System and method for automated customer service with contingent live interaction
View Patent ↗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.
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=r 1 , r 2 , . . . 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.