Systems and methods for responding to natural language speech utterance
First Claim
1. A method for responding to natural language speech utterances, comprising:
- receiving a natural language speech utterance at a speech unit connected to a computer device, wherein the speech unit converts the received natural language speech utterance into an electronic signal;
recognizing one or more words in the electronic signal with a speech recognition engine that operates on the computer device;
interpreting a meaning for the natural language speech utterance with a parser that further operates on the computer device, wherein interpreting the meaning for the natural language speech utterance includes;
identifying multiple requests contained in the natural language speech utterance from the one or more words recognized in the electronic signal; and
determining one or more contexts for the multiple requests contained in the natural language speech utterance; and
processing the multiple requests contained in the natural language speech utterance in a multi-threaded environment with an event manager that further operates on the computer device, wherein processing the multiple requests with the event manager includes;
sending a first event to a first domain agent configured to process requests in the one or more contexts, wherein the first domain agent creates a first plurality of asynchronous queries to process a first one of the multiple requests in response to receiving the first event from the event manager;
sending a second event to a second domain agent configured to process requests in the one or more contexts, wherein the second domain agent creates a second plurality of asynchronous queries to process a second one of the multiple requests in response to receiving the second event from the event manager;
receiving one or more response events that include information from one or more of the first domain agent processing the first one of the multiple requests or the second domain agent processing the second one of the multiple requests; and
creating a response to the multiple requests contained in the natural language speech utterance from the one or more response events.
5 Assignments
0 Petitions
Accused Products
Abstract
Systems and methods for receiving natural language queries and/or commands and execute the queries and/or commands. The systems and methods overcomes the deficiencies of prior art speech query and response systems through the application of a complete speech-based information query, retrieval, presentation and command environment. This environment makes significant use of context, prior information, domain knowledge, and user specific profile data to achieve a natural environment for one or more users making queries or commands in multiple domains. Through this integrated approach, a complete speech-based natural language query and response environment can be created. The systems and methods creates, stores and uses extensive personal profile information for each user, thereby improving the reliability of determining the context and presenting the expected results for a particular question or command.
692 Citations
16 Claims
-
1. A method for responding to natural language speech utterances, comprising:
-
receiving a natural language speech utterance at a speech unit connected to a computer device, wherein the speech unit converts the received natural language speech utterance into an electronic signal; recognizing one or more words in the electronic signal with a speech recognition engine that operates on the computer device; interpreting a meaning for the natural language speech utterance with a parser that further operates on the computer device, wherein interpreting the meaning for the natural language speech utterance includes; identifying multiple requests contained in the natural language speech utterance from the one or more words recognized in the electronic signal; and determining one or more contexts for the multiple requests contained in the natural language speech utterance; and processing the multiple requests contained in the natural language speech utterance in a multi-threaded environment with an event manager that further operates on the computer device, wherein processing the multiple requests with the event manager includes; sending a first event to a first domain agent configured to process requests in the one or more contexts, wherein the first domain agent creates a first plurality of asynchronous queries to process a first one of the multiple requests in response to receiving the first event from the event manager; sending a second event to a second domain agent configured to process requests in the one or more contexts, wherein the second domain agent creates a second plurality of asynchronous queries to process a second one of the multiple requests in response to receiving the second event from the event manager; receiving one or more response events that include information from one or more of the first domain agent processing the first one of the multiple requests or the second domain agent processing the second one of the multiple requests; and creating a response to the multiple requests contained in the natural language speech utterance from the one or more response events. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. A system for responding to natural language speech utterances, comprising:
-
a speech unit connected to a computer device, wherein the speech unit receives a natural language speech utterance and converts the received natural language speech into an electronic signal; a speech recognition engine that operates on the computer device, wherein the speech recognition engine recognizes one or more words in the electronic signal converted from the natural language speech utterance; a parser that further operates on the computer device, wherein the parser interprets a meaning for the natural language speech utterance from the one or more words recognized in the electronic signal, wherein the interpreted meaning for the natural language speech utterance includes multiple requests contained in the natural language speech utterance and one or more contexts for the multiple requests contained in the natural language speech utterance; and an event manager that processes the multiple requests contained in the natural language speech utterance in a multi-threaded environment, wherein the event manager further operates on the computer device and causes the computer device to; send a first event to a first domain agent configured to process requests in the one or more contexts, wherein the first domain agent creates a first plurality of asynchronous queries to process a first one of the multiple requests in response to receiving the first event from the event manager; send a second event to a second domain agent configured to process requests in the one or more contexts, wherein the second domain agent creates a second plurality of asynchronous queries to process a second one of the multiple requests in response to receiving the second event from the event manager; receive one or more response events that include information from one or more of the first domain agent processing the first one of the multiple requests or the second domain agent processing the second one of the multiple requests; and create a response to the multiple requests contained in the natural language speech utterance from the one or more response events. - View Dependent Claims (10, 11, 12, 13, 14, 15, 16)
-
Specification