The process of generation a knowledge graph for thai law

A Knowledge Graph tailored for Thai Law addresses compliance challenges by integrating legal domain expertise and advanced data modeling, providing a centralized, context-aware system for accurate legal compliance management and reducing non-compliance risks.

WO2026089666A1PCT designated stage Publication Date: 2026-04-30STELLIGENCE CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
PCT/TH2025/050006
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2024-10-24
Filing Date
2025-03-12
Publication Date
2026-04-30

AI Technical Summary

Technical Problem

Manufacturing companies face challenges in maintaining compliance with complex and scattered Thai legal regulations due to the lack of a centralized, context-aware system for tracking changes and interlinking legal documents, leading to inefficiencies and risks of non-compliance.

Method used

A Knowledge Graph (KG) specifically designed for Thai Law, integrating deep legal domain expertise and advanced data modeling, which maps and interconnects legal documents, leveraging multi-agent Large Language Models (LLMs) for precise legal text segmentation, entity recognition, and relationship mapping, ensuring adaptability to evolving legislative frameworks.

Benefits of technology

The KG provides a structured, context-aware foundation for accurate and reliable legal compliance management, reducing manual effort and risks of non-compliance by offering precise, actionable insights and enhancing Generative AI systems.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure TH2025050006_30042026_PF_FP_ABST
    Figure TH2025050006_30042026_PF_FP_ABST
Patent Text Reader

Abstract

The process of generation a knowledge graph for Thai law according to this invention consists of the following steps: data collection, text extraction, data chunking and embedding, ontology design, graph data model ingestion, and integration. A unique feature of the ontology design step is that it creates the structure for representing and linking legal concepts within the knowledge graph. This process includes extracting legal content, defining concepts and developing classes, specifying properties and developing relationships, developing hierarchy, and contextual alignment, all of which are integrated together.
Need to check novelty before this filing date? Find Prior Art