In recent years, significant breakthroughs have been made in the exploration and development of shale oil resources in China, and shale oil resources have become a key area of petroleum exploration and development in China. However, the matrix pores of terrestrial shale oil reservoirs are dense and the permeability is extremely low. At the same time, due to multiple factors such as strong heterogeneity of the reservoir, low and rapid decline in single well production, the scale and efficiency development of shale oil is difficult and faces significant challenges. Among them, how to effectively improve the optimization and deployment level and quality of horizontal well positions is the most important step to achieve cost reduction and efficiency increase. The conventional optimization of horizontal well positions requires manual operation of reservoir numerical simulation software, repeated production process simulation and dynamic analysis of multiple schemes, which is not only time-consuming, but also limited to selecting from a limited number of schemes. This paper relies on a genetic intelligence optimization algorithm based on heuristic learning, with net present value as the objective function, to quickly and automatically select solutions from a large number of development plans, achieving intelligent simulation calculation and analysis optimization throughout the entire process. The results show that this method has excellent optimization ability, can quickly determine the optimal horizontal well position, form the initial plan for optimal multi well deployment, reduce computational costs by more than 80%, and provide preliminary exploration for the scale benefit development of shale oil.