Aiming at the problem of data classification in enterprise cloud data, this article proposes a data classifier based on Particle Swarm Optimisation and Kernel Function Extreme Learning Machine (PSO-KELM) is proposed. PSO is utilised to get optimal parameters and the parameters of KELM are obtained accurately, which improves the accuracy of data classification. Through the cloud data test and a comparison with Kernel Function Extreme Learning Machine (KELM), Kernel Function Support Vector Machine (KSVM) and Semi-Supervised and Transfer Learning (SSTL), the better classification effect is obtained. Moreover, this article proposes an effective method for data classification.