Integration of Cloud Computing and Big Data Technology in Computer Informatization Construction

Abstract

The combination of big data with cloud computing technologies has surfaced as a paradigm-shifting approach in computer information building, fundamentally altering the ways in which enterprises handle, evaluate, and employ copious volumes of data. In this manuscript, Integration of Cloud Computing and Big Data Technology in Computer Informatization Construction (ICCBDT-CIC-RBAGCN-FOA) proposed. Initially input data are gathered from Internal Revenue Service Dataset. To execute this, input data is pre-processed, Adaptive-Noise Augmented Kalman Filter (ANAKF) and data cleaning; then pre- processed image is fed to computer information construction utilizing Relational Bilevel Aggregation Graph Convolutional Network to evaluate and analysis the process of computer information construction. In generally, RBAGCN doesn’t express adapting optimization strategies to determine optimal parameters to ensure Cloud Computing and Big Data Technology based computer information construction. Therefore, Fox-inspired Optimization Algorithm (FOA) is to optimize Relational Bilevel Aggregation Graph Convolutional Network which accurately constructs computer information. Then the ICCBDT-CIC-RBAGCN-FOA is implemented in Python and performance metrics such as Accuracy, Precision, Recall, Acceleration rate, Task execution rate and Response Time are analysed. Performance of ICCBDT-CIC-RBAGCN-FOA approach attains 18.57%, 22.15% and 31.10%  higher accuracy, 19.59%, 23.12% and 32.60% higher Precision and 19.57%, 25.15% and 31.60% higher Recall when analysed through existing techniques like Contactless technologies for smart cities: big data, IoT, and cloud infrastructures(CTSC-BDCI-SVML) , Designing an Accounting Information Management System Using Big Data and Cloud Technology(DAIMS-BDCT-RBM)  , Construction of Digital Platform of Religious and Cultural Resources Using Deep Learning and Its Big Data Analysis(CDP-RCR-BDA-CNN) methods respectively.