Unbiased design method for product kansei image design based on network evaluation data

被引：0
|
作者：
Lin L. [1 ,2 ]
Zhang Y. [1 ]
Niu Y. [3 ]
Yang M. [2 ]
机构：
[1] Key Laboratory of Advanced Manufacturing Technology of Ministry of Education, Guizhou University, Guiyang
[2] School of Mechanical Engineering, Guizhou University, Guiyang
[3] School of Mechanical Engineering, Southeast University, Nanjing
来源：
Dongnan Daxue Xuebao (Ziran Kexue Ban)/Journal of Southeast University (Natural Science Edition) | 2020年 / 50卷 / 01期
关键词：
Innovative design; Kansei engineering; Product design; User knowledge;
D O I：
10.3969/j.issn.1001-0505.2020.01.004
中图分类号：
学科分类号：
摘要：
To solve the problem of rare real user information and case-based reasoning in traditional kansei image design, an unbiased design method for product kansei image based on network evaluation data was proposed. Firstly, the network crawler was used to obtain the comment text of the product appearance in the Internet. Then, the text mining was introduced to analyze the product images and user demands for kansei, and the word vector was constructed to convert the kansei images into parameters. Furthermore, the morphological characteristics of the target product were depicted by the parametric curve, consequently, the parameterized data of product morphological characteristics were determined. Finally, the maximum information coefficient was calculated to select the dimensions of image parameters, and the mapping relationship based on random forest was constructed, the design parameters and its ranges of product were predicted based on mapping relationship. Taking the side profile design of the sedan car as an example, in the mapping relationship between the kansei image and design features, a correct ratio between 0.5 and 0.7 was 86.67%. The results show that the method can transform the user's real evaluation data into important input information in the image design process, so as to carry out the image-innovative design activities based on the description of the user's kansei demand without case-based reasoning. Thus, the unbiased design for images is efficiently realized. © 2020, Editorial Department of Journal of Southeast University. All right reserved.
引用
收藏
页码：26 / 32
页数：6
相关论文
共 22 条
  • [1] McDonagh D., Bruseberg A., Haslam C., Visual product evaluation: Exploring users' emotional relationships with products, Applied Ergonomics, 33, 3, pp. 231-240, (2002)
  • [2] Rosler F., Battenberg G., Schuttler F., Subjective perceptions and objective characteristics of control elements, ATZ Worldwide, 111, 4, pp. 38-43, (2009)
  • [3] Nagamachi M., Kansei engineering as a powerful consumer-oriented technology for product development, Applied Ergonomics, 33, 3, pp. 289-294, (2002)
  • [4] Wang C., Chin H., Integrating affective features with engineering features to seek the optimal product varieties with respect to the niche segments, Advanced Engineering Informatics, 33, pp. 350-359, (2017)
  • [5] Shieh M., Li Y.F., Yang C., Comparison of multi-objective evolutionary algorithms in hybrid Kansei engineering system for product form design, Advanced Engineering Informatics, 36, pp. 31-42, (2018)
  • [6] Hsiao S.W., Chiu F.Y., Lu S.H., Product-form design model based on genetic algorithms, International Journal of Industrial Ergonomics, 40, 3, pp. 237-246, (2010)
  • [7] Jiao Y.R., Qu Q.X., A proposal for Kansei knowledge extraction method based on natural language processing technology and online product reviews, Computers in Industry, 108, pp. 1-11, (2019)
  • [8] Chou J., A Kansei evaluation approach based on the technique of computing with words, Advanced Engineering Informatics, 30, 1, pp. 1-15, (2016)
  • [9] Hsiao Y.H., Chen M.C., Liao W.C., Logistics service design for cross-border E-commerce using Kansei engineering with text-mining-based online content analysis, Telematics and Informatics, 34, 4, pp. 284-302, (2017)
  • [10] Li S.B., Quan H.F., Hu J.J., Et al., Perceptual evaluation method of products based on online reviews data driven, Computer Integrated Manufacturing Systems, 24, 3, pp. 752-762, (2018)
123