This paper designs and studies the implementation framework of a recommendation meta-heuristic algorithm based on the multi-label k-nearest neighbor(ML-kNN). The multi-label k-nearest neighbor classification learning technology is applied to implement the best meta-heuristic algorithm ranking recommendation. In order to verify the effect, the multi-modal resource-constrained project scheduling problem(MRCPSP) is taken as the optimization object, and hundreds of examples of different scales are selected to extract landmarking features and problem basic features respectively; five meta-heuristic algorithms(genetics, particle swarm, tabu search, bee colony and ant colonies) are selected; the ML-kNN is applied to establish a meta-recommendation model; and the Hamming loss, single error rate, coverage rate, ranking loss and average accuracy rate are used to analyze and evaluate the recommendation effect. The experimental results show that the meta-heuristic algorithm based on ML-kNN recommendation is effective, among which, the single error rate of the ML-kNN based on landmarking features is 18.4%, and the average precision is 88.9%. The ML-kNN had been acquired the better recommendation effect in relative with the single label kNN. In addition, the ML-kNN method is able to achieve the ranking recommendations for all alternative algorithms. The research conclusions are expected to be extended to other combinatorial optimization algorithms.