Analysis On The Driving Force Of Dishes Based On Complex Network In Catering Field

With the gradual development of the catering industry and the development of catering cloud technology in Internet services,some catering businesses and service providers who have relatively sophisticated information management system accumulated a large number of catering transaction data.It is of great significance to find out the effective information from the transaction data for the precision marketing and sales risk assessment.However,there are many problems in the existing methods of data mining in catering history data,such as low precision and poor applicability.Based on complex network theory,this paper devotes to put forward an analysis method for food and beverage data based on complex network.In the food and beverage industry,the driving force of dishes reflect the ability of the dishes to stimulate the overall consumption growth of other dishes due to their own consumption growth.In this paper,we use the complex network theory to calculate and analyze the dynamic force of the dishes,and then carry out the effective information mining.In order to achieve the above target,this paper first analyzes and quantifies the relationship between food catering trade data,and by means of comparing with the random network model,a symbolic complex network of dishes is constructed,which can be used to make qualitative and quantitative calculation of the relationship reflecting the pulling and blocking impacts.Based on the symbol dishes network,this paper puts forward a new method to calculate the driving force of dishes by considering the combination between idea of complex network communication model and the characteristics of food and beverage data.Due to the particularity of the relationship between different dishes in catering data,the existing network propagation model can not fully reflect the relationship between dishes.According to the characteristics of symbolic network,this paper proposes a linear threshold model which can be used in the calculation of the dynamic force of dishes and applies it to the calculation of the driving force of dishes,through building a different activation strategy.On the basis of the above work,this paper has carried on the experiment on the real bill data provided by a catering company.This paper compares the proposed method with the traditional method of ranking dishes in the restaurant industry as well as the a node ranking method on symbol networks,to verify the rationality and validity of the proposed approach.