US 11,934,787 B2
Intent determination in a messaging dialog manager system
Yara Rizk, Cambridge, MA (US); Shubham Agarwal, Cambridge, MA (US); Yasaman Khazaeni, Needham, MA (US); and Calvin Phung, La Puente, CA (US)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on Apr. 29, 2021, as Appl. No. 17/243,694.
Prior Publication US 2022/0350970 A1, Nov. 3, 2022
Int. Cl. G06F 40/279 (2020.01); G06F 18/22 (2023.01); G06F 40/30 (2020.01); G06N 20/00 (2019.01); H04L 51/04 (2022.01)
CPC G06F 40/30 (2020.01) [G06F 18/22 (2023.01); G06F 40/279 (2020.01); G06N 20/00 (2019.01); H04L 51/04 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A computer-implemented method for improving intent determination in a messaging dialog manager system, the computer-implemented method comprising:
receiving, by one or more processors, first agent entry data corresponding to a first agent communicating in a messaging dialog interface;
determining, by the one or more processors, that the first agent entry data expects a response that is within a first response domain, wherein the response includes one or more classes and a first class of the one or more classes corresponds to an expected response to the first agent entry data and a second class of the one or more classes corresponds to no response is expected to the first agent entry data;
determining, by the one or more processors, that a first user entry entered in the messaging dialog interface is not within the first response domain;
identifying, by the one or more processors, a second agent configured with a second response domain that includes the first user entry;
transmitting, by the one or more processors, the first user entry to the second agent to facilitate a seamless transition of an established communicational flow between the first agent and the first user;
identifying, by the one or more processors, agent text data corresponding to a natural language (NL) text in the first agent entry data;
identifying, by the one or more processors, user text data corresponding to a natural language (NL) utterance in the first user entry;
determining, by the one or more processors, a first agent data entry topic based on the agent text data, wherein the first response domain corresponds to the first agent data entry topic;
determining, by the one or more processors, a first user entry topic based on the user text data; and
comparing, by the one or more processors, the first agent data entry topic and the first user entry topic to determine a similarity threshold is met.