KR20080006981A - System and method for offering intelligent home service - Google Patents

Abstract

An intelligent home service supply system and a method are provided to predict a home service to be offered to a user by obtaining biological and environmental contexts from a sensor device, thereby predicting even detailed contents and operation of the home service from the biological context. A sensor unit(110) obtains user environmental context and user biological context from a sensor device. A context manager(120) normalizes the obtained context data. A home service predictor(130) predicts a home service for a user by using the normalized data. A home service controller(140) controls the home service according to results predicted by the home service predictor.

Description

System and method for providing intelligent home service {System and method for offering intelligent home service}

1 is a block diagram of a room in which a smart home is implemented according to an embodiment of the present invention.

2 is a block diagram showing the configuration of an intelligent home service providing system according to an embodiment of the present invention.

3 is a diagram illustrating a sensor unit for obtaining a living body and an environment context from a sensor device.

4 is a diagram illustrating a context normalization table according to an embodiment of the present invention.

5 is a diagram illustrating a home service predictor for predicting a home service of a user by inputting normalized data.

FIG. 6 is a diagram illustrating a rule set in a rule-based pattern analyzer according to an embodiment of the present invention in a tree structure.

FIG. 7 is a diagram illustrating a structure for predicting a home service using a linear support vector machine (SVM) algorithm in a history-based pattern analyzer according to an embodiment of the present invention.

8 is a flowchart illustrating an intelligent home service providing method according to an embodiment of the present invention.

9 is a detailed flowchart of the home service prediction step S230 of FIG. 8.

<Explanation of symbols for the main parts of the drawings>

12: biometric context 14: environmental context

110: sensor unit 120: context management unit

130: home service prediction unit 132: rule-based pattern analysis unit

134: history-based pattern analysis unit 140: home service control unit

150: data management unit

The present invention relates to providing an intelligent home service, and more particularly, an intelligent home service providing system and method for obtaining a biological and environmental context from a sensor device and predicting and providing a home service to a user from the sensor device. It is about.

Recently, research on the home network environment is being actively conducted, and in particular, research on the home service that operates intelligently to enable mutual communication with human beings is being actively conducted.

Smart homes that provide automatic and efficient services for humans are realized by adding intelligent smart middleware to homes with ubiquitous computing.

Research on such middleware includes Microsoft's Easy living, Aware Home by AHRI (Aware Home Research Initiative), and Adaptive House.

Easy living suggests tracking a user's location and providing home appliances based on the user's location. However, Easy living mainly focuses on user location detection and user authentication, and does not contain information on intelligent home service provision by analyzing user and environment contexts.

On the other hand, Aware Home focuses on constructing an intelligent home suitable for the elderly who live alone, and provides appropriate services. For example, Aware Home provides a service that generates an alarm when there is no user movement for a certain period of time. In addition, Adaptive House proposed a method for maximizing user satisfaction while minimizing energy consumption. However, this study does not contain information on providing intelligent home services based on user and environment contexts.

That is, in the past, there have been various studies for implementing a smart home, but studies on providing a home service by predicting a user's behavior pattern by performing a situation analysis based on the user's biometric information and environment information are insufficient. The accuracy of was not high.

The present invention has been devised to improve the above problems, and the technical problem to be achieved by the present invention is to provide an intelligent home service that operates by predicting the user's behavior from the user's biological and environmental context.

The objects of the present invention are not limited to the above-mentioned objects, and other objects that are not mentioned will be clearly understood by those skilled in the art from the following description.

In order to achieve the above object, the intelligent home service providing system according to an embodiment of the present invention is a sensor unit for obtaining a user biological context and a user environment context from a sensor device, the context management unit for normalizing the obtained context data And a home service predictor for predicting a home service for a user using the normalized data, and a home service controller for controlling a home service according to a result predicted by the home service predictor.

In order to achieve the above object, the intelligent home service providing method according to an embodiment of the present invention comprises the steps of (a) obtaining user bio-context data and user environment context data from the sensor device, (b) Normalizing context data; (c) predicting a home service for a user using the normalized data; and (d) executing a home service according to the result predicted in step (c). .

Specific details of other embodiments are included in the detailed description and the drawings.

Advantages and features of the present invention and methods for achieving them will be apparent with reference to the embodiments described below in detail with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but can be implemented in various different forms, and only the embodiments make the disclosure of the present invention complete, and the general knowledge in the art to which the present invention belongs. It is provided to fully inform the person having the scope of the invention, which is defined only by the scope of the claims. Like reference numerals refer to like elements throughout.

