Systems and methods for enabling topic-based verbal interaction with a virtual assistant

1. A method for enabling verbal interaction with a virtual assistant without relying on express wake terms, the method comprising:

receiving an audio input for a virtual assistant, wherein the audio input comprises a plurality of terms and none of the terms is an express wake term for the virtual assistant;

retrieving, from the memory, a plurality of wake terms;

comparing the plurality of wake terms with the plurality of terms of the audio input;

in response to determining, based on the comparing, that none of the plurality of wake terms are present in the plurality of terms, determining a topic for the plurality of terms;

retrieving a plurality of topics stored in memory; and

determining whether the topic is within the plurality of topics, and (a) in response to determining that the topic is within the plurality of topics, generating a response to the audio input, or (b) in response to determining that the topic is not within the plurality of topics, generating no response to the audio input.

2. The method of claim 1 , wherein each respective topic in the plurality of topics is associated with a plurality of descriptive terms and wherein determining the topic for the plurality of terms comprises:

comparing the plurality of terms of the audio input with the plurality of descriptive terms of the topic;

determining, based on the comparing, that at least a threshold amount of the plurality of terms of the audio input match the plurality of descriptive terms of the topic; and

in response to determining that at least the threshold amount of the plurality of terms of the audio input match, determining that the plurality of terms of the audio input corresponds to the topic.

3. The method of claim 1 , wherein the plurality of topics comprises a first subset of topics for which responses should be generated and a second subset of topics for which responses should not be generated, and wherein determining the topic for the plurality of terms comprises:

determining that a number of the plurality of terms corresponds to both a first topic of the first subset and a second topic of the second subset;

identifying a first number of descriptive terms in the first topic and a second number of descriptive terms in the second topic;

normalizing the number by the first number to determine a first amount of matches in the first topic;

normalizing the number by the second number to determine a second amount of matches in the second topic;

determining whether the first amount is greater than the second amount; and

in response to determining that the first amount is greater than the second amount, determining that the plurality of terms of the audio input corresponds to the first topic.

4. The method of claim 1 , wherein each respective topic in the plurality of topics is associated with a plurality of essential descriptive terms and wherein determining the topic for the plurality of terms comprises:

comparing the plurality of terms of the audio input with the plurality of essential descriptive terms of the topic;

determining, based on the comparing, that at least a threshold amount of the plurality of essential descriptive terms match the plurality of terms of the audio input; and

in response to determining that at least a threshold amount of the plurality of essential descriptive terms match, determining that the plurality of terms of the audio input corresponds to the topic.

5. The method of claim 1 , wherein each respective topic of the plurality of topics is associated with a respective score stored in a database of topic scores, further comprising:

determining that the topic is within the plurality of topics;

determining whether a score of the topic is greater than a threshold score;

in response to determining that the score is greater than the threshold score, generating the response to the audio input; or

in response to determining that the score is less than the threshold score, generating no response to the audio input.

6. The method of claim 5 , further comprising:

subsequent to generating no response to the audio input, receiving an additional audio input indicating that the response is required; and

in response to receiving the additional audio input:

increasing a score of the topic in the database of topic scores; and

generating the response to the audio input.

7. The method of claim 5 , further comprising:

subsequent to generating the response to the audio input, receiving an additional audio input indicating that the response should not have been generated; and

in response to receiving the additional audio input, decreasing a score of the topic in the database of topic scores.

8. The method of claim 7 , wherein decreasing the score of the topic in the database further comprises:

determining a tone of the additional audio input;

determining a level of dissatisfaction based on the tone; and

decreasing the score by a magnitude proportional to the level of dissatisfaction.

9. The method of claim 5 , wherein the database of topic scores comprises, for each topic of the plurality of topics, a respective time-based score associated with a period of time.

10. A system for enabling verbal interaction with a virtual assistant without relying on express wake terms, the system comprising:

memory; and

control circuitry configured to:

receive an audio input for a virtual assistant, wherein the audio input comprises a plurality of terms and none of the terms is an express wake term for the virtual assistant;

retrieve, from the memory, a plurality of wake terms;

compare the plurality of wake terms with the plurality of terms of the audio input;

in response to determining, based on the comparing, that none of the plurality of wake terms are present in the plurality of terms, determine a topic for the plurality of terms;

retrieve a plurality of topics stored in the memory; and

determine whether the topic is within the plurality of topics, and (a) in response to determining that the topic is within the plurality of topics, generate a response to the audio input, or (b) in response to determining that the topic is not within the plurality of topics, generate no response to the audio input.

11. The system of claim 10 , wherein each respective topic in the plurality of topics is associated with a plurality of descriptive terms and wherein the control circuitry is configured to determine the topic for the plurality of terms by:

comparing the plurality of terms of the audio input with the plurality of descriptive terms of the topic;

determining, based on the comparing, that at least a threshold amount of the plurality of terms of the audio input match the plurality of descriptive terms of the topic; and

in response to determining that at least the threshold amount of the plurality of terms of the audio input match, determining that the plurality of terms of the audio input corresponds to the topic.

12. The system of claim 10 , wherein the plurality of topics comprises a first subset of topics for which responses should be generated and a second subset of topics for which responses should not be generated, and wherein the control circuitry is configured to determine the topic for the plurality of terms by:

determining that a number of the plurality of terms corresponds to both a first topic of the first subset and a second topic of the second subset;

identifying a first number of descriptive terms in the first topic and a second number of descriptive terms in the second topic;

normalizing the number by the first number to determine a first amount of matches in the first topic;

normalizing the number by the second number to determine a second amount of matches in the second topic;

determining whether the first amount is greater than the second amount; and

in response to determining that the first amount is greater than the second amount, determining that the plurality of terms of the audio input corresponds to the first topic.

13. The system of claim 10 , wherein each respective topic in the plurality of topics is associated with a plurality of essential descriptive terms and wherein the control circuitry is configured to determine the topic for the plurality of terms by:

comparing the plurality of terms of the audio input with the plurality of essential descriptive terms of the topic;

determining, based on the comparing, that at least a threshold amount of the plurality of essential descriptive terms match the plurality of terms of the audio input; and

in response to determining that at least a threshold amount of the plurality of essential descriptive terms match, determining that the plurality of terms of the audio input corresponds to the topic.

14. The system of claim 10 , wherein each respective topic of the plurality of topics is associated with a respective score stored in a database of topic scores, wherein the control circuitry is further configured to:

determine that the topic is within the plurality of topics;

determine whether a score of the topic is greater than a threshold score;

in response to determining that the score is greater than the threshold score, generate the response to the audio input; or

in response to determining that the score is less than the threshold score, generate no response to the audio input.

15. The system of claim 14 , wherein the control circuitry is further configured to:

subsequent to generating no response to the audio input, receive an additional audio input indicating that the response is required; and

in response to receiving the additional audio input:

increase a score of the topic in the database of topic scores; and

generate the response to the audio input.

16. The system of claim 14 , wherein the control circuitry is further configured to:

subsequent to generating the response to the audio input, receive an additional audio input indicating that the response should not have been generated; and

in response to receiving the additional audio input, decrease a score of the topic in the database of topic scores.

17. The system of claim 16 , wherein the control circuitry is configured to decrease the score of the topic in the database by:

determining a tone of the additional audio input;

determining a level of dissatisfaction based on the tone; and

decreasing the score by a magnitude proportional to the level of dissatisfaction.

18. The system of claim 14 , wherein the database of topic scores comprises, for each topic of the plurality of topics, a respective time-based score associated with a period of time.