Method and system for analyzing separated voice data of a telephonic communication between a customer and a contact center by applying a psychological behavioral model thereto

• US 8,094,803 B2
• Filed: 05/18/2005
• Issued: 01/10/2012
• Est. Priority Date: 05/18/2005
• Status: Active Grant

• Current Assignee: Mattersight Corporation (Nice Ltd)
• Original Assignee: Mattersight Corporation (Nice Ltd)
• Inventors: Danson, Christopher, Conway, Kelly, Capers, Keene Hedges, Brown, Douglas, Gustafson, David, Warford, Roger, Moore, Melissa
• Primary Examiner(s): AL AUBAIDI, RASHA S
• Application Number:
  US11/131,486
• Publication Number:
  US 20060262919A1
• Time in Patent Office: 2,428 Days
• Field of Search: 379/88.16, 379/265.02, 379/67.1
• US Class Current: 379/265.02
• 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 3/2218 Call detail recording
• CPC Class Codes: H04M 3/36 Statistical metering, e.g. recording occasions when traffic exceeds capacity of trunks
• CPC Class Codes: H04M 3/5175 Call or contact centers supervision arrangements

Abstract

A method for analyzing a telephonic communication between a customer and a contact center is provided. According to the method, a telephonic communication is separated into first and second constituent voice data. One of the first and second constituent voice data is analyzed. The analysis consist of translating one the constituent voice data into a text format and applying a predetermined linguistic-based psychological behavioral model to the translated voice data. In applying the behavioral model, the translated voice data is mined, and behavioral signifiers associated with the psychological behavioral model are identified in the voice data. The behavioral signifiers are automatically associated with at least one of a plurality of personality types associated with the psychological behavioral model. Behavioral assessment data is generated which corresponds to the analyzed voice data.

Claims

1. A method for analyzing a telephonic communication between a customer and a contact center, the method comprising:

receiving a single telephonic communication between a first communicant to the telephonic communication and a second communicant to the telephonic communication;

separating the single telephonic communication into at least first constituent voice data and second constituent voice data, the first constituent voice data being generated by the first communicant and the second constituent voice data being generated by the second communicant;

analyzing one of the separated first and second constituent voice data, the step of analyzing comprising;

translating one of the first and second constituent voice data into a text format;

applying a predetermined linguistic-based psychological behavioral model to the translated text of the one of the first and second constituent voice data, the applying step comprising the steps of;

mining the translated text of the one of the first and second constituent voice data by automatically identifying a plurality of behavioral signifiers in the translated text of the one of the first and second constituent voice data, the behavioral signifiers being associated with the psychological behavioral model; and

,

automatically associating the identified behavioral signifiers in the translated text of the one of the first and second constituent voice data with at least one of a plurality of personality types associated with the psychological behavioral model; and

,

generating behavioral assessment data from the analyzed one of the separated first and second constituted voice data, the behavioral assessment data including a personality type based on the analyzed one of the first and second constituent voice data based on the step of analyzing one of the first and second constituent voice data.

2. The method of claim 1, wherein the predetermined linguistic-based psychological behavioral model is the Process Communication Model®

.

3. The method of claim 1, wherein the predetermined linguistic-based psychological behavioral model includes an assessment of distress levels in a communication, the method further comprising the step of generating distress assessment data corresponding to the analyzed voice data.

4. The method of claim 1, further comprising the step of generating event data corresponding to at least one identifying indicia and time interval, the event data comprising at least one of behavioral assessment data and distress assessment data.

5. The method of claim 1, wherein the telephonic communication is one of a plurality of telephonic communications, the method further comprising the step of categorizing the telephonic communication as one of a plurality of call types.

6. The method of claim 1, wherein the telephonic communication is one of a plurality of telephonic communications, the computer program further comprising a code segment for categorizing each of the telephonic communications of the plurality of telephonic communications into one of a plurality of customer categories.

7. The method of claim 1 further comprising the step of selecting the telephonic communication from the plurality of telephonic communications based upon the customer category in which the telephonic communication is categorized.

