Granted Patent B2

US 11,290,400 · App. 16/711,970 · Granted Mar 29, 2022

Inventors: Thomas Fejes (Freshwater, AU); Michael Monegan (Redwood City, CA)

Assignee: CYARA SOLUTIONS PTY LTD

H04L51/046G06F11/3664H04L12/4625H04L41/5038H04L43/50H04L51/02H04L51/14H04M3/28H04M3/5175H04M3/5191H04M7/0045H04L41/5083H04L41/5093H04L67/02

Abstract

Claims (35)

1. A system for testing of automated customer response systems at contact centers, comprising:

a customer response testing system comprising a first plurality of programming instructions stored in a memory of, and operating a processor of, a computing device, wherein the first plurality of programming instructions, when operating on the processor, cause the computing device to:

retrieve a test case from a test case database;

retrieve a customer persona from a persona database;

generate a simulated customer query based on the test case;

create variations of the simulated customer query using a conversation multiplier, each variation reflecting a likely real-world variant of the simulated customer query;

modify each query variation based on the customer persona, each modification reflecting one or more traits of the customer persona;

connect to a customer response system at a contact center;

transmit each modified query variation of the simulated customer query to a customer response system at a contact center;

receive responses to each modified query variation sent from the customer response system at the contact center;

analyze each response received to determine whether the response is appropriate to the modified query variation sent; and

produce a result of the analysis.

2. The system of claim 1 , further comprising a real time conversation engine comprising a second plurality of programming instructions stored in the memory of, and operating on the processor of, the computing device, wherein the second plurality of programming instructions, when operating on the processor, cause the computing device to:

receive one or more of the modified query variations;

analyze the one or more of the modified query variations to determine a context, dialect, or level of formality;

receive a response corresponding to each of the one or more of the modified query variations;

analyze each to determine a context, dialect, or level of formality; and

compare the analysis of each of the one or more of the modified query variations with the corresponding response for that modified query variation to determine an appropriateness of die response.

3. A method for testing of automated customer response systems at contact centers, comprising the steps of:

retrieving a test case from a test case database;

retrieving a customer persona from a persona database;

generating a simulated customer query based on the test case as modified by the customer persona;

creating variations of the simulated customer query using a conversation multiplier, each variation reflecting a likely real-world variant of the simulated customer query;

modifying each query variation based on the customer persona, each modification reflecting one or more traits of the customer persona;

connecting to a customer response system at a contact center;

transmitting each modified query variation of the simulated customer query to a customer response system at a contact center;

receiving responses to each modified query variation sent from the customer response system at the contact center;

analyzing each response received to determine whether the response is appropriate to the modified query variation sent; and

producing a result of the analysis.

4. The method of claim 3 , further comprising the steps of:

receiving one or more of the modified query variations;

analyzing the one or more of the modified query variations to determine a context, dialect, or level of formality;

receiving a response corresponding to each of the one or more of the modified query variations;

analyzing each to determine a context, dialect, or level of formality; and

comparing the analysis of each of the one or more of the modified query variations with the corresponding response for that modified query variation to determine an appropriateness of the response.

Assignments (1)

Continuity (20)