Internet of Vehicles Information Processing Method with Vehicle-Mounted Cloud Grid as the Underlying Data Fusion Structure

With the development of electronic information network technology, large car networking systems can produce all kinds of data such as text, images, and videos, a large number of heterogeneous data, different features of heterogeneous data, and different data structures. In the Internet of vehicles, the beacon message generation strategy needs to be researched and designed on the premise of meeting the requirements of vehicle location accuracy and wireless communication performance. According to the Kalman filter differential prediction equation, the message generation model of Kalman filter beacon is established. In the deep learning research on the underlying data fusion algorithm, the most effective way to solve the problem of insufficient integration degree between the underlying data is to improve the data quality and ensure data sharing and reuse between multisource heterogeneous data. Therefore, the D-S evidence theory fusion model and rough set underlying model are proposed in the vehicle-mounted cloud network. Among them, the D-S evidence theory fusion model ensures the improvement of underlying data quality, forms effective rule combination, and reduces conflicts between rules through filtering evidence theory. The rough set underlying data fusion model optimizes the underlying data of each device by improving the rough set attribute reduction method of particle swarm optimization algorithm.