US 11,875,125 B2
System and method for designing artificial intelligence (AI) based hierarchical multi-conversation system
Navin Sabharwal, New Delhi (IN); and Amit Agrawal, Mathura (IN)
Assigned to HCL Technologies Limited, New Delhi (IN)
Filed by HCL Technologies Limited, New Delhi (IN)
Filed on Mar. 18, 2021, as Appl. No. 17/205,331.
Prior Publication US 2022/0300716 A1, Sep. 22, 2022
Int. Cl. G06F 40/35 (2020.01); G06N 20/00 (2019.01); G06F 16/2452 (2019.01); G06F 16/2457 (2019.01); G06F 40/279 (2020.01)
CPC G06F 40/35 (2020.01) [G06F 16/24522 (2019.01); G06F 16/24578 (2019.01); G06F 40/279 (2020.01); G06N 20/00 (2019.01)] 15 Claims
OG exemplary drawing
 
1. A method for determining a conversation system from a multi-conversation system using Artificial Intelligence (AI), the method comprising:
receiving, by an AI based hierarchical multi-conversation system, a user query associated with a domain from a plurality of domains;
creating, by the AI based hierarchical multi-conversation system, a hierarchical tree comprising a root node and at least one child node using a first pre-trained machine learning model, wherein the at least one child node is associated with match data corresponding to a topic related to the user query, and wherein at least one leaf child node is associated with match data corresponding to a sub-topic related to the user query;
traversing, by the AI based hierarchical multi-conversation system, the hierarchical tree for at least one path between the root node and the at least one leaf child node to identify a topic hierarchy based on a reinforcement learning algorithm,
wherein identifying the topic hierarchy further comprises:
generating a relationship between a first topic associated with a first child node and a second topic associated with a second child node, using a second pre-trained machine learning model;
checking relevancy of the generated relationship between the first topic and the second topic based on feedback data received from an expert from one or more experts, wherein the expert selects a pair of topics or sub-topics for incorrect relevancy of the generated relationship; and
determining variation of the topic or the sub-topic associated with the user query based on input received from at least one of a user or an expert, via a graphical user interface; and
wherein the at least one path is associated with a confidence score corresponding to mapping between the user query and the match data of nodes in the at least one path; and
determining, by the AI based hierarchical multi-conversation system, the conversation system from the multi-conversation system for outputting data to answer the user query corresponding to the at least one leaf child node of the at least one path with a highest confidence score.