US 12,450,487 B2
Artificial intelligence-based personalized financial recommendation assistant system and method
Marcus Edwards, Waterloo (CA); and Mark Church, Waterloo (CA)
Assigned to 10353744 Canada Ltd., Kitchener (CA)
Filed by 10353744 Canada Ltd., Kitchener (CA)
Filed on Mar. 26, 2021, as Appl. No. 17/214,372.
Claims priority of provisional application 63/000,167, filed on Mar. 26, 2020.
Prior Publication US 2021/0303973 A1, Sep. 30, 2021
Int. Cl. G06N 3/082 (2023.01); G06F 18/21 (2023.01); G06N 3/045 (2023.01); G06N 3/08 (2023.01); G06N 5/04 (2023.01)
CPC G06N 3/082 (2013.01) [G06F 18/2178 (2023.01); G06N 3/045 (2023.01); G06N 3/08 (2013.01); G06N 5/04 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A computer system for generating and providing intelligent recommendations using artificial intelligence (“AI”), the system comprising:
a memory for storing processor-executable instructions, user feedback data, user resource data representing user resources of a user, and user goal data representing user goals of the user;
a user interface (UI) configured to receive user input from the user;
a processor in communication with the memory, the processor configured to execute the processor-executable instructions comprising:
a first AI model for providing a user-specific graphical presentation of the user interface based on the user feedback data, the user resource data, the user goal data, and user interaction with the user interface, wherein the user-specific graphical presentation of the UI includes user-specific UI elements as determined by a generative code effectiveness learning model;
a second AI model for selecting user-specific strategy for achieving a financial goal based on the user feedback data, the user resource data, and the user goal data;
wherein, the first AI model constrains the second AI model based on user-specific inferences of strategies as determined from the user interaction with the user interface;
a model mapping module configured to implement a functional mapping between the first AI model and the second AI model through which the first AI model and second AI model communicate and mutually update each other, wherein the first and second AI models are in separate domains and similarities between morphologies of a plurality of learned inferences of the user are enforced across the domains, and wherein user-specific inferences are limited using morphologies of at least one user interface workflow that is known to constrain morphologies of at least one subgraph in the second AI model; and
a user interface generator module for generating a user-specific user interface for outputting the intelligent recommendations, including user-specific UI elements and the user-specific strategy based on the functional mapping between the first AI model and the second AI model, and receiving the user feedback data.