China’s express delivery industry has boomed in recent years, with the number of new parcels added each year now exceeding half of the overall U.S. express delivery volume, reaching 100 billion. China has established the most powerful and advanced express logistics system in the world. In the parcel packing process, the selection of appropriate packaging consumables is crucial, because the large scale of parcel quantity reduces the cost of each parcel consumable and brings great economic benefits. In the study, data preprocessing was first carried out to eliminate goods that were too large to be packed. Then, the problem was identified as 0–1 nonlinear integer programming, and the constrained planning problem was transformed into an unconstrained problem by means of an objective function, constraints, and introduction of weights to optimise the planning using a genetic algorithm. However, testing revealed that the genetic algorithm is prone to falling into local optimum, so a hybrid heuristic algorithm is used for the final optimisation, which is combined with a simulated annealing algorithm to avoid falling into local optimum. In Matlab programming, the algorithm is programmed for goods based on order grouping. In dealing with the cargo placement problem, two placement rules are provided for boxes and bags. For the size optimisation problem, the optimal solution for each covariate is computed and used as a replacement set for nonlinear programming.