Online multi-attribute procurement auction has been widely used in many fields, such as project bidding, government procurement and so on. However, in the actual procurement auction, purchasers often have varying degrees of uncertainty about the information such as commodity related attributes. So it is difficult to describe related attributes and determine the corresponding weights, thereby increasing the difficulty of purchaser's decision on supplier selection. To deal with these problems, from the purchaser's interests, considering the influence of the risk attitude on decision-making behavior and introduce the prospect theory, we study the decision question of supplier selection for online multi-attribute procurement auction in the case of coexistence of four fuzzy description modes. Under the condition of comprehensive considering of the subjective and objective factors for determining the attribute weights, we propose a new decision method of supplier selection for online multi-attribute procurement auction. Finally, relevant example analysis and comparison illustrate the effectiveness of the proposed method.