SYSTEM AND METHOD FOR HYBRID PROCESSING IN A NATURAL LANGUAGE VOICE SERVICES ENVIRONMENT
First Claim
1. A method for hybrid processing in a natural language voice services environment, comprising:
- detecting at least one multi-modal interaction at an electronic device, wherein the multi-modal interaction includes at least a natural language utterance;
communicating one or more messages containing information relating to the multi-modal interaction to a virtual router in communication with the electronic device, wherein the electronic device communicates the one or more messages to the virtual router through a messaging interface;
receiving one or more messages containing information relating to an intent of the multi-modal interaction at the electronic device, wherein the electronic device receives the one or more messages from the virtual router through the messaging interface; and
resolving the multi-modal interaction at the electronic device based on the information contained in the one or more messages received from the virtual router.
8 Assignments
0 Petitions
Accused Products
Abstract
A system and method for hybrid processing in a natural language voice services environment that includes a plurality of multi-modal devices may be provided. In particular, the hybrid processing may generally include the plurality of multi-modal devices cooperatively interpreting and processing one or more natural language utterances included in one or more multi-modal requests. For example, a virtual router may receive various messages that include encoded audio corresponding to a natural language utterance contained in a multi-modal interaction provided to one or more of the devices. The virtual router may then analyze the encoded audio to select a cleanest sample of the natural language utterance and communicate with one or more other devices in the environment to determine an intent of the multi-modal interaction. The virtual router may then coordinate resolving the multi-modal interaction based on the intent of the multi-modal interaction.
-
Citations
22 Claims
-
1. A method for hybrid processing in a natural language voice services environment, comprising:
-
detecting at least one multi-modal interaction at an electronic device, wherein the multi-modal interaction includes at least a natural language utterance; communicating one or more messages containing information relating to the multi-modal interaction to a virtual router in communication with the electronic device, wherein the electronic device communicates the one or more messages to the virtual router through a messaging interface; receiving one or more messages containing information relating to an intent of the multi-modal interaction at the electronic device, wherein the electronic device receives the one or more messages from the virtual router through the messaging interface; and resolving the multi-modal interaction at the electronic device based on the information contained in the one or more messages received from the virtual router. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9)
-
-
10. An electronic device for hybrid processing in a natural language voice services environment, wherein the electronic device is configured to:
-
detect at least one multi-modal interaction that includes at least a natural language utterance; communicate one or more messages containing information relating to the multi-modal interaction to a virtual router in communication with the electronic device, wherein the one or more messages are communicated to the virtual router through a messaging interface; receive one or more messages containing information relating to an intent of the multi-modal interaction from the virtual router through the messaging interface; and resolve the multi-modal interaction at the electronic device based on the information contained in the one or more messages received from the virtual router. - View Dependent Claims (11, 12, 13, 14, 15, 16, 17, 18)
-
-
19. A virtual router for hybrid processing in a natural language voice services environment, wherein the virtual router is configured to:
-
receive a plurality of messages that include encoded audio corresponding to a natural language utterance contained in a multi-modal interaction with a plurality of respective electronic devices; analyze the encoded audio in the plurality of messages to determine one of the plurality of messages that provides a cleanest sample of the natural language utterance; communicate one or more messages containing the encoded audio that provides the cleanest sample to a server in communication with the virtual router, wherein the one or more messages are communicated to the server through a messaging interface; receive one or more messages containing information relating to an intent of the multi-modal interaction from the server through the messaging interface; and return one or more messages containing the information relating to the intent of the multi-modal interaction to one or more of the plurality of electronic devices, wherein the one or more of the electronic devices resolve the multi-modal interaction based on the information relating to the intent of the multi-modal interaction. - View Dependent Claims (20, 21, 22)
-
Specification