基于多属性可能性网络的目标行为意图识别

Target Behavior Intention Recognition Based on Multi-attribute Possibility Network

针对海面目标行为意图识别存在耗时长和准确性低的问题,提出基于知识图谱和可能性网络结合的行为意图识别方法。首先,构建关于行为意图要素的知识图谱,利用知识图谱判断行为意图的多属性因素类型;然后,借助信息熵权为目标不同属性客观地分配权值,利用可能性网络模型给出条件可能性分布;最后依据推理定理进行行为意图的识别。实验结果证明,该方法对于行为意图识别具有有效性和实时性。

Aiming at the problems of time-consuming and low accuracy in behavior intention recognition of sea targets,a behavior intention recognition method based on knowledge graph and possibility network was proposed.Firstly,a knowledge map of behavioral intention elements was constructed to determine the types of multi-attribute factors of behavioral intention.Secondly,the information entropy weight was used as the objective weight of different attributes,and the conditional probability distribution is given by the possibility network model.Finally,the behavior intention was identified according to the inference theorem.Experimental results showed that the proposed method was effective and real-time for behavior intention recognition.