Conference PaperPDF Available

應用可拓学 GPT 于新产品的创意原型

Authors:

Abstract

GPT (ExtenicsGPT) 是一种创新方法,它将可拓学 (Extenics) 的原理与 ChatGPT 语 言模型相结合,为新产品生成创意原型。可拓学是一门研究事物拓展的可能性的原创性中 国新学科,是用形式化模式来创新,解决矛盾问题,从而产生新产品新思路的方法论。 同时,ChatGPT 是一种强大的语言模型,能够根据用户提供的提示(prompt)生成文本。 在 这种方法中,ChatGPT 用于生成一系列与新产品创意相关的提示和问题。 这些提示和问 题旨在激发创造性思维并帮助产生新想法及创意。 因此,用户可以基于可拓创新方法使 用这些提示和问题来生成一组潜在的产品特征和属性。 接下来,在解决了所提出的特征 中的潜在冲突或不一致之后,使用可拓学来分析这些特征和属性以获得最终的理想结果。 这有助于确保最终产品原型连贯一致。Dall-E 是一种图像生成系统,能够从文本描述中生 成逼真的图像。使用 Dall-E 生成产品原型,可以根据利益相关者的反馈改进和迭代原 型。 最后展示了使用 ExtenicsGPT 创建创意原型的案例。 通过使用 Dall-E 生成该原型图 像,利益相关者可以更好地可视化最终产品并提供更准确的反馈。 这种方法有可能加速 产品开发过程并生成创新和连贯的产品原型。 关键词:可拓学, 可拓学 GPT, ChatGPT, Dall-E, 原型
全球华人品质联盟(筹) 新加坡质量学院
A. 人工智能对制造和工程质量保证的影响
應用可拓学 GPT 于新产品的创意原型
黎剑虹 (LAI Kim-Hung, Lotto)
1
香港城市大学系统工程学系兼任教授
2
广东工业大学可拓与创新方法研究所研究员
*
通讯作者:
kimhlai@cityu.edu.hk
摘要
可拓学 GPT (ExtenicsGPT) 是一种创新方法,它将可拓学 (Extenics) 的原理与 ChatGPT
言模型相结合,为新产品生成创意原型。可拓学是一门研究事物拓展的可能性的原创性中
国新学科,是用形式化模式来创新,解决矛盾问题,从而产生新产品新思路的方法论。
同时,ChatGPT 是一种强大的语言模型,能够根据用户提供的提示(prompt)生成文本。
这种方法中,ChatGPT 用于生成一系列与新产品创意相关的提示和问题。 这些提示和问
题旨在激发创造性思维并帮助产生新想法及创意。 因此,用户可以基于可拓创新方法使
用这些提示和问题来生成一组潜在的产品特征和属性。 接下来,在解决了所提出的特征
中的潜在冲突或不一致之后,使用可拓学来分析这些特征和属性以获得最终的理想结果。
这有助于确保最终产品原型连贯一致。Dall-E 是一种图像生成系统,能够从文本描述中生
成逼真的图像。使用 Dall-E 生成产品原型,可以根据利益相关者的反馈改进和迭代原
型。 最后展示了使用 ExtenicsGPT 创建创意原型的案例。 通过使用 Dall-E 生成该原型图
像,利益相关者可以更好地可视化最终产品并提供更准确的反馈。 这种方法有可能加速
产品开发过程并生成创新和连贯的产品原型。
关键词:可拓学, 可拓GPT, ChatGPT, Dall-E, 原型
全球华人品质联盟(筹) 新加坡质量学院
A. 人工智能对制造和工程质量保证的影响
應用可拓學 GPT 於新產品的創意原型
黎劍虹 (LAI Kim-Hung, Lotto)
1
香港城市大學系統工程學系兼任教授
2
廣東工業大學可拓與創新方法研究所研究員
*
通訊作者:
kimhlai@cityu.edu.hk
一、简介
可拓学是一门新兴的中国原创新学科,它致力于研究事物的可拓性和通过形式化模型解决
矛盾问题的转化方法。该形式化模型可用于描述制造过程中各工序的生产情况和操作方式
以及新产品的开发。(Chen, et al., 2019; Yang, C.Y. and Cai, W., 2013)。 可拓创新方法源自
可拓学理论,用于提出新产品和服务。 为了简化该方法在商业和/工业中应用,提出了
