An Event Paths Optimization Method Based on Knowledge Graph of Military News
The event path analysis based on the event graph is an important means to assist decision-making.In the existing important event path optimization methods,the design of the evaluation index of the event path value is relatively simple,and most of them only take the output of the shortest path as the goal of path optimization.In order to more fully reflect the importance information of the event path,this paper proposes a new path value evaluation function based on three aspects:node importance,path scarcity and relationship edge score to enrich the event path value evaluation method.At the same time,in order to solve the problem of single application scenario and low search efficiency of the classical path search algorithm,a deviated path algorithm was designed based on the Dijkstra algo-rithm,which aims to meet different scenarios of path optimization and improve the search efficiency.Finally,a custom map of international military news affairs was used as a data set to conduct experiments.The results show that the search algorithm can reach the same level as the classic path search algorithm in terms of running memory usage,and the search speed has been improved.The importance of output The path meets the preset requirements.
NETL
NSTL
万方数据
