Method and system for analyzing caller interaction event data

• US 10,021,248 B2
• Filed: 02/13/2017
• Issued: 07/10/2018
• Est. Priority Date: 05/18/2005
• Status: Active Grant

• Current Assignee: Mattersight Corporation (Nice Ltd)
• Original Assignee: Mattersight Corporation (Nice Ltd)
• Inventors: Conway, Kelly, Capers, Keene Hedges, Danson, Christopher, Brown, Douglas, Gustafson, David, Warford, Roger, Moore, Melissa
• Primary Examiner(s): Nguyen, Khai N
• Application Number:
  US15/431,266
• Publication Number:
  US 20170155768A1
• Time in Patent Office: 512 Days
• Field of Search: 37921001, 37926501, 37926502, 37926503, 37926504, 37926505, 37926506, 37926507, 37926508, 37926509, 3792651, 37926511, 37926512, 37926513, 37926514, 37926601, 37926602, 37926603, 37926604, 37926605, 37926606, 37926607, 37926608, 37926609, 3792661
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04M 2201/40 using speech recognition
• CPC Class Codes: H04M 3/42221 Conversation recording systems at the subscriber's set H04M1/656
• CPC Class Codes: H04M 3/5175 Call or contact centers supervision arrangements
• CPC Class Codes: H04M 3/5183 Call or contact centers with computer-telephony arrangements
• CPC Class Codes: H04M 3/5191 interacting with the Internet

Abstract

A method for analyzing caller interaction events that includes receiving, by a processor, a caller interaction event between an agent and a caller, extracting, by a processor, caller event data from the caller interaction event, analyzing, by a processor, the caller event data, and generating, by a processor, a report displaying one or more selected categories of the caller event data. Systems and non-transitory, computer readable media that control an executable computer readable program code embodied therein, are also described.

Claims

1. A non-transitory, computer readable medium having an executable computer readable program code embedded therein, the executable computer readable program code for implementing a method of analyzing caller interaction events, which method comprises:

receiving a caller interaction event between an agent and a caller;

extracting caller event data from the caller interaction event;

generating a report displaying one or more selected categories of the caller event data; and

determining customer satisfaction following the caller interaction event based on the one or more selected categories of the caller event data.

2. The non-transitory, computer readable medium of claim 1, wherein the caller interaction event is converted to digital format.

3. The non-transitory, computer readable medium of claim 1, wherein the caller interaction event comprises at least one of a telephone call, a voice-based web interactions, voice over IP (“

VoIP”

), and video.

4. The non-transitory, computer readable medium of claim 1, wherein the caller interaction event includes one or more non-linguistic events.

5. The non-transitory, computer readable medium of claim 4, wherein each non-linguistic event comprises one or more of time of call, date of call, length of call, caller identification, agent identification, hold time, an early hold, a transfer, dead air time, a long average duration, overtalk, or a combination thereof.

6. The non-transitory, computer readable medium of claim 1, wherein the method further comprises separating an audio waveform of the caller interaction event after extracting the caller event data.

7. The non-transitory, computer readable medium of claim 1, wherein the report comprises a total number of calls received during a specified reporting interval, an average duration of call for all calls received during a time period, a greater than 150% duration for all calls by an agent, a greater than 90 second hold time for an agent, a greater than 30 second continuous silence time for an agent, a call transfer percentage for an agent resulting in a caller being transferred, or a combination thereof.

8. The non-transitory, computer readable medium of claim 1, wherein the method further comprises:

recording the caller interaction event; and

determining caller distress by conducting distress analysis of voice data associated with the caller from the recorded caller interaction event.

9. The non-transitory, computer readable medium of claim 1, wherein the method further comprises generating a caller satisfaction score based on a plurality of the following criteria:

(i) a long average duration of at least 150% of the length of a plurality of calls;

(ii) a hold time of at least 90 seconds;

(iii) a dead air time of at least 30 seconds;

(iv) caller distress; and

(v) program dissatisfaction.

