Knowledge graph information processing method and device, equipment, and storage medium

Abstract

The embodiment of the application provides an information processing method and device for a knowledge graph, equipment and a storage medium, and relates to the technical field of knowledge graphs andmachine learning. The method comprises the following steps: obtaining knowledge graphs corresponding to a plurality of map learning tasks respectively; performing dimension extension processing on the vector representation of a historical entity and the vector representation of a historical relationship appearing in the first k-1 graph learning tasks; determining initial vector representation ofa newly added entity and initial vector representation of a newly added relationship in the kth knowledge graph; in the process of executing the kth learning task, adjusting the initial vector representation of the target entity and the initial vector representation of the target relationship; and performing dimension compression processing on the learned vector representation of the target entityand the learned vector representation of the target relationship to obtain the vector representation of the target entity and the vector representation of the target relationship. According to the technical scheme provided by the embodiment of the application, the accuracy of knowledge graph learning can be improved.

Description

technical field [0001] The embodiments of the present application relate to the technical fields of knowledge graph and machine learning, and in particular, to an information processing method, device, device, and storage medium of a knowledge graph. Background technique [0002] As the overall knowledge of human beings continues to increase, it is necessary to frequently add the increased knowledge to the existing old knowledge graph, thereby continuously updating the knowledge graph. [0003] In related technologies, the knowledge map includes entities and relationships, and the old parameters of the learning model based on the knowledge map enable continuous learning of the knowledge map, reducing the change of old parameters that have a greater impact on old data samples, thereby reducing the disaster of the knowledge map during learning Probability of permanently forgetting old data. [0004] In the above techniques, when the number of new entities and new relations in...

AI Technical Summary

Problems solved by technology

[0004] In the above techniques, when the number of new entities and new relations in the knowledge graph increases substantially, the size of the feature space of the learning model is limited, making the learning accuracy of the knowledge graph lower

Images