Method and system for predicting problematic dialog situations in a task classification system
First Claim
1. A method comprising:
- determining whether a task classification decision can be made based on a user'"'"'s input communication, wherein if the task classification decision cannot be made, the method comprises;
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, 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.
7 Assignments
0 Petitions
Accused Products
Abstract
The invention concerns a system and method of predicting problematic dialogs in a task classification system based on the user'"'"'s input communications. The method may include determining whether a task classification decision can be made based on a first automated dialog exchange with the user. As such, if the task classification decision cannot be made, the method may determine whether the probability of conducting a successful automated dialog with the user based on whether the first dialog exchange 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.
166 Citations
26 Claims
-
1. A method comprising:
-
determining whether a task classification decision can be made based on a user'"'"'s input communication, wherein if the task classification decision cannot be made, the method comprises; 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, 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)
-
-
13. A method comprising:
-
determining whether a task classification decision can be made based on a user'"'"'s first input communication, wherein if the task classification decision cannot be made, the method comprises; for the first input communication, 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 user'"'"'s 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.
-
-
14. An automated dialog problem prediction system comprising:
-
a task classification processor that determines whether a task classification decision can be made based on the user'"'"'s input communication; a dialog manager that outputs dialog to the user; a dialog predictor that, if the task classification processor determines that a task classification decision cannot be made, 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;
wherein if the first threshold is exceeded, the dialog predictor prompts the dialog manager to conduct further dialog with the user; anda 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 (15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25)
-
-
26. An automated dialog problem prediction system, comprising:
-
a task classification processor that determines whether a task classification decision can be made based on the user'"'"'s input communication; a dialog manager that outputs dialog to the user; a dialog predictor that, if the task classification processor determines that a task classification decision cannot be made, 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 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 user'"'"'s 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