Prediction and Performance Optimization of Hospital Web Application Access Modes Based on Big Data Analysis

Abstract

Data in hospital information systems contain errors, inconsistencies, and other issues that mask the true underlying patterns in the data, making the existing time series patterns blurry and leading to increased prediction errors in access patterns. To this end, research is being conducted on the prediction and performance optimization of hospital web application access patterns based on big data analysis. Firstly, semi-structured log data and structured information data from hospital web applications are collected and preprocessed. Then, a deep belief network (DBN) is used for feature extraction, and a deep learning model consisting of a stacked restricted Boltzmann machine (RBM) and a BP neural network is utilized to automatically extract multidimensional information such as user behavior features, temporal features, and page features, constructing a comprehensive feature system. Finally, based on the gated recurrent unit (GRU) neural network for access mode prediction, the control information selection mechanism of GRU is utilized to capture time series information and improve the accuracy of prediction. The experimental results show that the proposed prediction method has a practical application value with a mean square error of 0–50 for predicting traffic and a response rate within 5 seconds after application.