Medical Big Data Service System

Medical electricity business is gradually from the blue ocean to the electricity business over the Red Sea,the network is increasingly becoming a medical advisory,drug delivery and related transactions of the important places.But the medical electricity on the platform of a variety of commodity data,sales data and medical service data is relatively independent.In order to produce independent data in the integration of medical and electrical industry and to explore buried in the data under the potential valuable information,so that can meet the growing demand for medical and electrical industry of big data.This paper presents a program to build a medical big data service system and provides special service for drug recommendation and sales forecasting.First of all,this paper introduces the composition of medical big data service system.The system is composed of medical big data acquisition,data analysis platform and report presentation of three subsystems.The big data acquisition subsystem is responsible for data collection and push data to the big data analysis platform.The data analysis subsystem is responsible for analyzing the collected data using the recommended algorithm and prediction algorithm to realize the characteristics of drug recommendation and drug sales forecast.The report presentation subsystem is responsible for presenting the results of the analysis in a visual form.Secondly,this paper studies the technology of text similarity calculation.In the process of extracting feature words,the text of the data is purified by taking into account the actual situation of the data,which reduces the data dimension and improves the accuracy of the calculation results.Combined with the characteristics of the text feature of the drug description,the traditional spatial vector model can not reflect the performance of the different order feature in the text similarity calculation.The experimental results show that the improved spatial vector model improves the similarity between drugs and the accuracy of drug recommendation.Finally,this paper studies the time series prediction model related technology,and introduces the ARIMA and GM(1,1)models in detail.In order to find a more accurate and effective prediction method,the ARIMA model is optimized by using the GM(1,1)model to correct the residuals of the ARIMA model.The experimental results show that the optimized GM-ARIMA model achieves the purpose of improving the prediction accuracy of the model.