Enhanced customer requirement classification for product design using big data and improved Kano model. (August 2021)

• Record Type: Journal Article
• Authors: Shi, Yanlin; Peng, Qingjin
• Is Part Of: Advanced engineering informatics. Volume 49(2021)
• Publication Date: 2021-08
• Subjects: Product design -- Big data -- Customer requirements -- Kano model -- Function implementation; Computer-aided engineering -- Periodicals; Engineering -- Data processing -- Periodicals; 620.00285
• DOI: 10.1016/j.aei.2021.101340
• Languages: English
• ISSNs: 1474-0346

Abstract

Highlights: Customer reviews are collected automatically using a focused crawling method. Product review comments are matched with CRs by a hierarchical semantic similarity method. A curve is formed to define relationships between CRs and the function implementation. CRs are classified efficiently and accurately to guide product design. Abstract: The classification of customer requirements (CRs) has a significant impact on the solution of product design. Existing CRs classification methods such as the Kano model and IPA model are time-consuming and inaccurate. This paper proposes a CRs classification method for product design using big data of online customer reviews of products to classify CRs accurately and efficiently. Comments of customer reviews are matched to CRs using a hierarchical semantic similarity method. Customer satisfaction degrees are defined based on emotional levels of adjectives and adverbs of customer comments using word vectors. The function implementation degree of each product is determined by specifications crawled from online products. Fitting curves are formed by defined customer satisfaction and function implementation of CRs using polynomial modeling and least square methods. Based on the slope of the fitted curves, CRs are classified to provide the minimum and maximum function implementations of CRs in each CR group to guide a product design process. The proposed method is applied in a case study of defining CRs classifications for design of upper limb rehabilitation devices. For verifying the proposed method, CRs defined by the existing methods are compared with CRs from the proposed method in design of an upper limb rehabilitation device.