Natural language interface using constrained intermediate dictionary of results

• US 7,177,798 B2
• Filed: 05/21/2001
• Issued: 02/13/2007
• Est. Priority Date: 04/07/2000
• Status: Expired due to Term

• Current Assignee: Rensselaer Polytechnic Institute
• Original Assignee: Rensselaer Polytechnic Institute
• Inventors: Boonjing, Veera, Hsu, Cheng
• Primary Examiner(s): Chawan, Vijay B.
• Application Number:
  US09/861,860
• Publication Number:
  US 20020059069A1
• Time in Patent Office: 2,094 Days
• Field of Search: 704/270.1, 704/9, 704/7, 704/201, 704/10, 706/45, 706/11, 706/927, 706/55, 707 2- 9, 707/104.1, 715/762, 715/709
• US Class Current: 704/9
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 15/18 using natural language modelling

Abstract

A method for processing a natural language input provided by a user includes: providing a natural language query input to the user; performing, based on the input, a search of one or more language-based databases; providing, through a user interface, a result of the search to the user; identifying, for the one or more language-based databases, a finite number of database objects; and determining a plurality of combinations of the finite number of database objects. The one or more language-based databases include at least one metadata database including at least one of a group of information types including case information, keywords, information models, and database values.

Claims

1. A method for processing a natural language input provided by a user, the method comprising:

providing a natural language query input by the user;

performing, based on the input, without augmentation, a search of one or more language-based databases including at least one metadata database comprising at least one of a group of information types comprising;

case information;

keywords;

information models; and

database values;

providing, through a user interface, a result of the search to the user;

identifying, for the one or more language-based databases, a finite number of database objects; and

determining a plurality of combinations of the finite number of database objects.

2. The method according to claim 1, further comprising a step of mapping the natural language query to the plurality of combinations.

3. The method according to claim 2, wherein the step of mapping comprises steps of:

identifying keywords in the natural language query; and

relating the keywords to the plurality of combinations.

4. The method according to claim 2, further comprising a step of determining a reference dictionary comprising:

case information;

keywords;

information models; and

database values.

5. The method according to claim 2, wherein the step of mapping further comprises resolving ambiguity between the keywords and the plurality of combinations.

6. The method according to claim 5, wherein the step of resolving includes determining an optimal interpretation of the natural language query using at least one of a group comprising rules and heuristics.

7. The method of claim 1 wherein providing a natural language query input by the user includes providing a natural language query input by the user without constraining said query grammatically or structurally.

8. The method of claim 7 wherein the natural language query comprises a sentence, multiple sentences, a non-sentence word group or a combination thereof.

9. A computer-implemented method for processing a natural language input comprising:

receiving a natural language input;

providing from said natural language input a plurality of language-based database objects;

identifying a finite number of permutations of the plurality of database objects, the database objects being stored in a metadata database comprising at least one of a group of information comprising

case information,

keywords,

information models, and

database values; and

interpreting at least one of the permutations to provide determination of a result of the natural language input.

10. The method according to claim 9, wherein the step of providing a plurality of database objects includes providing at least one of the group comprising data types, data instances, and database computational operators.

11. The method according to claim 10, wherein the step of interpreting includes mapping the at least one of the permutations to a database query.

12. The method according to claim 11, wherein the database query is formulated in a structured query language (SQL) query.

13. The method according to claim 9, wherein one or more permutations are eliminated.

14. The method according to claim 9, further comprising:

providing a reference dictionary comprising cases, keywords, information models, graphics, and database values;

identifying, in the natural language input, a plurality of elements that belong to the reference dictionary;

determining complete paths that are implied by the plurality of elements that span elements of the natural language input and which belong to the graphics of the reference dictionary.

15. The method according to claim 14, including determining a path that includes elements of at least the informational models and database values.

16. The method according to claim 14, further comprising:

providing rules and heuristics for searching; and

determining an optimum permutation based on the rules and heuristics.

17. The method according to claim 14, further comprising adding, as a result of user input, new cases and keywords to the reference dictionary.

18. The method according to claim 9, further comprising performing a search of a group of possible interpretations to determine an optimal interpretation of the natural language input.

19. The method according to claim 9, further comprising accepting the natural language input, wherein the action of accepting the natural language input accepts a free-format input.

20. The method according to claim 9, wherein of interpretation of natural language input is based on other than the results of analyzing syntax of the natural language query input.

21. The method according to claim 9, further comprising representing graphically elements of the metadata database.