US 12,341,732 B2
Ranking chatbot profiles
Rahul Dutta, Bangalore (IN); Amit Krishna, Bangalore (IN); Love Hasija, Sonepat (IN); and Atul Kumar, Bangalore (IN)
Assigned to Optum Technology, Inc., Eden Prairie, MN (US)
Filed by Optum Technology, Inc., Eden Prairie, MN (US)
Filed on Dec. 23, 2020, as Appl. No. 17/132,841.
Prior Publication US 2022/0200934 A1, Jun. 23, 2022
Int. Cl. G06N 20/00 (2019.01); G06F 40/35 (2020.01); G06N 3/045 (2023.01); G06V 40/10 (2022.01); G06V 40/16 (2022.01); G10L 15/22 (2006.01); H04L 51/02 (2022.01); H04L 67/50 (2022.01)
CPC H04L 51/02 (2013.01) [G06F 40/35 (2020.01); G06N 20/00 (2019.01); G06V 40/10 (2022.01); G06V 40/176 (2022.01); G10L 15/22 (2013.01); H04L 67/535 (2022.05); G06V 40/15 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
storing, by one or more processors, a score for each chatbot profile of a plurality of chatbot profiles, wherein each of the plurality of chatbot profiles corresponds to a respective persona;
for each chatbot profile of the plurality of chatbot profiles:
collecting, by the one or more processors, biometric response data for a user while the user has an interaction session with the chatbot profile, the biometric response data comprising blood oxygen saturation data;
determining, by the one or more processors, an emotional response value of the user based on the blood oxygen saturation data; and
updating, by the one or more processors, the score for the chatbot profile based on the emotional response value;
determining, by the one or more processors, a ranking of the plurality of chatbot profiles based on the scores for the plurality of chatbot profiles; and
selecting, by the one or more processors, a chatbot profile from the plurality of chatbot profiles for a subsequent interaction session with the user based on the ranking of the plurality of chatbot profiles.