Method and device for optimizing action scheme in simulated training system

Abstract

The invention discloses an action scheme optimization method and device in a simulation training system, aiming at training requirements, activities in training are divided into action units in stages, the action units are adopted to construct a desired action scheme, and for each action scheme, the action scheme is optimized. Constructing an efficiency model corresponding to the action scheme by taking each action unit and the action result in the action scheme as an efficiency unit, mapping the efficiency model into a Bayesian network, performing parameter learning on the Bayesian network, taking parameters corresponding to Bayesian network nodes obtained by learning as probabilities of the efficiency units, and calculating the efficiency of the action scheme according to the probabilities of the efficiency units. And selecting the action scheme meeting the condition or adjusting the action scheme. According to the method, the uncertainty in the action scheme and the complexity of the dependency relationship between the actions are well processed, and optimization and optimization of the scheme are realized through multi-dimensional evaluation, so that reasoning decision is supported.

Description

technical field [0001] The application belongs to the technical field of training optimization, and in particular relates to a method and device for optimizing an action plan in a simulation training system. Background technique [0002] The simulation training system is used for equipment operation training and cooperative command training. It is a comprehensive training evaluation for training personnel on duty to familiarize themselves with business processes, command coordination relationships, system platform operation proficiency, emergency response strategies, equipment and system failure analysis and elimination, etc. Process, a comprehensive, reasonable and effective assessment will help to improve the trainee's operational level and efficiency. [0003] Evaluation methods commonly used in prior art solutions mainly include methods such as index method, analytic hierarchy process, and ADC method. The index method can avoid the influence of a large number of uncerta...

AI Technical Summary

Problems solved by technology

[0005] 1. The establishment of the index system in the training evaluation system is often based on the subjective consciousness of experts or evaluators, and is not guided by training goals. Index construction is carried out on the basis of fully considering training needs

[0006] 2. The methods of task decomposition and entity abstraction are often used between the actions and nodes of training and evaluation elements, without considering the complex dependencies between actions

[0007] 3. There are many and complex evaluation elements in the training evaluation system, and it is difficult to form a unified evaluation standard and process to achieve comprehensive and effective evaluation

[0008] 4. The dimensions of the training results are relatively single, and it is impossible to intuitively judge the degree of influence of each element in the plan, and further configure the plan reasonably to improve performance

Images