Influence maximization data set processing method, device and system

The embodiment of the invention discloses an influence maximization data set processing method, which is applied to a cloud service platform, and comprises the steps of receiving to-be-analyzed socialdata subjected to homomorphic encryption, the to-be-analyzed social data comprising nodes formed by preference vectors used for representing set topic preferences of users; determining a weight valuebetween different nodes based on the preference vector, the weight value being used for representing mutual influence between the nodes; calculating a total inbound weight value of each node according to the weight value, and taking the node as a target node when determining that the total inbound weight value of the node is greater than a set threshold; and forming an influence maximization dataset according to the target node. The embodiment of the invention further discloses an influence maximization data set processing device and system. According to the embodiment of the invention, theencrypted to-be-analyzed dat