Method and device for evaluating threat degree of low, small and slow target

• Main Authors: CHEN YI, LI DONGCHEN, LI FEITAO, MO QIAOBO, CHU JUNBO, ZHAO RUIXIN, LI RENWEI, HU SHAOGANG, CHEN WEIDONG, LI YIJIE, RAN HUANHUAN, DONG PINGKAI, YANG WEI, LI HELUN, LIU YIAN, WANG DAN, CHEN CHUN
• Format: Patent
• Language: Chinese; English
• Published: 31.01.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention discloses a low, small and slow target threat degree assessment method and device. The method comprises the following steps: constructing a recurrent neural network model; constructing a feature matrix, taking the feature matrix as the input of a recurrent neural network model, and generating the feature matrix according to the target flight information collected in the time sequence; acquiring target flight information collected in a plurality of continuous historical time sequences, generating feature matrixes in one-to-one correspondence according to the target flight information, and combining all the feature matrixes into a training sample; performing training and parameter optimization on the recurrent neural network model; target flight information collected in a plurality of continuous real-time time sequences is obtained, feature matrixes are generated in a one-to-one correspondence mode according to the target flight information, all the feature matrixes are input into the trained recu