With the rapid development of urban power grids, the demand for efficient and reliable cable line wiring is growing. Traditional cable line wiring methods often face problems such as high cost, long construction period and difficulty in adapting to complex terrain. To solve these problems, this paper designs an optimal cable line path design system based on artificial intelligence. The system first uses geographic information data and power grid demand data to establish a multi-objective optimization model. Then, artificial intelligence algorithms such as genetic algorithm and particle swarm optimization algorithm are applied to solve the model to obtain the optimal cable line wiring solution. The experimental results show that the hybrid intelligent algorithm can further shorten the path length to 10.2 km, the shortest in the experiment. It also performs well in satisfying the constraints and fully meets all the constraints. The construction cost is reduced to 6.8 million yuan, the lowest among the three groups. In terms of safety risk and environmental impact index, it is 12% and 15% lower than that of other experimental groups, respectively. This fully demonstrates the advantage of the hybrid intelligent algorithm in that it can comprehensively consider multiple factors, while optimizing the path length and cost, and minimizing the safety risks and environmental impacts.