According to an embodiment, an electronic device comprises: a microphone; a processor; and a memory storing instructions executable by the processor, wherein execution of the instructions by the processor causes the processor to perform a plurality of operations comprising: receiving an audio signal including an utterance of a user from the microphone; obtaining information on an application and information on a goal for processing the utterance, determining whether to process the utterance with the electronic device or with a server, based on the information on the application, the information on the goal, and version information received from the server, determining whether to update the information on the application and the information on the goal based on the version information, the information on the application, and the information on the goal; when determining to process the utterance at the electronic device, processing the utterance; and when determining to process the utterance at the server, transmitting the utterance to the server.