Knowledge graph visualization method based on semantic attention model

Abstract

The invention discloses a knowledge graph visualization method based on a semantic attention model, and provides a knowledge visualization solution by combining multi-level multi-angle knowledge semantic similarity distance measurement with a user semantic attention model so as to support a visualization method of a global+local structure. According to the method, a semantic attention model between knowledge objects in a knowledge space is established, and the semantic attention between a focus object and the knowledge objects in the knowledge space is calculated; and visually displaying the knowledge graph according to the semantic attention. According to the invention, complex battlefield situation big data is analyzed and processed; the information objects with relatively short semanticdistances are highlighted and actively presented to the user; the big data knowledge graph retrieval method and system are beneficial to intelligently assisting a user in retrieving complex big dataknowledge, so that the user can see local details of an interested object and keep the overall impression of surrounding information, and good visual support is provided for big data knowledge graph retrieval application.

Description

technical field [0001] The invention belongs to the technical field of big data knowledge visualization, and more specifically, relates to a method for visualizing a knowledge graph based on a semantic attention model. Background technique [0002] The inherent characteristics of big data knowledge with spatio-temporal attributes in an open and dynamic environment presents multi-angle and multi-level complexity in terms of time, space and attributes. Moreover, its knowledge data is huge in scale and complex in data structure. How to highlight knowledge entities with close semantic distance to users in the knowledge retrieval visual interface and assist users in their cognition of knowledge has become a key issue. At the same time, when users zoom in on the details of recommended results on a limited screen during knowledge retrieval, they often lose global information. [0003] Researchers at home and abroad have designed some data visualization models, but they have not pr...

AI Technical Summary

Problems solved by technology

[0004] In view of the above defects or improvement needs of the prior art, the present invention provides a knowledge map visualization method based on the semantic attention model, which aims to establish a semantic attention model and visualize it by combining the multi-level and multi-angle knowledge similarity calculation method Display, thus solving the technical problem in the prior art that it is impossible to reasonably display the local structure information and global structure that the user cares about at multiple levels and from multiple angles

Images