Relation mining method and system based on graph structure data

Abstract

The invention discloses a relation mining method and system based on graph structure data, and the method comprises the steps: S1, obtaining and analyzing an image, and obtaining the graph structure data; S2, processing the graph structure data based on a task layer, and performing relationship reasoning on a graph structure to obtain sub-tasks; S3, completing interaction with the environment according to the sub-tasks to obtain corresponding rewards; S4, feeding back the corresponding rewards to the task layer; and S5, circulating the step S2-S4 until the sub-task with the maximum reward is completed. The system comprises an object and relationship detection module, a task layer module, an action layer module, a feedback module and a circulation module. According to the method, modeling is directly carried out, the relation between objects is utilized, and interpretation performance can be provided when the same performance is achieved. The relation mining method and system based on graph structure data can be widely applied to the field of reinforcement learning.

Description

technical field [0001] The invention belongs to the field of reinforcement learning, and in particular relates to a method and system for mining relationships based on graph structure data. Background technique [0002] Most of the existing deep reinforcement learning application scenarios are similar to unstructured data such as images. With the help of the nonlinear fitting ability of the neural network, a policy from the observed state to the action is learned. It is difficult to apply in high-level fields such as autonomous driving. In addition, the implicit relationship between objects learned by neural networks cannot be intuitively understood by humans. Contents of the invention [0003] In order to solve the above-mentioned technical problems, the object of the present invention is to provide a method and system for relational mining based on graph-structured data, using structured expression to model the relationship of objects, and using deep learning to propagat...

AI Technical Summary

Problems solved by technology

[0002] Most of the existing deep reinforcement learning application scenarios are similar to unstructured data such as images. With the help of the nonlinear fitting ability of the neural network, a strategy from the observed state to the action is learned. It is difficult to apply in high-level fields such as automatic driving. In addition, the implicit relationship between objects learned by the neural network cannot be intuitively understood by humans.

Images