Hereinafter, the present invention will be described with reference to the drawings for explaining an intelligent home service providing system and method according to embodiments of the present invention.

First, an intelligent home service providing system will be described.

Before the term is defined, the context is defined as information that can characterize the state of the object, where the object can be a person, place, or physical object. For example, it may be body temperature, pulse rate, room temperature, facial expression, human position, posture, and the like.

1 is a block diagram of a room in which a smart home is implemented according to an embodiment of the present invention.

The interior is largely divided into a room, a living room, a DVD room, and a kitchen, and each room is provided with a home service to be implemented by the present invention. For example, a DVD room is provided with a DVD, a living room is provided with a TV and a projector, a room is provided with audio and a PC, and each area is provided with one or more lights. In addition, a camera sensor is attached to each area, and various sensors such as temperature sensors are installed in the room and the user, although not shown in the drawing, to acquire the environment and the user's ecological information.

According to an embodiment of the present invention to be described later, when the user is in a specific area, the living body context 12 and the environment context 14 are obtained, and the TV, DVD, lighting, and the like are automatically operated based on the details. The content can be predicted and executed. For example, when a user enters a living room and sits on a couch, the user can turn on the TV, analyze the room temperature, and automatically operate the air conditioner. In addition, the user may select a TV channel (sports, news, drama) by analyzing the facial expression, pulse, posture, and the like of the user.

2 is a block diagram showing the configuration of an intelligent home service providing system according to an embodiment of the present invention.

The intelligent home service providing system according to an exemplary embodiment of the present invention may include a sensor unit 110, a context manager 120, a home service predictor 130, and a home service controller 140. In addition, the data management unit 150 may further include.

The sensor unit 110 obtains the user's biometric context 12 and environmental context 14 data from a sensor device such as a temperature sensor, a camera, a pulse rate, and a temperature sensor. Details will be described later with reference to FIG. 3.

The context manager 120 normalizes the context data obtained from the sensor device from a preset context normalization table. That is, the data of each context has various units and ranges, and normalizes the data in a specific range of each context to values such as 0.1, 0.2, 0.3, and the like.

The home service predictor 130 analyzes normalized data input from the context manager 120 to predict a home service to be provided for the user. The home service predictor 130 may include a rule-based pattern analyzer 132 for predicting a home service to be provided according to a preset context rule. In addition, the home service predictor 130 may further include a history-based pattern analyzer 134 for predicting detailed contents of the home service based on the obtained algorithm based on a predetermined algorithm. It may include.

The rule-based pattern analyzer 132 operates the home service when a specific context satisfies a predetermined rule, and the history-based pattern analyzer 134 performs the context based on user's behavior pattern data stored by conventional learning. When data is input, detailed contents of the home service may be predicted and executed by a predetermined algorithm. At this time, the predetermined algorithm preferably uses the SVM (Support Vector Machine) algorithm. A plurality of linear support vector machines (LSVMs) may be used to predict the home service hierarchically according to the user's location. The normalized context is input to the SVM algorithm, and the user's behavior pattern is predicted based on the data about the user's behavior pattern by the conventional learning stored in the data manager 150.

The home service controller 140 executes a home service according to the result predicted by the home service predictor 130.

3 is a diagram illustrating a sensor unit 110 that acquires a living body 12 and an environment context 14 from a sensor device.

The context according to an embodiment of the present invention includes five biological contexts 12 including pulse, body temperature, facial expression, eye focus, and posture of a user's biological characteristics, and an indoor temperature, a user's location, and a time's environmental characteristics. It consists of three environmental contexts (14). It will be appreciated by those skilled in the art that the context can represent not only the eight listed but also the biometric and environmental features of the user and can be variously selected if obtained by the sensor device. The eight contexts listed above can be obtained through each sensor device. The room temperature is from the temperature sensor, the eye focus is from the eye focus camera, the face expression is from the face detection camera, and the pulse and body temperature are controlled by the pulse sensor and temperature sensor connected to the personal digital assistant (PDA). Position and posture can be known through a number of cameras installed in each area of the room. It will be appreciated that the sensor device for detecting the context may be selected in various ways in consideration of cost and performance. The data of each context obtained from the sensor device in the sensor unit 110 is transmitted to the context manager 120.

