Internet-of-vehicles big data cross-domain analysis fusion method

Abstract

The invention relates to an Internet-of-vehicles big data cross-domain analysis fusion method, which is mainly characterized in that an Internet-of-vehicles cloud data mining architecture is established, and the Internet-of-vehicles cloud data mining architecture comprises a distributed data access engine, a parallel mining engine, proxy nodes and a Web server cluster; performing data mining by adopting an Internet-of-vehicles data mining algorithm; and realizing a parallel function of the shared memory by adopting a shared memory parallel computing technology. According to the method, a clouddata mining architecture which is composed of a distributed data access engine, a parallel mining engine, a Web server cluster and agent nodes and can support parallel computing is adopted, so that the supporting capability for mass data is improved; through a data preprocessing technology, an uncertain data preprocessing technology and an Internet-of-vehicles industry data processing and fusiontechnology, support of Internet-of-vehicles specific data such as streaming data is optimized; based on novel data mining algorithms such as mining, analysis, clustering technology, behavior recognition and anomaly detection of the Internet-of-vehicles streaming data, the intelligent level of the system is improved.

Description

technical field [0001] The invention belongs to the technical field of data mining and computing, in particular to a method for cross-domain analysis and fusion of big data of the Internet of Vehicles. Background technique [0002] At present, in order to meet the real-time, continuous, and fast arrival characteristics of IoT data streams and the application requirements of online analysis, it must be realized through stream data mining algorithms with low time complexity and low space complexity. [0003] As an important application of the Internet of Things, the Internet of Vehicles needs to fully mine the correlations in its stream data, for example, traffic accident black spot analysis (correlations between traffic accidents and time, location, weather conditions, etc.) and so on. Since a very important application of the Internet of Vehicles is to process and analyze various information, find abnormal situations and give early warnings, traditional data mining algorithm...

AI Technical Summary

Problems solved by technology

Since a very important application of the Internet of Vehicles is to process and analyze various information, find abnormal situations and give early warnings, traditional data mining algorithms are based on statistical ideas for detection, and the problem is that they need to know the distribution characteristics of the data in advance. However, due to the large amount of data in the Internet of Vehicles, it is impossible to analyze the distribution characteristics of all historical data; in addition, in the existing Internet of Vehicles system, the data stream generated by the Internet of Vehicles has the characteristics of real-time, continuous, and fast arrival, and there are online The application requirements of the analysis, and the diversity of data formats of the terminal collection equipment and other factors make the existing data mining algorithms unable to effectively analyze the data

Images