Systems and methods for enabling topic-based verbal interaction with a virtual assistant
Systems and methods are disclosed for enabling verbal interaction with an NLUI application without relying on express wake terms. The NLUI application receives an audio input comprising a plurality of terms. In response to determining that none of the terms is an express wake term pre-programmed into the NLUI application, the NLUI application determines a topic for the plurality of terms. The NLUI application then determines whether the topic is within a plurality of topics for which a response should be generated. If the determined topic of the audio input is within the plurality of topics, the NLUI application generates a response to the audio input.
1. A method for interacting with a virtual assistant, the method comprising:
receiving a first audio input;
determining a topic associated with the first audio input;
determining that a score associated with the topic is below a predetermined value;
in response to determining that the score associated with the topic is below the predetermined value, generating no response to the first audio input;
receiving a second audio input;
determining whether the second audio input indicates a request for a response for the first audio input; and
in response to determining that the second audio input indicates a request for a response for the first audio input:
increasing a score associated with the topic; and
generating a response to the first audio input.
2. The method of claim 1 , wherein the first audio input is received prior to the second audio input.
3. The method of claim 1 , further comprising:
receiving a third audio input;
determining that the third audio input is associated with the topic;
determining that the score is above the predetermined value; and
generating a response to the third audio input.
4. The method of claim 1 , wherein the first audio input does not comprise a wake word.
5. The method of claim 1 , wherein increasing the score associated with the topic comprises:
determining a tone associated with the second audio input;
determining a level of dissatisfaction based on the tone; and
increasing the score by a magnitude proportional to the level of dissatisfaction.
6. The method of claim 1 , wherein increasing the score associated with the topic comprises increasing a value of the score to greater than the predetermined value.
7. The method of claim 1 , wherein determining whether the second audio input indicates the request for the response for the first audio input, comprises determining whether the second audio input refers to the first audio input.
8. The method of claim 7 , wherein determining whether the second audio input refers to the first audio input comprises determining that less than a threshold amount of time has passed between receiving the first audio input and receiving the second audio input.
9. The method of claim 1 , further comprising:
prior to determining the topic associated with the first audio input:
retrieving a wake term from a memory;
comparing the wake term with a plurality of terms in the first audio input; and
in response to determining, based on the comparing, that the wake term is not present in the plurality of terms, determining the topic for the first audio input.
10. The method of claim 1 , wherein the score associated with the topic is a time-based score associated with the topic, and wherein increasing the time-based score associated with the topic, comprises:
identifying a time corresponding to the first input; and
increasing the time-based score associated with the topic that corresponds to the time.
11. A system for interacting with a virtual assistant, the system comprising control circuitry configured to:
receive a first audio input;
determine a topic associated with the first audio input;
determine that a score associated with the topic is below a predetermined value;
in response to determining that the score associated with the topic is below the predetermined value, generate no response to the first audio input;
receive a second audio input;
determine whether the second audio input indicates a request for a response for the first audio input; and
in response to determining that the second audio input indicates a request for a response for the first audio input:
increase a score associated with the topic; and
generate a response to the first audio input.
12. The system of claim 11 , wherein the first audio input is received, by the control circuitry, prior to the second audio input.
13. The system of claim 11 , wherein the control circuitry is further configured to:
receive a third audio input;
determine that the third audio input is associated with the topic;
determine that the score is above the predetermined value; and
generate a response to the third audio input.
14. The system of claim 11 , wherein the first audio input does not comprise a wake word.
15. The system of claim 11 , wherein the control circuitry is further configured, when increasing the score associated with the topic, to:
determine a tone associated with the second audio input;
determine a level of dissatisfaction based on the tone; and
increase the score by a magnitude proportional to the level of dissatisfaction.
16. The system of claim 11 , wherein the control circuitry is further configured, when increasing the score associated with the topic, to increase a value of the score to greater than the predetermined value.
17. The system of claim 11 , wherein the control circuitry is further configured, when determining whether the second audio input indicates the request for the response for the first audio input, to determine whether the second audio input refers to the first audio input.
18. The system of claim 17 , wherein the control circuitry is further configured, when determining whether the second audio input refers to the first audio input, to determine that less than a threshold amount of time has passed between receiving the first audio input and receiving the second audio input.
19. The system of claim 11 , wherein the control circuitry is further configured, prior to determining the topic associated with the first audio input, to:
retrieve a wake term;
compare the wake term with a plurality of terms in the first audio input; and
in response to determining, based on the comparing, that the wake term is not present in the plurality of terms, determining the topic for the first audio input.
20. The system of claim 11 , wherein the score associated with the topic is a time-based score associated with the topic, and wherein increasing the time-based score associated with the topic, comprises:
identifying a time corresponding to the first input; and
increasing the time-based score associated with the topic that corresponds to the time.