Search

JP-2026075047-A - Multi-agent process simulation

JP2026075047AJP 2026075047 AJP2026075047 AJP 2026075047AJP-2026075047-A

Abstract

[Problem] To provide a method for using a multi-agent system for process simulation. [Solution] The method uses historical process data to train multiple software agents, each representing a single task in the process, simulates the process by running a multi-agent system based on the candidate process model, and generates simulation results. The software agents operate autonomously within the multi-agent system based on their trained behavior. The method also uses a runtime configuration based on the candidate process model to generate runtime results for comparison with the simulation results, adjusts the candidate process model based on the comparison, and repeats the process simulation and execution using the adjusted multi-agent system and adjusted runtime configuration to generate an expanded process model. [Selection Diagram] Figure 5

Inventors

  • アンドレアス・ゲルバー

Assignees

  • エスアーペー エスエー

Dates

Publication Date
20260507
Application Date
20250903
Priority Date
20241021

Claims (20)

  1. A computer implementation method that is performed by a computer system comprising memory and at least one hardware processor, wherein the computer implementation method is A step of training multiple software agents using historical process data, wherein each of the multiple software agents represents a single task in the process; A step of simulating the process by running a multi-agent system and generating simulation results, wherein in the multi-agent system, the plurality of software agents are configured according to a candidate process model for the process and operate autonomously based on the training; The steps include: executing the process using the runtime configuration based on the candidate process model to generate runtime results for comparison with the simulation results; The steps include adjusting the candidate process model based on the above comparison, The steps include repeating the simulation of the process using a tuned multi-agent system corresponding to the tuned candidate process model, The steps include repeating the execution of the process using a modified runtime configuration corresponding to the modified candidate process model, A computer implementation method comprising the step of generating an expanded process model for the process based on the adjusted candidate process model.
  2. One of the aforementioned software agents comprises a machine learning model, and the training of the software agent is The computer implementation method according to claim 1, comprising the step of training the machine learning model on at least a subset of the historical process data relating to the single task represented by the software agent.
  3. The machine learning model comprises a finely tuned language model, and the training of the software agent is Steps to access a pre-trained language model, The steps include generating a fine-tuned language model by fine-tuning the pre-trained language model in the historical process data related to the single task, The computer implementation method according to claim 2, further comprising the step of generating a one-to-one mapping between the finely tuned language model and the single task represented by the software agent.
  4. The computer implementation method according to claim 2, wherein each of the plurality of software agents comprises a machine learning model trained on a subset of the historical process data related to its respective single task.
  5. The computer implementation method according to claim 1, further comprising the step of generating a one-to-one mapping between each of the plurality of software agents and the single task represented by the software agent, wherein the plurality of software agents correspond to a plurality of tasks defined by the candidate process model.
  6. The simulation of the process includes the step of performing a test simulation to test the candidate process model, and the training of the plurality of software agents is The steps include: using the plurality of software agents to perform a baseline simulation to generate baseline results for a baseline process model associated with the historical process data; The computer implementation method according to claim 1, further comprising the step of performing at least one of tuning or retraining at least a subset of the plurality of software agents based on the baseline results and the historical process data.
  7. The simulation of the process includes the step of performing a test simulation to test the candidate process model, and the computer implementation method is The steps include: using the plurality of software agents to perform a baseline simulation to generate baseline results for a baseline process model associated with the historical process data; The steps include: generating first performance data by comparing the baseline results with the simulation results; A step of automatically triggering the generation of the runtime configuration for the execution of the process based on the first performance data, The computer implementation method according to claim 1, further comprising the step of generating second performance data by comparing the runtime results with the simulation results in order to enable the adjustment of the candidate process model.
  8. A computer implementation method according to claim 1, further comprising the step of generating the runtime configuration by automatically configuring a robotic process automation (RPA) bot for the execution of the process, wherein the process is automatically executed by the RPA bot to generate the runtime result.
  9. Based on the above comparison, the steps include automatically triggering the retraining of at least a subset of the multiple software agents, The computer implementation method according to claim 1, further comprising the step of automatically repeating the simulation of the process after retraining at least the subset of the plurality of software agents.
  10. The computer implementation method according to claim 1, wherein the simulation of the process includes a step of automatically running the multi-agent system until the multi-agent system reaches equilibrium, and after the multi-agent system reaches equilibrium, the simulation results are generated.