8. A physical computer program product comprising a computer usable medium having an executable computer readable program code embodied therein, the executable computer readable program code for implementing a method of analyzing a telephonic communication and generating a report of behavioral assessment data therefrom, the method comprising:

receiving a single telephonic communication between a first communicant to the telephonic communication and a second communicant to the telephonic communication;

separating the single telephonic communication into at least first constituent voice data and second constituent voice data, the first constituent voice data being generated by the first communicant and the second constituent voice data being generated by the second communicant;

analyzing one of the separated first and second constituent voice data, the analyzing comprising;

translating the separated one of the first and second constituent voice data into a text format;

applying a predetermined linguistic-based psychological behavioral model to the translated text of the one of the first and second constituent voice data, the applying step comprising;

mining the translated text of the one of the first and second constituent voice data by automatically identifying at least one of a plurality of behavioral signifiers in the translated text of the one of the first and second constituent voice data, the at least one behavioral signifier being associated with the psychological behavioral model; and

,

automatically associating the identified behavioral signifiers in the translated text of the one of the first and second constituent voice data with at least one of a plurality of personality types associated with the psychological behavioral model; and

,

generating behavioral assessment data based on the analyzed one of the separated first and second constituent voice data, the behavioral assessment data including a personality type corresponding to the analyzed one of the first and second constituent voice data based on the step of analyzing one of the first and second constituent voice data.

9. The physical computer program product of claim 8, wherein the step of separating the single telephonic communication into a first constituent voice data and a second constituent voice data comprises:

identifying a communication protocol associated with the telephonic communication;

recording the telephonic communication to a first electronic data file comprising a first and second audio track, the first constituent voice data being automatically recorded on the first audio track based on the identified communication protocol, and the second constituent voice data being automatically recorded on the second audio track based on the identified communication protocol; and

,

separating at least one of the first and second constituent voice data recorded on the corresponding first and second track from the first electronic data file.

10. The physical computer program product of claim 8, wherein the predetermined linguistic-based psychological behavioral model is the Process Communication Model®

.

11. The physical computer program product of claim 8, further comprising executable computer readable program code for implementing the step of storing the behavioral assessment data, the behavioral data corresponding to at least one identifying indicia and being made available for subsequent analysis.

12. The physical computer program product of claim 8, wherein the predetermined linguistic-based psychological behavioral model includes an assessment of distress levels in a communication, the method further comprising the step of generating distress assessment data corresponding to the analyzed communication data.

13. The physical computer program product of claim 8, further comprising executable computer readable program code for implementing the step of generating event data corresponding to at least one identifying indicia and time interval, the event data comprising at least one of behavioral assessment data and distress assessment data.

14. The physical computer program product of claim 8, further comprising executable computer readable program code for implementing the steps of:

generating a graphical user interface for displaying a first field for enabling identification of customer interaction event information on a display, the customer interaction event information including analysis data based on the psychological behavioral model applied to the analyzed constituent voice data of each customer interaction event;

receiving input from a user for identifying at least a first customer interaction event; and

,

displaying the customer interaction event information for the first customer interaction event.

15. A physical computer program product comprising a computer usable medium having an executable computer readable program code embodied therein, the executable computer readable program code for implementing a method of analyzing a telephonic communication and generating a report of behavioral assessment data therefrom, the method comprising:

receiving a single telephonic communication in digital format, the single telephonic communication being between a first communicant to the telephonic communication and a second communicant to the telephonic communication and comprising a first constituent voice data and a second constituent voice data, the first constituent voice data being generated by the first communicant and the second constituent voice data being generated by the second communicant;

identifying a communication protocol associated with the single telephonic communication;

separating the first and second constituent voice data one from the other by recording the telephonic communication in stereo format to a first electronic data file, the first electronic data file comprising a first and second audio track, the first constituent voice data being automatically recorded on the first audio track based on the identified communication protocol, and the second constituent voice data being automatically recorded on the second audio track based on the identified communication protocol;

analyzing the separated first constituent voice data, the step for analyzing comprising;

applying a non-linguistic based analytic tool to the separated first constituent voice;

generating phone event data corresponding to the analyzed first constituent voice data;

translating the first constituent voice data into text format and storing the translated text of the first constituent voice data in a first text file;

applying a predetermined linguistic-based psychological behavioral model to the translated text of the first constituent voice data in the first text file, the applying step comprising;

mining the translated text of the first constituent voice data by automatically identifying at least one of a plurality of behavioral signifiers in the translated text of the first constituent voice data, the at least one behavioral signifier being associated with the psychological behavioral model; and

,

automatically associating the identified behavioral signifiers with at least one of a plurality of personality types associated with the psychological behavioral model; and

,

generating at least one of either behavioral assessment data including a personality type and distress assessment data based on the analyzed first voice data based on the step of analyzing one of the first and second constituent voice data.

