US 11,886,823 B2
Dynamically constructing and configuring a conversational agent learning model
Giuseppe Ciano, Rome (IT); Pietro Marella, Rome (IT); Leonardo Modeo, Rome (IT); and Luigi Pichetti, Rome (IT)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on Feb. 1, 2018, as Appl. No. 15/886,686.
Prior Publication US 2019/0238487 A1, Aug. 1, 2019
Int. Cl. H04L 51/00 (2022.01); G06F 40/35 (2020.01); H04L 51/02 (2022.01); G06N 5/02 (2023.01); G06N 20/00 (2019.01); G06F 40/30 (2020.01); G06F 40/56 (2020.01); G06F 40/216 (2020.01)
CPC G06F 40/35 (2020.01) [G06F 40/216 (2020.01); G06F 40/30 (2020.01); G06F 40/56 (2020.01); G06N 5/02 (2013.01); G06N 20/00 (2019.01); H04L 51/02 (2013.01)] 25 Claims
OG exemplary drawing
 
1. A method of dynamically constructing a conversational agent learning model, the method comprising:
retrieving a corpus of information, wherein the corpus of information includes records from a set of repositories and external data, including data from social networks or applications;
configuring the conversational agent learning model based upon the retrieved corpus of information, wherein configuring the conversational agent learning model comprises adding new model topics based upon completing a semantic analysis via an artificial intelligence computing system to classify unstructured content;
deploying the conversational agent learning model by facilitating interaction between the conversational agent learning model and a plurality of clients; and
updating the conversational agent learning model to address at least one modification to the corpus of information by adjusting dialog portion aspects to address questions regarding new technology or by adjusting dialog portion aspects to facilitate payment via the new technology.