Related Experiment Video
Updated: Jul 14, 2025

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
Published on: February 9, 2024
Emergency entity relationship extraction for water diversion project based on pre-trained model and multi-featured
Li Hu Wang1, Xue Mei Liu1,2,3, Yang Liu3
1School of Management and Economics, North China University of Water Resources and Electric Power, Zhengzhou, Henan, 450046, China.
This study introduces a novel PTM-MFGCN model for extracting emergency knowledge from water diversion projects. The model significantly improves accuracy and recall in emergency entity relationship extraction for better disaster management.
Area of Science:
- Information Science
- Computer Science
- Engineering Management
Background:
- Effective emergency management relies on extracting decision-making knowledge from complex emergency plan documents.
- Water diversion projects present unique challenges in emergency knowledge extraction due to extensive terminology and intricate relationships.
Purpose of the Study:
- To develop an advanced model for extracting emergency knowledge and relationships from water diversion project documents.
- To enhance the efficiency and capacity of emergency management through improved knowledge extraction.
Main Methods:
- A multi-feature graph convolutional network (PTM-MFGCN) based on a pre-trained model was proposed.
- Domain-specific terminology masking during pre-training enhanced model comprehension.
- A multi-feature adjacency matrix was introduced to capture complex relationships between entities.
Main Results:
- The PTM-MFGCN model demonstrated improved performance over baseline models.
- Accuracy increased by 2.84%, recall by 4.87%, and F1 score by 5.18% in emergency entity relationship extraction.
- A knowledge graph for water diversion emergency management was successfully constructed.
Conclusions:
- The PTM-MFGCN model effectively extracts emergency entity relationships in water diversion projects.
- This approach enhances emergency management efficiency and capability, mitigating risks to engineering safety.
- The developed knowledge graph supports better decision-making in water diversion emergencies.
More Related Videos
Related Concept Videos
Design Example: Design of an Irrigation Channel
Design Example: Creating a Hydraulic Model of a Dam Spillway
Modeling and Similitude
Design Example: Analyzing Capacity Contours for Flood Risk Assessment
Water and Mineral Acquisition
Weir

