Enterprise Speech Intelligence Analysis

• US 20100329437A1
• Filed: 06/24/2010
• Published: 12/30/2010
• Est. Priority Date: 06/24/2009
• Status: Active Grant

• Current Assignee: Nexidia Incorporated (Nice Ltd)
• Original Assignee: Nexidia Incorporated (Nice Ltd)
• Inventors: Gavalda, Marsal, Jeffs, Christopher J., Surdick, Robert Troy, Pledger, Philip Kyle
• Granted Patent: US 8,494,133 B2
• Time in Patent Office: Days
• US Class Current: 379/112.06
• CPC Class Codes: H04M 15/00 Arrangements for metering, time-control or time indication ; Metering, charging or billing arrangements for voice wireline or wireless communications, e.g. VoIP
• CPC Class Codes: H04M 15/06 Recording class or number of calling , i.e. A-party or called party , i.e. B-party
• CPC Class Codes: H04M 15/41 Billing record details, i.e. parameters, identifiers, structure of call data record [CDR]
• CPC Class Codes: H04M 15/58 based on statistics of usage or network monitoring
• CPC Class Codes: H04M 15/8038 Roaming or handoff

Abstract

A method includes accepting, via an input interface, a caller identifier parameter and a target value of at least one call series parameter; identifying, using a data processor, a plurality of calls each associated with the caller identifier parameter from amongst a set of calls stored in a call center database; analyzing, using the data processor, the identified plurality of calls to determine a value of the at least one call series parameter for the identified plurality of calls; comparing, using the data processor, the determined value of the at least one call series parameter with the target value of the at least one call series parameter; and defining, using the data processor, the identified plurality of calls as a call series based at least in part on results of the comparing.

Claims

1. A method comprising:

accepting, via an input interface, a caller identifier parameter and a target value of at least one call series parameter;

identifying, using a data processor, a plurality of calls each associated with the caller identifier parameter from amongst a set of calls stored in a call center database;

analyzing, using the data processor, the identified plurality of calls to determine a value of the at least one call series parameter for the identified plurality of calls;

comparing, using the data processor, the determined value of the at least one call series parameter with the target value of the at least one call series parameter; and

defining, using the data processor, the identified plurality of calls as a call series based at least in part on results of the comparing.

2. The method of claim 1, wherein the caller identifier parameter includes at least one of an identifier of a caller, an automatic number identification (ANI) associated with the caller, a telephone number of the caller, and content-based identification of the caller.

3. The method of claim 1, wherein identifying the plurality of calls each associated with the caller identifier parameter comprises:

identifying, from amongst the set of calls stored in the call center database, a first call in which a structured query is matched by the audio content; and

further identifying, from amongst the set of calls stored in the call center database, at least one subsequent call sharing a common caller identifier parameter with the first call.

4. The method of claim 1, wherein the call series parameter includes at least one of a minimum number of calls, a maximum number of calls, a maximum amount of time between consecutive calls, and a minimum amount of time between consecutive calls.

5. The method of claim 1, wherein the call series parameter includes at least one of a total duration of calls, a total duration of non-talk time, a percentage of non-talk time, and a number of occurrences of non-talk time.

6. The method of claim 1, wherein the call series parameter includes at least one structured query is matched by the audio content in a call.

7. The method of claim 1, wherein at least one call of the set is stored in the call center database in association with a metadata file.

8. A method for analyzing a set of call series, each call series of the set including a plurality of calls, the method including:

accepting, at a data processor, call series data characterizing each of the plurality of calls of the set;

analyzing, using the data processor, the call series data to identify an attribute shared by at least one call in each of the call series of the set; and

generating, using a report generation module, a report representative of the results of the analyzing.

9. The method of claim 8, wherein analyzing the call series data includes identifying a topic discussed during at least one call in each of the call series of the set.

10. The method of claim 8, wherein analyzing the call series data includes identifying a topic discussed during a first call in each of the call series of the set.

11. The method of claim 8, wherein analyzing the call series data includes identifying a topic discussed during a call subsequent to a first call in each of the call series of the set.

12. The method of claim 8, wherein analyzing the call series data includes identifying a correlation between a first topic discussed in a first topic call of a call series and a second topic discussed in a second topic call of the same call series.

13. The method of claim 12, wherein the correlation between the first topic and the second topic is determined based on at least one of the following:

a ratio of a number of second topic calls to a number of call series in which the first call of the call series is a first topic call;

a ratio of a number of second topic calls subsequent to the first topic call to a number of call series including at least one first topic call;

a ratio of a number of second topic calls to a number of call series including at least one first topic call;

a ratio of a number of call series including at least one second topic call to a number of call series including at least one first topic call;

a ratio of a number of second topic calls to a number of first topic calls;

a linear combination of a number of first topic calls and a number of second topic calls; and

a nonlinear combination of a number of first topic calls and a number of second topic calls.

14. The method of claim 8, wherein analyzing the call series data includes, for at least a first call series of the set, identifying a first topic discussed in a first call of the first call series and a second topic discussed in a subsequent call of the first call series.

15. The method of claim 14, wherein analyzing the call series data further includes determining a correlation between the first topic and the second topic.

16. The method of claim 8, wherein analyzing the call series data includes searching the call series data for occurrences of a search term.

17. The method of claim 8, wherein analyzing the call series data includes filtering the call series data.

18. The method of claim 8, wherein analyzing the call series data includes identifying a pattern of topics discussed in calls belonging to different call series of the set.

19. The method of claim 8, wherein the call series data include an identity of a call center agent associated with each of the calls of the set.

20. The method of claim 19, wherein analyzing the call center data includes, for each call center agent, determining a number of call series including at least one call associated with that call center agent.

21. The method of claim 19, wherein analyzing the call series data includes identifying a topic discussed in the calls associated with each call center agent.

22. The method of claim 8, wherein the call series data include an identity of a caller for each call of the set and a topic discussed in each call of the set.

23. The method of claim 22, wherein analyzing the call series data includes identifying topics discussed in at least some of the calls associated with each caller.