Apparatus and method for language expression using context and intent awareness

• US 8,560,301 B2
• Filed: 03/02/2010
• Issued: 10/15/2013
• Est. Priority Date: 05/22/2009
• Status: Expired due to Fees

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Kim, Yeo Jin
• Primary Examiner(s): GUERRA-ERAZO, EDGAR X
• Application Number:
  US12/715,423
• Publication Number:
  US 20100299138A1
• Time in Patent Office: 1,323 Days
• Field of Search: 704/3, 704/4, 704/9, 704/10, 704/235, 704/246, 704/243, 704/270, 704/270.1, 704/275, 704/260, 704/258, 704/207, 704/208, 704/210, 704/214, 704/215, 704/231, 704/257
• US Class Current: 704/9
• CPC Class Codes: G06F 40/205 Parsing

Abstract

A language expression apparatus and a method based on a context and a intent awareness, are provided. The apparatus and method may recognize a context and an intent of a user and may generate a language expression based on the recognized context and the recognized intent, thereby providing an interpretation/translation service and/or providing an education service for learning a language.

Claims

1. An apparatus for language expression based on context and intent awareness, the apparatus comprising:

a context recognizing unit configured to recognize a context of a user by analyzing sensing information collected from the user'"'"'s environment;

an intent recognizing unit configured to recognize an intent of the user based on the recognized context;

a language generating unit configured to generate a language expression based on the recognized context and the recognized intent and refine the substance of the language expression based upon information gathered from a source independent of the sensing information; and

an output unit configured to convert the refined language expression into a language that is understandable to the user, and to output the converted language expression.

2. The apparatus of claim 1, further comprising:

a knowledge database configured to store and maintain a knowledge model of at least one domain knowledge;

a behavioral model database configured to store and maintain a user behavior information model including at least one of a user profile of the user, a preference of the user, and a pattern of the user; and

a language database configured to store and maintain data with respect to the language that is understandable to the user.

3. The apparatus of claim 2, wherein the context recognizing unit recognizes the context of the user through at least one of a retrieval analysis with respect to the user'"'"'s environment, a logical inference, and a pattern recognition, and combines the collected sensing information with the knowledge model or the behavioral model.

4. The apparatus of claim 2, wherein the intent recognizing unit derives at least one inference intent by combining the recognized context with at least one of a cognitive model, the knowledge model, and the behavioral model.

5. The apparatus of claim 4, wherein the intent recognizing unit recognizes the intent of the user based on a predetermined evaluation function predetermined for the at least one analyzed inference intent.

6. The apparatus of claim 5, wherein the evaluation function analyzes a result of an evaluation with respect to a preference of the user and a detailed intent of the user corresponding to the at least one analyzed inference intent.

7. The apparatus of claim 1, further comprising:

an information collecting unit configured to collect the sensing information from the user'"'"'s environment through at least one of a hardware sensor and a software sensor.

8. The apparatus of claim 7, wherein the hardware sensor comprises at least one of a location identification sensor, a proximity identification sensor, a radio frequency identification (RFID) tag identification sensor, a motion sensor, an acceleration sensor, a gravity sensor, a pressure sensor, a sound sensor, a vision sensor, a touch sensor, a temperature sensor, a humidity sensor, a light sensor, and a bio-sensor.

9. The apparatus of claim 7, wherein the software sensor collects sensing data from at least one of an electronic calendar application, a scheduler application, an e-mail management application, a message management application, a communication application, a social network application, and a web site management application.

10. The apparatus of claim 1, wherein the language generating unit generates a first language expression by selecting at least one of a form, a sentence, and a phrase corresponding to the recognized context and the recognized intent.

11. The apparatus of claim 10, wherein the language generating unit generates a second language expression corresponding to the recognized context and the recognized intent, by combining the first language expression with the collected sensing information.

12. The apparatus of claim 11, wherein the output unit converts the second language expression into the language that is understandable to the user and outputs the converted second language expression.

13. The apparatus of claim 1, wherein the language generating unit performs one of setting of a language for the language expression based on a location of the user, and receiving of language set information for the language expression from the user.

14. A method for language expression based on context and intent awareness, the method comprising:

recognizing, with a processor, a context of a user by analyzing sensing information collected from the user'"'"'s environment;

recognizing an intent of the user based on the recognized context;

generating the language expression based on the recognized context and the recognized intent and refining the substance of the language expression based upon information gathered from a source independent of the sensing information;

converting the refined language expression into a language that is understandable to the user; and

outputting the converted language expression.

15. The method of claim 14, wherein recognizing the context of the user comprises:

recognizing the context of the user through at least one of a retrieval analysis with respect to the user'"'"'s environment, a logical inference, and a pattern recognition, and

combining the collected sensing information with a knowledge model or a behavioral model.

16. The method of claim 14, wherein the recognizing of the intent of the user comprises deriving at least one inference intent by combining the recognized context with at least one of a cognitive model, a knowledge model, and a behavioral model.

17. The method of claim 14, wherein the recognizing of the context of the user comprises:

collecting the sensing information from the user'"'"'s environment through at least one of a hardware sensor and a software sensor.

18. The method of claim 14, wherein the generating of the language expression comprises:

generating a first language expression by selecting at least one of a form, a sentence, and a phrase, corresponding to the recognized context and the recognized intent, and

generating a second language expression corresponding to the recognized context and the recognized intent, by combining the first language expression with the collected sensing information.

19. The method of claim 18, wherein the converting and outputting of the language expression comprises:

converting the second language expression into the language that is understandable to the user, and

outputting the converted second language expression.

20. A non-transitory computer readable storage medium storing instructions that, when executed by a processor, cause the processor to implement a method comprising:

recognizing a context of a user by analyzing sensing information collected from the user'"'"'s environment;

recognizing an intent of the user based on the recognized context;

generating a language expression based on the recognized context and the recognized intent and refining the substance of the language expression based upon information gathered from a source independent of the sensing information;

converting the refined language expression into a language that is understandable to the user; and

outputting the converted language expression.