Open AccessResearch on Non-structural Big Data Analysis Algorithm of Communication Network Based on Feature Fusion
Author(s) -
Xiangda Meng
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1982/1/012096
Subject(s) - big data , computer science , relevance (law) , delegate , feature (linguistics) , key (lock) , data mining , dimension (graph theory) , set (abstract data type) , data set , artificial intelligence , algorithm , data science , mathematics , linguistics , philosophy , computer security , political science , pure mathematics , law , programming language
Nowadays, Along with the fast development of information technology, the scale of data is increasing in an exponential way, and the worth of big data has been paid increasingly interested. At present, there are two key problems in the category of big data: how to delegate big data as a integrate model and what efficiently reduce dimensions of big data. Although the processing technology of various mold of data has been studied, the efficiency of parallel query has not been optimized deeply. Especially, it is more difficult to analyze the information of online users with widely dispersed information. A communication network non-structural big data analysis algorithm based on semantic relevance feature fusion is proposed, which reconstructs the high-dimensional phase space of the distributed information flow of cloud storage big data, extracts the semantic relevance dimension feature quantity of big data from the reconstructed phase space, and conducts adaptive learning training with the extracted feature quantity as the test set. Knowable from the simulation experiment that the algorithm effectively reduces the generation of redundant messages and improves the network running environment.