Multidimensional Evaluation of Network Information Resources based on Chaotic Coupling of Big Data

Abstract

Aiming at the problems of scattered user information resources in deep fusion social networks, which leads to poor accuracy of information resource detection and evaluation and large data transmission delay, a multidimensional evaluation method of network information resources based on chaotic coupling of big data is proposed. We construct a deep fusion social network information resource mining and feature extraction model, realize machine optimization of network information resources through decision scheduling, use similarity feature analysis to mine the joint association rules of deep fusion social network information resources, combine nonlinear system analysis methods to construct a big data chaotic coupling control model of network resource information, and realize the multidimensional phase space reconstruction of network information resources under the guidance of logistic chaotic mapping. The multi-dimensional evaluation and characterization of network resources are realized in the reconstructed phase space of deep fusion social network information resource distribution. The simulation results show that the method is used for the multidimensional evaluation of network information resources with a high level of convergence and good convergence, which effectively improves the access and scheduling capability of network information resources.