System for automated call analysis using context specific lexicon

• US 9,756,185 B1
• Filed: 12/28/2016
• Issued: 09/05/2017
• Est. Priority Date: 11/10/2014
• Status: Active Grant

• Current Assignee: Teton1, LLC
• Original Assignee: Teton1, LLC
• Inventors: Madden, Jr., Robert T., Derikart, Christopher P., Donnelly, Edward A.
• Primary Examiner(s): Deane, Jr., William
• Application Number:
  US15/391,962
• Time in Patent Office: 251 Days
• Field of Search: 37926501-26514
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: H04M 2201/42 Graphical user interfaces
• CPC Class Codes: H04M 2203/2038 Call context notifications
• CPC Class Codes: H04M 2203/303 Marking
• CPC Class Codes: H04M 2203/305 Recording playback features, e.g. increased speed
• CPC Class Codes: H04M 2203/403 Agent or workforce training
• 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

Abstract

A system and method for automated call analysis using context specific lexicons. A system includes memory and a processor configured to executed instructions. The system includes a recording component, a lexicon component, an analysis component, and a display component. The lexicon component defines a plurality of context specific lexicons, with each context specific lexicon having elements associated with one of a plurality of unique conversation segments. The analysis component configured to identify elements of the context specific lexicons, and associate each identified element with a time location in a telephonic conversation. The display component configured to graphically present a multi-line graph such that the intersections of the lines indicate transitions between the unique conversation segments.

Claims

1. A system comprising:

a memory to store instructions;

a processor, communicatively coupled to the memory, that executes or facilitates execution of the instructions, the instructions comprising;

a recording component configured to record a telephonic conversation between a first conversation participant and a second conversation participant;

a lexicon component that defines a plurality of context specific lexicons, wherein each of the plurality of context specific lexicons includes elements associated with one of a plurality of unique conversation segments;

an analysis component configured to perform automatic speech recognition on the telephonic conversation to identify elements of the context specific lexicons, the analysis component further configured to associate each identified element with a time location within the telephonic conversation at which the element occurred;

the analysis component further configured to determine a frequency of occurrence of the elements of each context specific lexicon associated with the corresponding unique conversation segment to identify transitions between the unique conversation segments; and

a display component configured to graphically present on a display a multi-line graph, wherein each line corresponds to the frequency of occurrence of the elements of one of the context specific lexicon associated with the corresponding unique conversation segment;

such that intersections of the lines indicate transitions between the unique conversation segments.

2. The system of claim 1, further comprising a scoring component configured to determine a duration of each unique conversation segment based on frequency of occurrence of the elements of the context specific lexicon associated with the corresponding unique conversation segment.

3. The system of claim 2, wherein the scoring component is further configured to assign a grade based on a comparison of the determined duration of each unique conversation segment, to a benchmark duration for each unique conversation segment.

4. The system of claim 1, further comprising a scoring component configured to determine an area of overlap between unique conversation segments based on frequency of occurrence of the elements of the context specific lexicon associated with the corresponding unique conversation segments.

5. The system of claim 4, wherein the scoring component is further configured to assign a grade based on the area of overlap between unique conversation segments, where a higher grade is assigned to a conversation with minimal overlap between the unique conversation segments, and where a lower grade is assigned to the conversation as the overlap increases.

6. The system of claim 1, wherein the duration of each unique conversation segment is determined as a percentage of a total duration of the telephonic conversation.

7. The system of claim 1, wherein the analysis component is further configured to determine a start time and an end time for each unique conversation segment as percentages of time of a duration of the conversation.

8. The system of claim 1, wherein the unique conversation segments are opening, discovery, solution and conclusion.

9. The system of claim 1, wherein at least a portion of the elements of the context specific lexicons include keywords or phrases.

10. The system of claim 1, further comprising a phone switch to collect and store the telephonic conversation before the telephonic conversation is analyzed by the system.

11. The system of claim 1, wherein the analysis component includes a tag detection logic configured to perform automatic speech recognition on the telephonic conversation, and a tag grouping logic configured to determine a frequency of occurrence of the elements of each context specific lexicon associated with the corresponding unique conversation segment.