Methods for natural language model training in natural language understanding (NLU) systems

1. A method of determining to perform an action of a query using a trained natural language model of a natural language understanding (NLU) system, the method comprising:

receiving the query including at least a content entity with a text string, wherein the text string corresponds to a prescribed action;

determining whether the text string corresponds to an audio input of a first group;

in response to determining the text string corresponds to an audio input of a first group, determining whether the text string includes an obsequious expression;

in response to determining the text string includes an obsequious expression:

determining whether the obsequious expression describes the content entity; and

in response to determining the obsequious expression describes the content entity, determining to not perform the prescribed action.

2. The method of claim 1 , further comprising;

in response to determining to not perform the prescribed action, generating an instructional message to transmit to an audio input originator, wherein the instruction message solicits a modified audio input that includes the content entity and an obsequious expression; and

in response to generating the instructional message, causing transmitting one or more instructional message audio signals corresponding to the instructional message or waiting a time period to receive a response to the instructional message.

3. The method of claim 2 , further comprising in response to receiving a response to the instructional message during the time period, determining whether the response includes the obsequious expression time period, wherein:

in response to determining the response includes the obsequious expression of choice, determining to perform the prescribed action; and

in response to determining the response does not include the obsequious expression of choice, determining to not perform the prescribed action.

4. The method of claim 1 , wherein determining whether the text string corresponds to an audio input of a first group is based on one or more acoustic characteristics of one or more audio signals corresponding to the audio input.

5. The method of claim 1 , further comprising transmitting the query to the natural language model to train the natural language model with the query.

6. The method of claim 1 , wherein determining whether the text string includes an obsequious expression comprises comparing the obsequious expression to a list of stored obsequious expressions for a match.

7. The method of claim 1 , wherein determining whether the obsequious expression describes the content entity comprises performing a natural language recognition process selected from a group of hidden Markov model, dynamic time warping, and artificial neural networks.

8. The method of claim 1 , further comprising updating a database with the content entity or with the obsequious expression.

9. The method of claim 1 , further comprising in response to determining the text string does not correspond to an audio input from a first group:

determining whether the text string includes an obsequious expression; and

in response to determining the text string includes an obsequious expression, determining whether the obsequious expression describes the content entity;

in response to determining the obsequious expression describes the content entity, determining to not perform the prescribed action; and

in response to determining the obsequious expression does not describe the content entity, determining to perform the prescribed action.

10. A system of determining to perform an action of a query using a trained natural language model of a natural language understanding (NLU) system, the system comprising:

input circuitry configured to receive the query including at least a content entity with a text string, wherein the text string corresponds to a prescribed action;

control circuitry configured to:

determine whether the text string corresponds to an audio input of a first group;

in response to determining the text string corresponds to an audio input of the first group, determine whether the text string includes an obsequious expression;

in response to determining the text string includes an obsequious expression:

determine whether the obsequious expression describes the content entity;

in response to determining the obsequious expression does not describe the content entity, determine to perform the prescribed action; and

in response to determining the obsequious expression describes the content entity, determine to not perform the prescribed action; and

in response to determining the text string does not include the obsequious expression, determine to not perform the prescribed action.

11. The system of claim 10 , wherein the control circuitry is further configured to:

in response to determining to not perform the prescribed action, generate an instructional message to transmit to an originator of the audio input, wherein the instruction message solicits a modified audio input that includes the content entity and an obsequious expression; and

in response to generating the instructional message, cause transmitting one or more instructional message audio signals corresponding to the instructional message or wait a time period to receive a response to the instructional message.

12. The system of claim 11 , wherein the control circuitry is further configured to in response to receiving a response to the instructional message during the time period, determine whether the response includes the obsequious expression, wherein:

in response to determining the response includes the obsequious expression, determining to perform the prescribed action; and

in response to determining the response does not include the obsequious expression, determining to not perform the prescribed action.

13. The system of claim 10 , wherein the control circuitry is further configured to determine whether the text string corresponds to an audio input of a first group based on an acoustic characteristic of one or more audio signals corresponding to the audio input.

14. The system of claim 10 , wherein the control circuitry is further configured to transmit the query to the natural language model to train the natural language model with the query.

15. The system of claim 10 , wherein determining whether the text string includes an obsequious expression, wherein the control circuitry is further configured to compare the obsequious expression to a list of stored obsequious expressions for a match.

16. The system of claim 10 , wherein in determining whether the obsequious expression describes the content entity, the control circuitry is further configured to perform a natural language recognition process selected from a group of hidden Markov model, dynamic time warping, and artificial neural networks.

17. The system of claim 10 , wherein the control circuitry is further configured to update a database with the content entity or with the obsequious expression.

18. The system of claim 10 , wherein the control circuitry is further configured to in response to determining the text string does not correspond to an audio input of a first group:

determine whether the text string includes an obsequious expression; and

in response to determining the text string includes an obsequious expression, determine whether the obsequious expression describes the content entity;

in response to determining the obsequious expression describes the content entity, determine to not perform the prescribed action; and

in response to determining the obsequious expression does not describe the content entity, determine to perform the prescribed action.

19. The method of claim 1 , further comprising:

in response to determining the obsequious expression does not describe the content entity, determining to perform the prescribed action.

20. The method of claim 1 , further comprising:

in response to determining the text string does not include the obsequious expression, determining to not perform the prescribed action.