Study On Closed-loop Quality Control Based On After-sale Service Of Products

In recent years,the rapid development of China's manufacturing industry has made the challenges faced by enterprises increasingly arduous,and enterprises are also increasingly aware of the importance and urgency of quality management.After-sale service quality control is an indispensable part of quality control,which is more and more widely considered to be the key factor for the success of manufacturing enterprises in today's competitive environment.This paper will focus on the implementation framework and key technologies of after-sales service quality control,and explore the quality problems in the process of after-sales service through data mining technology,which has important practical significance for improving product quality and service quality,and improving the market share and competitiveness of enterprises.At first,for the after-sale service for inquiry and feedback of quality problems in the quality control is less,difficult to solve the problem of quality defects from fountainhead,is proposed based on the product after-sales service quality of closed loop control framework,to guide the enterprise to realize the design,manufacture and after-sale service stage of quality control,and based on the quality of after-sales service phase feedback,lay the foundation for subsequent key technology research.Secondly,user requirements can provide decision support for quality improvement,but it is difficult to comprehensively obtain user requirements from user comments.Based on this,a user requirements mining model based on the improved dictionary and dependency syntax is proposed.The TF-IDF algorithm is used to extract product feature words and emotion words from the review data,and then the product features are quantified by combining the relevant dictionaries with the dependency syntax to obtain user requirements.Third,although massive data are generated in the process of maintenance,repair and other services,the analysis of these data is relatively scarce.Based on this,a service data mining model based on improved FP-Growth algorithm is proposed.By comparison and analysis of examples,it is concluded that the mining model based on the improved FP-Growth algorithm has shorter time and higher correlation than the mining model obtained by the improved algorithm.Then,aiming at the problem that the quality defects in the service process are difficult to be traced,the data warehouse of parts quality is established to integrate the data related to the quality of parts.On this basis,a traceability model of parts quality based on decision tree C4.5 algorithm is proposed to mine the key factors that affect the quality of products.A case study shows that the traceability model based on decision tree C4.5 algorithm and part quality data warehouse can effectively complete the quality traceability.Finally,based on the above framework and key technology research,the architecture and functional modules of the closed-loop quality control system based on product after-sales service are designed,and the development platform,database and Python language are used to complete the development of the system.