Full Recognition of Massive Products Based on Property Set

In recent years, with the development of e-commerce, the number of online products increases rapidly. Faced with such a mass of data, we need to establish an efficient unified product standard. However, in terms of the whole e-commerce industry there lacks a unified standard which can coordinate with existing standards. In this paper, we put forward an effective solution to unifying products, which is then applied to business intelligence data analysis. The main work and contributions are as follows: 1) an effective solution to unifying product data, 2) a parallel data mining algorithms which solves the problem of identifying similar products from massive product data, 3) the framework is universal, although our project is based on Taobao´s data cloud, it can also be applied to other e-commerce area.