US 11,792,251 B2
Media stream network action decisions
Craig M. Trim, Ventura, CA (US); Kimberly Greene Starks, Nashville, TN (US); Michael E. Alexander, Great Falls, VA (US); Gandhi Sivakumar, Victoria (AU); Kushal Patel, Pune (IN); and Sarvesh S. Patel, Pune (IN)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on Jan. 6, 2020, as Appl. No. 16/734,777.
Prior Publication US 2021/0211479 A1, Jul. 8, 2021
Int. Cl. H04L 65/75 (2022.01); H04L 65/80 (2022.01); G10L 15/26 (2006.01); H04L 67/55 (2022.01)
CPC H04L 65/75 (2022.05) [G10L 15/26 (2013.01); H04L 65/80 (2013.01); H04L 67/55 (2022.05)] 20 Claims
OG exemplary drawing
 
1. A computer implemented method comprising:
transmitting, during a media streaming session, streaming media to a user equipment (UE) device of a user, the transmitting streaming media including simultaneously transmitting a first media stream and a second media stream to the UE device, wherein the simultaneously transmitting the first media stream and the second media stream to the UE device is performed by a virtual machine (VM) running on a computing node of an edge computing environment, wherein the method includes, during the transmitting, migrating a virtual machine (VM) defining a media server from a core computing environment to an edge computing environment, wherein the VM is configured for simultaneously transmitting the first media stream and the second media stream to the UE device;
subjecting, by the VM running on the computing node of the edge computing environment, the first media stream to processing by natural language processing to provide a topic extracted from the first media stream;
subjecting, by the VM running on the computing node of the edge computing environment, the second media stream to processing by natural language processing to provide an extracted topic extracted from the second media stream;
identifying, by the VM running on the computing node of the edge computing environment, a match between the topic and the extracted topic; and
providing one or more output in response to the identifying the match between the topic and the extracted topic, wherein the first media stream is a primary media stream for primary viewing by the user, wherein the providing one or more output in response to the identifying the match between the topic and the extracted topic includes transmitting a notification to the user, wherein method includes examining a streaming media type of the first media stream, and querying a predictive model using the media type to return prediction data specifying predicted performance of a network slice configuration, and selecting a network slice using the prediction data, wherein the predictive model has been trained by machine learning using training data that comprises slice performance data from historical media streaming sessions, and wherein the method includes transmitting the first media stream over the network slice.