Research On Intelligent Recommendation To Mass Customization In The Big Data Environment

With the continuous development of the economy,consumers’ living standards are gradually improved,and the majority of users are no longer satisfied with the standardized products provided by the enterprise.At the same time,the development of enterprise information technology and the improvement of factory’s flexible manufacturing capabilities have created conditions for the formation and development of mass customization business models.In the big data environment,various types of data are exploding,and more and more custom solutions and module attribute values in the mass customization industry have been added to the customization link,making users who choose product customization feel at a loss when faced with a large number of choices.Therefore,based on the previous personalized recommendation research for mass customization,this thesis combined the existing big data environment to carry out corresponding improvement research to improve the accuracy of the mass customization intelligent recommendation results.Firstly,based on the review of previous research results,this thesis analyzes the existing problems of intelligent recommendation for Mass Customization under the big data environment: the traditional e-commerce recommendation directly applied to the recommendation process of mass customization industry will have certain discomfort and the arrival of the era of big data,which makes the traditional recommendation algorithm for mass customization have shortcomings,and in view of these problems,the thesis puts forward the corresponding improvement necessity and ideas;Secondly,a specific analysis of the mass customization industry intelligent recommendation system is carried out,and a new and more complete intelligent recommendation system model for mass customization--overall customization proposal + step-by-step customization proposal recommendation is proposed to meet the needs of different users,and explains the corresponding recommendation process;Thirdly,based on the analysis of the limitations of traditional recommendation algorithms and the characteristics of mass customization industry in big data environment,collaborative filtering recommendation algorithm is selected as the basic algorithm of intelligent recommendation for mass customization,and the user profile method is integrated to improve the traditional collaborative filtering recommendation algorithm ignores the user’s own interest preference,K-means clustering algorithm is integrated to improve the data sparsity of traditional collaborative filtering recommendation algorithm in big data environment,so as to further improve the accuracy of recommendation;Finally,the case of product customization in mobile phone industry is introduced to simulate and analyze the two improved hybrid recommendation algorithms,which verify the effectiveness and feasibility of the algorithm applied to mass customization intelligent recommendation.