In order to solve the fast pairing and power allocation problem of Non-Orthogonal Multiple Access (NOMA) under imperfect serial interference cancellation conditions. The paper proposes a deep reinforcement learning-based user pairing and power optimization scheme for NOMA. First, the paper considers the scenario of imperfect Serial Interference Cancellation (SIC) for multiuser NOMA, and constructs an optimization problem to maximize the system reachable communication rate with user pairing and user transmit power allocation factor as optimization variables. The condition of user pairing using NOMA under the imperfect SIC condition is analyzed, and the user power allocation for the maximum reachable rate under this condition is introduced. Second, the user pairing problem is treated as a combinatorial optimization problem, and a novel user pairing scheme is designed based on the real-time requirement using an improved pointer network. Simulation results show that this scheme can effectively improve the reachable rate of the NOMA system to 99.8% of the optimal exhaustive search algorithm, and has the advantages of real-time and adapting to the dynamic change of the number of users.