<p>Motivated by the limited computing and storage resources of smart devices (SDs), existing resource management schemes under the traditional mobile edge computing (MEC) system couldn’t fully utilize the network resources. This article proposes a novel relay-assisted MEC architecture to provision SDs, where an idle relay device assumes the dual role of providing fee-based communication and computing services. At the same time, tasks generated by applications exhibit three distinct processing modes: local execution, relay offloading, and edge computing. To minimize the execution cost associated with communication and computing services from the user’s perspective, joint computation offloading, relay selection strategy, computation resource allocation, and spectrum resource allocation (JORA) problem is formulated, which is a non-convex problem. Subsequently, a two-stage iterative algorithm is designed to solve the JORA problem using block coordinate descent, reconstruction linearization technology, and convex optimization methods. Simulation results show the effectiveness of the proposed JORA algorithm, which can significantly save the execution cost for edge users.</p>