16. The physical computer program product of claim 15, wherein the predetermined linguistic-based psychological behavioral model is the Process Communication Model®

.

17. The physical computer program product of claim 15 further comprising executable computer readable program code for implementing the steps of:

analyzing the separated second constituent voice data, the step of analyzing comprising;

applying a non-linguistic based analytic tool to the separated second constituent voice data and for generating phone event data corresponding to the analyzed second constituent voice data;

translating the second constituent voice data into text format and storing the translated text of the second voice data in a second text file;

applying a predetermined linguistic-based psychological behavioral model to the translated text of the second constituent voice data in the second text file, the step of applying the predetermined linguistic-based psychological behavioral model the comprising;

mining the translated text of the second constituent voice data by automatically identifying at least one of a plurality of behavioral signifiers in the translated text of the second constituent voice data, the at least one behavioral signifier being associated with the psychological behavioral model; and

,

automatically associating the identified behavioral signifiers with at least one of a plurality of personality types associated with the psychological behavioral model;

generating at least one of either behavioral assessment data including a personality type and distress assessment data based on the analyzed second voice data;

a code segment for generating call assessment data by comparatively analyzing the behavioral assessment data and distress assessment data corresponding to the analyzed first voice data and the behavioral assessment data and distress assessment data corresponding to the analyzed second voice data; and

,

outputting event data, the event data comprising call assessment data corresponding to at least one identifying indicia and at least one predetermined time interval.

18. The physical computer program product of claim 17, wherein the predetermined linguistic-based psychological behavioral model is the Process Communication Model®

.

19. The physical computer program product of claim 17, further comprising executable computer readable program code for implementing the steps of:

generating a graphical user interface for displaying a first field for enabling identification of customer interaction event information on a display, the customer interaction event information including analysis data based on the psychological behavioral model applied to the analyzed constituent voice data of each customer interaction event;

receiving input from a user for identifying at least a first customer interaction event; and

,

displaying the customer interaction event information for the first customer interaction event.

20. A physical computer program product comprising a computer usable medium having an executable computer readable program code embodied therein, the executable computer readable program code for implementing a method of analyzing a telephonic communication and generating a report of behavioral assessment data therefrom, the method comprising:

receiving a single telephonic communication between a first communicant to the telephonic communication and a second communicant to the telephonic communication;

separating the single telephonic communication into at least first constituent voice data and second constituent voice data, the single telephonic communication being between a first communicant to the telephonic communication and a second communicant to the telephonic communication, the first constituent voice data being generated by the first communicant and the second constituent voice data being generated by the second communicant, the step of separating comprising;

identifying a communication protocol associated with the single telephonic communication;

recording the single telephonic communication to a first and second audio track of a first electronic data file, the first constituent voice data being automatically recorded on the first audio track based on the identified communication protocol, and the second constituent voice data being automatically recorded on the second audio track based on the identified communication protocol;

extracting at least one of the first and second constituent voice data recorded on the corresponding first and second track from the first electronic data file;

analyzing the extracted one of the first and second constituent voice data, the a code segment for analyzing comprising;

translating one of the first and second constituent voice data into a text format;

applying a predetermined linguistic-based psychological behavioral model to the translated text of the one of the first and second constituent voice data, the applying step comprising;

mining the translated text of the voice data by automatically identifying at least one of a plurality of behavioral signifiers in the translated text of the one of the first and second constituent voice data, the at least one behavioral signifier being associated with the psychological behavioral model; and

,

automatically associating the identified behavioral signifiers with at least one of a plurality of personality types associated with the psychological behavioral model; and

,

generating behavioral assessment data from the analyzed one of the separated first and second constituted voice data, the behavioral assessment data including a personality type based on the analyzed one of the first and second constituent voice data based on the step of analyzing one of the first and second constituent voice data.