METHODS AND APPARATUS FOR INTEGRATION OF VISUAL AND NATURAL LANGUAGE QUERY INTERFACES FOR CONTEXT-SENSITIVE DATA EXPLORATION

• US 20090132506A1
• Filed: 11/20/2007
• Published: 05/21/2009
• Est. Priority Date: 11/20/2007
• Status: Abandoned Application

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Houck, Keith C., Pan, Shimei, Zhou, Michelle X., Kissa, Peter
• Application Number:
  US11/943,405
• Publication Number:
  US 20090132506A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/90332 Natural language query formulation or dialogue systems

Abstract

Methods and apparatus are provided for integrating a visual query interface and a natural language interface. The disclosed interface embeds a first of the visual query interface and the natural language interface into a second of the visual query interface and the natural language interface. The disclosed interface can also receives one or more natural language expressions in the natural language interface and one or more visual query expressions in the visual query interface in a same search turn. The disclosed interface can also receive a first query comprised of a first of a natural language query and a visual query; process the first query; and creates a substantially equivalent query to the first query in a second of the natural language query and the visual query The disclosed interface can process a natural language query to determine if a portion of the natural language query is not understood; and convert at least a portion of the natural language query to a visual query.

Claims

1. A method for integrating a visual query interface and a natural language interfaces comprising:

providing an interface that embeds a first of said visual query interface and said natural language interface into a second of said visual query interface and said natural language interface.

2. The method of claim 1, further comprising the step of receiving one or more natural language expressions in a visual query.

3. The method of claim 1, further comprising the step of processing each visual query element in said visual query.

4. The method of claim 3, further comprising the step of applying NL interpretation to each NL expression in said visual query.

5. The method of claim 1, further comprising the step of receiving one or more visual query expressions in a natural language query.

6. The method of claim 5, wherein an interpretation dictionary used by an NL query interpreter is augmented with one or more graphical symbols.

7. A method for integrating a visual query interface and a natural language interfaces comprising:

providing said visual query interface and said natural language interface;

receiving one or more natural language expressions in said natural language interface;

receiving one or more visual query expressions in said visual query interface in a same search turn as said one or more natural language expressions are received; and

processing said one or more natural language expressions and said one or more visual query expressions in said same search turn.

8. The method of claim 7, further comprising the step of applying said one or more natural language expressions to an NL interpreter and said one or more visual query expressions to a visual query interpreter.

9. The method of claim 7, further comprising the step of integrating results from said visual query mode and said natural language mode.

10. A method for integrating a visual query interface and a natural language interface, comprising:

providing said visual query interface and said natural language interface;

receiving a first query comprised of a first of a natural language query and a visual query;

processing said first query; and

creating a substantially equivalent query to said first query in a second of said natural language query and said visual query.

11. The method of claim 10, further comprising the step of processing said substantially equivalent query.

12. The method of claim 10, further comprising the step of providing said substantially equivalent query for editing as a basis for a subsequent query.

13. A method for integrating a visual query interface and a natural language interfaces comprising:

providing said visual query interface and said natural language interface;

receiving a natural language query;

processing said natural language query to determine if a portion of said natural language query is not under stood; and

converting at least a portion of said natural language query to a visual query; and

receiving one or more visual constraints to specify said portion of said natural language query is not understood.

14. The method of claim 13, further comprising the step of applying said natural language query to a natural language interpreter.

15. The method of claim 13, further comprising the step of determining if said natural language query has an error

16. The method of claim 13, further comprising the step of formulating an interpretation result based on a portion part of said natural language query that is understood.

17. The method of claim 16, further comprising the step of generating a partial interpretation result by ignoring one or more unknown words.

18. The method of claim 17, wherein said converting step converts said partial interpretation result to a visual query.

19. The method of claim 18, further comprising the step of receiving one or more revisions to said visual query to describe one or more unknown words.

20. The method of claim 18, further comprising the step of receiving one or more revisions to said visual query to correct an interpretation error in said visual query.