Mining and Analysis of Multidimensional Information in Big Multimedia Data Using Association Rule Mapping Model

This paper aims to explore a new algorithm that can effectively handle big data in multidimensional information networks with high mining accuracy, fast execution efficiency, and low memory consumption. The algorithm adopts an association rule mapping-based approach, which can efficiently process large volumes of data. This algorithm can establish a complex mapping mechanism to identify the interrelationships among various network datasets, greatly enhancing mining accuracy by incorporating parameters such as relative error. Additionally, data from different subspaces can be divided based on the strength of their interconnections, resulting in better mining results for various data types. In the experiments, simulations were conducted to analyze the algorithm’s memory usage, mining accuracy, and runtime under different dataset sizes. The results demonstrate that the association rule mapping-based mining algorithm can significantly improve mining accuracy and also has advantages in reducing memory usage and increasing computational speed.