Geological disaster knowledge graph construction method and system based on artificial intelligence

By constructing a three-layer semantic ontology graph and a dual-chain space-time graph, combined with graph neural networks and reverse causal path chain reconstruction methods, the problem of insufficient dynamic modeling of geological disaster knowledge graphs in existing technologies is solved, the dynamic state propagation and causal path tracing of geological disaster risks are realized, and the risk prediction ability is improved.

CN120598007AActive Publication Date: 2025-09-05四川省第五地质大队
6 Cites 1 Cited by

Patent Information

Application Number
CN202510677366.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-05-26
Publication Date
2025-09-05
Estimated Expiration
2045-05-26

AI Technical Summary

Technical Problem

Existing technologies are unable to achieve physical predictive modeling and dynamic updating, as well as joint modeling of spatial topological relationships and temporal evolution states. They lack the ability to dynamically analyze and predict the evolution mechanism of geological hazards, resulting in insufficient explainable predictions of disaster risk states by geological hazard knowledge graphs.

Method used

The artificial intelligence-based geological disaster knowledge graph construction method constructs a three-layer semantic ontology graph including landslide structure unit layer, physical and mechanical parameter layer and logical causal relationship layer, uses a double-chain spatiotemporal graph construction method to generate spatial profile structure chain and time series state chain, and adopts a graph neural network graph topology modeling mechanism, combined with disturbance-aware graph neural network and reverse causal path chain reconstruction method, to finally construct a double-chain coupled spatiotemporal geological disaster knowledge graph.

Benefits of technology

The dynamic state propagation and risk score prediction of the geological disaster knowledge graph are realized, and causal path reasoning and tracing can be performed under external disturbance conditions, which improves the risk state interpretable prediction ability of the geological disaster knowledge graph.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention relates to the technical field of knowledge graph construction, in particular to a geological disaster knowledge graph construction method and system based on artificial intelligence. The method comprises the following steps: extracting a geological semantic triple set by using a semantic physical collaborative preprocessing method, and constructing a three-layer semantic ontology map; generating a spatial profile structure chain and a time sequence state chain by using a double-chain space-time atlas construction method, and constructing a double-chain coupling atlas structure; performing node state propagation calculation by adopting a disturbance perception graph neural network mechanism to obtain a risk state prediction result of a landslide structure unit layer under each time node; and generating a landslide risk propagation path chain by adopting a reverse causal path chain reconstruction method, and migrating propagation parameters and response rules in the historical landslide map structure into the double-chain coupling map structure to construct the double-chain coupling space-time geological disaster knowledge map. According to the invention, landslide state prediction and causal path reasoning are realized through a double-chain graph structure and a disturbance perception graph neural network.
Need to check novelty before this filing date? Find Prior Art