“可拓创新四步法” (Yang, C.Y. and Cai, W., 2013; Yang, C.Y., 2018)。其它工业及学术应用如
药板包装, 在线教学, 抗疫策略分析及创新管理等 (Lai, K.H. Lotto, 2019, 2020, 2021 &
2022)。
2022 年,ChatGPT 和 Dall-E 首次向公众开放,随后在全球范围内获得了广泛关注。
特别是在高等教育、医学教育和创业领域,提出了许多创造性和潜在的应用(Amri M.M. &
Hisan U.K., 2023; Short C.E. & Short J.C., 2023; Tajik E. & Tajik F., 2023)。
对于高等教育来说,创新和技术管理以及创业精神和创业生态系统是热门话题,它致力于
提高学生对新产品和服务开发的创造力和创新能力(Lai, K.H. Lotto, 2020)。用一些学生提
出的案例來讨论和比较 ChatGPT 评估和 Dall-E 生成的原型。
本文探讨了 ChatGPT 和 Dall-E 通过可拓创新方法生成新产品原型的潜在好处,并讨论了
实际应用示例。
二、文献综述
可拓学是由蔡文教授自 1983 年发表第一篇论文《可拓集与不兼容问题》以来所创立的基
元理论、可拓论和可拓工程(Cai, W., 1983; Yang, C.Y. and Cai, W., 2013)。 基元(B)是可拓
学的逻辑单元,包括物元(M)、事元(A)和关系元(R)。 每个元素都是由对象(O)、特征
(c)及其量值(v)组成的,表示为 B =(O,c,v) (见图 1)。
全球华人品质联盟(筹) 新加坡质量学院
1 基元族 - 构成可拓学模型的关键元素
为了简化給商业和工业应用的,可拓创新四步法提出了建模-拓展-变换-选择(METS)
(Lai, K.H. Lotto, 2019; Yang, C.Y., 2018)(见图 2)。
2 演示了四个步骤,说明如下:
1 步:建模
可拓学使用形式化语言来表达物件,事件,关系和问题,并建立形式化模型。
此,第一步是基于基元(对象,特征,量值)建立模型,称为“可拓模型”。 可拓模型用于
表示量变和质变的过程以及临界状态,以便描述解决矛盾问题的过程。
3.2.2 2 步:拓展
第二步是拓展基元的思想,称之为“可拓分析”。 可拓分析包含四种方法,分别是
“发散树”(Divergence),“相关网”(Correlative),“蕴含系”(Implication) 和“分合链”(Opening-
up)。拓展的另一种方法是“共轭分析”。
3.2.3 3 步:变换
可拓变换理论是将矛盾问题转化为兼容问题的工具。 有四种拓展转换方法,如下
所示。
i) 基本变换(替代、增减、扩缩、分解、重复)
ii) 变换的基本运算(积、与、或、逆运算)
iii) 传导变换(从事物的相关性)
iv) 共轭变换(虚实、软硬、潜显、负正)
全球华人品质联盟(筹) 新加坡质量学院
3.2.4 4 步:选择
由于可拓变换产生了大量的想法,我们需要优先评估的方法。关联函数是一种定量
工具,它基于延伸距离来表示物质特征的程度。 它在“选择”步骤中称为“优度评估方法”。
下面的这个方法有八个步骤。
i) 根据实际情况确定测量指标
ii) 选择优度的类型
iii) 确定测量指标的权重系数
iv) 首先通过不可或缺的指标进行评估
v) 建立关联函数并计算关联程度
vi) 算标准关联度
vii) 计算优度
viii) 选择优度较高的方案
2 可拓创新四步法(METS)
ChatGPT 是一个大型语言模型,其中 GPT 代表“Generative Pre-trained Transformer”,由
OpenAI 开发。 该模型已经过广泛的互联网文本数据的训练,使其能够对用户输入生成连
贯且上下文相关的回应。 Dall-E 是 OpenAI 开发的另一种 AI 模型,专门用于根据文本描
述创建图像。 “Dall-E”这个名字是艺术家名字“Salvador Dali”和“Pixar's WALL-E”的组合。
人工智能工具 ChatGPT 和 Dall-E 可用于创建交互式教育材料。 学生可以提出问题并获得
