Method for evaluating threat of group to single target

Abstract

The invention discloses a threat assessment method for a group to a single target. The method comprises the following steps: S1, acquiring group information and target information; s2, constructing a dynamic Bayesian network by using the acquired information; s3, performing discretization processing on each node state in the constructed dynamic Bayesian network; s4, after discrete processing, determining a conditional probability table; s5, obtaining the probability distribution of the time slices according to the node states, the relationship between the nodes and the conditional probability table; s6, calculating a group threat level according to the probability distribution; s7, outputting a group threat level calculation result and the like. According to the invention, accurate and rapid threat assessment of a group to a single target is realized, and the granularity concerned by threat assessment is improved from a single platform to the group; the method overcomes the defects that the evaluation result is inaccurate when a part of parameters of a traditional algorithm are missing, continuous change in time is not considered, and the threat level judgment result fluctuates when the probability of different threat states is close in a Bayesian network method.

Description

technical field [0001] The present invention relates to the technical field of information fusion, and more specifically, relates to a threat assessment method for a group to a single target. Background technique [0002] Modern warfare presents a trend of fast pace and complexity, and the amount of information has increased massively, which has greatly increased the cognitive pressure of commanders. Groups have replaced individual platforms and become the initiators and bearers of threat events. There is an urgent need for real-time assessment of threats at the granularity of groups to support commanders in rapid battlefield perception, reduce cognitive pressure, and make quick and efficient decisions. [0003] The current typical threat assessment methods mainly include: fuzzy mathematics method, multi-attribute decision-making, evidence theory method, neural network method, Bayesian network method and so on. However, traditional algorithms still mainly focus on a single...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the deficiencies of the prior art, provide a method for group-to-single-target threat assessment, realize the accurate and fast threat assessment of a group to a single target, and raise the granularity of threat assessment from a single platform to a group, It overcomes the defects of inaccurate evaluation results when some parameters of the traditional algorithm are missing, does not consider the continuous change in time, and the defect of the Bayesian network method that the threat level judgment results fluctuate when the probabilities of different threat states are close

Images