US 11,900,320 B2
Utilizing machine learning models for identifying a subject of a query, a context for the subject, and a workflow
Rajashree Chandrashekar, Bengaluru (IN); Raghuram Yaddanapudi, Hyderabad (IN); Arjun Marri, Hyderabad (IN); Jayateerth Kulkarni, Bangalore (IN); Tapan Kumar Jain, Faridabad (IN); and Gopali Raval Contractor, Mumbai (IN)
Assigned to Accenture Global Solutions Limited, Dublin (IE)
Filed by Accenture Global Solutions Limited, Dublin (IE)
Filed on Nov. 9, 2020, as Appl. No. 17/093,071.
Prior Publication US 2022/0147934 A1, May 12, 2022
Int. Cl. G06Q 10/10 (2023.01); G06F 9/451 (2018.01); G06Q 40/08 (2012.01); G06Q 10/0639 (2023.01); G06F 40/40 (2020.01); G06F 16/953 (2019.01); G06N 20/00 (2019.01); G06Q 30/0201 (2023.01); G06Q 30/018 (2023.01); H04L 9/40 (2022.01); G06Q 10/0635 (2023.01); G06F 3/0482 (2013.01)
CPC G06Q 10/10 (2013.01) [G06F 9/453 (2018.02); G06F 16/953 (2019.01); G06F 40/40 (2020.01); G06N 20/00 (2019.01); G06Q 10/0635 (2013.01); G06Q 10/06393 (2013.01); G06Q 30/0185 (2013.01); G06Q 30/0201 (2013.01); G06Q 40/08 (2013.01); H04L 63/08 (2013.01); G06F 3/0482 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
receiving, by a device and from a user device, a query for information from a user associated with the user device;
receiving, by the device and from an enterprise system, product/service data identifying products and services to be offered by the user;
processing, by the device, the query and the product/service data, with a context model, to identify a subject of the query and a context for the subject based on identifying a role of the user,
wherein identifying the role is based on determining role information, identifying a job description and a computing resource the user is permitted to access based on the role, based on using credentials associated with the user to identify the user and identifying the role based on accessing a data structure storing information mapping the user to the role,
wherein identifying the context for the subject is based on the role and a navigation history associated with the user, and
wherein processing the query and the product/service data comprise:
identifying a first set of values using a first one or more natural language processing (NLP) techniques,
wherein identifying the first set of values using the first one or more NLP techniques includes:
 executing a token-based NLP technique to identify the subject,
 executing an approximation-based NLP technique to identify the subject, or
 executing a category-based NLP technique to identify to the subject,
identifying a second set of values using a second one or more NLP techniques,
wherein identifying the second set of values using the first one or more NLP techniques includes:
 executing the token-based NLP technique to identify the subject,
 executing the approximation-based NLP technique to identify the subject, or
 executing the category-based NLP technique to identify to the subject,
addressing conflicting values based on filtering the first set of values and the second set of values into a third set of values that excludes the conflicting values, and
using the third set of values to identify the subject and the context for the subject;
processing, by the device, the subject and the context for the subject, with an intelligent automation model, to determine a workflow for the user identifying one or more actions, instructions for performing the one or more actions, and information identifying an order in which the one or more actions are to be performed;
processing, by the device, the product/service data, the subject, and the context for the subject, with an insights model, to determine a key performance indicator or a decision associated with one of the products or the services,
wherein the key performance indicator is associated with a proficiency of the user with utilizing the enterprise system to perform a particular function; and
providing, by the device, data identifying one or more of the workflow, the key performance indicator, or the decision to the user device via a virtual assistant or a user interface.