Method and system for accurate automatic call tracking and analysis

• US 10,264,125 B2
• Filed: 10/04/2016
• Issued: 04/16/2019
• Est. Priority Date: 03/30/2010
• Status: Active Grant

• Current Assignee: Call Compass, LLC
• Original Assignee: Call Compass, LLC
• Inventors: Bernstein, Eric F, Aldrich, Grant L, Gilmore, Jasson
• Primary Examiner(s): Nguyen, Khai N.
• Application Number:
  US15/285,373
• Publication Number:
  US 20170026515A1
• Time in Patent Office: 924 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: G06Q 10/02 Reservations, e.g. for tickets, services or events
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 25/48 specially adapted for particular use
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 2203/552 Call annotations
• CPC Class Codes: H04M 3/5175 Call or contact centers supervision arrangements

Abstract

There is disclosed a method in a data processing system for automatically and accurately determining an outcome of a phone call by using signifiers or audibles as a way to increase accuracy without altering the flow of the conversation. The disclosed method can be used in any call center, such as a high volume call center used in the financial (banking), insurance, rental (hotel or car), ticket sales, and the like. The method comprises receiving voice data of a phone call; transmitting a response communication based on the voice data, wherein the response communication includes at least one audible or signifier; identifying, by at least one processor, the at least one audible or signifier in the response communication; and automatically determining the outcome of the phone call based on the audible or signifier in the response communication. A data processing system and a non-transitory computer-readable medium for storing instructions consistent with the described method are also disclosed.

Claims

1. A method in a data processing system for automatically determining an outcome of a phone call, the method comprising:

receiving voice data of a phone call;

transmitting, by at least one processor, a response communication based on the voice data, wherein the response communication includes at least one audible or signifier;

identifying, by the at least one processor, the at least one audible or signifier in the response communication;

determining whether there is at least one signifier is in the response communication;

when the at least one signifier is in the response;

accessing a signifier database,

determining a word count associated with the signifier,

determining adjacent words based on the word count associated with the signifier and a direction associated with the signifier when the word count associated with the signifier is not zero, and

determining adjacent words based on words between the signifier and a stop signifier when the word count associated with the signifier is zero; and

automatically determining the outcome of the phone call based on the at least one audible or signifier in the response communication.

2. The method of claim 1, wherein the response communication is generated by a call operator.

3. The method of claim 1, wherein the at least one audible or signifier includes at least one word that is not commonly used in conversation.

4. The method of claim 1, wherein the at least one audible or signifier includes a plurality of words.

5. The method of claim 1, wherein identifying the at least one audible or signifier comprises:

automatically transcribing the response communication into text data;

generating a list of words based on the text data;

accessing a list of audibles and signifiers stored in a database; and

associating the list of words and with the list of audibles and signifiers.

6. The method of claim 5 further comprising:

assigning the call to a human screener when there is no association between the list of words and with the list of audibles and signifiers.

7. The method of claim 5 further comprising:

applying a set of logic rules when more than one audible or signifier are identified.

8. The method of claim 1, wherein the outcome comprises one of:

(1) the caller booked an appointment, and (2) the caller did not book an appointment.

9. The method of claim 1, wherein the outcome comprises one of (1) the caller purchased a product, and (2) the caller did not purchase a product.

10. The method of claim 1 further comprising:

automatically determining a condition discussed during the phone call.

11. The method of claim 1 further comprising:

automatically determining a service or product associated with the phone call based on the audible or signifier in the response communication.

12. The method of claim 1 further comprising:

automatically determining if a caller made a purchase associated based on the audible or signifier in the response communication.

13. The method of claim 1, wherein:

the at least one audible or signifier is an erase audible; and

the outcome of the phone call is null when at least one audible or signifier is an erase audible.

14. The method of claim 1, wherein the phone call is intended for a financial services office and the caller is one of:

(a) a client of the financial services office, and (2) a potential client of the financial services office.

