Knowledge map optimal path query system and method based on depth reinforcement learning

Abstract

The invention provides a knowledge map optimal path inquiry method based on depth reinforcement learning, includes two modules, module 1 and module 2, the first module is an offline training module ofthe knowledge map optimal path model, the second module is the on-line application module of the knowledge map optimal path model, the knowledge map optimal path model offline training module is provided with a depth reinforcement learning component, to present the entity carries on the depth intensification training study, so that that next entity is obtain, as the following entity repeats the train learning of the current entity, so that the optimal path model is obtained.The invention adds the generalization ability of the model and improves the calculation accuracy. The logic structure ofthe invention is clear and the calculation mode is flexible. Especially, the reinforcement learning and the depth learning can be distributed and the operation efficiency is improved.

Description

technical field [0001] The present invention relates to the field of computers, in particular to a knowledge map optimal path query system and method based on deep reinforcement learning. Background technique [0002] Knowledge Graph aims to describe and describe various entities (Entity) and the relationship between entities (Relation) in the real world. It is usually organized and represented by a directed graph, and the nodes in the graph represent entities, while An edge is composed of a relationship, which is used to connect two entities and describe whether they have the relationship described by the relationship; if there is an edge between the two entities, it means that there is a relationship between them, otherwise it means that there is no relationship . In practical applications, a value between 0 and 1 is added to each entity relationship in the knowledge graph (that is, each edge of the graph), reflecting the degree of association between entities; according ...

AI Technical Summary

Problems solved by technology

These techniques meet the requirements in terms of query efficiency. However, since some intermediate points are discarded by pruning, the query accuracy is reduced, and if the pruning is not done properly, the query may not be able to find the shortest path. If pruning between two points Too few branches, easy to degenerate into breadth-first search, low time efficiency and poor scalability

It is difficult to achieve a balance between time and space in the shortest path of the precise query probability knowledge map, and it is difficult to ensure that the query time meets the user's requirements and the query quality is also guaranteed

Images