Simulation system and simulation method

Abstract

A simulation system and a simulation method are provided. The simulation system includes: a user interface module configured to receive an external input; a control module configured to control a behavior described in a preset simulation logic program based on the external input, wherein in the preset simulation logic program, the state in a simulated item and the behavior of driving the state change are described in a code form, when the external input includes a learnable parameter, the control module acquires an optimization value of the learnable parameter from an optimization module, andperforms a step of controlling the behavior described in the preset simulation logic program based on the external input by taking the optimization value as a value of the learnable parameter; a simulation module configured to run the preset simulation logic program in response to the control of the control module; and an optimization module configured to perform optimization learning on the valueof the learnable parameter based on the simulation result data output by the simulation module.

Description

technical field [0001] The present invention generally relates to the field of artificial intelligence, and more specifically, relates to a data-driven simulation system and simulation method. Background technique [0002] Simulation (or simulation) is the approximation or imitation of how a process or system works. A simulator is software that emulates the operation of a process or system over time. The simulator needs to extract the key states involved in the operation of the system, and use the program to simulate the changes of these states (which can be called the behavior of the system). The emulator can be used for system simulation, analysis, tuning, testing, teaching, etc., and has a wide range of applications. [0003] Traditional simulators abstract system behavior into mathematical formulas or solutions to mathematical problems through domain knowledge, and at the same time determine the parameters involved in mathematical formulas or problems, and further conv...

AI Technical Summary

Problems solved by technology

For example, in the supply chain scenario, it is necessary to simulate the order arrival behavior, but the order arrival is the result of the interaction of multiple factors, the process is too complicated, and it is difficult to abstract it into simple rules

2. Lack of domain knowledge about parameters

Therefore, under the premise of a given level of abstraction, traditional simulators cannot use useful data available in reality, and the accuracy (the ability to reflect the real system) is limited by the accuracy and completeness of domain knowledge

Images