System and method for automated customer service with contingent live interaction

• US 9,549,065 B1
• Filed: 10/24/2012
• Issued: 01/17/2017
• Est. Priority Date: 05/22/2006
• Status: Active Grant

• Current Assignee: Concentrix CVG Customer Management Delaware LLC (Synnex Corporation)
• Original Assignee: Convergys Customer Management Delaware LLC (Concentrix CVG Customer Management Group, Inc.)
• Inventors: Naik, Jayant M., Coy, Cordell, Peterson, Dale Robert, DiFonzo, Joseph, Weagraff, Stephen D., Yuschik, Matthew, Nutter, Michael Louis, Birch, Robert, Cunningham, Scot, Kim, Woosung, Irwin, Scott
• Primary Examiner(s): King, Simon
• Application Number:
  US13/659,366
• Time in Patent Office: 1,546 Days
• Field of Search: 379/265.02, 379/265.03, 704/251
• US Class Current: 1/1
• CPC Class Codes: H04M 2203/355 Interactive dialogue design tools, features or methods
• CPC Class Codes: H04M 3/22 Arrangements for supervision, monitoring or testing
• CPC Class Codes: H04M 3/493 Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals

Abstract

A balance between customer satisfaction and cost to providing customer care can be achieved based on the use of online interaction classification techniques. Such techniques can use measurements such as a log likelihood ratio to determine if an interaction should be removed from automation to live support if it appears necessary.

Claims

1. A computerized system for determining when to transfer a user from an automated service to a live agent comprising:

a) a self-service solution (SSS); and

b) a monitoring module;

wherein

i) said user interacts with said SSS;

ii) said monitoring module evaluates, after each turn in said SSS, a probability that said user'"'"'s interaction with the SSS is good and probability that said user'"'"'s interaction with the SSS is bad;

iii) said monitoring module signals an alarm to bring in a human agent if a log of the ratio of said good probability over said bad probability is below predetermined threshold.

2. The computerized system as claimed in claim 1 wherein:

a) said monitoring module evaluates the probability that the user'"'"'s interaction with the SSS is good using P(x|LM_good);

b) the monitoring module evaluates the probability that the user'"'"'s interaction with the SSS is bad using P(x|LM_bad);

c) x=r₁, r₂, . . . r_n;

d) each r is a response made by the user in the user'"'"'s interaction with SSS;

e) LM_good is a first classification model trained using records of one or more previous interactions classified as good; and

f) LM_bad is a second classification model trained using records of one or more previous interactions classified as bad.

3. The computerized system as claimed in claim 1 wherein said monitoring module evaluates said probabilities based on a boostexter classifier in an iterative algorithm.

4. The computerized system as claimed in claim 1 wherein said threshold may be dynamically reset based on a lifetime value of a relationship with said user.