相关视觉示例支持的详细解释,从而增强他们的理解和参与。 例如,这种组合模型可以
通过创造互动且引人入胜的学习体验,为医学教育提供新的维度。 Dall-E 成功生成了气
胸肺部 X 射线图像和心电图 (ECG)。 总体而言,ChatGPT 通过成功模拟医患互动展示了
巨大的潜力,但 Dall-E 的能力仍然低于预期(Amri M.M. & Hisan U.K., 2023)。
全球华人品质联盟(筹) 新加坡质量学院
通过三个视角:面向学生、面向教师和面向系统的工具的研究,检查了 ChatGPT 的潜在
功能让利益相关者(例如教育工作者、管理人员和高等教育学生)对 ChatGPT 使用的适
当性有一个深入而细致的了解。 对于面向学生的工具,学生可以用它来提高他们的深度
学习、批判思维和写作技能。 对于面向教师的工具,它可以通过自动化任务来提高教师
的效率,例如编写教案、设计课程大纲、创建测验/测试问题、对学生表现进行评分等。
ChatGPT 作为面向系统的工具在高等教育可以简化行政任务,节省时间并减少工作量
(Tajik, E., & Tajik, F., 2023)。 ChatGPT 和其他形式的生成人工智能 (GenAI) 将影响学术研
究、教学和商业实践的进行和评估领域。 特别是知识产权以及版权和专利法的相关影响
是有争议的(Peres, R., et al., 2023)。
ChatGPT 在创业领域的一些潜在应用。 ChatGPT 是内容创建的可行工具,可用于完善电
梯推介、社交媒体推介和众筹推介,这些内容通常用于创业言论。 作者总结道,生成模
型的新兴和持久价值从本质上讲取决于有效的提示工程(Prompt Engineering) (Short, C. E.,
& Short, J. C., 2023)。
可拓智能是一种新型人工智能,通过扩展智能来智能处理矛盾。基于可拓学的理论和方法
来转化信息和知识,运用可拓学基本元理论和矛盾分析方法,建立问题的可拓模型为:
P=L*G,L 为当前条件,G 为目标,如图 3 所示(Li, X. et al., 2020)。
3 获取系统信息解决问题的可拓智能方法
全球华人品质联盟(筹) 新加坡质量学院
对于工业工程来说,提出了可拓智能应用的新方向来解决提高产品质量和利润率、同时降
低产品不良率及其生产成本等矛盾目标(Li, X. et al., 2022)。
建议将可拓学和工业设计结合起来,使用形式模型来扩展思维并产生具有竞争力的新产品
设计创意。 提出了根据主属性、子属性和属性值路径的物元数据库,并且可以将其放在
互联网上,允许全世界所有用户访问和使用它,从而产生很多想法(Dou, J., Li, H., & Li, X.,
2018)。 因此,ChatGPT 和 Dall-E 可以用于可拓学,特别是增强物元数据库来填补设计和
产品可视化的空白。
三、方法论
可拓学 GPT(ExtenicsGPT)的方法是使用可拓学、ChatGPT 和 Dall-E 为新产品生成创意
原型和可视化设计。 可拓学 GPT 的关键概念如图 4 所示。可拓学中的可拓创新四步法
(METS) 是创建新产品创意的关键过程,ChatGPT 可以增强事物扩展的可能性,以创造更
多创意,并通过以下方式评估最终创意: 学习数据库和 Dall-E 有助于可视化要绘制的原
型想法。
4 结合 METS、ChatGPT 和 Dall-E 的可拓学 GPT 方法
全球华人品质联盟(筹) 新加坡质量学院
可拓学 GPT 方法的拟议应用如下:
建模:ChatGPT 可以增强其对象 (O)、特征 (c) 和值 (v) 中的基本元素 (B)。 通过
ChatGPT,我们可以要求列出一些市场上现有的产品作为背景信息并得到一些启
示。
拓展:拓展是关键的基本元素,扩展分析方法,尤其是 ChatGPT 常用的发散分析方法。
对于物元,我们可以使用 ChatGPT 列出特定对象(产品或服务)中尽可能多的特
征和量值。 对于事元,它可以用于根据操作/功能 (Oa) 列出尽可能多的对象,以扩
