The embodiment of the invention provides an energy Internet user electricity consumption prediction method. The method comprises the following steps of dividing user electricity consumption data to bepredicted into multiple target data blocks to be predicted; obtaining the correlation coefficient and the amplitude ratio between the target data block to be predicted corresponding to each time period and the plurality of reference target data blocks based on a prediction model corresponding to each time period after training; and carrying out weighted average on the reference target data blockwhose correlation coefficient is greater than a first preset threshold and an amplitude ratio is less than a second preset threshold, and taking the result of weighted average as the prediction resultof the target data block to be predicted. By using the energy Internet user electricity consumption prediction method and system, through the correlation coefficient and the amplitude ratio among autoregressive estimation sequence blocks, estimation matching and the weighted average are combined so as to realize accurate multi-point simultaneous electricity consumption prediction.