Automatically unsubscribing from automated calls based on call audio patterns

1. A system for automatically unsubscribing from automated calls based on automated call audio patterns, the system comprising:

at least one processor of a computing device of a user; and

at least one memory comprising computer program code, the at least one memory and the computer program code configured to, with the at least one processor, cause the at least one processor to:

access, by a call screening engine on the computing device, audio data of an incoming call;

generate, by the call screening engine, an incoming call audio pattern based on the audio data of the incoming call;

compare, by the call screening engine, the incoming call audio pattern to an automated call audio pattern set, the automated call audio pattern set including at least one of audio patterns associated with calls identified as automated calls or audio patterns associated with calls from which users have previously unsubscribed;

based on comparing the incoming call audio pattern to the automated call audio pattern set, prompt, by the call screening engine, the user for a call response instruction; and

based on the call response instruction from the user:

identify, by the call screening engine, an unsubscribe operation indication in the incoming call audio pattern;

perform, by the call screening engine, an unsubscribe operation associated with the identified unsubscribe operation indication; and

update, by the call screening engine, the automated call audio pattern set based on the incoming call audio pattern.

2. The system of claim 1 , wherein comparing the incoming call audio pattern to the automated call audio pattern set includes generating a user prompt score associated with the incoming call audio pattern based on similarities between pattern portions of the incoming call audio pattern and pattern portions of the automated call audio pattern set; and

wherein prompting the user for the call response instruction is further based on the generated user prompt score exceeding a user prompt threshold.

3. The system of claim 2 , wherein comparing the incoming call audio pattern to the automated call audio pattern set includes generating an automatic unsubscribe score associated with the incoming call audio pattern based on similarities between pattern portions of the incoming call audio pattern and pattern portions of the automated call audio pattern set; and

wherein the at least one memory and the computer program code are configured to, with the at least one processor, further cause the at least one processor to:

based on the automatic unsubscribe score exceeding an automatic unsubscribe threshold, identify, by the call screening engine, the unsubscribe operation indication in the incoming call audio pattern and perform, by the call screening engine, the unsubscribe operation associated with the identified unsubscribe operation indication without prompting the user.

4. The system of claim 1 , wherein generating the incoming call audio pattern includes determining a call source of the incoming call audio pattern; and

wherein updating the automated call audio pattern set based on the incoming call audio pattern includes recording the determined call source in an unsubscribed call source data set.

5. The system of claim 4 , wherein comparing the incoming call audio pattern to an automated call audio pattern set further includes comparing the determined call source to call sources in a high-risk merchant data set;

wherein prompting the user for the call response instruction is further based on the determined call source matching at least one call source in the high-risk merchant data set; and

wherein prompting the user includes providing an indication to the user that the determined call source is associated with a high-risk merchant of the high-risk merchant data set associated with the matched at least one call source.

6. The system of claim 4 , wherein the at least one memory and the computer program code are configured to, with the at least one processor, further cause the at least one processor to:

based on the determined call source of the incoming call audio pattern matching a recorded call source in the unsubscribed call source data set, storing the accessed audio data of the incoming call in a repeat call data store, whereby the stored audio data is made available to the user for use in taking action against the call source.

7. The system of claim 1 , wherein prompting the user for the call response instruction includes enabling the user to listen to at least a portion of the incoming call.

8. The system of claim 1 , wherein comparing the incoming call audio pattern to the automated call audio pattern set further includes classifying the incoming call audio pattern based on a call classifier model associated with the automated call audio pattern set;

wherein prompting the user for a call response instruction is further based on a classification result of classifying the incoming call audio pattern; and

wherein updating the automated call audio pattern set further includes training the call classifier model based on the updated automated call audio pattern set.

9. The system of claim 1 , wherein the at least one memory and the computer program code are configured to, with the at least one processor, further cause the at least one processor to:

based on comparing the incoming call audio pattern to the automated call audio pattern set, request, by the call screening engine, from a calling party of the incoming call, at least one of a calling party identifier or a call purpose; and

based on receiving at least one of the calling party identifier or the call purpose, provide, by the call screening engine, the received at least one of the calling party identifier or the call purpose to the user when prompting the user for a call response instruction.

10. A computerized method for automatically unsubscribing from automated calls based on automated call audio patterns, the method comprising:

accessing, by a call screening engine on a computing device of a user, audio data of an incoming call;

generating, by the call screening engine, an incoming call audio pattern based on the audio data of the incoming call;

comparing, by the call screening engine, the incoming call audio pattern to an automated call audio pattern set, the automated call audio pattern set including at least one of audio patterns associated with calls identified as automated calls or audio patterns associated with calls from which users have previously unsubscribed;

based on comparing the incoming call audio pattern to the automated call audio pattern set, prompting, by the call screening engine, the user for a call response instruction; and

based on the call response instruction from the user:

identifying, by the call screening engine, an unsubscribe operation indication in the incoming call audio pattern;

performing, by the call screening engine, an unsubscribe operation associated with the identified unsubscribe operation indication; and

updating, by the call screening engine, the automated call audio pattern set based on the incoming call audio pattern.