展对该产品的想法。 对于关系元来说,它与事元类似,为不同的部分扩展不同的
关系对象。
变换:结合步骤拓展中产生的想法,通过扩展转换方法进行创作。
选择:人工和 ChatGPT 都可以进行优先度评估及进行比较,从而选出优秀的新产品创
意。 使用 Dall-E 创建原型草图,以便新产品可视化。
使用可拓学 GPT(Extenics、ChatGPT 和 Dall-E 的组合模型),产品设计师可以探索和把
想法可视化。 通过描述他们的设计概念或在选择步骤后提供文字提示,他们可以快速生
成视觉图像,帮助产品、时装、室内设计等的创意过程。
四、结果与讨论
城大智能制造工程学士(BEng ITME)工学士《专业工程实践》课程中,学生在课程中用可
拓创新方法的作业为例,评估比较新产品创意原型。
可拓学中的可拓创新四步法(METS)已被用于课堂作业,帮助学生为产品或服务创造一
些新的想法。 从《专业工程实践》课程中选取了三个案例,对学生和 ChatGDP 的“选择”
步骤进行了比较。 然后使用 Dall-E 创建的原型想法图来比较学生的互联网搜索图。
ChatGPT 评估的第一个学生组提示语句如下:
“请根据以下产品的新颖性、实用性和成本效益来评估总分,其中新颖性从 1 10 占总
分的 30%,实用性从 1 10 占总分的 30%,成本效益从 1 10 占总分 占总分的 40%
产品展示如下。 列出其单项得分和总分:
i) 一支可以温暖用户双手的笔,表示温暖用户男朋友或女朋友的心
ii) 配备 U 盘的笔一支
iii) 一支可以发电的笔”
三个原型想法的总分如表 1 所示。想法一是最高分,与学生小组选择相同。
全球华人品质联盟(筹) 新加坡质量学院
1 三笔创意原型的 ChatGPT 评估分数
Prototype
Ideas
Novelty
(1-10) 30%
Practical
(1-10) 30%
Cost Effective
(1-10) 40%
Overall
(x out of 10)
i)
0.3 x 7
0.3 x 6
0.4 x 5
6.9
2.1
1.8
2
ii)
0.3 x 4
0.3 x 8
0.4 x 7
6.4
1.2
2.4
2.8
iii)
0.3 x 9
0.3 x 4
0.4 x 3
5.1
2.7
1.2
1.2
ChatGPT 对“男女朋友暖笔”原型各项标准的解释如下:
新颖性:这个概念看起来比较新颖和独特,因为它结合了暖手功能和浪漫指标。我们将
新颖性分数指定为 7
实用性:保持双手温暖很有用,尤其是在寒冷的环境中。 然而,浪漫指标可能更多的是
一种新奇的功能,而不是实用的功能。 让我们给实用性打分为 6
成本效益:考虑到附加的暖手功能和浪漫指标,这种钢笔的生产成本可能会比普通钢笔
更高。 让我们将成本效益分数指定为 5
由于学生没有创建图像,只能在互联网上搜索钢笔图,无法更清晰地展示原型。 然后利
Dall-E 绘制原型供参考。
Dall-E 的提示是:“一支彩色笔,可以在冬天用來温暖你的男朋友或女朋友的手和心。
自学生搜索和 Dall-E 创建的图像如图 5 所示。然而,Dall-E 创建的笔原型图像并不令人
惊讶或富有创意。
Student’s internet searched example
Dall-E - Pen 2
全球华人品质联盟(筹) 新加坡质量学院
Dall-E - Pen 1
Dall-E - Pen 3
5 由 Dall-E 创建和学生互联网搜索的笔图像
另外两个团队的学生也类似,他们的原型图像分别如图 6 和图 7 所示。
Dall-E 的提示是:“一个多尺寸的球可以选择我们想玩的运动(手球、篮球等)。”学生搜
索和 Dall-E 创建的图像如图 6 所示。此时,Dall -E 未能创造出具有多尺寸功能的球,仅
将不同尺寸的球组合在一起。
Student’s internet searched example
Dall-E - Ball 1
6 由 Dall-E 创建和学生互联网搜索的多尺寸球图像
全球华人品质联盟(筹) 新加坡质量学院
Dall-E 的提示是:“药箱底部的一层中嵌入了红外传感器。 如果在规定的服药时间内没有
