Method and System for Providing Information Services Related to Multimodal Inputs

• US 20060218192A1
• Filed: 06/09/2006
• Published: 09/28/2006
• Est. Priority Date: 08/31/2004
• Status: Active Grant

• Current Assignee: Tahoe Research Limited (f/k/a Learndale Limited) (Vector Capital Corporation)
• Original Assignee: Kumar C. Gopalakrishnan
• Inventors: Gopalakrishnan, Kumar C.
• Granted Patent: US 7,853,582 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/435 Filtering based on additional data, e.g. user or group profiles
• CPC Class Codes: G06F 16/48 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/51 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/58 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/583 using metadata automatically derived from the content

Abstract

A system and method provides information services related to multimodal inputs. Several different types of data used as multimodal inputs are described. Also described are various methods involving the generation of contexts using multimodal inputs, synthesizing context-information service mappings and identifying and providing information services.

Claims

1. A method comprising:

providing an information service related to a multimodal input using a context constituent.

2. The method as recited in claim 1 wherein the context constituent includes a primary data, the primary data comprising at least one of:

a) a textual data;

b) a visual imagery;

c) an audio data;

d) a user input;

e) a database of history of usage of a system by a user;

f) a classification of the primary data;

g) a user group;

h) a user preference;

i) a communication channel characteristic;

j) an explicitly specified system parameter;

or

k) a domain knowledge.

3. The method as recited in claim 1 wherein the context constituent includes a metadata, the metadata comprising at least one of:

a) a location data;

b) a motion data;

c) a time data;

d) a user access privilege;

e) a financial transaction;

f) an environmental factor;

or

g) an instrument parameter.

4. The method as recited in claim 1 wherein the context constituent includes an implicit data, the implicit data extracted from the multimodal input, the implicit data comprising at least one of:

a) a text in a visual imagery;

b) a logo;

c) a symbol;

d) a layout information in a visual imagery;

e) a text in an audio data;

f) a musical element;

g) a user behavior;

or

h) an environment behavior.

5. The method as recited in claim 4 wherein each implicit data includes a confidence measure.

6. The method as recited in claim 1 wherein the context constituent is included in generating a context.

7. The method as recited in claim 6 further comprising representing a plurality of contexts in an overlapping hierarchy.

8. The method as recited in claim 6 further comprising including a database of stored contexts.

9. The method as recited in claim 8 wherein the stored context is entered in the database by a user of the system.

10. The method as recited in claim 8 wherein the stored context is entered in the database by an operator of the system.

11. The method as recited in claim 8 wherein the stored context is generated by the system and entered into the database.

12. The method as recited in claim 11 wherein the stored context is generated by a system using an input, the input comprising at least one of:

a) an XML data;

b) an RSS data;

or

c) a PDF document.

13. The method as recited in claim 8 further comprising creating a mapping of an information service to a stored context.

14. The method as recited in claim 13 wherein the mapping is created by an entity, the entity comprising at least one of:

a) a user of the system;

or

b) an operator of the system.

15. The method as recited in claim 13 wherein the mapping is created by the system.

16. The method as recited in claim 6 further comprising identifying an information service related to a context.

17. The method as recited in claim 8 wherein the information service is identified using the database of stored contexts.

18. The method recited in claim 17 further comprising using a first context to match a second context in the stored context database and using the second context to identify the information service.

19. The method as recited in claim 16 wherein the identified information service is used as another context.

20. A computer program product for providing an information service related to a multimodal input, the computer program product being embodied in a computer readable medium and comprising computer instructions for:

a) generating an implicit data;

b) generating a context;

c) storing a context in a database;

d) synthesizing context-information service mapping;

e) identifying a context in a database using a query comprising another context;

f) identifying an information service.