Method and system of generating reference variations for directory assistance data

• US 8,611,505 B2
• Filed: 11/02/2009
• Issued: 12/17/2013
• Est. Priority Date: 07/24/2000
• Status: Expired due to Fees

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Oppenheim, Kyle, Mitby, David, Kibre, Nick
• Primary Examiner(s): Anwah, Olisa
• Application Number:
  US12/611,064
• Publication Number:
  US 20100049502A1
• Time in Patent Office: 1,506 Days
• Field of Search: 379/88.01, 379/88.02, 379/218.01, 704/8, 704/9, 704/270, 704/270.1, 704/275
• US Class Current: 379/88.01
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 3/4931 Directory assistance systems

Abstract

Methods and systems of performing user input recognition are disclosed. A digital directory comprising listings is accessed. Metadata information is associated with individual listings describing the individual listings. The metadata information is modified to generate transformed metadata information. Therefore, the transformed metadata information is generated as a function of context information relating to a typical user interaction with the listings. Information is generated for aiding in an automated user input recognition process based on the transformed metadata information.

Claims

1. A method of performing input recognition on a listing in a data source using a metadata tag for the listing, the method, comprising:

generating transformed metadata by modifying the metadata tag;

determining the semantic relevancy of the transformed metadata;

applying rules to the transformed metadata to generate modified metadata based on the semantic relevancy;

generating information using the modified metadata for aiding in an automated user input recognition process.

2. The method of claim 1, wherein, the determining the semantic relevancy comprises, resolving tag conflicts.

3. The method of claim 1, wherein, the determining the semantic relevancy comprises, suppressing over-generated tags.

4. The method of claim 1 wherein the automated user input recognition process is a text input recognition process.

5. The method of claim 1 wherein the generating information for aiding in an automated user input recognition process comprises:

based on the transformed metadata, generating a plurality of reference variances associated with the listings; and

based on the plurality of reference variances, generating a grammar as the information for aiding in an automated user input recognition process.

6. The method of claim 5 wherein the plurality of reference variances reflect typical variations in human references to the listings.

7. The method of. claim 5 further comprising supplying the grammar to the automated user input recognition process.

8. The method of claim 1 wherein the associating individual listings with metadata information describing the individual listings comprises tagging the individual listings.

9. The method of claim 1 wherein the metadata information describing the individual listings is selected from the group comprising:

a known entity;

an address;

a business name;

a main listing;

a department; and

a person'"'"'s name.

10. The method of claim 1 wherein the modifying the metadata information comprises identifying groups of listings as pertaining to recognized listing group types.

11. The method of claim 10 wherein the recognized listings group types comprise:

a retail group type;

a hospital group type;

an airline group type; and

a government group type.

12. A system for user input recognition comprising:

a metadata generator operable to generate metadata information describing individual listings of a digital directory and to associate the metadata information with the individual listings;

a metadata transformer to determine semantic relevancy of the metadata information and apply rules to the metadata information to generate modified metadata;

logic operable to generate information for aiding in a user input recognition process based on the modified metadata.

13. The system of claim 12, wherein the metadata generator comprises a plurality of tagger modules operable to determine meanings of individual listings of the digital directory and to generate respective tags associated therewith.

14. The system of claim 13, wherein the metadata generator is further operable to tag listings in the digital directory based on metadata context.

15. The system of claim 13, wherein the metadata generator is further operable to determine relevant tags for releasable directory listings in the digital directory based on metadata context.

16. The system of claim 15, further comprising a presentation name generator operable to generate presentation names for the releasable listings.

17. The system of claim 12, wherein the metadata transformer comprises a plurality of context handlers operable to determine meanings of individual listings of the digital directory based on identifying a group listing type within which an individual listing resides.

18. The system of claim 12, wherein the user input is speech and further comprising a grammar generator operable to generate speech recognition grammar based on the information for aiding in a user input recognition process.

19. The system of claim 12, wherein the logic is further operable to generate the information for aiding in a user recognition process based on the metadata information generated by the first metadata generator.

20. The system of claim 12, further comprising a directory search engine that is able to determine a telephone number from the digital directory based on a selected entry of the information for aiding in a user input recognition process.

21. The system of claim 12 wherein the user input is text based input.

22. A computer readable memory having stored thereon instructions that when executed on a processor implement a method of generating input parameters usable in a user input recognition process, the method comprising:

generating transformed metadata by modifying a metadata tag;

determining the semantic relevancy of the transformed metadata;

applying rules to the transformed metadata to generate modified metadata based on the semantic relevancy;

generating the input parameters using the modified metadata for aiding in an automated user input recognition process; and

outputting the result to a user as a playback confirmation.

23. The computer readable memory of claim 22, further comprising, performing contextual analysis by applying telephone operator frequency data.

24. The computer readable memory of claim 23, wherein the performing contextual analysis comprises modifying a first metadata based on a first listing of the telephone directory data based on relationship between a second metadata associated with a second listing.

25. The computer readable memory of claim 23, wherein the method further comprises:

recognizing a first synonym phrase of the plurality of synonym phrases in a user input directory request;

determining a telephone number from the telephone directory data based on the first synonym phrase; and

supplying the telephone number to the user.

26. The computer readable memory of claim 25, wherein the performing contextual analysis comprises determining relevant tags for releasable telephone listings in the telephone directory data based on contextual analysis of the metadata.

27. The computer readable memory of claim 26, wherein the method further comprises generating presentation names for the releasable telephone listings.

28. The computer readable memory of claim 27, wherein the generating the plurality of synonym phrases further comprises basing at least one of the synonym phrases on the relevant tags for the releasable listings.