Natural language expression in response to a query

• US 8,645,405 B2
• Filed: 01/05/2006
• Issued: 02/04/2014
• Est. Priority Date: 05/02/2000
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Chang, Jane Wen, Lau, Raymond, McCandless, Michael Kyle
• Primary Examiner(s): Pulliam, Christyann
• Assistant Examiner(s): Chojnacki, Mellissa M
• Application Number:
  US11/326,554
• Publication Number:
  US 20060123045A1
• Time in Patent Office: 2,952 Days
• Field of Search: 707/759, 707/765
• US Class Current: 707/759
• CPC Class Codes: G06F 16/24522 Translation of natural language queries to structured queries
• CPC Class Codes: G06F 16/24575 using context
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 40/56 Natural language generation
• CPC Class Codes: Y10S 707/917 Text
• CPC Class Codes: Y10S 707/959 Network
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching

Abstract

Methods and apparatus, including computer products, for generating a natural language expression in response to a query. A computer-implemented method of generating a natural language expression in response to a query, includes generating a text frame from the query, and processing the text frame in conjunction with a grammar and one or more logic configuration files applied recursively to the text frame to generate the natural language expression from the query, the logic configuration files including functions that can pass arguments.

Claims

1. A computer-implemented method of generating a natural language expression in response to a query, comprising:

generating, in a computer, a text frame from the query;

processing, in the computer, the text frame in conjunction with one or more prose configuration files that contain a set of rules, wherein the rules are applied to the text frame to convert normalized text generated from the query to prose; and

displaying, in the computer, a natural language expression to a user that combines the prose from the query with results from performing the query.

2. The computer-implemented method of claim 1 further comprising matching the query to content residing in a database to generate the results from performing the query.

3. The computer-implemented method of claim 2 in which the database resides in a server in a network.

4. The computer-implemented method of claim 2 in which the matched content is a search result summary.

5. The computer-implemented method of claim 1 wherein the text frame comprises a data structure, the data structure representing an expanded query, the expanded query representing different elements of the query and different criteria of the query.

6. The computer-implemented method of claim 5 wherein the data structure comprises rows, each of the rows having a key, the key identifying information in each of the rows.

7. The computer-implemented method of claim 6 wherein the data structure further comprises a plurality of data structures.

8. The computer-implemented method of claim 1 wherein the generating the text frame further comprises encapsulating the processed text frame in a markup language.

9. The computer-implemented method of claim 8 wherein the markup language is extensible markup language (XML).

10. The computer-implemented method of claim 8 wherein the markup language is hypertext markup language (HTML).

11. A computer-implemented method of processing a query comprising:

generating, in a computer, a text frame for the query;

loading, in the computer, one or more prose configuration files;

processing, in the computer, the text frame in conjunction with the one or more prose configuration files to generate prose from the query; and

displaying, in the computer, a natural language expression to a user that combines the prose from the query with results from performing the query.

12. The computer-implemented method of claim 11 further comprising matching the query to content residing in a database to generate the results from performing the query.

13. The computer-implemented method of claim 12 in which the database resides in a server in a network.

14. The computer-implemented method of claim 12 in which the matched content is a search result summary.

15. The computer-implemented method of claim 14 in which the text frame comprises a data structure, the data structure representing an expanded query, the expanded query representing different elements of the query and different criteria of the query.

16. The computer-implemented method of claim 15 in which the data structure comprises rows, each of the rows having a key, the key identifying information in each of the rows.

17. The computer-implemented method of claim 16 in which the data structure comprises a plurality of data structures.

18. The computer-implemented method of claim 11 in which generating the text frame further comprises encapsulating the processed text frame in a markup language.