Method and apparatus for a frequently-asked questions portal workflow

• US 9,064,001 B2
• Filed: 03/15/2013
• Issued: 06/23/2015
• Est. Priority Date: 03/15/2013
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Liu, Ding, Tremblay, Real, Tremblay, Jerome, Robillard, Serge
• Primary Examiner(s): Ly, Anh
• Application Number:
  US13/832,896
• Publication Number:
  US 20140280169A1
• Time in Patent Office: 830 Days
• Field of Search: 707/739, 707/749, 707/736, 707/740, 707/E17.046, 707/723, 707/769, 707/722, 707/E17.069, 707/E17.089, 704/275, 704/257, 704/254, 704/239, 704/9, 704/8, 704/E15.018, 704/236, 704/270.1, 704/270, 717/173, 717/171, 717/106, 455/414.1, 706/12, 706/11, 706/55, 715/764, 709/226, 379/265.02, 379/88.05, 379/67.1, 379/88.6
• US Class Current: 1/1
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06Q 30/0641 Shopping interfaces
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning

Abstract

In FAQ based systems, associating questions with answers can be a time consuming task if performed manually. In one embodiment, a method of building a frequently-asked questions (FAQ) portal can include creating cluster labels. The labels can include predefined universal semantic labels and application-specific labels. The method can further include applying the cluster labels to clusters of queries within an FAQ application. The method can additionally include adjusting the application-specific labels to support combined and newly created clusters of queries based on application-specific queries within the FAQ application on an ongoing basis and reapplying the universal semantic labels and the adjusted application-specific labels to the combined and newly created clusters of queries. The method and system proposed herein allow for the automated clustering of queries and association with applicable answers, which leads to higher efficiencies for a faster response time for a user.

Claims

1. A method of building a frequently-asked questions (FAQ) portal, the method comprising:

in a processor of an electronic device;

creating cluster labels, the cluster labels including predefined universal semantic labels and application-specific labels;

applying the cluster labels to clusters of queries within an FAQ application; and

adjusting the application-specific labels to support combined and newly created clusters of queries based on application-specific queries within the FAQ application on an ongoing basis and reapplying the universal semantic labels and the adjusted application-specific labels to the combined and newly created clusters of queries to enable automated clustering of queries and association with applicable answers to improve response time by the electronic device for providing a user with an answer to a query.

2. The method of claim 1 further comprising creating seed clusters based on answers to the queries of the clusters.

3. The method of claim 1, further comprising creating clusters by extracting features of answers independent of the queries.

4. The method of claim 1, further comprising creating one-to-many mappings from the universal semantic labels to the application-specific labels, the one-to-many mappings applying to clusters of queries for which the FAQ application is configured to issue at least one of multiple answers.

5. The method of claim 4, further comprising applying a user-history of the FAQ application to define a one-to-many mapping from the universal semantic label to a most-likely application-specific label.

6. The method of claim 1, wherein creating the cluster labels further includes using content of the query itself as the application-specific label.

7. The method of claim 1, further comprising creating clusters by extracting features of answers dependent on the queries.

8. A system for building a frequently-asked questions (FAQ) portal, the system comprising:

an electronic device including at least one processor, the at least one processor configured to implement;

a labeling module configured to create cluster labels, the cluster labels including predefined universal semantic labels and application-specific labels;

a label application module configured to apply the cluster labels to clusters of queries within an FAQ application; and

an adjustment module configured to adjust the application-specific labels to support combined and newly created clusters of queries based on application-specific queries within the FAQ application on an ongoing basis and reapplying the universal semantic labels and the adjusted application-specific labels to the combined and newly created clusters of queries to enable automated clustering of queries and association with applicable answers to improve response time by the electronic device for providing a user with an answer to a query.

9. The system of claim 8, further comprising a cluster creation module configured to create seed clusters based on answers to the queries of the clusters.

10. The system of claim 8, further comprising a cluster creation module configured to create clusters by extracting features of answers independent of the queries.

11. The system of claim 8, further comprising a mapping module configured to create one-to-many mappings from the universal semantic labels to the application-specific labels, the one-to-many mappings applying to clusters of queries for which the FAQ application is configured to issue at least one of multiple answers.

12. The system of claim 11, further comprising applying a user-history of the FAQ application to define a one-to-many mapping from the universal semantic label to a most-likely application-specific label.

13. The system of claim 8, wherein the labeling module is further configured to use content of the query itself as the application-specific label.

14. The system of claim 8, further comprising creating clusters by extracting features of answers dependent on the queries.

15. A non-transitory computer-readable medium configured to store instructions for building a frequently-asked questions (FAQ)-portal, the instructions, when loaded and executed by a processor, causes the processor to:

create cluster labels, the cluster labels including predefined universal semantic labels and application-specific labels;

apply the cluster labels to clusters of queries within an FAQ application; and

adjust the application-specific labels to support combined and newly created clusters of queries based on application-specific queries within the FAQ application on an ongoing basis and reapplying the universal semantic labels and the adjusted application-specific labels to the combined and newly created clusters of queries.

16. The non-transitory computer readable medium of claim 15, wherein the instructions further cause the processor to create seed clusters based on answers to the queries of the clusters.

17. The non-transitory computer readable medium of claim 15, wherein the instructions further cause the processor to create clusters by extracting features of answers independent of the queries.

18. The non-transitory computer readable medium of claim 15, wherein the instructions further cause the processor to create one-to-many mappings from the universal semantic labels to the application-specific labels, the one-to-many mappings applying to clusters of queries for which the FAQ application is configured to issue at least one of multiple answers.

19. The non-transitory computer readable medium of claim 18, wherein the instructions further cause the processor to apply a user-history of the FAQ application to define a one-to-many mapping from the universal semantic label to a most-likely application-specific label.

20. The non-transitory computer readable medium of claim 15, wherein creating the cluster labels further includes using content of the query itself as the application-specific label.