abstract |
Communication interface; At least one processor operatively connected with the communication interface; And at least one memory operatively coupled to the at least one processor, wherein the processor, when executed in the memory, comprises: an automatic speech recognition (ASR) module; And a plurality of natural language understanding (NLU) modules operating independently of each other, further comprising: causing the processor to receive first voice data including first user speech over the communication interface, Process the first voice data to generate first text data based on the first user utterance using the automatic speech recognition module, and use the first text data using a first NLU module of the plurality of NLU modules. Process to provide a first intent, and one or more items associated with the first intent, and generate a first response based at least in part on the first intent and the one or more items via the communication interface. Providing at least some of the first intent, and at least some of the one or more items to another NLU module of at least some of the plurality of NLU modules The system which the instruction is to be stored to provide is disclosed. In addition to this, various embodiments identified through the specification are possible. |