Product optimization design based on online review and orthogonal experiment under the background of big data

Abstract

The individuation and diversity of customer demands motivates enterprises to compete in various aspects of services, such as product categories, cost, performance, marketing and after-sales service. Among them, product optimization design is the most important link, which determines whether an enterprise can achieve sustainable development in the market of fierce competition. For this reason, enterprises must implement various competitive strategies in terms of product diversity and characteristics. To solve this challenge, optimizing innovative product design is the key to help enterprises gain competitive advantage in the market. This paper presents a product optimization design based on online review and orthogonal experiment under the background of big data to meet customer needs. First, the big data of online reviews are collected from the web platform through the data collector, and the original data are processed by the apriori algorithm. Secondly, the fuzzy clustering was used to analyze the processed online reviews data to obtain customer needs. Finally, the product is optimized by orthogonal test based on customer needs. This paper analyzes the case of Huawei Honor 9 mobile phone, and obtains that the product appearance is the most concerned and dissatisfied product attribute of customers, and then optimizes the design of product appearance to improve customer satisfaction. Through this method, enterprises can improve the design of products according to the needs of customers in time, effectively overcome the defects of products, and help enterprises to establish a good relationship with customers, so as to promote the sustainable development of enterprises in the competitive market.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 11 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.