Intellectual property contributions in telecommunications and machine learning
Systems and methods to identify whether user traffic is generated indoors or outdoors using geolocation data, network data, and building maps to generate demand density maps for capacity planning.
Machine learning system that uses historical data to recommend top capacity solutions for new locations using clustering techniques.
Systems to identify indoor vs outdoor traffic patterns for improved capacity planning and building-level network optimization.
Systems that analyze network and vehicular congestion on roadways to generate enhanced maps showing optimal routes with maximum network coverage.
Methods for generating demand density maps depicting network traffic usage patterns at building level for hotspot identification.
Machine learning model trained on historical capacity solutions to recommend optimal deployment strategies for new locations.
Systems to detect abnormal behavior of cell sites and customers to enhance capacity planning and identify congestion patterns.
Methods for merging vehicular and network congestion data to help users plan trips with optimal network coverage.
Systems for identifying and predicting network congestion at cell sites to enable preventive and remedial actions.
Methods for determining reduced average user throughput and predicting congestion occurrences at telecommunications cell sites.
Systems for facilitating identification and prediction of congestion at cell sites within LTE networks.