Telecom Network Data Service Prediction via Historical Behavior
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional cellular telecommunications networks face challenges in accurately predicting user location and radio conditions, leading to inconsistent data service and customer dissatisfaction, especially in areas with poor coverage, as existing methods rely on velocity and current location, which are inaccurate for long-term predictions and fail to account for changes in user route.
Innovation Solution
A method that retrieves historical user behavior data to predict future location within the network, allowing for accurate determination of network capabilities and service modifications, including adjusting base station configurations and resource allocation, to provide consistent service even in areas with poor coverage, without relying on device information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If current location and velocity data are used to predict future user location, then the prediction process is simple and fast, but the prediction accuracy is poor especially for long-term predictions and when users change route
Solution Approach 1:
The system performs preliminary actions by collecting and storing historical behavior data (location, velocity, route information) in advance. This historical data is then used to predict future user location with higher accuracy, eliminating the need for complex real-time calculations while maintaining prediction precision even when users change route
Solution Approach 2:
The patent introduces historical behavior data as an intermediary element between current state and future prediction. This intermediary data layer enables accurate long-term location prediction without requiring complex real-time computation, as the historical patterns serve as a mediator that captures user behavior trends
2Measurement precision
If device information and constant iterative recalculation are used to improve location prediction accuracy, then prediction accuracy may improve slightly, but data overheads and processing overheads increase significantly
Solution Approach 1:
The system applies self-service by utilizing already-collected historical behavior data stored in the network, eliminating the need for continuous device information collection and iterative recalculation. The historical data serves the prediction function directly, reducing both data overheads and processing overheads while maintaining high prediction accuracy
Solution Approach 2:
By performing preliminary data collection and storage of historical behavior patterns, the system avoids the need for constant iterative recalculation. The pre-stored historical data enables accurate predictions without requiring continuous processing, thereby reducing energy loss from ongoing computations
3Reliability
If network parameters and service parameters are adjusted based on predicted future location, then data service consistency can be improved, but the system requires accurate long-term location prediction capability
Solution Approach 1:
The system performs preliminary location prediction using historical behavior data to identify future locations where coverage deficiencies may occur. Based on these predictions, network parameters and service parameters are adjusted in advance, ensuring data service consistency without requiring complex long-term prediction algorithms
Solution Approach 2:
Historical behavior data serves as an intermediary that enables reliable parameter adjustment for service consistency. This intermediary data layer provides sufficient accuracy for predicting future locations where service optimization is needed, without requiring extremely precise long-term location prediction
4Device complexity
If conventional methods assume constant direction of travel for location prediction, then the prediction process is simple, but the accuracy deteriorates when users make turns or change route
Solution Approach 1:
Historical behavior data acts as an intermediary that captures actual user routing patterns including turns and route changes. This intermediary data enables accurate future location prediction without requiring complex real-time tracking, as the historical patterns naturally account for route variations
Solution Approach 2:
The system uses self-service by leveraging already-stored historical behavior data that inherently contains routing information. This eliminates the need for complex constant-direction assumptions or continuous route tracking, providing accurate predictions while maintaining simple processing
Data Source
AI summary
According to one aspect of the present invention there is provided a method for controlling data service for a user of a telecommunication network. The method comprising: retrieving data associated with historical behavior of the user within the network; predicting, based on said data and on a current user location within the network, a future user location within the network; performing a determination of network capability at the future user location; and modifying, in response to the determination, a configuration of the network and/or a service parameter associated with the user. A network element, system and computer program product are also provided.