| CPC G06V 10/82 (2022.01) [G06F 18/217 (2023.01); G06F 18/2413 (2023.01); G06F 18/251 (2023.01); G06V 10/764 (2022.01); G06V 10/776 (2022.01); G06V 10/803 (2022.01)] | 10 Claims |
|
1. A reinforcement learning-based sensor data management system, comprising:
a processor configured to:
manage virtualized objects that correspond to sensors included in a sensor network to update data received from each of the sensors and queries representing a data quality requested by an application;
calculate an abstracted action that abstracts a size of an action space of the sensor network based on present state information of the virtualized objects and the queries;
calculate scores for virtualized objects based on position relationships between the calculated abstracted action the virtualized objects; and
assign priorities to the virtualized objects based on the calculated scores to update data received from the sensors to the virtualized objects according to the priorities,
wherein the present state information includes aging degrees indicating time intervals between times at which the virtualized objects are most recently updated and a present time, update execution times indicating times required to update the virtualized objects after determining to update the virtualized objects, and remaining execution times indicating times remaining until updates of the virtualized object are completed, and
wherein the queries include aging degree upper limits and deadlines for the virtualized objects.
|