兵棋推演空中任务智能预测方法研究

对战场敌空中目标作战任务进行高效、准确地自动判断，是态势认知的基础和辅助作战资源分配的关键。结合前馈深度神经网络和长短时记忆网络模型计算特点，设计了2个针对性基指标学习器，然后根据基指标交叉熵进行加权组合，用于进一步学习器训练评价指标，既能有效防止模型过拟合，又能提高模型训练效率。测试结果表明，所提模型能较好防止模型过拟合，并能以较高的准确率判断战场敌目标作战任务。

Research on Intelligent Prediction Method of Wargaming Air Mission

The efficient, accurate and automatic judgment of the combat mission or intention of the enemy's air targets in the battlefield is the basis of situation awareness and the key to the allocation of auxiliary combat resources. Combined with the calculation characteristics of feed forward deep neural network and long-term and short-term memory network model, two targeted basic index learners are designed, and then the weighted combination is carried out according to the cross entropy of the basic index, which can be used to further train the evaluation index of the learner. It can not only effectively prevent the model from over fitting, but also improve the efficiency of model training. The test results show that the proposed model can prevent the over fitting of the model and judge the combat mission or intention of the enemy target with high accuracy.