US 11,914,650 B2
Data amalgamation management between multiple digital personal assistants
Craig M. Trim, Ventura, CA (US); Nadiya Kochura, Bolton, MA (US); Jeremy R. Fox, Georgetown, TX (US); and Fang Lu, Billerica, MA (US)
Assigned to INTERNATIONAL BUSINESS MACHINES CORPORATION, Armonk, NY (US)
Filed by INTERNATIONAL BUSINESS MACHINES CORPORATION, Armonk, NY (US)
Filed on Jul. 22, 2020, as Appl. No. 16/935,380.
Prior Publication US 2022/0027414 A1, Jan. 27, 2022
Int. Cl. G06F 16/9032 (2019.01); G06F 9/46 (2006.01); G06F 9/54 (2006.01); G06F 16/9535 (2019.01); G06F 9/451 (2018.01)
CPC G06F 16/90332 (2019.01) [G06F 9/453 (2018.02); G06F 9/465 (2013.01); G06F 9/54 (2013.01); G06F 16/9535 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A processor-implemented method for data amalgamation management, the method comprising:
monitoring conversation between a user and a first virtual assistant from a plurality of virtual assistants for a confidence score value being below a confidence threshold value, wherein the confidence score value is associated with each answer of the first virtual assistant;
generating a dialog flow for answering by a second virtual assistant, wherein the dialog flow is related to a first answer, the confidence score value of the first answer being below the confidence threshold value; and
in response to the second virtual assistant generating a second answer corresponding to a second confidence score value that is above the confidence threshold value, transferring knowledge base data of a topic associated with the dialog flow from the second virtual assistant to the first virtual assistant.