A Deep Learning-Based Knowledge Graph Framework for Intelligent Management Scheduling Decision of Enterprises

Due to the huge magnitude expansion of data volume, the application of cloud computing and the Internet of Things is growing year by year. However, more and more industrial production requires real-time and efficient handling of resource scheduling. Therefore, this paper develops a deep learning-based knowledge graph framework for resource scheduling decision of enterprise. Single-objective and multi-objective problems for computing resources are studied, and the network nodes of computing resources are set with the help of network topology theory. For the single-objective problem, the mathematical model is constructed with the optimization objective of minimizing the time delay. For the multi-objective problem, the mathematical model is constructed with the optimization objectives of minimizing both time delay and energy consumption. Combining the historical scheduling scheme with the introduction of a genetic algorithm, an initial optimization method is proposed for the scheduling problem of mixed flow shop, and the optimization problem is solved to minimize the maximum completion time. The simulation experiments are conducted to evaluate the proposed method, and the obtained results show that the proposal can well realize intelligent management scheduling decision for enterprises.