Device for processing user voice input

Abstract

Disclosed is a server device. At least one server according to an embodiment comprises a network interface, a storage, and at least one processor for providing a voice recognition service. The at least one processor may be configured to: receive, through the network interface, a first utterance of a first user from a first terminal of the first user registered in the voice recognition service; store the received first utterance in the storage; after storing the first utterance in the storage, receive, through the network interface, a second utterance of a second user from a second terminal of the second user registered in the voice recognition service; in response to the reception of the second utterance of the second user, generate a response message corresponding to the second utterance on the basis of the first utterance of the first user that is associated with the second user; and provide the response message to the second terminal through the network interface. Additional various embodiments identified through the specification are possible.

Dependencies are inferred from the claim text.