Apparatus and method of ubiquitous context-aware agent based on sensor networks

• US 7,847,699 B2
• Filed: 10/16/2006
• Issued: 12/07/2010
• Est. Priority Date: 12/06/2005
• Status: Active Grant

• Current Assignee: Electronics and Telecommunications Research Institute
• Original Assignee: Electronics and Telecommunications Research Institute
• Inventors: Lee, Hyun-Jeong, Lim, Shin-Young, Huh, Jae-Doo
• Primary Examiner(s): PHAM, TOAN NGOC
• Application Number:
  US12/085,315
• Publication Number:
  US 20090261978A1
• Time in Patent Office: 1,513 Days
• Field of Search: 340/573.1, 340/505, 340/517, 340/521, 340/522, 340/531, 340/3.3, 340/286.02, 707/705, 709/203, 709/226, 706/46, 706/47
• US Class Current: 340/573.1
• CPC Class Codes: H04L 12/2803 Home automation networks
• CPC Class Codes: H04L 12/2829 involving user profiles according to which the execution of a home appliance functionality is automatically triggered
• CPC Class Codes: H04L 67/12 specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
• CPC Class Codes: H04W 4/027 using movement velocity, acceleration information
• CPC Class Codes: H04W 4/38 for collecting sensor information

Abstract

An apparatus and method for context awareness by detecting intentions of a user in the ubiquitous environment using context information which is created by analyzing real world data collected from sensors are provided. The apparatus is configured of a sensor platform, a context-aware agent and a service provider. The sensor platform collects data of real world and transmits the collected data to the context-aware agent. The context-aware agent integrates the data of real world from the sensor platform, and stores and manages context information according to the integrated data. The service provider automatically controls objects to perform necessary operations to provide a predetermined intelligent services according to the context information received from the context-aware agent.

Claims

1. An apparatus of an ubiquitous context-aware agent based on a sensor network, the apparatus comprising:

a sensor platform for collecting data of real world and transmitting the collected data to a context-aware agent;

the context-aware agent for interpreting and integrating the data of real world from the sensor platform, and storing and managing context information according to the interpreted and integrated data; and

a service provider for receiving the context information from the context-aware agent, and automatically performing operations according to the received context information, wherein the context-aware agent includes a context interpreter for receiving the collected data from the sensor platform and interpreting the received data to be viewable to a human and a computer;

an integrator for receiving an interpreted context information from the context interpreter and integrating the received context information in a predetermined format;

a space manager for receiving the interpreted context information from the context interpreter and detecting users'"'"' intention with reference to a relation between a users'"'"' movement and static objects in a predetermined space;

a home map manager for receiving the interpreted context information from the context interpreter, and displaying current states of a real world to the user using the interpreted context information;

a context storage for storing information transferred from the context integrator, the space manager and the home map manager, and outputting the stored information in response to a request; and

a context manager for receiving the predetermined format of the integrated context information from the context integrator and managing the context information stored in the context storage.

2. The apparatus of claim 1, wherein the sensor platform includes:

a sensor node for collecting the data of real world; and

a sensor coordinator for transferring the collected data to the context-aware agent.

3. The apparatus of claim 1, wherein the context integrator transfers information related to a service context to the service provider.

4. The apparatus of claim 1, wherein the home map manager displays a ubiquitous space in a form of a graphic user interface (GUI), and the ubiquitous space is displayed to the user by adding, deleting and updating objects in the ubiquitous space according to the context.

5. The apparatus of claim 1, wherein the service provider receives information

related to a context requiring a service among the contexts from the context integrator, receives the context information from the context storage, infers users'"'"' intention through analyzing a relation between the interpreted context information and static objects, and providing an automated service according to the inferred intention.

6. The apparatus of claim 1, wherein the context integrator transfers the context information to the service provider when the context information interpreted at the context interpreter is an urgent message.

7. A method of context-awareness using an ubiquitous context-aware agent based on a sensor network comprising:

detecting sensing-data related to a real world collected through a sensor platform, and transforming the sensing-data to context information by analyzing a meaning of the sensing-data;

determining whether a value of the transformed context information is in a normal range or not if a type of the transformed context information is an environmental context;

setting an urgent flag, storing corresponding context information and transferring the context information to a service provider if the value of the transformed context information is not in the normal range;

integrating context information, storing corresponding context information, filtering the stored context information and transmitting the filtered context information to the service provider if the value of the transformed context information is in the normal range;

analyzing a relation between a moving object and a static object if the type of the transformed context information is a position context, detecting an intentions of a user according to a position, and determining whether it'"'"'s value is in a normal range or not; and

integrating context information, storing corresponding context information, filtering the stored context information and providing the filtered context information to the service provider if the value is in the normal range.

8. The method of claim 7, wherein in the operation of the integrating, storing, filtering and transmitting, the context information is integrated and the integrated context information is displayed as a GUI (graphic user interface) format through a home map.

9. The method of claim 7, wherein in order to detect the users'"'"' intention in the operation of the analyzing, detecting and determining, a comparative state between the static object and the moving object is detected based on the analyzed position information and direction information, a position relation between the static object and the moving object is defined with reference to a time, and a meaning of the movement made by the moving object is inferred using rules made according to characteristics of the static object.

10. The method of claim 7, wherein in the operation of the integrating, storing, filtering and providing, the context information is integrated and the integrated context information is displayed in a GUI (graphic user interface) format through a home map.

11. The method of claim 7, further comprising setting an urgent flag, storing corresponding context information and providing the stored context information to the service provider if the value is not in the normal range in the operation of the analyzing m detecting and determining.

12. A method of inferring a position context in a context-aware method using an ubiquitous context-aware agent based on a sensor network, the method comprising:

determining a type of an object through monitoring context information in real time, and creating an object model and an object area model if the type of the object is a static object;

detecting a qualitative state if the type of the object is a moving object in the operation of the determining and creating or if the object model and the object area model are created in the operation of the determining and creating;

generating a qualitative state message based on the detected qualitative state and storing the generated qualitative state message;

generating an object relation message by inferring an object relation using the qualitative state message and storing the generated object relation message; and

generating a semantic model using a stored object relation model, generating a semantic model message according to the generated semantic model and storing the semantic model message.

13. The method of claim 12, wherein in the operation of the determining and creating, the type of the object is determined by monitoring context information in real time, and if the type of the object is the static object, an object model and an object area model are created with reference to information related to a size of a real static object, and a type and a size of a functional area of the real static object, where the object model expresses the position and the size of the sensed static object and the object area model expresses the position and the size of the functional area of the sensed static object.

14. The method of claim 12, wherein in the operation of the detecting, the qualitative state is detected by comparing position information of the moving object transmitted in real time with reference to the object model and the object area model of the static model.

15. The method of claim 12, wherein in the operation of the generating an object relation message and storing the generated object relation message, a relation of the moving object and the static object is analyzed to determine whether the relation is which one of qualitative states approach, reside and leave, and the object relation message is created to have a predetermined format using one of a position relation information on, front, rear, left and right.

16. The method of claim 12, wherein in the operation of the generating a semantic model and generating a semantic model message, the semantic model is inferred with reference to a semantic model basic knowledge including previously-defined rules based on characteristics of the static object by receiving the object relation message, and the semantic model message with a predetermined format is created and stored.

17. The method of claim 16, wherein the semantic model message is transmitted a service provider to provide a service to a user in real time according to the semantic model message.