| CPC G06F 16/90332 (2019.01) [G06F 16/9535 (2019.01); G10L 15/22 (2013.01); G10L 2015/225 (2013.01)] | 20 Claims |

|
1. A device, comprising:
at least one processor; and
a memory including instructions that, when executed by the at least one processor, cause the at least one processor to:
receive a representation of a spoken question from a client device, the spoken question having been received via a virtual assistant at the client device;
determine, based at least in part on the representation of the spoken question, at least one intent of the spoken question;
select a first information domain of a plurality of information domains that corresponds to the determined at least one intent;
send the representation of the spoken question to the selected first information domain comprising plural search subdomains, each of the plural search subdomains being configured to provide a respective candidate answer to the spoken question in a format that differs from those provided by the other search subdomains of the plural search subdomains;
receive, in response to sending the representation of the spoken question, the respective candidate answer and a corresponding respective confidence score from each respective search subdomain of the plural search subdomains, wherein the corresponding respective confidence score indicates a likelihood, determined by the respective search subdomain, of a correctness of the respective candidate answer with regard to the spoken question; and
provide at least one of the candidate answers to the client device, for providing an answer to the spoken question based on the at least one of the candidate answers.
|