[论文解读] Revolutionizing Process Mining: A Novel Architecture for ChatGPT Integration and Enhanced User Experience through Optimized Prompt Engineering

Mehrdad Agha Mohammad Ali Kermani, Hamid Seddighi+1 more|arXiv (Cornell University)|May 17, 2024

Artificial Intelligence in Healthcare and Education被引用 5

一句话总结

本论文提出通过基于 ETL 的架构和定制的提示工程，将 ChatGPT 集成到过程挖掘工具中，以提升用户体验和分析能力，并用使用 BehfaLab 的工具的数据对 17 家公司的数据进行验证。

ABSTRACT

In the rapidly evolving field of business process management, there is a growing need for analytical tools that can transform complex data into actionable insights. This research introduces a novel approach by integrating Large Language Models (LLMs), such as ChatGPT, into process mining tools, making process analytics more accessible to a wider audience. The study aims to investigate how ChatGPT enhances analytical capabilities, improves user experience, increases accessibility, and optimizes the architectural frameworks of process mining tools. The key innovation of this research lies in developing a tailored prompt engineering strategy for each process mining submodule, ensuring that the AI-generated outputs are accurate and relevant to the context. The integration architecture follows an Extract, Transform, Load (ETL) process, which includes various process mining engine modules and utilizes zero-shot and optimized prompt engineering techniques. ChatGPT is connected via APIs and receives structured outputs from the process mining modules, enabling conversational interactions. To validate the effectiveness of this approach, the researchers used data from 17 companies that employ BehfaLab's Process Mining Tool. The results showed significant improvements in user experience, with an expert panel rating 72% of the results as "Good". This research contributes to the advancement of business process analysis methodologies by combining process mining with artificial intelligence. Future research directions include further optimization of prompt engineering, exploration of integration with other AI technologies, and assessment of scalability across various business environments. This study paves the way for continuous innovation at the intersection of process mining and artificial intelligence, promising to revolutionize the way businesses analyze and optimize their processes.

研究动机与目标

• 激发让更广泛的受众能够访问、AI 辅助的过程挖掘的需求。
• 探索像 ChatGPT 这样的 LLM 如何提升过程挖掘的分析能力和用户体验。
• 为每个过程挖掘子模块制定定制的提示工程策略，以确保 AI 输出的准确性。
• 提出一种基于 ETL 的集成架构，通过 API 将过程挖掘模块与 ChatGPT 连接。

提出的方法

• 使用 ETL 管道通过 API 将过程挖掘引擎模块与 ChatGPT 集成。
• 应用零-shot 和优化后的提示工程技术来生成与上下文相关的输出。
• 连接 ChatGPT 以接收来自过程挖掘模块的结构化输出，实现对话互动。
• 使用 17 家公司数据来验证该方法，这些公司使用 BehfaLab’s Process Mining Tool。
• 通过专家小组对 AI 输出的评分为 Good（72%）来评估用户体验。

实验结果

研究问题

• RQ1 ChatGPT 集成如何提高过程挖掘工具的可访问性和易用性？
• RQ2 每个子模块的哪些提示工程策略能产生准确且相关的 AI 输出？
• RQ3 基于 ETL 的集成框架是否能提升 ChatGPT 与过程挖掘引擎之间的交互？
• RQ4 在多家公司中使用 AI 辅助的过程挖掘对用户体验的量化影响是什么？

主要发现

• 专家小组将 72% 的 AI 辅助输出评为 Good。
• 来自使用 BehfaLab’s Process Mining Tool 的 17 家公司的验证数据支持提升的用户体验。
• 该架构通过将来自过程挖掘模块的结构化输出提供给 ChatGPT，使对话交互成为可能。
• 针对每个子模块的定制提示工程提高了 AI 生成洞察的相关性和准确性。