US 11,954,453 B2
Natural language generation by an edge computing device
Chih-Hsiung Liu, Taipei (TW); I-Chien Lin, Taipei (TW); Cheng-Fang Lin, New Taipei (TW); and Joey H. Y. Tseng, Taipei (TW)
Assigned to INTERNATIONAL BUSINESS MACHINES CORPORATION, Armonk, NY (US)
Filed by INTERNATIONAL BUSINESS MACHINES CORPORATION, Armonk, NY (US)
Filed on Mar. 12, 2019, as Appl. No. 16/299,665.
Prior Publication US 2020/0293914 A1, Sep. 17, 2020
Int. Cl. G10L 25/00 (2013.01); G06F 17/18 (2006.01); G06F 18/214 (2023.01); G06F 40/56 (2020.01); G06N 3/08 (2023.01); G06N 5/025 (2023.01); G06V 10/764 (2022.01); G06V 10/774 (2022.01); G06V 10/80 (2022.01); G06V 10/82 (2022.01); G10L 25/30 (2013.01); G10L 15/02 (2006.01); G10L 15/16 (2006.01)
CPC G06F 40/56 (2020.01) [G06F 17/18 (2013.01); G06F 18/2148 (2023.01); G06N 3/08 (2013.01); G06N 5/025 (2013.01); G06V 10/764 (2022.01); G06V 10/7747 (2022.01); G06V 10/806 (2022.01); G06V 10/82 (2022.01); G10L 25/30 (2013.01); G10L 15/02 (2013.01); G10L 15/16 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
receiving, by an edge computing device, event data from an edge event;
determining, by the edge computing device, that a network connection to a cloud server is not available;
extracting, by the edge computing device, features of the event data;
predicting, by a local neural network of the edge computing device, an action for the edge computing device to take based on the features of the event data, wherein the predicted action is associated with a confidence level;
determining, by the edge computing device, that the confidence level associated with the predicted action for the edge computing device to take does not meet a predetermined threshold value; and
determining, by the edge computing device, whether the network connection to the cloud server is now available in response to the determining that the confidence level associated with the predicted action for the edge computing device to take does not meet the predetermined threshold value.