The scale of urban new parking space is studied in this paper to alleviate the problem of the imbalance between the supply and demand of urban parking space. The shared berth allocation model is introduced to predict the parking demand, and grey ideal correlation entropy theory is used to propose the concept of parking lot scale correction coefficient, and then the number of new parking lot berths is calculated. In the research, three newly-built parking lots within the business district of Lhasa Shenli Times were selected as the research objects, and the current parking supply status, actual parking demand, and average walking distance of their commercial and residential areas were investigated and analyzed. The particle group optimization algorithm were introduced to obtain the parking demand of the newly-built parking lot, and then the berth scale of the newly-built parking lot is calculated based on the correction coefficient. The results of this paper is hoped to effectively make up for the shortcomings of the shared berth allocation model in practical applications, and provide a solution to the parking problem in urban commercial circles.