The increasing dependence of electrical power system and natural gas system in the energy Internet makes the integrated energy system provide higher requirements for load forecasting of different energy systems. In this paper, a combined load forecasting method for electricity and gas based on long-short term memory network and weight sharing is proposed. In the prediction model, firstly, the correlation coefficient is used to analyze the weather factors, and the important weather factors of the energy loads are extracted. The long-short term memory network is used as the main forecasting algorithm, and the weight sharing mode is used to analyze the correlation between the two loads. The results show that the algorithm in this paper can effectively improve the accuracy of electrical power load and natural gas load forecasting in the integrated energy system, which has promotion for application.