The problem of error accumulation is caused by the supervision of deep neural network text generation model. In order to solve this problem, a text generation model based on the reinforcement of antagonistic thought training is proposed.The adversarial network can be generated by the proposed model, and then the adversarial network can be used for identification, the learning reward function can be optimized, and the generated model can be optimized to reduce the probability of error accumulation.More text structure knowledge can be added into the generated text model by integrating the target guidance feature into the actual generation process to make the generated text model have higher authenticity. In this paper, the author optimizes the adversarial text generation method on the basis of target-guided optimization, which can be used for reference by practitioners.

Energy Internet (EI) can provide consumers with flexible energy-sharing services. Recently, artificial intelligence (AI) technology has been widely used in the field of EI. Generative adversarial network (GAN) is one of the hottest research directions in the field of AI in recent years, and its excellent data generation ability has attracted wide attention. First, this paper introduces the framework, advantages, disadvantages, and improvement of classic GAN. Then, the application of GAN in the field of EI is reviewed. Finally, the paper is summarized, and the possible application of GAN in EI is prospected.