US 12,299,746 B2
Generative artificial intelligence-based agents using customized neural networks
Thomas N. Blair, Irvine, CA (US); Alex A. Kurzhanskiy, Albany, CA (US); Spyros J. Lazaris, Los Angeles, CA (US); Leo Richard Jolicoeur, Reno, NV (US); Michael G. Mcerlean, Sioux Falls, SD (US); Tony Chiyung Lei, Reno, NV (US); and Craig I. Forman, San Francisco, CA (US)
Assigned to AGBLOX, INC., Irvine, CA (US)
Filed by AGBLOX, INC., Irvine, CA (US)
Filed on Feb. 5, 2024, as Appl. No. 18/432,523.
Application 18/432,523 is a continuation of application No. 17/240,961, filed on Apr. 26, 2021, granted, now 11,893,641.
Application 17/240,961 is a continuation of application No. 17/135,784, filed on Dec. 28, 2020, granted, now 10,991,048, issued on Apr. 27, 2021.
Application 17/135,784 is a continuation of application No. 16/945,169, filed on Jul. 31, 2020, granted, now 10,878,505, issued on Dec. 29, 2020.
Prior Publication US 2024/0242286 A1, Jul. 18, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 40/06 (2012.01); G06F 18/24 (2023.01); G06F 40/20 (2020.01); G06N 3/08 (2023.01); G06N 20/00 (2019.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01)
CPC G06Q 40/06 (2013.01) [G06F 18/24 (2023.01); G06F 40/20 (2020.01); G06N 3/08 (2013.01); G06N 20/00 (2019.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01)] 30 Claims
OG exemplary drawing
 
1. A method, comprising:
defining a selected asset-based subject matter;
receiving input data relative to the selected asset-based subject matter, the input data comprised of structured data sources and unstructured data sources;
developing a customized artificial intelligence-based agent configured to analyze the selected asset-based subject matter over time in response to one or more user-driven queries that are specific to one or more characteristics of the selected asset-based subject matter, by:
contextualizing the input data in a multi-layer machine learning-based model by:
building a taxonomy comprising specific keywords and keyword pairings that identify one or more predictors for the selected asset-based subject matter from the unstructured data sources,
identifying discrete-time data points constructed from the structured data sources that define temporal parameters relative to the selected asset-based subject matter,
modifying the taxonomy with the temporal parameters to create a set of classified content, and
constructing knowledge-based rules representing specific knowledge relative to the selected asset-based subject matter and derived from subject matter-specific indicators in the input data,
mapping the taxonomy and the knowledge-based rules into one or more subject matter-specific neural networks; and
executing the customized artificial intelligence-based agent in response to the one or more user-driven queries,
wherein responses to one or more user-driven queries are generated relative to the one or more characteristics of the selected asset-based subject matter by the customized artificial intelligence agent, and automatically initiate one or more actionable outcomes representing a performance of the selected asset-based subject matter that are executed by the customized artificial intelligence-based agent.