Disambiguating results within a speech based IVR session

• US 7,260,537 B2
• Filed: 03/25/2003
• Issued: 08/21/2007
• Est. Priority Date: 03/25/2003
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Creamer, Thomas E., Moore, Victor S., Davis, Brent L., Jaiswal, Peeyush
• Primary Examiner(s): {hacek over (S)}mits; Talivaldis Ivars
• Assistant Examiner(s): Rider; Justin W
• Application Number:
  US10/396,081
• Publication Number:
  US 20040193403A1
• Time in Patent Office: 1,610 Days
• Field of Search: 704/270.1, 379/93.12
• US Class Current: 704/270.1
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning

Abstract

Within an interactive voice response system, a method of automatically disambiguating results presented to a user can include determining the identity of a user within an interactive voice response session, receiving user inputs specifying selections in an interactive voice response menu hierarchy, and storing historical information specifying the user selections within a profile associated with the identity of the user. For at least one subsequent input from the user, identifying the historical information associated with the identity of the user and using the historical information to reduce a number of possible selections in the interactive voice response menu hierarchy which are presented to the user.

Claims

1. Within an interactive voice response system, a method of automatically disambiguating results presented to a user comprising:

determining the identity of a user within an interactive voice response session;

receiving user inputs in response to presenting menu options during the interactive voice response session, wherein said presented menu options specify at least one of a plurality of hierarchical nodes of the voice response menu hierarchy, wherein each of said nodes corresponds to points within the interactive voice response menu hierarchy at which the user can choose to traverse one or more child nodes, wherein said user inputs specify at least one among a user selection of one of said presented menu options and a user query of said nodes of said voice response menu hierarchy;

storing historical information specifying the received user inputs within a profile associated with the identity of the user, wherein the user profile specifies at least one among a path that was traversed during the interactive voice response session and at least a portion of a user query recognized during the interactive voice response session, wherein the path being specified by at least one branch indicator links a parent node and a child node;

for at least one subsequent input from the user, identifying the historical information associated with the identity of the user; and

using the historical information to reduce a number of possible nodes from the interactive voice response menu hierarchy which are presented to the user, wherein the number of possible selections is reduced in response to at least one among a current path matching a path specified in the user profile and a current query matching a recognized query specified in the user profile.

2. The method of claim 1, wherein said step of using the historical information comprises reducing the number of possible path selections.

3. The method of claim 2, wherein said subsequent user input is received during a second interactive voice response session, said step of using the historical information further comprising:

comparing a path being traversed during the second interactive voice response session with at least one path specified by the historical information;

determining at least one path specified by the historical information which corresponds with the path being traversed during the second interactive voice response session; and

presenting the corresponding at least one path to the user as a possible interactive voice response menu selection.

4. The method of claim 1, wherein at least one of the user inputs specifies a query, said method further comprising:

determining a plurality of results responsive to the query; and

receiving a disamnbiguating user input specifying a particular result from the plurality of results;

wherein the historical information specifies user selected query results, the subsequent input specifies a query yielding a plurality of results for which historical information has been stored, and the potential selections which are reduced during said step of using historical information are the results of the subsequent query.

5. The method of claim 4, wherein said subsequent input is received during a second interactive voice response session.

6. A computer-readable storage, having stored thereon a computer program having a plurality of code sections executable by a machine for causing the machine to perform the steps of:

determining the identity of a user within an interactive voice response session;

receiving user inputs in response to presenting menu options during the interactive voice response session, wherein said presented menu options specify at least one of a plurality of hierarchical nodes of the voice response menu hierarchy, wherein each of said nodes corresponds to points within the interactive voice response menu hierarchy at which the user can choose to traverse one or more child nodes, wherein said user inputs specify at least one among a user selection of one of said presented menu options and a user query of said nodes of said voice response menu hierarchy;

storing historical information specifying the received user inputs within a profile associated with the identity of the user, wherein the user profile specifies at least one among a path that was traversed during the interactive voice response session and at least a portion of a user query recognized during the interactive voice response session, wherein the path being specified by at least one branch indicator links a parent node and a child node;

for at least one subsequent input from the user, identifying the historical information associated with the identity of the user; and

using the historical information to reduce a number of possible nodes from the interactive voice response menu hierarchy which are presented to the user, wherein the number of possible selections is reduced in response to at least one among a current path matching a path specified in the user profile and a current query matching a recognized query specified in the user profile.

7. The computer-readable storage of claim 6, wherein said step of using the historical information comprises reducing the number of possible path selections.

8. The computer-readable storage of claim 7, wherein said subsequent user input is received during a second interactive voice response session, said step of using the historical information further comprising:

comparing a path being traversed during the second interactive voice response session with at least one path specified by the historical information;

determining at least one path specified by the historical information which corresponds with the path being traversed during the second interactive voice response session; and

presenting the corresponding at least one path to the user as a possible interactive voice response menu selection.

9. The computer-readable storage of claim 6, wherein at least one of the user inputs specifies a query, said method further comprising:

determining a plurality of results responsive to the query; and

receiving a disambiguating user input specifying a particular result from the plurality of results;

wherein the historical information specifies user selected query results, the subsequent input specifies a query yielding a plurality of results for which historical information has been stored, and the potential selections which are reduced during said step of using historical information are the results of the subsequent query.

10. The computer-readable of claim 9, wherein said subsequent input is received during a second interactive voice response session.

11. An interactive voice response system for automatically disambiguating results presented to a user, said interactive voice response system comprising:

means for determining the identity of a user within an interactive voice response session;

means for receiving user inputs in response to presenting menu options during the interactive voice response session, wherein said presented menu options specify at least one of a plurality of hierarchical nodes of the voice response menu hierarchy, wherein each of said nodes corresponds to points within the interactive voice response menu hierarchy at which the user can choose to traverse one or more child nodes, wherein said user inputs specify at least one among a user selection of one of said presented menu options and a user query of said nodes of said voice response menu hierarchy;

means for storing historical information specifying the received user inputs within a profile associated with the identity of the user, wherein the user profile specifies at least one among a path that was traversed during the interactive voice response session and at least a portion of a user query recognized during the interactive voice response session, wherein the path being specified by at least one branch indicator links a parent node and a child node;

means for identifying the historical information associated with the identity of the user for at least one subsequent input from the user; and

using the historical information to reduce a number of possible nodes from in the interactive voice response menu hierarchy which are presented to the user, wherein the number of possible selections is reduced in response to at least one among a current path matching a path specified in the user profile and a current query matching a recognized query specified in the user profile.