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 enabling a verbal interaction without relying on an express wake term, the method comprising:
receiving an audio input comprising a plurality of terms, wherein none of the plurality of terms is an express wake term for a virtual assistant;
determining, based on a topic associated with the plurality of terms, whether the audio input is directed to the virtual assistant;
in response to determining that the audio input is directed to the virtual assistant, generating a response to the audio input; and
in response to determining that the audio input is not directed to the virtual assistant, generating no response to the audio input.
2. The method of claim 1 , wherein determining, based on the topic associated with the plurality of terms, whether the audio input is directed to the virtual assistant, comprises:
determining that the audio input is directed to the virtual assistant when the virtual assistant is capable of responding to the topic; and
determining that the audio input is not directed to the virtual assistant when the virtual assistant is not capable of responding to the topic.
3. The method of claim 1 , wherein the topic is associated with a plurality of descriptive terms, and wherein determining the topic associated with the plurality of terms comprises determining that a term, of the plurality of terms, matches a descriptive term, of the plurality of descriptive terms associated with the topic.
4. The method of claim 1 , wherein generating the response to the audio input comprises:
identifying a query in the audio input;
performing a search based on the query;
retrieving results based on the search; and
causing to be output the retrieved results.
5. The method of claim 1 , wherein determining whether the audio input is directed to the virtual assistant further comprises:
determining a time of receipt of the audio input;
identifying a period of time associated with the topic;
determining that the audio input is directed to the virtual assistant when the time of receipt is associated within the period of time associated with the topic; and
determining that the audio input is not directed to the virtual assistant when the time of receipt is not within the period of time associated with the topic.
6. The method of claim 1 , wherein the audio input is a first audio input, further comprising:
in response to generating the response to the first audio input, receiving a second audio input;
detecting, based on the second audio input, dissatisfaction with the response; and
based on detecting the dissatisfaction, reducing the probability of determining that a future audio input is directed to the virtual assistant when the future audio input is associated with the topic.
7. The method of claim 6 , wherein detecting the dissatisfaction with the response comprises detecting a negative tone of the second audio input.
8. The method of claim 7 , further comprising determining a level of dissatisfaction based on the negative tone, wherein the reduction in probability is proportional to the level of dissatisfaction.
9. The method of claim 1 , wherein generating the response to the audio input comprises generating for display a visual response based on the audio input.
10. The method of claim 1 wherein determining, based on the topic associated with the plurality of terms, whether the audio input is directed to the virtual assistant comprises, determining whether the virtual assistant is capable of providing a response associated with the topic.
11. A system for enabling a verbal interaction without relying on an express wake term, the system comprising control circuitry configured to:
receive an audio input comprising a plurality of terms, wherein none of the plurality of terms is an express wake term for a virtual assistant;
determine, based on a topic associated with the plurality of terms, whether the audio input is directed to the virtual assistant;
in response to determining that the audio input is directed to the virtual assistant, generate a response to the audio input; and
in response to determining that the audio input is not directed to the virtual assistant, generate no response to the audio input.
12. The system of claim 11 , wherein the control circuitry is further configured, when determining, based on the topic associated with the plurality of terms, whether the audio input is directed to the virtual assistant, to:
determine that the audio input is directed to the virtual assistant when the virtual assistant is capable of responding to the topic; and
determine that the audio input is not directed to the virtual assistant when the virtual assistant is not capable of responding to the topic.
13. The system of claim 11 , wherein the topic is associated with a plurality of descriptive terms, and wherein the control circuitry is further configured, when determining the topic associated with the plurality of terms, to determine that a term, of the plurality of terms, matches a descriptive term, of the plurality of descriptive terms associated with the topic.
14. The system of claim 11 , wherein the control circuitry is further configured, when generating the response to the audio input to:
identify a query in the audio input;
perform a search based on the query;
retrieve results based on the search; and
cause to be output the retrieved results.
15. The system of claim 11 , wherein the control circuitry is further configured, when determining whether the audio input is directed to the virtual assistant to:
determine a time of receipt of the audio input;
identify a period of time associated with the topic;
determine that the audio input is directed to the virtual assistant when the time of receipt is associated within the period of time associated with the topic; and
determine that the audio input is not directed to the virtual assistant when the time of receipt is not within the period of time associated with the topic.
16. The system of claim 11 , wherein the audio input is a first audio input, and wherein the control circuitry is further configured to:
in response to generating the response to the first audio input, receive a second audio input;
detect, based on the second audio input, dissatisfaction with the response; and
based on detecting the dissatisfaction, reduce the probability of determining that a future audio input is directed to the virtual assistant when the future audio input is associated with the topic.
17. The system of claim 16 , wherein the control circuitry is further configured, when detecting the dissatisfaction with the response to detect a negative tone of the second audio input.
18. The system of claim 17 , wherein the control circuitry is further configured to determine a level of dissatisfaction based on the negative tone, wherein the reduction in probability is proportional to the level of dissatisfaction.
19. The system of claim 11 , wherein generating the response to the audio input comprises generating for display a visual response based on the audio input.
20. The system of claim 11 wherein determining, based on the topic associated with the plurality of terms, whether the audio input is directed to the virtual assistant comprises, determining whether the virtual assistant is capable of providing a response associated with the topic.