes from organizing them into an engineering system that connects business semantics, real data, controlled actions, permissions, and feedback loops, enabling reusable, governable capabilities across queries, applications, and agents — not merely a static model diagram.

PalantirRuntime SystemSemantic Layer
0 likes · 19 min read
Palantir Ontology Isn't Just Schema Design — It's a Runtime Semantic Platform
Data Bricklaying Diary
Data Bricklaying Diary
Aug 15, 2026 · Industry Insights

Beyond 4A: Ontology-Driven Data Governance for AI-Ready Enterprise Architecture

This article explains why traditional 4A enterprise architecture fails to support AI agents, proposes an ontology semantic platform as a computable cross-domain layer, and outlines an 8-step approach to transform static architecture assets into dynamic, AI-ready business context with semantic services and action contracts.

4A architectureAI agentsOntology-Driven Data Governance
0 likes · 13 min read
Beyond 4A: Ontology-Driven Data Governance for AI-Ready Enterprise Architecture
Data Integration and Governance
Data Integration and Governance
Aug 13, 2026 · Artificial Intelligence

Why Traditional Wide-Table Data Warehousing Won’t Suffice in the Data Agent Era

The article argues that while wide tables remain useful for fixed, high‑frequency analyses, the rise of Data Agents requires data warehouses to go beyond simple tables and provide business semantics, unified metrics, context, and governance so AI can understand and answer complex business questions accurately.

AI AnalyticsData Agentbusiness semantics
0 likes · 18 min read
Why Traditional Wide-Table Data Warehousing Won’t Suffice in the Data Agent Era
Data Bricklaying Diary
Data Bricklaying Diary
Aug 8, 2026 · Artificial Intelligence

Why Large Models Alone Fail in Industry AI: The Semantic Platform Gap

The article argues that industry AI requires a semantic platform to connect large models, data platforms, and business scenarios by structuring business objects, processes, states, rules, evidence, and action contracts, enabling verifiable, traceable agent execution and continuous model-data resonance.

AI agentsIndustry AILarge Language Models
0 likes · 12 min read
Why Large Models Alone Fail in Industry AI: The Semantic Platform Gap
Data Bricklaying Diary
Data Bricklaying Diary
Aug 6, 2026 · Artificial Intelligence

From Ontology Semantics to Ontology Intelligence: Why Understanding Business ≠ Driving It

The article distinguishes ontology semantics (AI understanding business objects, states, rules) from ontology intelligence (explainable decisions, contract-constrained actions, auditable loops), outlining seven engineering capabilities needed to close the loop and emphasizing a minimal viable loop around high-value decisions.

Action ContractsAgent ArchitectureAgent Runtime
0 likes · 16 min read
From Ontology Semantics to Ontology Intelligence: Why Understanding Business ≠ Driving It
Data Bricklaying Diary
Data Bricklaying Diary
Aug 5, 2026 · Industry Insights

Ontology Intelligence: Closing the Engineering Gap for Enterprise AI Agents

This article introduces the Ontology Intelligence series, explaining why enterprise AI agents fail in production without unified business semantics, current object state, explainable decisions, controlled actions, and continuous governance—outlining a five-layer framework and scenario-based criteria for adopting ontology-driven architectures.

AI Production GapAgent ArchitectureControlled Actions
0 likes · 18 min read
Ontology Intelligence: Closing the Engineering Gap for Enterprise AI Agents
Yunqi AI+
Yunqi AI+
Jul 25, 2026 · Artificial Intelligence

Designing Ontology After Microservices in AI‑Native Service Architecture

After a decade of microservices, the article argues that AI agents expose semantic gaps across CRM, ERP, and other systems, and proposes an Ontology Service Layer that unifies objects, relationships, states, metrics, actions, policies, and evidence to enable controlled, auditable AI‑native execution.

AI agentsbusiness semanticsmicroservices
0 likes · 21 min read
Designing Ontology After Microservices in AI‑Native Service Architecture
Data Bricklaying Diary
Data Bricklaying Diary
Jul 22, 2026 · Artificial Intelligence

Beyond Accuracy: A Five-Layer Framework for Evaluating High-Quality AI Datasets

This article presents a five-layer evaluation framework for high-quality AI datasets—covering basic data quality, business semantics, task adaptation, AI application effects, and trustworthy operations—emphasizing task-specific validation over generic metrics and advocating admission vs. optimization metrics with automated, expert, and task-based verification.

AI data qualityRAG evaluationadmission metrics
0 likes · 13 min read
Beyond Accuracy: A Five-Layer Framework for Evaluating High-Quality AI Datasets
Data Bricklaying Diary
Data Bricklaying Diary
Jul 20, 2026 · Big Data

High-Quality Datasets: Beyond Cleaned Data for AI Tasks

This article defines high-quality datasets as task-oriented data products with business semantics, evidence traceability, usage boundaries, and continuous governance — not merely cleaned data — and explains why they are essential for reliable AI training, RAG, and Agent applications.

AI data preparationAgentRAG
0 likes · 13 min read
High-Quality Datasets: Beyond Cleaned Data for AI Tasks