  11. The computer implementation method according to claim 10, wherein the simulation of the process includes a step of automatically introducing an error into the process before the generation of the simulation results.
  12. The steps of automatically repeating the adjustment of the candidate process model, the simulation of the process, and the execution of the process until the simulation result is detected to satisfy at least one predetermined condition relating to the runtime result, The computer implementation method according to claim 1, further comprising the step of triggering the generation of the deployment process model for deploying the process in response to detection that the simulation result satisfies the at least one predetermined condition relating to the runtime result.
  13. The steps include determining, based on one or more predetermined performance indicators, that the simulation results for the adjusted candidate process model correspond to the runtime results for the adjusted candidate process model, The computer implementation method according to claim 1, further comprising the step of triggering the generation of the deployment process model for deploying the process in response to a determination that the simulation results for the adjusted candidate process model correspond to the runtime results for the adjusted candidate process model.
  14. The computer implementation method according to claim 1, wherein the trained behavior of each of the plurality of software agents is defined by parameters that control the behavior of the software agent.
  15. It is a system, At least one memory for storing instructions, The system comprises one or more processors configured by the instructions to perform an operation, and the operation is Training multiple software agents using historical process data, wherein each of the multiple software agents represents a single task in the process. The process is simulated and simulation results are generated by executing a multi-agent system, wherein the multiple software agents in the multi-agent system are configured according to a candidate process model for the process and operate autonomously based on the training. Using the runtime configuration based on the candidate process model, the process is executed to generate runtime results for comparison with the simulation results. Based on the above comparison, the candidate process model is adjusted, Repeating the simulation of the process using a tuned multi-agent system corresponding to the tuned candidate process model, Repeating the execution of the process using a modified runtime configuration corresponding to the modified candidate process model, A system comprising generating an expanded process model for the process based on the adjusted candidate process model.
  16. One of the aforementioned software agents comprises a machine learning model, and the training of the software agent is The system according to claim 15, comprising training the machine learning model on at least a subset of the historical process data relating to the single task represented by the software agent.
  17. The simulation of the process includes performing a test simulation to test the candidate process model, and the operation is, Perform a baseline simulation to generate baseline results for the baseline process model, By comparing the baseline results with the simulation results, first performance data is generated. Based on the first performance data, the generation of the runtime configuration for the execution of the process is automatically triggered, The system according to claim 15, further comprising generating second performance data by comparing the runtime results with the simulation results in order to enable the adjustment of the candidate process model.
  18. One or more non-temporary computer-readable media that store computer-executable instructions that cause a computing system to perform an operation when executed by the computing system, wherein the operation is Training multiple software agents using historical process data, wherein each of the multiple software agents represents a single task in the process. The process is simulated and simulation results are generated by executing a multi-agent system, wherein the multiple software agents in the multi-agent system are configured according to a candidate process model for the process and operate autonomously based on the training. Using the runtime configuration based on the candidate process model, the process is executed to generate runtime results for comparison with the simulation results. Based on the above comparison, the candidate process model is adjusted, Repeating the simulation of the process using a tuned multi-agent system corresponding to the tuned candidate process model, Repeating the execution of the process using a modified runtime configuration corresponding to the modified candidate process model, One or more non-temporary computer-readable media, comprising generating an expanded process model for the process based on the adjusted candidate process model.
  19. One of the aforementioned software agents comprises a machine learning model, and the training of the software agent is One or more non-temporary computer-readable media according to claim 18, comprising training the machine learning model on at least a subset of the historical process data relating to the single task represented by the software agent.
  20. The simulation of the process includes performing a test simulation to test the candidate process model, and the operation is, Perform a baseline simulation to generate baseline results for the baseline process model, By comparing the baseline results with the simulation results, first performance data is generated. Based on the first performance data, the generation of the runtime configuration for the execution of the process is automatically triggered, One or more non-temporary computer-readable media according to claim 18, further comprising generating second performance data by comparing the runtime results with the simulation results in order to enable the adjustment of the candidate process model.

