Automated dialog system and method

• US 7,529,667 B1
• Filed: 09/06/2005
• Issued: 05/05/2009
• Est. Priority Date: 11/15/2000
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Walker, Marilyn Ann, Gorin, Allen Louis, Wright, Jeremy H., Geary, Irene Langkilde
• Primary Examiner(s): Lerner, Martin
• Application Number:
  US11/219,628
• Time in Patent Office: 1,337 Days
• Field of Search: 704/9, 704/240, 704/257, 704/270, 704/275, 379/88.01
• 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

This invention concerns a method and system for monitoring an automated dialog system for the automatic recognition of language understanding errors based on a user'"'"'s input communications. The method illustratively determines whether a probability of understanding the user'"'"'s input communication exceeds a first threshold. If the first threshold is exceeded, further dialog is conducted with the user. Otherwise, the user may be directed to a human for assistance. The method also illustratively determines whether the probability also exceeds a second threshold, the second threshold being higher than the first. If so, then further dialog is conducted with the user using the current dialog strategy. However, if the probability falls between a first threshold and a second threshold, the dialog strategy may be adapted in order to improve the chances of conducting a successful dialog with the user. Conducting further automated dialog with the user in an attempt to identify a particular task that the user wants the system to perform is carried out only upon a determination that there is at least a predetermined probability that further automated dialog will enable the system to identify the particular task.

Claims

1. A method implemented by a system for identifying a particular task that a user wishes to have performed from among a predetermined set of tasks, the method comprising

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

ii) determining 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).

2. The method 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 method 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 method 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 method 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 method 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 method 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 method 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.