检测到红外线因体温而变化。 然后连接到用户和家人手机上的语音芯片就会被激活来提
醒他。来自学生搜索和 Dall-E 创建的图像如图 7 所示。这次图像更接近带有红外传感器
的盒子,但没有药物盒分离。
Student’s internet searched example
Dall-E - Reminder Medicine Box 2
Dall-E - Reminder Medicine Box 1
Dall-E - Reminder Medicine Box 3
7 由 Dall-E 创建和学生互联网搜索的提醒药盒图像
五、结论
ChatGPT 和 Dall-E 是可拓创新方法创建新产品/服务原型的良好补充工具。 ChatGPT 通过
成功模拟产品设计师的洞察力、通过完善描述、总结文本、甚至建议新产品以及评估不同
的创意来协助研究和设计,展示了其潜力。
在可拓学 GPT(ExtenicsGPT)方法中,ChatGPT 可以用于每个步骤。 然而,案例研究主
要集中在最后一个阶段“选择”。 如果对学生和 ChatGPT 都采用类似的标准,则获得的最
佳想法与笔、球和药物盒的情况相似。ChatGPT 评估会对给出的分数提供简单合理的描
述,但在个别和团体评估的比较中不够一致。
全球华人品质联盟(筹) 新加坡质量学院
不幸的是,三个案例的最终原型图像表明 Dall-E 的能力仍然低于我们的预期。 仅通过文
本提示生成逼真图像的能力应该更具体,建议提示语句模式为[物体]、[功能]、[风格]、
[形容词]、[情感]、[颜色]等。如果我们对提示工程 (prompt engineering)持乐观态度,
Dall-E 有潜力在不久的将来帮助产品设计可视化。总的来说,ChatGPT 和 Dall-E 可以作
为集思广益的伙伴工具,帮助我们点燃创造性思维,并通过可拓学 GPT(ExtenicsGPT)
可视化原型,展示了生成创造性和连贯性产品原型的潜力。
参考文献:
Amri, M. M., & Hisan, U. K. (2023). Incorporating AI Tools into Medical Education:
Harnessing the Benefits of ChatGPT and Dall-E. Journal of Novel Engineering
Science and Technology, 2(02), 34-39.
Cai, W. (1983) “Extension Set and Non-Compatible Problems”, Scientific Exploration (1),
pp.83-97.
Chen, S., Li, X., Liu, R., & Zeng, S. (2019). Extension data mining method for improving
product manufacturing quality. Procedia Computer Science, 162, 146-155.
Dou, J., Li, H., & Li, X. (2018). Problem-oriented industrial designing method on extenics.
Procedia computer science, 139, 356-363.
Lai, Lotto K.H. (2019). QMS based Innovation Management using Extension Innovation
Methodology. Proceedings of the 17th ANQ Congress in Bangkok.
Lai, Lotto K.H. (2020). Case study: revamp of an engineering course and students’ feedback
on online teaching during COVID-19. The Journal of The Hong Kong Institution of
Engineers, 48, 20-23.
