In order to solve the problem of unreasonable distribution route, the tobacco distribution route optimization model was established according to the characteristics of tobacco distribution.

In order to solve the problem of distribution area segmentation of tobacco distribution, an improved K-means clustering algorithm was proposed.

Genetic algorithms are applied to design the encoding scheme,selection,crossover and mutation operator as well as to establish computer simulation models to find the solution,which obtains the optimal allocation schema of the cigarette distribution region partition and solves the corresponding problems.

Taking Jinan Tobacco Distribution Center as an example, the paper introduces the establishment of modern cigarette logistics system and the efficiency produced and puts forward the concept of 'public logistics information platform'.

In this paper, the vehicle routing optimization of cigarette distribution of the city based on Particle Swarm Optimization (PSO) is researched.

This article introduces the concept、core technologies of business intelligence and introduced mainly neural network, genetic algorithm used by the article,introduced the architecture of business intelligence,according to the architecture,designed the architecture based on tobacco formula.