Scholarlink

Artificial intelligence (AI) is rapidly transforming various domains, paving the way for Industry 5.0, which emphasizes synergy between humans and autonomous systems. In the context of micro and small businesses, AI-driven solutions offer significant advantages in redesigning organizational processes by overcoming the limitations of traditional methods, which are often labor-intensive and costly due to their reliance on manual process interpretation and external consulting services. This research presents an innovative AI-based approach to automating the detection of inefficiencies and structural gaps in enterprise management systems. Our methodology utilizes large language models (LLMs) and BPMN-based process modeling to enhance accuracy and efficiency in identifying organizational inefficiencies. As an experimental case, we analyzed the business processes of a micro-enterprise in the tourism sector, using regulatory documents and process descriptions. Generative AI based on LLMs was employed to extract, analyze, and optimize business regulations, significantly improving process transparency and workflow automation. Performance evaluation metrics such as precision, recall, and F1-score validated the effectiveness of the proposed approach. Additionally, we developed a conceptual model of an intelligent decision-support system based on Galbraith’s Star Model, comprising five integrated analytical modules. The technical implementation and cloud-based testing demonstrated a measurable reduction in operational costs and improved decision-making efficiency. Future work will focus on developing a custom AI-driven enterprise assistant using open source LLMs, further advancing intelligent decision-making systems for micro and small businesses.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Intelligent Support and Modeling of Organizational Structure Redesign for Micro and Small Businesses based on Large Language Models and Fuzzy Rules

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Vladimir Berezovsky,
  • Natalia Sluzova,
  • Artem Vahrushev,
  • Daniil Gubkin,
  • Vladislav Potyomin

摘要

Artificial intelligence (AI) is rapidly transforming various domains, paving the way for Industry 5.0, which emphasizes synergy between humans and autonomous systems. In the context of micro and small businesses, AI-driven solutions offer significant advantages in redesigning organizational processes by overcoming the limitations of traditional methods, which are often labor-intensive and costly due to their reliance on manual process interpretation and external consulting services. This research presents an innovative AI-based approach to automating the detection of inefficiencies and structural gaps in enterprise management systems. Our methodology utilizes large language models (LLMs) and BPMN-based process modeling to enhance accuracy and efficiency in identifying organizational inefficiencies. As an experimental case, we analyzed the business processes of a micro-enterprise in the tourism sector, using regulatory documents and process descriptions. Generative AI based on LLMs was employed to extract, analyze, and optimize business regulations, significantly improving process transparency and workflow automation. Performance evaluation metrics such as precision, recall, and F1-score validated the effectiveness of the proposed approach. Additionally, we developed a conceptual model of an intelligent decision-support system based on Galbraith’s Star Model, comprising five integrated analytical modules. The technical implementation and cloud-based testing demonstrated a measurable reduction in operational costs and improved decision-making efficiency. Future work will focus on developing a custom AI-driven enterprise assistant using open source LLMs, further advancing intelligent decision-making systems for micro and small businesses.