Lai, Lotto K.H. (2021). Research on Extension Six Sigma Method in Medicine Board
Packaging”, China Quality, CAQ, Vol.482, pp.21-28 (In Chinese)
Lai, Lotto K.H. (2022). Analysis of anti-epidemic strategies using Chinese original
innovation methodology to enhance decision quality”, The Journal of The Hong
Kong Institution of Engineers, Vol.50, July 2022, pp.6-12.
Li, X., Guo, H., & Chen, S. (2020). Extension intelligence for process manufacturing. In
Journal of Physics: Conference Series (Vol. 1605, No. 1, p. 012046). IOP Publishing.
全球华人品质联盟(筹) 新加坡质量学院
Li, X., Liu, D., Sun, J., & Zhu, Z. (2022). Challenges of Industrial Engineering in Big Data
Environment and Its new Directions on Extension Intelligence. Procedia Computer
Science, 214, 1561-1567.
Peres, R., Schreier, M., Schweidel, D., & Sorescu, A. (2023). On ChatGPT and beyond: How
generative artificial intelligence may affect research, teaching, and practice.
International Journal of Research in Marketing.
Short, C. E., & Short, J. C. (2023). The artificially intelligent entrepreneur: ChatGPT, prompt
engineering, and entrepreneurial rhetoric creation. Journal of Business Venturing
Insights, 19, e00388.
Tajik, E., & Tajik, F. (2023). A comprehensive Examination of the potential application of
Chat GPT in Higher Education Institutions. TechRxiv. Preprint, 1-10.
Yang, C.Y. and Cai, W. (2013) Extenics: Theory, Method and Application. Beijing: Science
Press.
Yang, C.Y. (2018). Extension innovation method. CRC press.
ResearchGate has not been able to resolve any citations for this publication.
Article
Full-text available
Artificial intelligence (AI) has shown promising potential to transform various fields, including medical education. Recently, the rapid advancement of AI has led to many ``new'' discoveries that caught everyone's attention. Among those discoveries are introduced by OpenAI (e.g., ChatGPT, Dall-E, and the most recent, GPT-4). The integration of AI tools, such as ChatGPT and Dall-E, can offer a new dimension to medical education by creating an interactive and engaging learning experience. In this article, we explore the potential benefits of ChatGPT and Dall-E in medical education and provide practical utilization examples of those tools. For starters, ChatGPT, or in this sense, any other similar large language models, can simulate patient interactions in a safe environment, allowing medical learners to practice their communication skills and diagnosis techniques. Furthermore, it can assist medical students and researchers in reading and writing academic articles by accurately summarizing the key points of a given topic and generating an indistinguishable abstract. In addition, ChatGPT can also create problems for medical assignments and exam practice. In this article, we also discussed ChatGPT's capability to answer standard medical assignment problems. Dall-E, on the other hand, can generate dummy copyright-free and consent-free medical images (e.g., x-ray and electrocardiogram (ECG) graphs), allowing medical learners to practice and enhance their interpretation skills. Incorporating AI-based tools into medical education can provide a new approach to teaching and learning, bridging the gap between theory and practice, and unlocking new avenues for learning and discoveries for both, the students and the instructors. It can also offer a cost-effective solution to simulate real-world scenarios that would otherwise require significant resources and time. In summary, this article concludes that AI-based tools have the potential to revolutionize medical education, empowering medical learners with the skills and knowledge necessary to excel in their field.
Article
Full-text available
The article employed Chinese original innovation methodology "Extenics" to study anti-epidemic strategies using transformation bridge method so as to enhance the decision quality.
