System and method for analyzing and classifying calls without transcription

• US 9,614,962 B2
• Filed: 08/24/2015
• Issued: 04/04/2017
• Est. Priority Date: 03/15/2013
• Status: Active Grant

• Current Assignee: Marchex Incorporated
• Original Assignee: Marchex Incorporated
• Inventors: Kolbegger, Chris, Flaks, Jason, Graber, Tim, Rieger, Bryan, Ismail, Ziad, Ramanathan, Govindaraj, Spehr, Darren, Berk, Matthew
• Primary Examiner(s): Teshale, Akelaw
• Application Number:
  US14/834,196
• Publication Number:
  US 20150365530A1
• Time in Patent Office: 589 Days
• Field of Search: 379 3201, 379 39, 379 45, 379 8801, 379 8802, 379 8808, 379 8816, 379 8822, 37910101, 379242, 379 2, 379 6505-26602, 37926503, 37911209, 379189, 37920112, 37920401, 37926512
• CPC Class Codes: G10L 25/51 for comparison or discrimination
• CPC Class Codes: G10L 25/78 Detection of presence or absence of voice signals switching of direction of transmission by voice frequency in two-way loud-speaking telephone systems H04M9/10
• CPC Class Codes: G10L 25/93 Discriminating between voiced and unvoiced parts of speech signals G10L25/90 takes precedence
• CPC Class Codes: H04L 41/5067 Customer-centric QoS measurements
• CPC Class Codes: H04L 43/0852 Delays
• CPC Class Codes: H04M 2203/559 Sorting systems
• CPC Class Codes: H04M 3/2281 Call monitoring, e.g. for law enforcement purposes; Call tracing; Detection or prevention of malicious calls
• CPC Class Codes: H04M 3/42221 Conversation recording systems at the subscriber's set H04M1/656
• CPC Class Codes: H04M 3/5166 in combination with interactive voice response systems or voice portals, e.g. as front-ends
• CPC Class Codes: H04M 3/5175 Call or contact centers supervision arrangements

Abstract

A facility and method for analyzing and classifying calls without transcription. The facility analyzes individual frames of an audio to identify speech and measure the amount of time spent in speech for each channel (e.g., caller channel, agent channel). Additional telephony metrics such as R-factor or MOS score and other metadata may be factored in as audio analysis inputs. The facility then analyzes the frames together as a whole and formulates a clustered-frame representation of a conversation to further identify dialog patterns and characterize call classification. Based on the data in the clustered-frame representation, the facility is able to make estimations of call classification. The correlation of dialog patterns to call classification may be utilized to develop targeted solutions for call classification issues, target certain advertising channels over others, evaluate advertising placements at scale, score callers, and to identify spammers.

Claims

1. A computing system for analyzing telephone calls to identify a low quality telephone call and take corrective action, the computing system comprising:

a memory for storing programmed instructions;

a processor configured to execute the programmed instructions to perform operations including;

receiving, by a computing system, a group of telephone calls,

wherein each telephone call in the received group of telephone calls is associated with one or more call parameters; and

wherein an audio signal of each telephone call in the received group of telephone calls carries one or more channels;

for each telephone call in the received group of telephone calls;

monitoring, by the computing system, a time-in-activity of each of the one or more channels by tracking on each channel when there is activity, wherein the time-in-activity comprises speech activity and non-speech activity;

determining, by the computing system, whether the monitored time-in-activity of each of the one or more channels is indicative of a low quality telephone call based on a dialogue pattern identified in the one or more channels;

identifying, by the computing system, call parameters that are correlated with determined low quality telephone calls;

identifying, by the computing system, a subsequent telephone call to monitor, wherein the subsequent telephone call is associated with one or more call parameters;

determining, by the computing system, whether one or more call parameters of the subsequent telephone call is present that correlate with determined low quality telephone calls; and

in response to determining that one or more call parameters of the subsequent telephone call correlate with determined low quality telephone calls, taking a corrective action with respect to the subsequent telephone call.

2. The computing system of claim 1 wherein the monitored time-in-activity is indicative of a low quality telephone call when:

a predetermined amount of time-in-activity for a first channel of the one or more channels corresponds to speech and a relatively insubstantial amount of time-in-activity for a second channel of the one or more channels corresponds to speech;

or

time-in-activity for the first channel coincides with time-in-activity of the second channel.

3. The computing system of claim 1 wherein the monitored time-in-activity is indicative of a low quality telephone call when no speech is detected on any of the one or more channels, or speech is detected on only one of the one or more channels.

4. The computing system of claim 1 wherein the monitored time-in-activity is indicative of a low quality telephone call when a synthesized voice is detected on any of the one or more channels.

