CPC G06F 40/35 (2020.01) [G06F 40/279 (2020.01); G10L 15/22 (2013.01); G10L 15/26 (2013.01); G10L 2015/228 (2013.01)] | 20 Claims |
1. A method implemented by one or more processors, the method comprising:
receiving a user request based on input provided by a user during a current user session via a dialog system interface, wherein the at least one user request includes speech input;
determining user request text for the user request, wherein determining the user request text includes performing speech recognition to convert the speech input to the user request text;
determining an intent for the at least one user request based on the user request text;
determining, based on the user request text for the at least one user request, one or more conversational contexts for the user session, wherein the one or more conversational contexts are a subset of available conversational contexts and are determined based on:
searching the available conversational contexts to determine the one or more conversational contexts that are a subset of the available conversational contexts, including determining that the one or more conversational contexts were applied to one or more previous user requests during the current user session;
selecting, from a plurality of dialog system rules, a given dialog system rule based on the given dialog system rule being associated with the identified given conversational context;
determining, based on the given dialog system rule, that the intent of the user request cannot be fulfilled without additional information; and
generating a follow-up query that includes a request for the additional information.
|