Mobile edge computing (MEC) is an efficient technology that enables end users to achieve the goal of high bandwidth and low latency by offloading computationally intensive tasks from mobile devices to edge servers. Computing offloading in the mobile edge computing environment plays an important role in reducing user load and enhancing terminal computing capabilities. This study considers service caching, and proposes a cloud-side-end collaborative computing offloading framework, in which D2D communication and opportunistic networks are introduced. Based on the established model, the offloading decision problem is transformed into a mixed integer nonlinear programming problem, and an iterative mechanism is formulated for the non-cooperative game interaction between wireless characteristics and mobile users to jointly determine the computational offloading plan. The proposed computational offloading algorithm theoretically proves that the multi-user computational offloading game under this framework is an exact potential game (EPG), and the offloading decision is to uninstall under the optimal benefit strategy in the entire network. Taking into account the computing resources of the server, the amount of data for offloading tasks, and the delay requirements of tasks, based on the Gale-Shapley matching theory, the best user association matching algorithm is improved and proposed. Finally, the simulation results show that the proposed unloading decision algorithm has a faster convergence rate and is superior to other benchmark algorithms in terms of energy efficiency.