Method and system for predicting problematic situations in a automated dialog
First Claim
Patent Images
1. A method comprising:
- determining whether a probability of conducting a successful dialog with a user exceeds a first threshold, a successful dialog being a dialog exchange between an automated dialog system and the user that results in processing of an input communication of the user to a stage consistent with the user'"'"'s intent, wherein if the first threshold is exceeded, further dialog is conducted with the user, andwherein the probability is determined using dialog training data stored in a dialog training database, the dialog training data including at least one of dialog classification models and extracted dialog features.
4 Assignments
0 Petitions
Accused Products
Abstract
The invention concerns a system and method of predicting problematic dialogs in an automated dialog system based on the user'"'"'s input communications. The method may include determining whether a probability of conducting a successful dialog with the user exceeds a first threshold. The successful dialog may be defined as a dialog exchange between an automated dialog system and the user that results in at least one of processing of the user'"'"'s input communication and routing the user'"'"'s input communication. The method may further operate such that if the first threshold is exceeded, further dialog is conducted with the user. Otherwise, the user may be directed to a human for assistance.
69 Citations
23 Claims
-
1. A method comprising:
-
determining whether a probability of conducting a successful dialog with a user exceeds a first threshold, a successful dialog being a dialog exchange between an automated dialog system and the user that results in processing of an input communication of the user to a stage consistent with the user'"'"'s intent, wherein if the first threshold is exceeded, further dialog is conducted with the user, and wherein the probability is determined using dialog training data stored in a dialog training database, the dialog training data including at least one of dialog classification models and extracted dialog features. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11)
-
-
12. A method comprising:
-
for a first input communication of a user, determining whether a probability of conducting a successful dialog with the user exceeds a first threshold, a successful dialog being a dialog exchange between an automated dialog system and the user that results in processing of an input communication of the user to a stage consistent with the user'"'"'s intent; if the first threshold is exceeded, storing a first dialog exchange in a dialog history database, wherein the first dialog exchange includes a first automated dialog output and the first input communication of the user and the further dialog conducted with the user results in a second dialog exchange, wherein the second dialog exchange includes a second dialog output and a second input communication of the user; and determining whether the probability of conducting a successful dialog with the user exceeds the first threshold using the first dialog exchange and the second dialog exchange.
-
-
13. An automated dialog problem prediction system, comprising:
-
a dialog manager that outputs dialog to a user; a dialog predictor that determines whether a probability of conducting a successful dialog being with the user exceeds a first threshold, a successful dialog being a dialog exchange between an automated dialog system and the user that results in processing of an input communication of the user to a stage consistent with the user'"'"'s intent, wherein if the first threshold is exceeded, the dialog predictor prompts the dialog manager to conduct further dialog with the user; and a dialog training database for storing dialog training data, wherein the dialog predictor determines the probability using the dialog training data stored in a dialog training database, the dialog training data including at least one of dialog classification models and extracted dialog features. - View Dependent Claims (14, 15, 16, 17, 18, 19, 20, 21, 22)
-
-
23. An automated dialog problem prediction system, comprising:
-
a dialog manager that outputs dialog to a user; a dialog predictor that determines whether a probability of conducting a successful dialog with the user exceeds a first threshold, a successful dialog being a dialog exchange between an automated dialog system and the user that results in processing of an input communication of the user to a stage consistent with the user'"'"'s intent, wherein if the first threshold is exceeded, the dialog predictor prompts the dialog manager to conduct further dialog with the user; and a dialog history database that stores a first dialog exchange, wherein the first dialog exchange includes a first automated dialog output and a first input communication of the user, and the further dialog conducted with the user results in a second dialog exchange, the second dialog exchange including a second dialog output and a second input communication of the user, and the dialog predictor determining whether the probability of conducting a successful dialog with the user exceeds the first threshold using the first dialog exchange and the second dialog exchange.
-
Specification