Entity relationship prediction method and prediction system based on knowledge representation learning

Abstract

The invention discloses an entity relationship prediction method and a prediction system based on knowledge representation learning. The method comprises four modules, namely, knowledge preparation, knowledge representation model construction, knowledge representation model training and entity relationship prediction. The knowledge preparation module completes the data preparation and builds the knowledge map. The knowledge representation model construction module completes the construction of the model, which eliminates the semantic differences among different types of entities through projection operation; the training module of knowledge representation model forms the final knowledge representation model based on the parameters of the iterative training knowledge representation model ofknowledge map. Entity relationship prediction module can predict the possible relationship between any given two entities. The method of the invention predicts entity relationship based on knowledgemap, projects different types of entities to the same semantic space through a spatial projection algorithm, and performs calculation operation, thereby achieving high reliability of prediction results.

Description

technical field [0001] The invention belongs to the field of relationship prediction between entities, and relates to an entity relationship prediction method and a prediction system based on knowledge graphs and machine learning. Background technique [0002] In the future network environment, battlefield information and various intelligence information are widely distributed, with fragmented and fragmented distribution characteristics, and intelligence information is often hidden in scattered fragmented information. In the fast-paced war environment in the future, the information service system must be able to discover the hidden relationship between information from scattered information, quickly extract valuable information, and quickly provide commanders with high-quality information support. [0003] At present, most scholars' research directions on entity relationship mainly focus on entity relationship extraction and entity relationship reasoning. The research on en...

AI Technical Summary

Problems solved by technology

[0006] The matching technology used in the existing knowledge map-based retrieval technology can only search for existing relationships, but cannot dig out the relationships hidden in the data. Sometimes due to the limitations of data collection, the latter data loss, etc., will cause knowledge map It is incomplete, but using the technology of knowledge representation learning to predict the relationship can solve this problem very well. Given any two entities, the possible relationship between the two can be predicted, and the order of the relationship can be calculated according to the knowledge representation vector , sorted by possibility, to provide references and suggestions for commanders or intelligence analysts

Images