Distributed big data processing method

The invention provides a distributed big data processing method, and relates to the technical field of data processing. Nodes in a hypercube data model are divided into two sub-hypercubes, data in each sub-hypercube is processed, and along with variation of the scale n, the time complexity of a hypercube model distributed algorithm is obviously lower than that of a timestamp distributed algorithm and a DFS (depth-first-search) minimum spanning tree distributed algorithm. When n is greater than k, the efficiency of the hypercube model distributed algorithm is obviously higher than that of the timestamp distributed algorithm and the DFS minimum spanning tree distributed algorithm. 本发明提供了种分布式大数据处理方法，涉及数据处理技术领域。将超立方体数据模型中的节点划分为两个子超立方体，然后分别对每个子超立方体中的数据进行处理，随着规模n的变化，超立方体模型分布式算法的时间复杂度明显低于时戳分布式算法和DFS最小生成树分布式算法的时间复杂度。当n>k时，超立方体模型分布式算法的效率明显高于时戳分布式算法和DFS最小生成树分布式算法的效率。