In today’s rapidly evolving society, information technology is transforming into a new driving force for solving specific problems. As artificial intelligence and big data technologies mature, they significantly impact modern industrial development. This study addresses issues in the basic ant colony algorithm, such as overlooking better solutions and excessive runtime, by designing a novel hybrid optimization ant colony algorithm. By incorporating the substitution strategy from the tabu algorithm, adding an elite ant local search process, and integrating aspects of genetic algorithms, this hybrid approach effectively extends the basic ant colony algorithm. It largely avoids premature convergence and enhances algorithm efficiency. Matlab simulations demonstrate the hybrid ant colony algorithm’s advantages in various aspects of the solution process through data tables and iterative graphs. This research into artificial intelligence algorithms is expected to positively impact industrial production, potentially reducing resource waste and promoting social progress.