深度学习技术下的消费者动机设计模型研究

doi:10.3969/j.issn.1007-7375.2022.06.014

工业工程 ›› 2022, Vol. 25 ›› Issue (6): 120-125.doi: 10.3969/j.issn.1007-7375.2022.06.014

深度学习技术下的消费者动机设计模型研究

孙斐, 陆定邦, 赵雨淋, 孙悦

广东工业大学艺术与设计学院，广东广州 510006

收稿日期:2022-05-25 发布日期:2022-12-23
作者简介:孙斐(1974—)，女，山东省人，博士研究生，主要研究方向为艺术设计理论、产业发展研究
基金资助:
广东省科技计划海外名师资助项目(2020A1414010314))

Research on the Motivation Design Model Based on Deep Learning Technology

SUN Fei, LUH Dingbang, ZHAO Yulin, SUN Yue

School of Art & Design, Guangdong University of Technology, Guangzhou 510006, China

Received:2022-05-25 Published:2022-12-23

摘要/Abstract

摘要： 提出基于深度学习技术的一种快速有效的产品分类方法MdmNet，将人的动机思维方式嵌入机器学习形成新产品设计的技术方法。运用消费者信息推理方法和加权融合模块，在基准数据集Cars上进行实验，根据生产方的产品特性提出基于多神经网络特征融合的动机需求分类，其思想在于使用MDM与多神经网络融合来增加对图像库中数据的特征提取。此方法可显著提高新产品分类的性能。与对比模型比较，其性能在准确率等指标上面均有体现。在基准数据集Cars上，当设置参数W_a为0.1，参数W_b 为0.9，MdmNet输出的Top-1、Top-5及Top-10正确率相对于设计师视角的传统算法可分别有所提高。MdmNet适用于数据量少、时间短的此类系统对象。

关键词: 动机设计模型, 深度学习, 产品分类, 新产品开发, 目标消费者

Abstract: A fast and effective product classification method based on deep learning technology, MdmNet, is proposed, which embeds human's motivation thinking mode into machine learning to form a new product design method. By using the consumer information reasoning method and the weighted fusion module, an experiment is carried out on the benchmark data set Cars. According to the product characteristics of the producer, a classification of motive requirements based on multi-neural network feature fusion is proposed. This idea is to use MDM and multi-neural network fusion to increase the feature extraction of image database data. This method can significantly improve the performance of new product classification, compared with the comparison model, its performance is reflected in the accuracy and other indicators. On the benchmark Dataset Cars, when set to 0.1 and 0.9, MdmNet outputs Top-1, Top-5, and Top-10 correct rates are higher than those of traditional algorithms from the designer's point of view. MdmNet is suitable for such system objects with small amount of data and short time.

Key words: motivation design model, deep learning, product classification, new product development, target consumers

中图分类号:

J0-03

孙斐, 陆定邦, 赵雨淋, 孙悦. 深度学习技术下的消费者动机设计模型研究[J]. 工业工程, 2022, 25(6): 120-125.

SUN Fei, LUH Dingbang, ZHAO Yulin, SUN Yue. Research on the Motivation Design Model Based on Deep Learning Technology[J]. Industrial Engineering Journal, 2022, 25(6): 120-125.

参考文献

[1] MOUSAVI S A, SEITI H, HAFEZALKOTOB A, et al. Application of risk-based fuzzy decision support systems in new product development: An R-VIKOR approach[J/OL]. Applied Soft Computing, 2021, 109: (2021-09). https://doi.org/10.1016/j.asoc.2021.107456.
[2] CHRISTENSEN C M, OVERDORF M. Meeting the challenge of disruptive change[J]. Harvard Business Review, 2000(March-April): 67-76
[3] LUH D B, MA C H, HSIEH M H, et al. Applying an empathic design model to gain an understanding of consumers' cognitive orientations and develop a product prototype[J]. Journal of Industrial Engineering and Management (JIEM) , 2011, 5(1): 229-258
[4] LUH D B, MA C H, HSIEH M H, et al. Using the systematic empathic design method for customer- centered products development[J]. Journal of Integrated Design and Process Science, 2012, 16(4): 31-54
[5] DE FERRAN F, GRUNERT K G. French fair trade coffee buyers' purchasing motives: an exploratory study using means-end chains analysis[J]. Food Quality and Preference, 2007, 18(2): 218-229
[6] LUH D B. Keynote speech, design as opportunity driver[C/OL]. (2021-01-25). https://uni.dongseo.ac.kr/adcf/index.php?pCode=MN8000035&mode=view&idx=295.
[7] LUH D B, KO Y T, MA C H. A structural matrix- based modelling for designing product variety[J]. Journal of Engineering Design, 2011, 22(1): 1-29
[8] 谢焸君, 郑美芳, 江宝焜, 等. 新产品开发流程. ppt [EB/ OL]. (2017-05-10). https://max.book118.com/html/2017/0509/105611289.shtm.
[9] TATIKONDA M V, ROSENTHAL S R. Technology novelty, project complexity, and product development execution success[J]. IEEE Transactions on Engineering Management, 2000, 47(1): 74-87
[10] PIEKARA A, KRZYWONOS M, KOPACZ M. Dietary supplements intended for children—proposed classification of products available on the market[J]. Journal of Dietary Supplements, 2021(2): 1-11
[11] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. Imagenet classification with deep convolutional neural networks[J]. Advances in Neural Information Processing Systems, 2012, 25: 1097-1105
[12] LUH D B. The development of psychological indexes for product design and the concepts for product phases[J]. Design Management Journal (Former Series) , 1994, 5(1): 30-39
[13] LIN K, YANG H F, HSIAO J H, et al. Deep learning of binary hash codes for fast image retrieval [C/OL]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops. Boston: IEEE, 2015: (2015-10-26). https://ieeexplore.ieee.org/document/7301269.
[14] LU C C, LUH D B. A comparison of assessment methods and raters in product creativity[J]. Creativity Research Journal, 2012, 24(4): 331-337
[15] LUH D B, LU C C. From cognitive style to creativity achievement: the mediating role of passion[J]. Psychology of Aesthetics, Creativity, and the Arts, 2012, 6(3): 282
[16] LUH D B, KO Y T, MA C H. A dynamic planning approach for new product development[J]. Concurrent Engineering, 2009, 17(1): 43-59

深度学习技术下的消费者动机设计模型研究

Research on the Motivation Design Model Based on Deep Learning Technology

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

编辑推荐

Metrics

本文评价

[1]	周昊飞. 基于GRU神经网络的自相关过程残差控制图[J]. 工业工程, 2022, 25(1): 108-113.
[2]	张鹏伟, 苏秦, 李乘龙. 基于模糊评价方法的新产品开发过程可靠性度量[J]. 工业工程, 2012, 15(5): 60-65.