10. The non-transitory, computer readable medium of claim 1, wherein the method further comprises generating a visual statistics link for displaying caller interaction event statistics.

11. The non-transitory, computer readable medium of claim 10, wherein the statistics comprise a number of calls including a hold exceeding a predetermined time limit, a number of calls exceeding a 30-second continuous silence time, or both.

12. A system configured to analyze caller interaction events which comprises one or more associated processors configured to:

receive a caller interaction event between an agent and a caller;

extract caller event data from the caller interaction event;

analyze the caller event data;

generate a report displaying one or more selected categories of the caller event data; and

determine customer satisfaction following the caller interaction event based on the one or more selected categories of the caller event data.

13. The system of claim 12, wherein the caller interaction event includes one or more non-linguistic events.

14. The system of claim 13, wherein each non-linguistic event comprises one or more of time of call, date of call, length of call, caller identification, agent identification, hold time, an early hold, a transfer, dead air time, a long average duration, overtalk, or a combination thereof.

15. The system of claim 12, wherein the report comprises a total number of calls received during a specified reporting interval, an average duration of call for all calls received during a time period, a greater than 150% duration for all calls by an agent, a greater than 90 second hold time for an agent, a greater than 30 second continuous silence time for an agent, a call transfer percentage for an agent resulting in a caller being transferred, or a combination thereof.

16. The system of claim 12, wherein the one or more associated processors are further configured to:

record the caller interaction event; and

determine caller distress by conducting distress analysis of voice data associated with the caller from the recorded caller interaction event.

17. The system of claim 12, wherein the one or more associated processors are further configured to generate a caller satisfaction score based on a plurality of the following criteria:

(i) a long average duration of at least 150% of the length of a plurality of calls;

(ii) a hold time of at least 90 seconds;

(iii) a dead air time of at least 30 seconds;

(iv) caller distress; and

(v) program dissatisfaction.

18. The system of claim 12, wherein the one or more associated processors are further configured to generate a visual statistics link for displaying caller interaction event statistics.

19. The system of claim 18, wherein the statistics comprise a number of calls including a hold exceeding a predetermined time limit, a number of calls exceeding a 30-second continuous silence time, or both.

20. A method of analyzing caller interaction events, which comprises:

receiving, by a processor, a caller interaction event between an agent and a caller;

extracting, by the processor, caller event data from the caller interaction event;

analyzing, by the processor, the caller event data;

generating, by the processor, a report displaying one or more selected categories of the caller event data; and

determining, by the processor, customer satisfaction following the caller interaction event based on the one or more selected categories of the caller event data.

21. The method of claim 20, wherein the caller interaction event is selected to include one or more non-linguistic events.

22. The method of claim 21, wherein each non-linguistic event is selected to comprise one or more of time of call, date of call, length of call, caller identification, agent identification, hold time, an early hold, a transfer, dead air time, a long average duration, overtalk, or a combination thereof.

23. The method of claim 20, wherein the report is selected to comprise a total number of calls received during a specified reporting interval, an average duration of call for all calls received during a time period, a greater than 150% duration for all calls by an agent, a greater than 90 second hold time for an agent, a greater than 30 second continuous silence time for an agent, a call transfer percentage for an agent resulting in a caller being transferred, or a combination thereof.

24. The method of claim 20, which further comprises:

recording the caller interaction event; and

determining caller distress by conducting distress analysis of voice data associated with the caller from the recorded caller interaction event.

25. The method of claim 20, which further comprises generating a caller satisfaction score based on a plurality of the following criteria:

(i) a long average duration of at least 150% of the length of a plurality of calls;

(ii) a hold time of at least 90 seconds;

(iii) a dead air time of at least 30seconds;

(iv) caller distress; and

(v) program dissatisfaction.

26. The method of claim 20, which further comprises generating a visual statistics link for displaying caller interaction event statistics.

27. The method of claim 26, wherein the statistics are selected to comprise a number of calls including a hold exceeding a predetermined time limit, a number of calls exceeding a 30-second continuous silence time, or both.