Wise in Vaccine Allocation

In this paper, the machine learning method and mathematical model are used to predict the number of future vaccinations, and the problem of how to distribute vaccines to central hospitals, community hospitals and health centers is solved [1], [2]. In the context of the growing importance of vaccination, we need to rationalize the distribution of vaccines to central hospitals, community hospitals and health centers, taking into account the need and cost of vaccination. First, in order to predict the national daily vaccination figures for the next three months, we consulted relevant website data to obtain the vaccination figures for each day since the vaccination began in March 2021, and made the forecast for the next three months through the time series prediction method LSTM [3], [4]. Combined with the increment of the number of daily vaccinations as the label value, the final prediction results were obtained. Second, we first collected data and analyzed and processed the characteristics. Through collinearity analysis [5], we found that the number of residents and the number of medical personnel had strong collinearity, and the logarithm of the number of residents was calculated with log10. Then AHP [6] was used to analyze the impact of the number of nearby residents, convenient transportation, number of medical personnel, vaccine storage and transportation costs on vaccine distribution, and CR index was used to evaluate our model. The third question is to substitute the collected data of the two regions into the model of the previous question, and we subtract 10% number of nearby residents from the index of central hospitals as a penalty for crowd gathering. Got central hospitals, community hospitals, and health centers vaccine distribution ratio: Hangzhou Gongshu District 4.8:3.3:1.9; Harbin Daoli District 3.6:4.7:1.7 [7]. Fourth, in combination with our model and conclusions, we provide an adequate explanation for vaccine distribution.