SYSTEM AND METHOD FOR THE QUALITY ASSESSMENT OF QUERIES

• US 20090248647A1
• Filed: 03/25/2008
• Published: 10/01/2009
• Est. Priority Date: 03/25/2008
• Status: Abandoned Application

• Current Assignee: Verint Systems Limited (Verint Systems Incorporated)
• Original Assignee: Verint Systems Limited (Verint Systems Incorporated)
• Inventors: Brand, Michael, Ziv, Omer, Baum, Daniel Mark, Shapira, Ido, Stauber, Yitzhak, Gvili, Yaron
• Application Number:
  US12/055,102
• Publication Number:
  US 20090248647A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/685 using automatically derived transcript of audio data, e.g. lyrics speech recognition G10L15/00

Abstract

A computer system coupled to a database is configured to receive a database query, and evaluate a set of records from a database based on the database query. The database comprises a plurality of records, and each record comprises text translated from audio. The system then determines a plurality of measurement terms based on the database query, and processes at least a portion of the text of at least one record of the database to determine a quality of the database query based on the occurrences of the measurement terms within the portion of text, and performs an action based on the quality of the database query.

Claims

1. A method for analyzing a database query comprising:

receiving a database query;

evaluating a set of records from a database based on the database query, the database comprising a plurality of records, each record comprising text translated from audio;

determining a plurality of measurement terms based on the database query;

processing at least a portion of the text of at least one record of the database to determine a quality of the database query based on the occurrences of the measurement terms within the portion of text; and

performing an action based on the quality of the database query.

2. The method for analyzing a database query of claim 1, wherein the measurement terms comprise terms from the database query.

3. The method for analyzing a database query of claim 1, wherein the measurement terms comprise synonyms, homophones, and alternate inflections of terms from the database query.

4. The method analyzing a database query of claim 1, wherein processing at least a portion of the text of at least one record of the database further comprises:

processing at least a portion of the text of at least one record of the database to determine the quality of the database query based on the location and frequency of the measurement terms alone and with respect to each other occurring within the text.

5. The method for analyzing a database query of claim 1, wherein at least one record includes a confidence score corresponding to the confidence of the translation of the portion of the text from audio to text.

6. The method for analyzing a database query of claim 5, wherein processing at least a portion of the text of at least one record of the database further comprises:

processing at least a portion of the text of at least one record of the database to determine the quality of the database query based on the confidence score of the at least a portion of text.

7. The method for analyzing a database query of claim 1, further comprising:

processing the set of records with the database query to determine a stability of the database query; and

modifying the quality of the database query based on the stability of the database query.

8. The method for analyzing a database query of claim 1, wherein at least one record also includes metadata.

9. The method for analyzing a database query of claim 1, further comprising:

processing at least a portion of the metadata of at least one record of the database to determine a quality of the database query.

10. The method for analyzing a database query of claim 1, wherein the action includes modifying the database query.

11. The method for analyzing a database query of claim 1, wherein the action includes suggesting modification of the database query to a user.

12. The method for analyzing a database query of claim 1, wherein evaluating a set of records from the database includes determining a score for each record based on the occurrences of the measurement terms within each record.

13. The method for analyzing a database query of claim 1, wherein the text comprises phonetic symbols.

14. A method for analyzing a database query comprising:

receiving a first database query;

evaluating a first set of records from a database based on the first database query, the database comprising a plurality of records, each record comprising text translated from audio;

receiving a second database query;

determining a plurality of second measurement terms based on the second database query;

processing at least a portion of the text of at least one record of the first set of records to determine a coupling of the first database query and the second database query based on the occurrences of the second measurement terms within the portion of the text of at least one record of the first set of records; and

performing an action based on the coupling of the first database query and the second database query.

15. The method for analyzing a database query of claim 14, further comprising:

determining a plurality of first measurement terms based on the first database query;

evaluating a second set of records from the database based on the second database query; and

processing at least a portion of the text of at least one record of the second set of records to further determine the coupling of the first database query and the second database query based on the occurrences of the first measurement terms within the portion of the text of at least one record of the second set of records.

16. The method for analyzing a database query of claim 15, further comprising:

processing at least a portion of the text of at least one record of the database to determine a quality of the first database query based on the occurrences of the first measurement terms within the portion of text; and

processing at least a portion of the text of at least one record of the database to determine a quality of the second database query based on the occurrences of the second measurement terms within the portion of text; and

performing an action based on the quality of the first database query and the quality of the second database query.

17. A computer-readable medium having instructions stored thereon for operating a computer system, wherein the instructions, when executed by the computer system, direct the computer system to:

receive a database query;

evaluate a set of records from a database based on the database query, the database comprising a plurality of records, each record comprising text translated from audio;

determine a plurality of measurement terms based on the query;

process at least a portion of the text of at least one record of the database to determine a quality of the database query based on the occurrences of the measurement terms within the portion of text; and

perform an action based on the quality of the database query.

18. The computer-readable medium of claim 17, wherein the instructions, when executed by the computer system, further direct the computer system to:

process at least a portion of the text of at least one record of the database to determine the quality of the database query based on the location and frequency of the measurement terms alone and with respect to each other occurring within the text.

19. The computer-readable medium of claim 17, wherein at least a portion of the text within a record includes a confidence score corresponding to the confidence of the translation of the portion of the text from audio to text.

20. The computer-readable medium of claim 19, wherein the instructions, when executed by the computer system, further direct the computer system to:

process at least a portion of the text of at least one record of the database to determine the quality of the database query based on the confidence score of the at least a portion of text.

21. The computer-readable medium of claim 17, wherein the instructions, when executed by the computer system, further direct the computer system to:

process the set of records with the query to determine a stability of the database query; and

modify the quality of the database query based on the stability of the database query.

22. A computer system comprising:

a storage system containing software; and

a processing system coupled to the storage system;

wherein the processing system is instructed by the software to;

receive a database query;

evaluate a set of records from a database based on the database query, the database comprising a plurality of records, each record comprising text translated from audio;

determine a plurality of measurement terms based on the database query;

process at least a portion of the text of at least one record of the database to determine a quality of the database query based on the occurrences of the measurement terms within the portion of text; and

perform an action based on the quality of the database query.

23. The computer system of claim 22, wherein the processing system is further instructed by the software to:

process at least a portion of the text of at least one record of the database to determine the quality of the database query based on the location and frequency of the measurement terms alone and with respect to each other occurring within the text.

24. The computer system of claim 22, wherein at least a portion of the text within a record includes a confidence score corresponding to the confidence of the translation of the portion of the text from audio to text.

25. The computer system of claim 24, wherein the processing system is further instructed by the software to:

process at least a portion of the text of at least one record of the database to determine the quality of the database query based on the confidence score of the at least a portion of text.