Natural language understanding monitoring system for identifying a task

• US 7,933,773 B1
• Filed: 03/25/2009
• Issued: 04/26/2011
• Est. Priority Date: 11/15/2000
• Status: Expired due to Fees

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Gorin, Allen Louis, Geary, Irene Langkilde, Walker, Marilyn Ann, Wright, Jeremy H.
• Primary Examiner(s): Lerner, Martin
• Application Number:
  US12/383,685
• Time in Patent Office: 762 Days
• Field of Search: 704/9, 704/240, 704/257, 704/270, 704/275, 379/88.01, 379/88.04
• US Class Current: 704/240
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: H04M 3/4936 Speech interaction details speech recognition per se G10L15/00

Abstract

A natural language understanding monitoring system adapted to conduct an automated dialog with a user. If the system is unable to identify from the automated dialog, to at least a predetermined level of confidence, any one of a plurality of predetermined tasks as being a particular task that the user wants to have performed, the system makes a determination of the value of a probability that further automated dialog will enable the system to identify the particular task, and determines whether or not to conduct further automated dialog with the user, in an attempt to identify the particular task, based on the relative values of the determined probability and a predetermined threshold value. The probability value determination is based on inputs from the user during the automated dialog.

Claims

1. A natural language understanding monitoring system for identifying a particular task that a user wishes to have performed from among a predetermined set of tasks, the natural language understanding monitoring system including at least a speech recognizer, and the natural language understanding monitoring system being adapted to

a) conduct an automated dialog with the user, and

b) if the system is unable to identify from the automated dialog conducted in (a) any one of the predetermined tasks as being the particular task to at least a predetermined level of confidence,

i) make a determination of the value of a probability that further automated dialog will enable the system to identify the particular task, and

ii) determine whether or not to conduct further automated dialog with the user, in an attempt to identify the particular task, based on the relative values of the probability determined in (i) and a predetermined threshold value

iii) said probability value determination being based on inputs from the user during the automated dialog conducted in (a),

wherein at least one of a) and b) are carried out by the system using a programmed processor.

2. The natural language understanding monitoring system of claim 1 wherein the automated dialog conducted in (a) comprises an initial automated dialog with the user and at least one further automated dialog with the user.

3. The natural language understanding monitoring system of claim 1 wherein said probability is a function of at least a particular machine output during said automated dialog conducted in (a) and an input communication from the user in response to that machine output.

4. The natural language understanding monitoring system of claim 3 wherein said probability is a further function of at least a particular machine output during said further automated dialog and an input communication from the user in response to that machine output.

5. The natural language understanding monitoring system of claim 1 wherein said probability is a function of each machine output during said automated dialog conducted in (a) and each input communication from the user in response to each machine output.

6. The natural language understanding monitoring system of claim 1 wherein said probability is a function of at least natural-language-understanding data derived from input communication from the user during said automated dialog conducted in (a).

7. The natural language understanding monitoring system of claim 1 wherein said further automated dialog is conducted using one of a) a current dialog strategy and b) an adapted dialog strategy selected as a function of the probability that said further automated dialog will enable the system to identify the particular task.

8. The natural language understanding monitoring system of claim 1 wherein said determining whether or not to conduct further automated dialog with the user is based on whether the value of the probability determined in (i) is greater than said predetermined threshold value.