Description

The subject matter disclosed herein generally relates to computer implementations and systems for simulating process behavior. More specifically, the subject matter in this disclosure relates to multi-agent systems for process simulation. Process simulation generally involves the use of computational models to reproduce process behavior. Process simulation can help predict the impact of changes on a process, estimate future process performance, identify bottlenecks, and improve resource allocation. Applications of business process simulation range from manufacturing and logistics to healthcare and finance, where understanding and improving process flows can lead to increased efficiency and cost-effectiveness. Simulation systems can be complex and time-consuming, often requiring extensive manual configuration. For example, the technical complexity of modeling an entire business process involving multiple roles and tasks can make it difficult to understand and consider all relevant aspects of the real world, or to manage dependencies and interactions within the process. As a result, the final simulation of such a process may exhibit insufficient technical performance, waste computing resources, and, if any, lead to limited improvements. "daveshap ACE_Framework: ACE (Autonomous Cognitive Entities)", GitHub, Inc., [Online]. Retrieved from the Internet: URL: https: github.com daveshap ACE_Framework, (2024), 4 pgs"AutoGen: Enabling next-generation large language model applications", Microsoft Research, [Online]. Retrieved from the Internet: URL: https: www.microsoft.com en-us research blog autogen-enabling-next-generation-large-language-model-applications , (9 25 23), 9 pgsAFT AB, OMAR, "Microsoft Copilot Studio: Building copilots with agent capabilities", Microsoft Copilot Blog, [Online]. Retrieved from the Internet: URL: https: www.microsoft.com en-us microsoft-copilot blog copilot-studio microsoft-copilot-studio-building-copilots-with-agent-capabilities , (5 21 24), 6 pgsSHAPIRO, DAVID, "ACE Framework Overview and Intro: Autonomous Al Agents!", YouTube, [Online]. Retrieved from the Internet: URL: https: www.youtube.com watch?v=A_BL_pu4Gtk, (Accessed 10-22-24), 2 pgsSULIS, EMILIO, "Chapter 1: Introducing Agent-Based Simulation for the Business Processes", Agent-Based Business Process Simulation - A Primer with Applications and Examples, Springer, (2022), 3-12SULIS, EMILIO, "Chapter 6: The Agent-Based Business Process Simulation Approach", Agent-Based Business Process Simulation - A Primer with Applications and Examples, Springer, (2022), 105-128SULIS, EMILIO, "Chapter 7: Multi-Agent Systems and Business Process Management", Agent-Based Business Process Simulation - A Primer with Applications and Examples, Springer, (2022), 131-138 This diagram illustrates a schematic representation of a network environment, including process modeling systems, process automation systems, and multi-agent simulation systems, using several examples.Here are some examples of block diagrams of the components of a multi-agent simulation system.This is a flowchart of process tasks with several examples.This diagram illustrates, using several examples, the mapping of process tasks to agents in a multi-agent system.This flowchart illustrates how to use a multi-agent system to simulate a process, using several examples.This flowchart shows the operation of the training phase of how to utilize a multi-agent system for simulation, using several examples.This flowchart shows the operation of the simulation and execution phases of the method in Figure 6, using several examples.This diagram provides a schematic overview of training and using machine learning programs, using several examples.This block diagram shows software architectures for computing devices, with several examples.Block diagrams of machines in the form of computer systems, by some example, in which instructions can be executed within the machine in order to cause the machine to perform any one or more of the methods described herein. The systems and methods described herein relate to techniques for simulating processes by using software agents to represent each task in the process. Thus, the entire process may be represented by multiple software agents, where each software agent represents one individual task or step of the process. In some examples, the software agents provide building blocks for constructing the process simulation. The software agents can be combined, individually adjusted, or reconfigured to represent the process model, thereby providing flexibility for process simulation. As used herein, “software agent,” or simply “agent,” refers to a program or model designed or configured to perform or represent a single, specific task. As used herein, “multi-agent system” refers to a computer implementation system of multiple interacting software agents, where each software agent represents a single, specific task. For example, in a purchase order processing process,