US 11,989,636 B1
System and method for persuadable collaborative conversational AI
Richard Leeds, Bellevue, WA (US); and Elon Gasper, Bellevue, WA (US)
Assigned to Conversation Processing Intelligence Corp., Bellevue, WA (US)
Filed by Conversation Processing Intelligence Corp, Bellevue, WA (US)
Filed on Jul. 20, 2022, as Appl. No. 17/869,700.
Application 17/869,700 is a continuation in part of application No. 17/466,976, filed on Sep. 3, 2021, granted, now 11,431,660.
Claims priority of provisional application 63/083,769, filed on Sep. 25, 2020.
Claims priority of provisional application 63/149,163, filed on Feb. 12, 2021.
Claims priority of provisional application 63/185,324, filed on May 6, 2021.
Int. Cl. G06N 3/004 (2023.01); G06F 40/35 (2020.01)
CPC G06N 3/004 (2013.01) [G06F 40/35 (2020.01)] 26 Claims
OG exemplary drawing
 
1. A method for improved decision-making in an artificial intelligence having an experience chain data structure based on past experience, the steps comprising:
receiving a conversational input in natural language form, said input to which the artificial intelligence responds by deciding on a response;
recording the conversational input as a new experience chain link;
adding links representing at least one of associated contexts, memories, correlations, and causations to the new experience chain link;
determining at least one desired outcome;
predicting a value of the at least one desired outcome;
selecting a response based on the predicted value of the at least one desired outcome;
transmitting the response to a receiver;
observing the result of the response; and
creating a new extended experience chain data structure including context, prediction, correlation, and causation links to encode reinforcement based on the observed result.