Study on the method of multi-agent generation algorithm within special artificial society scene

Multi-agent generation within a special scene is a basic problem for the research on artificial society. In the context of public health emergency, the multi-agent model of an artificial campus is built; based on the deep analysis of the problem, we consider that a special scene in artificial society is approximate to a polygon determined by some key points (border points). Therefore the problem of multi-agent generation is converted to inner-point generation in the polygon. The grid-based method is proposed to divide the scene polygon reasonably consistent to the density. The filtering mechanism of grids generated is proposed. Finally, the experiment shows that the method could be used to generate some agents with some properties in a special scene randomly, and has certain reference value.