4 is a diagram illustrating a context normalization table according to an embodiment of the present invention.

Since each context data has various units and ranges, as shown in FIG. 4, each context data is normalized to nine values of 0.1 to 0.9. In the table, the user's pulse was normalized to a total of nine values, which means that the average adult pulse at rest is about 72 times per minute, and pulses below 40 and pulses above 140 correspond to the actual user's emergency. I will exclude it. In the case of body temperature, the normal body temperature of a person is normalized to 9 levels in this range, considering that there are differences between ages and individuals, but usually 34 to 39 degrees. For facial expressions, see six basic facial expressions (Surprise, Fear, Sad, Angry) by Charles Darwin (see "The expression of the emotions in man and animals", Electronic Text Center, University of Virginia Library). , Disgust, Happy) and no expression (Blank). In the case of room temperature, normalization was carried out in 9 steps, considering that the room temperature that an average person feels comfortable is 19 to 22 degrees. The time was normalized into nine steps as shown in the table, taking into account the time spent by humans. The user location was normalized by dividing the room into nine zones. The normalization table of FIG. 4 is just an example according to an embodiment of the present invention, and the normalization process may be divided into not only nine values but also the data in more detail and normalized to more values or normalized to fewer values. to be.

The context manager 120 receives context data from the sensor 110 at predetermined time intervals. If the input data is out of the above-described context normalization table, an error process is performed and data is input again from the sensor unit 110. The context data that has passed the error check is normalized according to a preset context normalization table, and the normalized data is transmitted to the home service predictor 130.

FIG. 5 is a diagram illustrating a home service predictor for predicting a home service of a user by inputting normalized data. FIG. 6 is a diagram illustrating a rule set by the rule-based pattern analyzer 132 according to an embodiment of the present invention. 7 is a diagram illustrating a tree structure, and FIG. 7 is a diagram illustrating a structure of predicting a home service using a linear support vector machine (SVM) algorithm in the history-based pattern analyzer 134 according to an embodiment of the present invention.

Referring to FIG. 5, the home service predictor 130 may include a rule-based pattern analyzer 132 and a history-based pattern analyzer 134. The rule-based pattern analyzer 132 primarily enters contexts such as the user's location, posture, time, body temperature, and room temperature to determine which home service to operate, and secondly, the history-based pattern analyzer 134. The biometric context 12 such as pulse, body temperature, facial expression, posture, etc. is input to predict the detailed contents of the home service.

As an example, the action of the rule-based pattern analysis unit 132 is described as sitting in the user's location context and sofa in the living room, such as the TV in the living room is automatically turned on when the user enters the living room and sits on the sofa ( motion_sit) turns on the TV according to a preset context rule when the user posture context is input. This serves to power up each home service according to a preset context rule. For another example, referring to the rule of the tree structure of FIG. 6, when the user enters the living room, the air conditioner may be automatically operated when the room temperature is higher than 24 degrees. 6 is merely an example according to an embodiment of the present invention, and may be variously changed according to a user and a setting. In general, the rule-based pattern analyzer 132 may input a context such as a user's location and posture, time, body temperature, and room temperature.

The rule-based pattern analyzer 132 operates only the home service and cannot predict the detailed contents of each home service. That is, when the user sits on the sofa in the living room, it is impossible to predict whether to turn on the sports channel or the news channel only by turning on the TV. In addition, even if the user automatically enters the room and lies in the bed, it is impossible to predict whether to provide rock music, classical music, or dance music even if audio is automatically played. This is because such detailed content contents are difficult to predict only by contextual contents that a user enters a room and lies in a bed. In addition, a rule regarding the biometric context 12 data when the user turns on the audio may be input to the rule-based pattern analyzer 132 in advance, but the amount of the data is too large and the result predicted from such data may not be accurate. This is because there is a high possibility.

In the history-based pattern analysis unit 134, a plurality of pieces of data (eg, 'a user watches a sports channel when the user's pulse, body temperature, and facial expression have a specific value') according to a conventional learning method are known. Data about the data), and then input the current context to predict the user's behavior pattern. In general, the biometric context 12 such as a pulse, body temperature, facial expression, user posture, or the like may be input to the history-based pattern analyzer 134. In the present invention, the SVM (Support Vector Machine) algorithm can be used as shown in FIG. A plurality of linear support vector machines (LSVMs) are used to hierarchically execute home services according to the user's location. The context is input to the SVM algorithm, and data about the user's pattern by conventional learning is loaded from the data manager 150 to predict the user's pattern based on this. The predicted result is delivered to the home service controller 140, and the home service controller 140 executes the home service according to the predicted result.

