Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2410.07677 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916431808954368 |
|---|---|
| author | Yao, Xu Wu, Xiaoxu Li, Xi Xu, Huan Li, Chenlei Huang, Ping Li, Si Ma, Xiaoning Shan, Jiulong |
| author_facet | Yao, Xu Wu, Xiaoxu Li, Xi Xu, Huan Li, Chenlei Huang, Ping Li, Si Ma, Xiaoning Shan, Jiulong |
| contents | Manufacturing quality audits are pivotal for ensuring high product standards in mass production environments. Traditional auditing processes, however, are labor-intensive and reliant on human expertise, posing challenges in maintaining transparency, accountability, and continuous improvement across complex global supply chains. To address these challenges, we propose a smart audit system empowered by large language models (LLMs). Our approach introduces three innovations: a dynamic risk assessment model that streamlines audit procedures and optimizes resource allocation; a manufacturing compliance copilot that enhances data processing, retrieval, and evaluation for a self-evolving manufacturing knowledge base; and a Re-act framework commonality analysis agent that provides real-time, customized analysis to empower engineers with insights for supplier improvement. These enhancements elevate audit efficiency and effectiveness, with testing scenarios demonstrating an improvement of over 24%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_07677 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Smart Audit System Empowered by LLM Yao, Xu Wu, Xiaoxu Li, Xi Xu, Huan Li, Chenlei Huang, Ping Li, Si Ma, Xiaoning Shan, Jiulong Computation and Language Manufacturing quality audits are pivotal for ensuring high product standards in mass production environments. Traditional auditing processes, however, are labor-intensive and reliant on human expertise, posing challenges in maintaining transparency, accountability, and continuous improvement across complex global supply chains. To address these challenges, we propose a smart audit system empowered by large language models (LLMs). Our approach introduces three innovations: a dynamic risk assessment model that streamlines audit procedures and optimizes resource allocation; a manufacturing compliance copilot that enhances data processing, retrieval, and evaluation for a self-evolving manufacturing knowledge base; and a Re-act framework commonality analysis agent that provides real-time, customized analysis to empower engineers with insights for supplier improvement. These enhancements elevate audit efficiency and effectiveness, with testing scenarios demonstrating an improvement of over 24%. |
| title | Smart Audit System Empowered by LLM |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2410.07677 |