Method and system for voice ordering utilizing product information

• US 8,321,277 B2
• Filed: 06/30/2008
• Issued: 11/27/2012
• Est. Priority Date: 06/18/2008
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Coulomb, Beatrice, Gibault, Dimitris, Occello, Audrey, Palaysi, Christophe
• Primary Examiner(s): Chawan, Vijay B
• Application Number:
  US12/164,633
• Publication Number:
  US 20090319272A1
• Time in Patent Office: 1,611 Days
• Field of Search: 704/270, 704/270.1, 704/275, 704/251, 704/231, 704/239, 704/254, 704/234, 704/257, 704/233, 379/88.03, 379/88.01, 379/88.04, 379/88.17, 707/999.01, 707/999.003, 707/999.006, 707/790, 705/14.64, 705/39, 705/14.44, 705/14.55, 705/14.23, 705/14.25, 705/14.36, 705/14.51
• US Class Current: 705/14.44
• CPC Class Codes: G06Q 30/0603 Catalogue ordering
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems

Abstract

A method for voice ordering utilizing catalog taxonomies and hierarchical categorization relationships in product information management (PIM) systems includes: prompting a user with a query to input speech into a speech recognition engine; translating the inputted speech into a series of words; querying a product information management component (PIM) based on the series of words; wherein the querying is performed as a matching algorithm against PIM category and attribute keywords; returning coded results to a voice synthesizer to produce at least one of: a voice response, and a text response to the user; and wherein in the coded results indicate one or more of: a not found message for zero matches, a confirmation of a suitable single match, a request for additional information in the event one or more of the following occurs: more than one matching item, category, and item attribute was found in the PIM.

Claims

1. A method for improved voice ordering from a product catalog using a product information management (PIM) component, the method comprising:

receiving, from a speech recognition component, one or more words corresponding to a voice input;

searching, by at least one processor, the PIM component to identify at least one matching item and/or category in the product catalog based, at least in part, on the one or more received words and at least one item attribute associated with at least one item and/or at least one category attribute associated with at least one category in the PIM component; and

outputting coded results to a voice synthesis component in response to the search, wherein the coded results indicate whether the search resulted in the identification of at least one matching item and/or category in the PIM component.

2. The method of claim 1, wherein the PIM component is configured to organize items, categories, and sub categories in a hierarchical structure of levels, wherein at least some levels of the hierarchical structure are associated with one or more attributes, and wherein searching the PIM component comprises searching the PIM component based, at least in part, on the one or more attributes associated with the levels of the hierarchical structure.

3. The method of claim 1, wherein the coded results indicate that no matching items and no matching categories were identified and wherein the method further comprises instructing the voice synthesis component to generate an error message including a request for additional voice input from the user.

4. The method of claim 1, wherein the coded results indicate a single matching item was identified and wherein the method further comprises instructing the voice synthesis component to generate a request for confirmation of the single matching item from the user.

5. The method of claim 4, further comprising:

receiving a response to the request for confirmation, wherein the response identifies the single matching item as correct; and

continuing an ordering process for the single matching item.

6. The method of claim 4, further comprising:

receiving a response to the request for confirmation, wherein the response identifies the single matching item as incorrect;

instructing the voice synthesis component to generate a request for additional sub category and/or item attributes; and

storing information related to the coded results including the identification of the single matching item.

7. The method of claim 1, wherein the coded results indicate multiple matching items were identified, wherein the method further comprises:

determining if there are one or more matching categories corresponding to the matching items;

instructing the voice synthesis component to generate a request for additional voice input from the user in response to determining there are no matching categories corresponding to the matching items;

instructing the voice synthesis component to generate a request for subcategory and/or item attributes in response to determining that there is a single matching category corresponding to the matching items; and

instructing the voice synthesis component to generate a request for confirmation of a suitable category in response to determining that there are multiple categories corresponding to the matching items.

