In a large-scale data environment, information systems face many challenges such as complex resource distribution, frequent task requests, and high real-time response requirements, and traditional scheduling algorithms are difficult to meet the system's needs in terms of efficiency, scalability, and intelligence. This paper focuses on the intelligent scheduling and optimization of information systems in the context of big data, systematically analyzes the shortcomings of current scheduling techniques in resource allocation, multi-objective optimization and dynamic environment adaptability, and proposes a scheduling model integrating artificial intelligence and mathematical optimization methods. By introducing intelligent algorithms such as reinforcement learning and evolutionary computation, and combining the multi-objective optimization strategy and dynamic adjustment mechanism, a set of information system scheduling optimization framework applicable to heterogeneous resource environment is constructed. Experimental validation shows that the proposed method outperforms traditional schemes in terms of resource utilization, task response time and system stability, and has good generalization ability and engineering practical value. This study provides theoretical support and practical path for improving the scheduling efficiency and intelligence of information systems in large-scale data processing.
Jiahui Yu (Sun,) studied this question.