Free text matching system and method

• US 8,589,165 B1
• Filed: 01/24/2012
• Issued: 11/19/2013
• Est. Priority Date: 09/20/2007
• Status: Active Grant

• Current Assignee: United Services Automobile Association
• Original Assignee: United Services Automobile Association
• Inventors: Meyer, Gregory Brian, Nicholson, James Elden
• Primary Examiner(s): Desir, Pierre-Louis
• Assistant Examiner(s): Sirjani, Fariba
• Application Number:
  US13/357,542
• Time in Patent Office: 665 Days
• Field of Search: 704/260
• US Class Current: 704/260
• CPC Class Codes: G06F 16/3343 using phonetics
• CPC Class Codes: G06F 40/20 Natural language analysis semantic analysis of natural language G06F40/30

Abstract

The present disclosure provides method and system for converting a free text expression of an identity to a phonetic equivalent code. The conversion follows a set of rules based on phonetic groupings and compresses the expression to a shorter series of characters than the expression. The phonetic equivalent code may be compared to one or more other phonetic equivalent code to establish a correlation between the codes. The phonetic equivalent code of the free text expression may be associated with the code of a known identity. The known identity may be provided to a user for confirmation of the identity. Further, a plurality of expressions stored in a database may be consolidated by converting the expressions to phonetic equivalent codes, comparing the codes to find correlations, and if appropriate reducing the number of expressions or mapping the expressions to a fewer number of expressions.

Claims

1. A method, comprising:

allowing an input of an expression associated with a desired identity;

electronically converting the expression to a phonetic equivalent code;

comparing the phonetic equivalent code to a plurality of phonetic equivalent codes of a known identity to determine correlations;

correlating the expression with the known identity based on the phonetic equivalent code associated with at least one of a plurality of expressions of the known identity having a threshold correlation to the phonetic equivalent code associated with the expression of the desired identity;

electronically providing the known identity;

allowing an input of a verification that the electronically provided known identity matches the desired identity; and

eliminating from a database another of the plurality of expressions of the known identity having a threshold correlation to the phonetic equivalent code associated with the expression of the desired identity.

2. The method of claim 1, wherein the method includes comparing the code to the plurality of codes with multiple passes of incrementally changing correlation criteria.

3. The method of claim 2, wherein the method includes comparing the code to the plurality of codes until a threshold correlation is at least reached in the comparison between the codes.

4. The method of claim 1, wherein the method includes:

obtaining a plurality of known identities; and

converting the known identities to a plurality of phonetic equivalent codes.

5. The method of claim 1, wherein the method includes allowing a user to enter the expression in a free text data field.

6. The method of claim 1, wherein the method includes allowing a user to enter the expression via a voice system.

7. The method of claim 4, wherein converting the known identities to the plurality of phonetic equivalent codes includes using frequency-weighted, lossy equivalent letter characterizations.

8. A non-transitory computer-readable medium having instructions stored thereon, the instructions executable by a processor to:

electronically convert an expression of an identity to a phonetic equivalent code;

compare the phonetic equivalent code to a plurality of phonetic equivalent codes associated with a plurality of known identities to determine correlations between the phonetic equivalent code and the plurality of phonetic equivalent codes;

correlate the expression with a selected identity based on the phonetic equivalent code for the expression having a threshold correlation to a phonetic equivalent code associated with an expression of the selected identity; and

eliminate from a database another expression of the selected identity having a threshold correlation to the phonetic equivalent code associated with the expression.

9. The non-transitory computer-readable medium of claim 8, wherein the instructions include instructions executable to reduce a quantity of the expressions of the identity based on the threshold correlation.

10. The non-transitory computer-readable medium of claim 8, wherein the instructions include instructions executable to compare the phonetic equivalent codes with multiple passes of incrementally changing criteria.

11. The non-transitory computer-readable medium of claim 8, wherein the instructions include instructions executable to use lossy equivalent letter characterizations.

12. The non-transitory computer-readable medium of claim 8, wherein the instructions include instructions executable to use frequency-weighted, lossy equivalent letter characterizations.

13. The non-transitory computer-readable medium of claim 8, wherein the instructions include instructions executable to search for phonetic equivalent codes in the order of the characterizations to priority search for most frequently used letters by characterizations.

14. The non-transitory computer-readable medium of claim 8, wherein the instructions include instructions executable to associate a portion of the expression with a predetermined equivalent.

15. A system, comprising:

a processor; and

a memory configured to store instructions executable by the processor to;

establish a plurality of letter characterizations for an alphabet having a plurality of letters;

assign a character to represent each of the letter characterizations;

assign a plurality of the alphabet letters to the letter characterizations, each letter characterization having at least one letter;

electronically convert an expression of an identity input by a user to a phonetic equivalent code using the characters of the letter characterizations;

provide the phonetic equivalent code to the user;

correlate the expression with a selected identity based on the phonetic equivalent code for the expression having a threshold correlation to at least one of a plurality of phonetic equivalent codes associated with at least one of a plurality of expressions of the selected identity; and

eliminating from a database another of the plurality of expressions of the selected identity having a threshold correlation to the phonetic equivalent code associated with the expression.

16. The system of claim 15, wherein the instructions include instructions executable to establish an order of the letter characterizations using frequency of usage of a letter selected from each characterization.

17. The system of claim 16, wherein the instructions include instructions executable to prioritize the letter characterizations in order by selecting a most frequently used letter in each characterization and comparing a frequency of usage of the most frequently used letter in each characterization.

18. The system of claim 15, wherein the instructions include instructions executable to use lossy equivalent letter characterizations.

19. The system of claim 15, wherein the instructions include instructions executable to use frequency-weighted, lossy equivalent letter characterizations.

20. The system of claim 15, wherein the instructions include instructions executable to:

establish a set of categories of lossy equivalent letter characterizations;

assign a character to each of the letter characterizations; and

prioritize the letter characterizations in order by selecting a most frequently used letter in each characterization and comparing a frequency of usage of the most frequently used letter in each characterization to establish the order of characterizations.