“…As shown in Figure 3, the network graph G aa � (A ∪ A, β aa ) between prediction regions represents the distance relationship of each region, where A represents the region to be predicted, β aa represents the set of edges e ij between any two regions, and the weight w ij represents the distance between the two areas. On the right side of Figure 4, the network graph G ap � (A ∪ P, β ap ) between the area and the POIs represents the distribution of POIs in the prediction area, where P represents the collection of POI categories, and the categories p 1 ∼p 10 are, respectively, expressed as transportation spots, factories, parks, stores, eating and drinking establishments, stadiums, schools, real estate, entertainment establishments, and other establishments [9]. β ap represents the set of edges e ij between the region and the POI category, and its weight w ij represents the number of POIs containing category p j in the prediction area i. e network graph G ar � (A ∪ R, β ar ) between the area and the road network in the left part of the figure represents the distribution of road segments in the prediction area, where R represents the set of road segment categories, β ar represents the set of edges e ij between the region and the road segment categories, and its weight w ij represents the total length of the roads of category r j included in the prediction area i.…”