Method and system for accurate automatic call tracking and analysis
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.
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.