RPA operation workflow redundancy scheduling method and system based on deep reinforcement learning

The invention provides an RPA work workflow redundancy scheduling method and system based on deep reinforcement learning, and the method comprises the steps: S1, drawing an RPA work workflow, obtaining the execution data of each RPA work through the RPA work workflow, and converting the execution data into work features; s2, acquiring resource fluctuation and hardware information of a corresponding machine through an RPA actuator, and converting the resource fluctuation and the hardware information into resource characteristics of a cluster machine; and S3, constructing a deep reinforcement learning agent, constructing an input state of the agent through the job features and the resource features, performing training optimization on the agent according to a reward function, and outputting a redundancy scheduling strategy. According to the invention, a multi-objective optimization scheduling strategy oriented to the success rate, the resource overhead and the execution time can be formulated according to the o