An electronic device is disclosed, and may include a communication circuit, a memory, and a processor operatively connected to the communication circuit and the memory. The memory stores instructions that, when executed, cause the processor to recognize a second external device that will perform an operation corresponding to a first utterance received by a first external device, to establish a first session between the first external device and the second external device, to recognize a device, which will perform an operation corresponding to a second utterance received by a third external device, while maintaining the first session, to determine whether to establish a second session between the third external device and the second external device based on a specified first condition when the device that will perform the operation corresponding to the second utterance is the second external device, and to establish the second session independently of the first session or establish an integrated session between the first external device, the second external device, and the third external device by integrating the first session and the second session when establishing the second session, on a basis of a specified second condition.