CPC G06F 9/543 (2013.01) [G06F 9/5027 (2013.01); G06F 9/541 (2013.01); G06F 40/40 (2020.01); G06F 2209/5015 (2013.01)] | 20 Claims |
1. A computer-implemented method of determining at least one user intent for interacting with an automated computing system, the computer-implemented method comprising:
receiving a message from a user for the automated computing system, wherein the message comprises message objects in the message;
executing, for the automated computing system, a natural language classifier comprising a machine learning engine including at least one machine learning model trained using a corpora of natural language expressions associated with different user intents, wherein the corpora of natural language expressions comprises service description information for services provided by at least one service provider and previous messages sent by one or more users including the user;
generating, by the natural language classifier using the machine learning engine, weighted probabilities that words or phrases from the message objects in the message are related to words or phrases from the corpora of natural language expressions;
determining, using the natural language classifier from the weighted probabilities, a natural language expression from the corpora of natural language expressions;
associating, using the natural language classifier, the natural language expression with the at least one user intent; and
providing, via the automated computing system, a response to the message based on the associating.
|