US 11,941,500 B2
System for engagement of human agents for decision-making in a dynamically changing environment
Satyendra Pal Rana, Austin, TX (US); Ekrem Alper Murat, Shelby Township, MI (US); and Ratna Babu Chinnam, Rochester, MI (US)
Assigned to AGILE SYSTEMS, LLC, Rochester, MI (US)
Filed by Agile Systems, LLC, Rochester, MI (US)
Filed on Dec. 20, 2022, as Appl. No. 18/068,636.
Application 18/068,636 is a continuation in part of application No. 17/643,635, filed on Dec. 10, 2021, granted, now 11,531,501.
Prior Publication US 2023/0186162 A1, Jun. 15, 2023
Int. Cl. G06N 20/00 (2019.01)
CPC G06N 20/00 (2019.01) 27 Claims
OG exemplary drawing
 
14. A method for engagement of human agents for decision-making in a dynamically changing environment, the method comprising:
receiving, by a processor, an information request relating to a problem requiring a decision;
receiving, by the processor, problem data comprising metadata associated to the problem, and decision-making data;
generating, by the processor, training data comprising a plurality of information requests, problem data corresponding to the plurality of information requests, and corresponding information types for each of the plurality of information requests;
training, by the processor, an acquisition model based on the generated training data using at least one of a Natural Language Processing (NLP) algorithm, and a Natural Language Understanding (NLU) algorithm;
determining, by the processor, an information type, based on the problem data, using the acquisition model, wherein the information type is at least one of a fact, an opinion, and a judgement;
identifying, by the processor, at least one human agent from a list of one or more human agents for the information request based on the problem data, wherein the at least one human agent is identified using an engagement model;
determining, by the processor, a Request Elicitation Type (RET) for the at least one human agent based on the problem data and the information type using an elicitation model;
receiving, by the processor, an input from the at least one human agent for the information request based on the information type, and the RET; and
continuously enhancing, by the processor, the decision-making data based on the received input, the determined request elicitation type, and the determined information type.