Therefore, the present invention inputs the living body 12 and the environment context 14 obtained from the sensor device to the rule-based pattern analyzer 132 and the history-based pattern analyzer 134 to more accurately predict the behavior pattern of the user. Can predict the pattern of the user in more detail.

In this case, the term '~ part' means a hardware component such as software, a field programmable gate array (FPGA), or an application specific integrated circuit (ASIC), and performs certain functions. However, it is not meant to be limited to software or hardware. The component may be configured to be in an addressable storage medium and may be configured to play one or more processors. Thus, as an example, the component may include components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, procedures, Subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functionality provided by the components can be combined into a smaller number of components or further separated into additional components. In addition, the components may be implemented to regenerate one or more CPUs in a device.

8 is a flowchart illustrating an intelligent home service providing method according to an embodiment of the present invention, and FIG. 9 is a detailed flowchart of the home service prediction step S230 of FIG. 8.

According to an embodiment of the present invention, the intelligent home service providing method may include obtaining a user's living body 12 and an environment context 14 from a sensor (S210), normalizing acquired context data (S220), and normalized Predicting a home service for the user from the data (S230), and executing the home service according to the predicted result (S240).

Predicting a home service (S230) may include performing rule-based pattern analysis (S232) for predicting a home service to be provided according to a preset context rule. The method may further include a history-based pattern analysis step S234 of predicting detailed contents of the home service based on the obtained algorithm data based on a predetermined algorithm. At this time, it is preferable that the predetermined algorithm uses the SVM algorithm.

In the present invention, the biometrics 12 context data including pulse, body temperature, facial expression, eye focus, and user posture can be obtained from the sensor device.

In addition, in the present invention, the environment context 14 data including the user location, room temperature, and time may be obtained from the sensor device.

Those skilled in the art will appreciate that the present invention can be embodied in other specific forms without changing the technical spirit or essential features of the present invention. Therefore, it should be understood that the embodiments described above are exemplary in all respects and not restrictive. The scope of the present invention is indicated by the scope of the following claims rather than the above description, and all changes or modifications derived from the meaning and scope of the claims and their equivalents are included in the scope of the present invention. Should be interpreted.

According to the intelligent home service providing system and method of the present invention as described above has one or more of the following effects.

First, there is an advantage that the home service can be predicted from the biometric and environmental context of the user.

Second, the detailed contents can be predicted from the biometric context as well as the operation of the home service.

Third, the user's behavior can be predicted more accurately by using both rule-based pattern history and history-based pattern prediction simultaneously.

Claims (13)

A sensor unit for obtaining a user biological context and a user environment context from the sensor device; A context manager which normalizes the obtained context data; A home service predictor for predicting a home service for a user using the normalized data; And And a home service control unit for controlling a home service according to a result predicted by the home service prediction unit. The method of claim 1, And a data manager which stores home service data executed by the user and context data at this time. The method according to claim 1 or 2, The biometric context data includes information about pulse rate, body temperature, facial expression, eye focus and user posture. The method according to claim 1 or 2, The environmental content data includes information about user location, room temperature and time. The method according to claim 1 or 2, The home service predictor includes a rule-based pattern analyzer for predicting a home service to be provided according to a preset context rule. The method of claim 5, The home service predictor further includes a history-based pattern analyzer for predicting detailed contents of the home service by inputting the context data to a predetermined algorithm. The method of claim 6, The predetermined algorithm comprises a support vector machine (SVM) algorithm.  (a) obtaining user biometric context data and user environment context data from the sensor device; (b) normalizing the obtained context data; (c) predicting a home service for a user using the normalized data; And (d) executing a home service according to the result predicted in step (c). The method of claim 8, The biometric context data includes information on pulse rate, body temperature, facial expression, eye focus and user posture. The method of claim 8, The environmental content data includes information about user location, room temperature and time. The method of claim 8, wherein step (c) comprises: (c1) a rule-based pattern analysis step of predicting a home service to be provided according to a preset context rule. The method of claim 11, wherein step (c) comprises: and (c2) a history-based pattern analysis step of inputting the context data into a predetermined algorithm to predict detailed contents of a home service. The method of claim 12, The predetermined algorithm comprises a support vector machine (SVM) algorithm.

Images