15. The method of claim 14, wherein the phone call outcome comprises one of:

(1) the caller opened an account, (2) the caller request mortgage information, (3) the caller cancelled an account, (4) the caller made a transaction, (5) the caller made a transfer, (6) the caller made a trade, (7) the caller is closing an account, (8) the caller requested taxes information, (9) the caller cannot login to an online account, (10) the caller is requesting a new credit.

16. The method of claim 1, wherein the phone call intended for a tickets retail office and the caller is one of:

(1) a client of the ticket retail office, and (2) a potential client of the ticket retail office.

17. The method of claim 11, wherein the phone call outcome comprises one of:

(1) the caller purchased a ticket, (2) the caller inquired event is sold out, (3) the caller requested event information, (4) the caller asked about venue information, (5) the caller made a group purchase, (6) the caller reserved a suite, (7) the caller is requesting a refund, (8) caller bought premium tickets, (9) the caller inquired ticket packages, (10) the caller bought ticket packages.

18. The method of claim 1, wherein the phone call is intended for a marketing services office and the caller is one of:

(1) a client of the marketing services office, and (2) a potential client of the marketing services office.

19. A data processing system for automatically determining an outcome of a phone call, the system comprising:

a database comprising data associated with audibles and signifiers;

a memory configured to store instructions to cause a processor to;

receive voice data of a phone call;

transmit a response communication based on the voice data, wherein the response communication includes at least one audible or signifier;

identify the at least one audible or signifier in the response communication;

determine whether there is at least one signifier is in the response communication;

when the at least one signifier is in the response communication;

access the database,

determine a word count associated with the signifier,

determine adjacent words based on the word count associated with the signifier and a direction associated with the signifier when the word count associated with the signifier is not zero, and

determine adjacent words based on words between the signifier and a stop signifier when the word count associated with the signifier is zero; and

determine the outcome of the phone call based on the audible or signifier in the response communication.

20. The data processing system of claim 19, wherein the at least one audible or signifier includes a word not commonly used in conversation.

21. The data processing system of claim 19, wherein the at least one audible or signifier includes a plurality of words.

22. The data processing system of claim 19, wherein to identify the at least one audible or signifier, the processor is configured to:

automatically transcribe the response communication into text data;

generate a list of words based on the text data;

access a list of audibles and signifiers stored in a call analysis server; and

associate the list of words and with the list of audibles and signifiers.

23. The data processing system of claim 22, wherein the processor is further configured to:

assign the call to a human screener when there is no association between the list of words and with the list of audibles and signifiers.

24. The data processing system of claim 22, wherein the processor is further configured to:

apply a set of logic rules when more than one audible or signifier are identified.

25. The data processing system of claim 19, wherein the outcome comprises one of:

(1) the caller booked an appointment, and (2) the caller did not book an appointment.

26. The data processing system of claim 19, wherein the outcome comprises one of (1) the caller purchased a product, and (2) the caller did not purchase a product.

27. The data processing system of claim 19 wherein the processor is further configures to:

automatically determine a condition discussed during the phone call.

28. The data processing system of claim 19, wherein the processor is further configured to:

determining a service or product associated with the phone call based on the audible or signifier in the response communication.

29. The data processing system of claim 19, wherein the processor is further configured to:

automatically determining if a caller made a purchase associated based on the audible or signifier in the response communication.

30. The data processing system of claim 19, wherein:

the at least one audible or signifier is an erase audible; and

the processor determine the outcome of the phone call as null when at least one audible or signifier is an erase audible.

31. A non-transitory computer-readable medium storing instructions which, when executed, cause one or more processors to perform a method for determining an outcome of a phone call, comprising:

receiving voice data of a phone call;

transmitting a response communication based on the voice data, wherein the response communication includes at least one audible or signifier;

identifying, by at least one processor, the at least one audible or signifier in the response communication;

determining whether there is at least one signifier is in the response communication;

when the at least one signifier is in the response;

accessing a signifier database,

determining a word count associated with the signifier,

determining adjacent words based on the word count associated with the signifier and a direction associated with the signifier when the word count associated with the signifier is not zero, and

determining adjacent words based on words between the signifier and a stop signifier when the word count associated with the signifier is zero; and

automatically determining the outcome of the phone call based on the audible or signifier in the response communication.