Research Article
Query Optimization Method for Massive Heterogeneous Data of Internet of Things Based on Machine Learning
@INPROCEEDINGS{10.1007/978-3-030-67871-5_31, author={Yun-wei Li and Lei Ma}, title={Query Optimization Method for Massive Heterogeneous Data of Internet of Things Based on Machine Learning}, proceedings={Advanced Hybrid Information Processing. 4th EAI International Conference, ADHIP 2020, Binzhou, China, September 26-27, 2020, Proceedings, Part I}, proceedings_a={ADHIP}, year={2021}, month={2}, keywords={Machine learning Dirichlet smoothing method Heterogeneous data Internet of things}, doi={10.1007/978-3-030-67871-5_31} }- Yun-wei Li
Lei Ma
Year: 2021
Query Optimization Method for Massive Heterogeneous Data of Internet of Things Based on Machine Learning
ADHIP
Springer
DOI: 10.1007/978-3-030-67871-5_31
Abstract
In view of the problem that the traditional query optimization method of massive heterogeneous data of the Internet of things can not describe the data characteristics clearly, which results in the long execution time of data query, a query optimization method of massive heterogeneous data of the Internet of things based on machine learning is designed. It divides the massive heterogeneous data query level of the Internet of things, and extracts the data characteristics according to the hierarchical structure and the Dirichlet smoothing method in machine learning. The feature data is transformed into a query tree, and a dynamic data dictionary is constructed. The data dictionary is referred to the traditional query optimization method of massive heterogeneous data in the Internet of things. At this point, the query optimization method for massive heterogeneous data of the Internet of Things based on machine learning is designed. The test link of the construction method shows that the use effect of this method is better than the original method and the method based on artificial intelligence technology.
