| CPC G06Q 50/01 (2013.01) [G06N 5/01 (2023.01); G06N 5/02 (2013.01); G06N 20/00 (2019.01)] | 17 Claims |

|
1. A computer-implemented method comprising:
receiving, by a computing device, a natural language input, wherein the natural language input is associated with a device;
preprocessing the natural language input based on a relevance value of one or more substrings of the natural language input;
determining that the preprocessed natural language input includes a query that can be resolved by a machine-learning model;
executing the machine-learning model using the preprocessed natural language input, wherein the machine-learning model identifies one or more responses that are likely to resolve the query;
selecting a particular response from the one or more responses;
defining, by the computing device, a narrative flow using a set of strings derived from substrings of a set natural language inputs and substrings of the particular response generated by the machine-learning model; and
facilitating a transmission including the narrative flow and the particular response as a response to the natural language input.
|