Conference Paper
Full-text available
The most popular management standard for organizations is ISO 9001 Quality Management System (QMS). We would like to extend the organization innovation started from ISO 9001 QMS foundation to Innovation Management System (InnoMS). Recently, International Organization for Standardisation (ISO) has established technical committee (ISO/TC 279) to develop, maintain and promote standards in the fields of innovation management. Their scope is "Standardization of terminology tools and methods and interactions between relevant parties to enable innovation." ISO 56000 series (previous ISO 50500 series) are under construction. Another famous innovation standard named CEN/TS 16555-1:2013 "Innovation management-Part 1: Innovation management system" which is issued by Technical Committee (CEN/TC 389) of European Committee for Standard in 2013. It was found a system approach of innovation through the integration of QMS and Innovation Management System (InnoMS) to be synergized. In order to implement the QMS based Innovation Management (QInnoM) practically, we introduce an Extension Innovation Method which is original developed from China named "Extenics". Extenics is defined as "a science which studies the possibility of extending things and rules and methods of developing innovation with formalized patterns, and is used to resolve contradictory problems." The founder Prof. Cai Wen started his research on Extenics (originally called Matter-element Analysis) since 1976. It was one of systematic innovation tools or approaches for implementation of innovation projects for solving different contradiction problems. This paper aims to develop Extension QMS based Innovation Management System (ExQInnoMS) through ISO/FDIS 56002 and CEN/TS 16555-1, as well as, introduce the Extension Innovation Method for innovation activities in different level under ExQInnoMS.
Article
Full-text available
An engineering course accredited by the HKIE named SEEM 4066 which aims to strengthen students' understanding of the role of engineers in the society and how engineers must adopt the rapid change of the social and technological environment. The syllabus of SEEM 4066 was reviewed and updated with more innovation and technology-oriented content 1, 2. In response to the COVID-19 outbreak, CityU has implemented campus-wide and real-time online teaching for postgraduate and undergraduate students since 7 February 2020. The first class was held on 18 January 2020 and then changed into online teaching on the second class on 8 February 2020 after Chinese New Year because of COVID-19 outbreak. After this significant change, the online course has incorporated more interactive elements for students through polling, weekly quizzes, surveys, team projects and personal development essays relating to their engineering career development.
Article
Full-text available
It is more and more important to improve the market competitiveness of enterprises by providing high-quality products meeting the market demand. However, the product manufacturing process of most manufacturers is not perfect, and a variety of product quality management methods are mixed with each other, which leads to the urgent need to reduce the nonconforming product rate produced by many production lines and the inability to accurately capture the reasons why the good rate is not up to standard. Customer satisfaction gradually decreases with the development of personalized times. The rapid accumulation of big data in the Internet environment has brought new opportunities for the study of the details of the production process.Extenics uses formal models to describe the production situation and operation mode of each process in the manufacturing process.This paper uses the extension data mining method to determine the factors that affect the product’s qualified rate by collecting the data on each process of the production line, and by extension transformation, the qualified rate of the product is obviously improved.The simulation results show that this kind of extension data mining method provides a new idea for enterprises to improve the product manufacturing quality and product qualification rate, which is helpful for enterprises to realize a more perfect quality management system.
Article
To better understand the role of artificial intelligence in the development of entrepreneurial rhetoric, we examine how generative language models such as ChatGPT serve as viable tools for content creation. Using an established framework for examining CEO celebrity (Creator, Transformer, Rebel, and Savior), we illustrate how such models can effectively produce and refine elevator pitches, social media pitches, and crowdfunding pitches commonly used in the study of entrepreneurial rhetoric. We demonstrate ChatGPT’s ability to mimic each celebrity CEO archetype by prompting language in the style of exemplars, including Elon Musk, Indra Nooyi, Tony Hsieh, and Lisa Su. Implications of prompt engineering—the fine-tuning of inputs fed into language models to produce precise output—for entrepreneurship research and practice are discussed. We conclude by advancing the idea that the emergent and enduring value of generative models is, at its core, dependent on effective prompt engineering.
Article
Industrial engineering is facing both challenges and opportunities in the era of intelligent manufacturing under the environment of Internet of things and big data. Meanwhile intelligent problem solving in industrial engineering is becoming an important research direction. On the cross study of Extenics and industrial engineering, we analyze the extension intelligent technology and methods of extenics to solve complex problems almost run through the whole process from customer management, manufacturing, logistics and after service in industry. Extenics provides a new methodology for deep integration of extension data mining on industrial engineering data and artificial intelligence for complex problem solving, which may form a new direction of Extension industrial engineering (EIE) with wide application prospects. The case study proves the feasibility and effectiveness of our new methods and its models.