Probability hypergraph-driven geoscience knowledge graph reasoning optimization system and method

Abstract

The invention discloses a probability hypergraph-driven geoscience knowledge graph reasoning optimization system and method, and belongs to the technical field of geographic big data analysis. The system comprises a geoscience knowledge graph input module, a geoscience ontology setting module, a hypergraph model construction module, a hypergraph auto-encoder module and a geoscience knowledge graph general reasoning optimization module. The method comprises the following steps: disassembling a geoscience knowledge graph structure; constructing a knowledge data hypergraph model; calculating a hypergraph information transmission probability; according to the geoscience knowledge graph reasoning optimization method, a many-to-many graph node hyperedge rule is adopted, the graph structure shape of the geoscience knowledge graph is changed, due to the fact that the many-to-many graph node hyperedge rule is adopted, the common and opposite relation between geographic knowledge is remarkably expressed, the hidden geoscience process phenomenon and correlation are achieved, and the reasoning optimization of the geoscience knowledge graph is achieved. Unstructured calculation or reasoning is changed into structured calculation or reasoning, and the difficult problem that many-to-many geoscience knowledge graph network structure problems cannot be solved in the field for a long time is solved.

Description

technical field [0001] The invention belongs to the technical field of geographic big data analysis, and in particular relates to a probabilistic hypergraph-driven geoscience knowledge graph reasoning optimization system and method. Background technique [0002] The development of artificial intelligence today can solve many problems, but there are also many problems that are difficult to understand: how to make machines truly understand human language is still not enough. Further planning the development path of machine learning has become a hot topic today. Machine learning is still only in computational intelligence and perceptual intelligence. How to make machines have cognitive ability, imitate people to recognize some things, and improve the cognitive ability of machine learning is a new topic. Knowledge graph is to fill the gap between human and machine. important method. [0003] A knowledge graph is a semantic network graph that describes various entities, or conc...

AI Technical Summary

Problems solved by technology

[0008] Aiming at the deficiencies of the prior art, the present invention proposes a probabilistic hypergraph-driven geoscience knowledge map reasoning optimization system and method, with the purpose of solving the existing application graph convolutional neural network technology, which cannot solve the many-to-many geoscience knowledge map network Structural problems, and the problem of not being able to define semantics for each geoscience knowledge map relationship

Images