11. The computerized method of claim 10 , wherein comparing the incoming call audio pattern to the automated call audio pattern set includes generating a user prompt score associated with the incoming call audio pattern based on similarities between pattern portions of the incoming call audio pattern and pattern portions of the automated call audio pattern set; and

wherein prompting the user for the call response instruction is further based on the generated user prompt score exceeding a user prompt threshold.

12. The computerized method of claim 11 , wherein comparing the incoming call audio pattern to the automated call audio pattern set includes generating an automatic unsubscribe score associated with the incoming call audio pattern based on similarities between pattern portions of the incoming call audio pattern and pattern portions of the automated call audio pattern set; and

Further comprising:

based on the automatic unsubscribe score exceeding an automatic unsubscribe threshold, identifying, by the call screening engine, the unsubscribe operation indication in the incoming call audio pattern and performing, by the call screening engine, the unsubscribe operation associated with the identified unsubscribe operation indication without prompting the user.

13. The computerized method of claim 10 , wherein generating the incoming call audio pattern includes determining a call source of the incoming call audio pattern; and

wherein updating the automated call audio pattern set based on the incoming call audio pattern includes recording the determined call source in an unsubscribed call source data set.

14. The computerized method of claim 13 , wherein comparing the incoming call audio pattern to an automated call audio pattern set further includes comparing the determined call source to call sources in a high-risk merchant data set;

wherein prompting the user for the call response instruction is further based on the determined call source matching at least one call source in the high-risk merchant data set; and

wherein prompting the user includes providing an indication to the user that the determined call source is associated with a high-risk merchant of the high-risk merchant data set associated with the matched at least one call source.

15. The computerized method of claim 13 , further comprising, based on the determined call source of the incoming call audio pattern matching a recorded call source in the unsubscribed call source data set, storing the accessed audio data of the incoming call in a repeat call data store, whereby the stored audio data is made available to the user for use in taking action against the call source.

16. The computerized method of claim 10 , wherein prompting the user for the call response instruction includes enabling the user to listen to at least a portion of the incoming call.

17. The computerized method of claim 10 , wherein comparing the incoming call audio pattern to the automated call audio pattern set further includes classifying the incoming call audio pattern based on a call classifier model associated with the automated call audio pattern set;

wherein prompting the user for a call response instruction is further based on a classification result of classifying the incoming call audio pattern; and

wherein updating the automated call audio pattern set further includes training the call classifier model based on the updated automated call audio pattern set.

18. The computerized method of claim 10 , further comprising:

based on comparing the incoming call audio pattern to the automated call audio pattern set, requesting, by the call screening engine, from a calling party of the incoming call, at least one of a calling party identifier or a call purpose; and

based on receiving the at least one of the calling party identifier or the call purpose, providing, by the call screening engine, the received at least one of the calling party identifier or the call purpose to the user when prompting the user for a call response instruction.

19. One or more non-transitory computer readable storage medium having computer-executable instructions for automatically unsubscribing from automated calls based on automated call audio patterns that, upon execution by a processor, cause the processor to at least:

access, by a call screening engine, audio data of an incoming call;

generate, by the call screening engine, an incoming call audio pattern based on the audio data of the incoming call;

compare, by the call screening engine, the incoming call audio pattern to an automated call audio pattern set, the automated call audio pattern set including at least one of audio patterns associated with calls identified as automated calls or audio patterns associated with calls from which users have previously unsubscribed;

based on comparing the incoming call audio pattern to the automated call audio pattern set, prompt, by the call screening engine, the user for a call response instruction; and

based on the call response instruction from the user:

identify, by the call screening engine, an unsubscribe operation indication in the incoming call audio pattern;

perform, by the call screening engine, an unsubscribe operation associated with the identified unsubscribe operation indication; and

update, by the call screening engine, the automated call audio pattern set based on the incoming call audio pattern.

20. The one or more non-transitory computer storage medium of claim 19 , wherein comparing the incoming call audio pattern to the automated call audio pattern set includes generating a user prompt score and an automatic unsubscribe score associated with the incoming call audio pattern based on similarities between pattern portions of the incoming call audio pattern and pattern portions of the automated call audio pattern set;

wherein prompting the user for a call response instruction is further based on the generated user prompt score exceeding a user prompt threshold; and

wherein the computer-executable instructions, upon execution by a processor, further cause the processor to at least:

based on the automatic unsubscribe score exceeding an automatic unsubscribe threshold, identify, by the call screening engine, an unsubscribe operation indication in the incoming call audio pattern and perform, by the call screening engine, an unsubscribe operation associated with the identified unsubscribe operation indication without prompting the user.