8. A non-transitory computer readable medium encoded with a plurality of instructions that, when executed by a computer, perform a method comprising:

receiving, from a speech recognition component, one or more words corresponding to a voice input;

searching a product information management (PIM) component to identify at least one matching item and/or category in a product catalog based, at least in part, on the one or more received words and at least one item attribute associated with at least one item and/or at least one category attribute associated with at least one category in the PIM component; and

outputting coded results to a voice synthesis component in response to the search, wherein the coded results indicate whether the search resulted in the identification of at least one matching item and/or category in the PIM component.

9. The computer-readable medium of claim 8, wherein the PIM component is configured to organize items, categories, and sub categories in a hierarchical structure of levels, wherein at least some levels of the hierarchical structure are associated with one or more attributes, and wherein searching the PIM component comprises searching the PIM component based, at least in part, on the one or more attributes associated with the levels of the hierarchical structure.

10. The computer-readable medium of claim 8, wherein the coded results indicate that no matching items and no matching categories were identified and wherein the method further comprises instructing the voice synthesis component to generate an error message including a request for additional voice input from the user.

11. The computer-readable medium of claim 8, wherein the coded results indicate a single matching item was identified and wherein the method further comprises instructing the voice synthesis component to generate a request for confirmation of the single matching item from the user.

12. The computer-readable medium of claim 11, wherein the method further comprises:

receiving a response to the request for confirmation, wherein the response identifies the single matching item as correct; and

continuing an ordering process for the single matching item.

13. The computer readable medium of claim 11, wherein the method further comprises:

receiving a response to the request for confirmation, wherein the response identifies the single matching item as incorrect;

instructing the voice synthesis component to generate a request for additional sub category and/or item attributes; and

storing information related to the coded results including the identification of the single matching item.

14. The computer-readable medium of claim 8, wherein the coded results indicate multiple matching items were identified, wherein the method further comprises:

determining if there are one or more matching categories corresponding to the matching items;

instructing the voice synthesis component to generate a request for additional voice input from the user in response to determining there are no matching categories corresponding to the matching items;

instructing the voice synthesis component to generate a request for subcategory and/or item attributes in response to determining that there is a single matching category corresponding to the matching items; and

instructing the voice synthesis component to generate a request for confirmation of a suitable category in response to determining that there are multiple categories corresponding to the matching items.

15. An apparatus configured to search a product information management (PIM) component, the apparatus comprising:

a system processor programmed to;

receive, from a speech recognition component, one or more words corresponding to a voice input;

search the PIM component to identify at least one matching item and/or category in a product catalog based, at least in part, on the one or more received words and at least one item attribute associated with at least one item and/or at least one category attribute associated with at least one category in the PIM component; and

output coded results to a voice synthesis component in response to the search, wherein the coded results indicate whether the search resulted in the identification of at least one matching item and/or category in the PIM component.

16. The apparatus of claim 15, wherein the coded results indicate that no matching items and no matching categories were identified and wherein the system processor is further programmed to instruct the voice synthesis component to generate an error message including a request for additional voice input from the user.

17. The apparatus of claim 15, wherein the coded results indicate a single matching item was identified and wherein the system processor is further programmed to instruct the voice synthesis component to generate a request for confirmation of the single matching item from the user.

18. The apparatus of claim 17, wherein the system processor is further programmed to:

receive a response to the request for confirmation, wherein the response identifies the single matching item as correct; and

continue an ordering process for the single matching item.

19. The apparatus of claim 17, wherein the system processor is further programmed to:

receive a response to the request for confirmation, wherein the response identifies the single matching item as incorrect;

instruct the voice synthesis component to generate a request for additional sub category and/or item attributes; and

store information related to the coded results including the identification of the single matching item.

20. The apparatus of claim 17, wherein the coded results indicate multiple matching items were identified, wherein the system processor is further programmed to:

determine if there are one or more matching categories corresponding to the matching items;

instruct the voice synthesis component to generate a request for additional voice input from the user in response to determining there are no matching categories corresponding to the matching items;

instruct the voice synthesis component to generate a request for subcategory and/or item attributes in response to determining that there is a single matching category corresponding to the matching items; and

instruct the voice synthesis component to generate a request for confirmation of a suitable category in response to determining that there are multiple categories corresponding to the matching items.