AX Insight

AX Insight

How to parse HWP and Word documents and convert them into structured data such as JSON

HWP and Word documents are processed differently in document parsing. This article summarizes the processing approach by format, differences in output formats, JSON conversion, and how to connect to RAG document preprocessing.

2026.08.28

AX Insight

Causes and Solutions for RAG Search Failures in Official and Legal Documents – Recognizing Korean Document Hierarchical Structures

When official and legal documents are used in RAG, does the search retrieve irrelevant clauses? We've outlined three reasons why the Article, Paragraph, Subparagraph, and Item hierarchy and official document tables are damaged during parsing and chunking, and how to restore search accuracy by recognizing Korean document hierarchical structures.

2026.08.27

AX Insight

Public Institution HWP Parsing Solution Adoption Checklist | GS Certification, Network Separation, and On-Premises Criteria

When selecting a document parsing solution for public institutions, it is easy to overlook critical requirements such as native HWP and HWPX processing, network separation and on-premises deployment, and GS certification. This five-point checklist consolidates these considerations, helping you identify what to verify before adoption to avoid implementation failures.

2026.08.25

AX Insight

How to Improve RAG Chunking Quality: Preprocessing Strategies Preserving Document Hierarchical Structure

Low RAG (Retrieval-Augmented Generation) chunking quality can lead to incorrect answers when documents are uploaded. While it may seem that documents are organized into searchable units through parsing and chunking, ... <a title="How to Improve RAG Chunking Quality: Preprocessing Strategies Preserving Document Hierarchical Structure" class="read-more" href="https://blog.hancom.com/en/rag-chunking-quality-document-hierarchy-preprocessing/" aria-label="Read more about How to Improve RAG Chunking Quality: Preprocessing Strategies Preserving Document Hierarchical Structure">Read more</a>

2026.08.21

AX Insight

Why Unstructured Data Parsing Is Difficult and How to Structure It with AI Document Parsing

This article identifies the challenges of unstructured data parsing—spanning table handling, HWP format constraints, and OCR limitations—and explains how AI document parsing transforms HWP, HWPX, PDF, and OOXML files into structured JSON data, drawing on research papers and official technical documentation.

2026.08.20

AX Insight

If image/table data extraction is corrupted during parsing: A complete guide from merged cells to multi-level headers

If image/table data extraction breaks during parsing: A complete guide from merged cells to multi-level headers (content thumbnail image)

2026.08.18