5. The computing system of claim 1 wherein at least one call parameter corresponds to a time, distribution channel, advertiser, or circuit that is associated with the telephone call.

6. The computing system of claim 1 wherein the corrective action is deprioritizing the subsequent telephone such that the subsequent telephone call is allowed to be kept on hold for a longer period of time than a non-deprioritized telephone call.

7. The computing system of claim 1 wherein the corrective action is blocking the subsequent telephone call by preventing the subsequent telephone call from reaching the intended recipient.

8. The computing system of claim 1 wherein the corrective action is providing an alert regarding the presence of the low quality call.

9. The computing system of claim 1 wherein the audio signal of the telephone call is a live, unrecorded telephone call or a pre-recorded file.

10. A method in a computing system for analyzing telephone calls to identify a low quality telephone call and take corrective action, the method comprising:

receiving, by a computing system, a group of telephone calls,

wherein each telephone call in the received group of telephone calls is associated with one or more call parameters; and

wherein an audio signal of each telephone call in the received group of telephone calls carries one or more channels;

for each telephone call in the received group of telephone calls;

monitoring, by the computing system, a time-in-activity of each of the one or more channels by tracking on each channel when there is activity, wherein the time-in-activity comprises speech activity and non-speech activity;

determining, by the computing system, whether the monitored time-in-activity of each of the one or more channels is indicative of a low quality telephone call based on a dialogue pattern identified in the one or more channels;

identifying, by the computing system, call parameters that are correlated with determined low quality telephone calls;

identifying, by the computing system, a subsequent telephone call to monitor, wherein the subsequent telephone call is associated with one or more call parameters;

determining, by the computing system, whether one or more call parameters of the subsequent telephone call is present that correlate with determined low quality telephone calls; and

in response to determining that one or more call parameters of the subsequent telephone call correlate with determined low quality telephone calls, taking a corrective action with respect to the subsequent telephone call.

11. The method of claim 10 wherein the monitored time-in-activity is indicative of a low quality telephone call when:

a predetermined amount of time-in-activity for a first channel of the one or more channels corresponds to speech and a relatively insubstantial amount of time-in-activity for a second channel of the one or more channels corresponds to speech;

or

time-in-activity for the first channel coincides with time-in-activity of the second channel.

12. The method of claim 10 wherein the monitored time-in-activity is indicative of a low quality telephone call when no speech is detected on any of the one or more channels, or speech is detected on only one of the one or more channels.

13. The method of claim 10 wherein the monitored time-in-activity is indicative of a low quality telephone call when a synthesized voice is detected on any of the one or more channels.

14. The method of claim 10 wherein at least one call parameter corresponds to a time, distribution channel, advertiser, or circuit that is associated with the telephone call.

15. The method of claim 10 wherein the corrective action is deprioritizing the subsequent telephone such that the subsequent telephone call is allowed to be kept on hold for a longer period of time than a non-deprioritized telephone call.

16. The method of claim 10 wherein the corrective action is blocking the subsequent telephone call by preventing the subsequent telephone call from reaching the intended recipient.

17. The computing system of claim 10 wherein the corrective action is providing an alert regarding the presence of the low quality call.

18. The method of claim 10 wherein the audio signal of the telephone call is a live, unrecorded telephone call or a pre-recorded file.

19. The method of claim 10 wherein at least one channel is a client channel and at least one channel is an agent channel.

20. A non-transitory computer readable storage medium with instructions stored thereon that, when executed by a computing system, cause the computing system to perform a method for analyzing telephone calls to identify a low quality telephone call and take corrective action, the method comprising:

receiving, by a computing system, a group of telephone calls,

wherein each telephone call in the received group of telephone calls is associated with one or more call parameters; and

wherein an audio signal of each telephone call in the received group of telephone calls carries one or more channels;

for each telephone call in the received group of telephone calls;

monitoring, by the computing system, a time-in-activity of each of the one or more channels by tracking on each channel when there is activity, wherein the time-in-activity comprises speech activity and non-speech activity;

determining, by the computing system, whether the monitored time-in-activity of each of the one or more channels is indicative of a low quality telephone call based on a dialogue pattern identified in the one or more channels;

identifying, by the computing system, call parameters that are correlated with determined low quality telephone calls;

identifying, by the computing system, a subsequent telephone call to monitor, wherein the subsequent telephone call is associated with one or more call parameters;

determining, by the computing system, whether one or more call parameters of the subsequent telephone call is present that correlate with determined low quality telephone calls; and

in response to determining that one or more call parameters of the subsequent telephone call correlate with determined low quality telephone calls, taking a corrective action with respect to the subsequent telephone call.