Research on Optimization of Big Data Fusion QM Model Based on Block-chain Distribution

Abstract

In terms of poor classification and detection effect of big data fusion QM model as well as weak feature mining ability, a big data fusion QM model based on block-chain distribution optimization is proposed in the paper. Moreover, a block storage structure model for the distribution of big data is first established on the block-chain to perform shared scheduling according to the attribute distribution of the distributed big data on the block-chain, and then the big data of the distributed big data on the block-chain is mined. On this basis, the differentiated feature distributed retrieval method is used to cluster the distributed big data information on the block-chain, and the rough set feature quantity is extracted from the fuzzy cluster center. Meanwhile, combining the fuzzy correlation feature detection method, the information of the block-chain distributed big data is reorganized to extract the statistical features of each module. In addition, the quantitative recursion in the process of block-chain distributed big data fusion is analyzed, so that the optimization design of the QM model of block-chain distributed big data fusion can be realized. The simulation results show that the feature resolution ability of block-chain distributed big data fusion with the method proposed in the paper is better, and the classification detection and feature mining capabilities of block-chain distributed big data are improved, which has high application value in the block-chain distributed big data information retrieval and scheduling.