The invention discloses a data processing method and device, and aims at improving the data processing efficiency. The data processing method comprises the following steps of: receiving data information sent by at least one second processing node by a first processing node, wherein the data information comprises a first data set and index information corresponding to the first data set, and the index information is used for representing public feature vectors of to-be-processed data in the first data set; searching at least one second data set different from the index information from a data set library of the first processing node according to the index information in the data information; and clustering the first data set and the at least one second data set into one data set when the fact that the first data set and the at least one second data set comprise at least one same to-be-processed data is determined.