Genealogy Big Data: AI and Cultural Heritage

Research vision

Chinese genealogies record population migration, family evolution, social relationships, and cultural history. We combine database systems, knowledge graphs, AI, and digital humanities to support digitization, collaborative editing, knowledge organization, intelligent annotation, and knowledge services. Our platform spans collection, management, analysis, and services to preserve genealogical heritage and enable knowledge discovery.

Project support

Independent projects of the Laboratory of Intelligent Computing for Cultural Heritage, Wuhan University:

• Key Technologies for an AI-driven Genealogy Platform (January–December 2026)
• A Study of Clans around Dongting Lake Based on the Luojia TOTEM Genealogy Database (January–December 2023)
• Key Technologies for a Genealogy Platform (January–December 2022)

Awards

• Most Popular Project Award and Outstanding Interaction Award, Chinese Digital Humanities Annual Conference, 2022

Research directions

Genealogy data management

We investigate genealogy data modeling, object management, collaborative editing, and version control to transform printed genealogies into structured digital resources and support long-term maintenance and evolution.

Intelligent annotation and knowledge extraction

We develop AI methods to identify people, places, official titles, and kinship relations in complex genealogy documents, improving digitization and enabling digital humanities research.

Selected publications and patents

Bibliographic records below retain their original titles.

• An Object-Deputy Approach For Chinese Genealogy Collaborative Management. CSCWD 2022: 95-100
• PZXG: A Genealogy Data Service Platform for Kinship Management and Application. ICKG 2020: 505-512
• 基于图数据库的在线族谱编录系统.《计算机应用》2015年1期
• 内存数据管理技术在族谱信息系统中的应用. 2014华东师范大学“数据科学与工程”论坛内存计算数据管理主题报告会
• 基于目标检测的吊线图族谱数字化方法、系统及设备. [发明专利]CN115797957B, 公开日：2026-01-02
• 一种矢量化家谱书生成方法及系统. [发明专利]CN111797056B, 公开日：2024-04-19
• 一种基于特征描述的地图缩放比例推断方法. [发明专利]CN111667394B, 公开日：2023-04-18
• 一种并行处理的大型族谱世系图的生成方法及装置. [发明专利]CN110110270B, 公开日：2021-01-15
• 一种矢量化家谱书生成方法及系统. [发明专利]CN111797056A, 公开日：2020-10-20
• Feature-aware multi-head self-attention hashing for Chinese ancient document image retrieval. Appl. Soft Comput. 193: 114770 (2026)
• CAT: A Collaborative Annotation Tool for Chinese Genealogy Textual Documents. CSCWD 2023: 1043-1048