国产大模型App在机械工厂品管的应用试验  

Application Test of Domestic Large Language Model App in Quality Manage of Mechanical Factory

作　　者：彭秋阳 程振涛 Peng Qiuyang;Cheng Zhentao(Guangzhou Haozhi Industrial Co.,Ltd.,Guangzhou 511356,China)

机构地区：[1]广州市昊志机电股份有限公司,广州511356

出　　处：《机电工程技术》2024年第8期258-262,共5页Mechanical & Electrical Engineering Technology

摘　　要：探索将国产大模型App用于机械工厂品管的优劣势和潜在发展方向。通过对比人类专家和国产大模型App回答的方式建立应用评价指标,对大模型应用于机械工厂品管工作的表现进行了评分。基于大模型的得分以及有无关键失误,评估其用于机械厂品管的可行性,验证了国产大模型的当前应用发展进度。结果表明不同公司的模型在同类任务中表现未见明显区别,在辅助快速入门方面大模型有一定优势,但是深度上代替不了行业专家,相比宣传中的大模型是生产力提升工具的说法,实际是目前还有较大进步空间。归纳了国产大模型在品管领域应用的优劣势,并指出可能发展方向,对国产大模型的应用和发展有一定参考意义。The purpose of the study is to explore the application of domestic large language models based chatbot App in quality control of machinery factory,and to establish application evaluation indexes by comparing human experts and domestic chatbot App responses,the performance in quality control of mechanical factory using domestic chatbot App is evaluated.Based on the scores of domestic chatbot App and whether there have any critical errors,the current application and development progress of domestic large language models is verified.The results show that there is no significant difference in the performance of models from different companies in similar tasks.Large models have certain advantages in assisting quick entry,but they cannot replace industry experts in depth.Compared to the claim that large models are productivity improvement tools in propaganda,there is still a lot of room for improvement at present.The advantages and disadvantages of domestic large models in the field of quality control are summarized,and possible development directions are pointed out,which has certain reference significance for the application and development of domestic large models.

关 键 词：国产大模型 APP 品管 

分 类 号：TP319[自动化与计算机技术—计算机软件与理论]