Apparatus and method for event-driven content analysis

• US 20050108775A1
• Filed: 11/13/2003
• Published: 05/19/2005
• Est. Priority Date: 11/05/2003
• Status: Active Grant

• Current Assignee: Nice Ltd
• Original Assignee: Nice Systems Limited (Nice Ltd)
• Inventors: Gabay, Shay, Bachar, Aviv
• Granted Patent: US 8,060,364 B2
• Time in Patent Office: Days
• US Class Current: 725/135
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 3/4936 Speech interaction details speech recognition per se G10L15/00
• 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

Abstract

An apparatus and method for the event-driven analysis of media contents derived from customer interactions is disclosed. Content analysis is executed exclusively on those segments of the interaction media that are relevant in a given context. The steps of the analysis are carried out either in a static or dynamic manner where less demanding on resources analysis type is performed prior to more demanding analysis type.

Claims

1. An apparatus for event-driven content analysis, within a computerized system having a processing unit and a storage unit, the apparatus comprising the elements of:

a media type selector component to select a type of an interaction media inputted for analysis from an at least one interaction recording or storage device;

a pivot spot definer component to mark an at least one position in the interaction media to indicate the occurrence of an at least one pre-defined event or data item; and

a region of interest definer component to determine the limits of an at least one segment of the interaction associated with the location of the pivot spot.

2. The apparatus of claim 1 further comprising a content analysis input selector component to determine an at least one input or parameter for an at least one analyzer component.

3. The apparatus of claim 1 further comprises an analysis type selector component to identify and to select an at least one analyzer component type for determining the Region of Interest.

4. The apparatus of claim 1 further comprising an audio analyzer component for performing an analysis on the media selected by the media selector component in a location adjacent to the pivot spot identified by the pivot spot defined component.

5. The apparatus of claim 1 further comprising an analyzer component for performing an analysis on the media selected by the media selector component in a location adjacent to the pivot spot identified by the pivot spot definer component using an analyzer selected by the analysis type selector using parameters fed to, or selected by the content analysis input selector component.

6. The apparatus of claim 1 further comprising an analyzer component for performing an analysis on the media selected by the media selector component within the region of interest identified by the region of interest definer component using an analyzer selected by the analysis type selector using parameters fed to, or selected by the content analysis input selector component.

7. The apparatus of claim 1 wherein the region of interest defined by the region of interest definer component further comprises an optimization component for optimizing the region of interest.

8. The apparatus of claim 1 further comprises a content analysis inputs table to hold in storage the at least one selectable input values.

9. The apparatus of claim 1 further comprises the element of an audio analyzer component to analyze the audio elements of the interaction data.

10. The apparatus of claim 1 further comprises a computer telephony interface events analyzer component to identify and capture at least one common telephony events associated with the interaction data.

11. The apparatus of claim 1 further comprises a screen event analyzer component to identify and capture an at least one screen and an at least one screen event associated with the interaction data.

12. The apparatus of claim 4 wherein the audio analyzer component further comprises the elements of:

a word spotting component to locate and identify pre-defined terms or patterns in the speech elements of the interaction data;

an emotion analysis component to locate and identify positive or negative emotions in the interaction data; and

a talk analyzer component to identify and locate specific pre-defined speech events in the speech elements of the information data.

13. The apparatus of claim 1 further comprising an analysis module for performing an anlysis on the media.

14. The apparatus of claim 1 wherein the interaction is one of the following:

a telephone call, and e-mail message, an audio recording, a video, multimedia data or an interaction media.

15. The apparatus of claim 14 wherein the interaction media is at least one data packet carrying voice or other media over internet protocol.

16. The apparatus of claim 1 wherein the region of interest is a specific segment of the interaction media that is analyzed to extract meaningful interaction-specific information in an organization.

17. The apparatus of claim 1 wherein the interaction meta-data is an at least one computer telephony integrated or CRM event.

18. The apparatus of claim 1 wherein the interaction meta-data is associated with the at least one screen event.

19. A method for event-driven content analysis, within a computerized system having a processing unit and a storage unit, the method comprising the steps of:

determining an at least one pivot spot on an interaction media associated with an at least one event associated with the interaction media to be analyzed;

determining the limits of the at least one segment of the interaction media to be analyzed, said limits defining a region of interest within the interaction; and

executing an at least one analysis instruction step on the at least one segment of the interaction media.

20. The method of claim 19 further comprising the step of selecting an interaction media to analyze.

21. The method of claim 19 further comprising the step of selecting a method for the analysis of the at least one interaction media based on the at least one event associated with the interaction.

22. The method of claim 19 further comprising the step of selecting a method for the analysis of the at least one interaction media based on the result of a previously performed analysis.

23. The method of claim 19 further comprising the step of selecting the parameters to be used in the at least one analysis instruction step on the at least one segment of the interaction media.

24. The method of claim 19 further comprising the step of optimizing the region of interest by performing an at least one analysis instruction step within the region of interest and readjusting the region of interest in accordance with the results of the at least one analysis instruction step.

25. The method of claim 19 wherein the region of interest is predetermined by a user or an apparatus.

26. The method of claim 19 further comprises the steps of receiving interaction data and associated meta-data from an at least one interaction.

27. The method of claim 19 wherein the at least one analysis instruction step comprises the step of analyzing the speech elements of the interaction data for the presence of pre-defined words or phrases.

28. The method of claim 19 wherein the at least one analysis instruction step comprises the step of analyzing the speech elements of the interaction data to detect positive and negative emotions.

29. The method of claim 19 wherein the at least one analysis instruction step comprises the steps of analyzing the speech elements of the interaction data for pre-defined speech patterns.

30. The method of claim 19 further comprises the steps of:

identifying an at least one pre-defined computer telephony integrated event in the interaction data; and

identifying an at least one pre-defined screen event in the interaction data.

31. The method of claim 19 further comprising the steps of:

determining the execution sequence of the content analysis steps; and

selecting at least one input to an at least one content analysis step to provide for the optimized performance of the analysis step.

32. The method of claim 19 further comprises performing an at least one content analysis step during the capturing of the interaction data and the interaction meta-data.

33. The method of claim 19 further comprising the step of adjusting the at least one pivot spot or region of interest on the interaction media.