A new framework of data assessment and prioritization for real-time prediction of spatial information is presented. In next generation mobile networks, the real-time prediction of spatial information will be a promising application. Recent developments of the machine learning technology have enabled prediction of spatial information, which would be quite useful for smart mobility services including navigation, driving assistance, and self-driving. Image sensors in mobile devices like smartphones and tablets and in vehicles such as cars and drones and real-time cognitive computing like automatic number/license plate recognition systems and object recognition systems are also key enablers for forming spatial information. However, since image data collected by mobile devices and vehicles need to be delivered to the server in real time to extract input data for real-time prediction, the uplink transmission speed of mobile networks is a major impediment. The framework of data assessment and prioritization proposed in this paper reduces the uplink traffic volume while maintaining the prediction accuracy of spatial information. In our framework, machine learning is used to estimate the importance of each data element and to predict spatial information under the limitation of available data. Numerical evaluation using actual vehicle mobility dataset demonstrated the validity of this approach.