CONTEXT AWARE SYSTEM AND CONTEXT AWARE METHOD THEREOF

• US 20090157587A1
• Filed: 07/11/2008
• Published: 06/18/2009
• Est. Priority Date: 12/17/2007
• Status: Active Grant

• Current Assignee: Electronics and Telecommunications Research Institute
• Original Assignee: Electronics and Telecommunications Research Institute
• Inventors: CHOI, Jae Hun, PARK, Seon Hee, PARK, Soo Jun, LIM, Myung Eun
• Granted Patent: US 8,010,478 B2
• Time in Patent Office: Days
• US Class Current: 706/47
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/046 Forward inferencing; Production systems

Abstract

A context aware system and a context aware method thereof perform a reasoning to be aware of contexts in ubiquitous environments. The context aware method includes procedures of modeling a knowledge base describing context information including constraints; classifying the context information described in the knowledge base according to the constraints; filtering fact data having same constraints as input sensor data from the classified context data; storing only rules, which satisfy the filtered fact data and constraints, in an working memory; and inferring a service context by reasoning the stored fact data and rules. The method receives input sensor data, associated with a subject, continuously monitored and serviced by indoor sensors, performs a reasoning based upon the input sensor data, in order to be aware of the present contexts of the subject and also provide, in real-time, a service suitable for the present contexts, thereby promoting the convenience of life.

Claims

1. A context aware system comprising:

a knowledge base describing context information including constraints;

a classifier classifying the context information described in the knowledge base according to the constraints;

a fact filter filtering fact data having same constraints as input sensor data from the classified context information; and

a reasoning engine storing only the filtered fact data and rules that satisfy the constrains, and inferring a service context by reasoning the stored fact data and rules.

2. The context aware system of claim 1, wherein the context information includes rules, which describe objects, relations of the objects, facts of declaration of actual instances of the objects, which construct a context, conditions about the relations of the objects and the instances, and occurring conditions of predetermined context and service.

3. The context aware system of claim 1, wherein the classifier includes:

a spatial constraint classifier classifying fact data to be in one category in the constraints, the fact data having a same spatial constraint as an object, which has a described spatial constraint;

a temporal constraint classifier classifying fact data to be in one category in the constraints, the fact data having a same temporal constraint as an object, which has a described temporal constraint; and

an object constraint classifier classifying fact data to be in one category in the constraints, the fact data having a same temporal constraint as an object, which has a described object constraint.

4. The context aware system of claim 1, wherein the reasoning engine includes an working memory, which stores only the rules that satisfies the filtered fact data and the constraints.

5. A context aware method of a context aware system comprising:

modeling a knowledge base describing context information including constraints;

classifying the context information described in the knowledge base according to the constraints;

filtering fact data having same constraints as input sensor data from the classified context data;

storing only rules, which satisfy the filtered fact data and constraints, in an working memory; and

inferring a service context by reasoning the stored fact data and rules.

6. The context aware method of claim 5, wherein the context information includes rules, which describe objects, relations of the objects, facts of declaration of actual instances of the objects, which construct a context, conditions about the relations of the objects and the instances, and occurring conditions of predetermined context and service.

7. The context aware method of claim 5, wherein the constraints include a spatial constraint expressed by a name of a place, which indicates a space, a temporal constraint expressed by a reference time and a range from the reference time, and an object constraint expressed by a name of a predetermined object, which constructs the knowledge base.

8. The context aware method of claim 5, wherein the filtering of fact data having same constraints as input sensor data from the classified context data, comprises:

receiving the input sensor data;

checking data corresponding spatial/temporal values in the sensor data; and

filtering the classified context information to acquire fact data in same spatial/temporal ranges as the sensor data, corresponding to the checked spatial/temporal values.

9. The context aware method of claim 5, wherein the classifying of the context information described in the knowledge base according to the constraints, comprises:

classifying fact data to be in one category in the constraints, the fact data having a same spatial constraint as an object, which has a described spatial constraint;

classifying fact data to be in one category, the fact data having a same temporal constraint as an object in the constraints, which has a described temporal constraint; and

classifying fact data to be in one category in the constraints, the fact data having a same temporal constraint as an object, which has a described object constraint.