Systems for identifying the answering party of an automated voice call

Patent metadata

Field	Value
Publication number	US-12452373-B2
Application number	US-202318390462-A
Country	US
Kind code	B2
Filing date	Dec 20, 2023
Priority date	Jun 9, 2020
Publication date	Oct 21, 2025
Grant date	Oct 21, 2025

Abstract

Disclosed herein are systems and methods for determining whether an automated telephone call has been answered by a particular user, a different person, or a voicemail service. In response to determining that the call has been answered by the user, a different person, or a voicemail service, the systems and methods can output different respective messages, initiate messaging to the user via alternate communication paths, or perform other actions.

First claim

What is claimed is:

1. A non-transitory, computer-readable medium having instructions stored thereon that, when executed by one or more processors, causes a system to:
receive audio data associated with a call to a user device associated with a user;
detect an utterance from the audio data;
perform a comparison of the utterance to stored data;
determine, based on the comparison, whether the utterance corresponds to a voicemail greeting;
responsive to the utterance not corresponding to the voicemail greeting:
responsive to identifying the user:
output a person-focused recording comprising confidential information associated with the user;

responsive to not identifying the user:
output a person-focused recording omitting confidential information associated with the user;

responsive to the utterance corresponding to the voicemail greeting:
identify that the voicemail greeting is a customized voicemail greeting associated with the user;
identify, based on the comparison and a voicemail greeting database, a message duration of the customized voicemail greeting from the stored data; and
responsive to identifying the message duration, output a first recording after the message duration has expired, wherein the first recording is voicemail-focused and omits confidential information associated with the user.

2. The non-transitory, computer-readable medium of claim 1 , wherein identifying the user further comprises:
detecting voice biometric data associated with the audio data; and
performing an identification comparison of the voice biometric data to stored voice biometric data associated with the user to determine an identification level of similarity between the voice biometric data and the stored voice biometric data.

3. The non-transitory, computer-readable medium of claim 1 , wherein:
the call is a video call, and
the instructions, when executed by the one or more processors, further cause the system to:
receive video call data comprising video data and the audio data; and
extract the audio data from the video call data.

4. The non-transitory, computer-readable medium of claim 1 , wherein:
the stored data comprises data indicative of one or more default voicemail greetings, and
determining that the utterance corresponds to the voicemail greeting comprises:
determining, based on the comparison, a level of similarity between the utterance and data indicative of a default voicemail greeting of the one or more default voicemail greetings, and
determining that the level of similarity is greater than or equal to a predetermined threshold.

5. The non-transitory, computer-readable medium of claim 1 , wherein the instructions, when executed by the one or more processors, further cause the system to:
generating at least a portion of the stored data during an initial call prior to the receipt of the audio data by:
detecting an audible prompt to begin recording an initial utterance;
determining the message duration associated with the initial utterance, the message duration being indicative an amount of time between the call becoming connected and detection of the audible prompt to begin recording the initial utterance; and
storing the message duration and data indicative of the initial utterance in the stored data.

6. The non-transitory, computer-readable medium of claim 1 , wherein the instructions, when executed by the one or more processors, further cause the system to:
initiate an attempt to contact a user of the user device via a communication path that is different from the call.

7. The non-transitory, computer-readable medium of claim 1 , wherein the instructions, when executed by the one or more processors, further cause the system to:
responsive to identifying the message duration, disable audio monitoring of the call.

8. A system comprising:
one or more processors; and
memory in communication with the one or more processors and storing instructions that, when executed by the one or more processors, are configured to:
receive audio data associated with a call to a user device associated with a user;
determine whether the audio data corresponds to a voicemail greeting;
responsive to the audio data not corresponding to the voicemail greeting, output a person-focused recording comprising confidential information associated with the user;
responsive to the audio data corresponding to the voicemail greeting:
identify that the voicemail greeting is a customized voicemail greeting associated with the user;
identify a message duration of the customized voicemail greeting; and

after the message duration has expired, output a first recording, wherein the first recording is voicemail-focused and omits confidential information associated with the user.

9. The system of claim 8 , wherein the instructions, when executed by the one or more processors, are further configured to cause the system to:
detect an utterance from the audio data; and
perform a comparison of the utterance to stored data.

10. The system of claim 9 , wherein the instructions, when executed by the one or more processors, are further configured to cause the system to:
responsive to the utterance not corresponding to the voicemail greeting:
detect voice biometric data associated with the audio data;
perform an identification comparison of the voice biometric data to stored voice biometric data associated with the user to determine an identification level of similarity between the voice biometric data and the stored voice biometric data; and
responsive to determining that the identification level of similarity is greater than or equal to a first predetermined threshold, output a second recording that includes information for the user.

11. The system of claim 10 , wherein:
determining whether the utterance corresponds to the customized voicemail greeting further comprises:
determine, based on the comparison, a level of similarity between the utterance and the customized voicemail greeting, and
determine that the utterance corresponds to the customized voicemail greeting in response to determining that the level of similarity is greater than or equal to a second predetermined threshold.

12. The system of claim 10 , wherein:
the first recording is a generalized recording that omits confidential information associated with the user, and
the second recording is a user-specific recording that includes confidential information associated with the user.

13. The system of claim 10 , wherein the stored voice biometric data comprises the customized voicemail greeting.

14. The system of claim 8 , wherein the instructions, when executed by the one or more processors, further cause the system to:
detect baseline voice biometric data associated with the user during an audio interaction with the user or a customized voicemail greeting associated with the user; and
store the baseline voice biometric data as the stored voice biometric data.

15. A method comprising:
receiving audio data associated with a call to a user device associated with a user;
determining whether the audio data corresponds to a voicemail greeting;
responsive to the audio data corresponding to the voicemail greeting:
identifying that the voicemail greeting is a customized voicemail greeting associated with the user;
identifying a message duration of the customized voicemail greeting; and
after the message duration ends, outputting a first recording, wherein the first recording is voicemail-focused and omits confidential information associated with the user.

16. The method of claim 15 , furth

Assignees

• Capital One Services Llc

Inventors

• Benkreira Abdelkader
• Edwards Joshua
• Mossoba Michael

Classifications

• H04M1/82

  Line monitoring circuits for call progress or status discrimination {(for detecting caller identity H04M1/573)} · CPC title

• G10L15/22

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• H04M2250/74

  with voice recognition means · CPC title

• H04M3/436

  Arrangements for screening incoming calls {, i.e. evaluating the characteristics of a call before deciding whether to answer it (based on the calling party profile H04M3/42059; based on location H04M3/42348; based on presence H04M3/42365; diversion H04M3/54)} · CPC title

• H04M2201/18

  Comparators · CPC title