KR101900754B1 - Method for establishing user definition motion and motion recognition apparatus using the same - Google Patents

Abstract

The present invention relates to a user operation defining method and a motion recognizing apparatus for extracting a characteristic of a motion performed by a user and automatically setting a recognition condition of a user operation performed by one or more unit operations, The motion information may be calculated based on the sensed values of the at least one sensor, and the motion information may be continuously calculated. The at least one motion information may include one or more Extracts a sampling point, extracts an operation order and a recognition condition of the extracted sampling point, and generates an operation definition table for the operation of the user.

Description

TECHNICAL FIELD [0001] The present invention relates to a method for defining a user's motion and a motion recognition apparatus using the motion recognition apparatus.

The present invention relates to a method and apparatus for recognizing an operation of a user by using one or more sensors, and more particularly, to a method and apparatus for extracting a feature of a motion performed by a user, To a user-defined operation method that enables recognition of a user-defined operation, and to an operation recognition apparatus using the same.

In recent years, with the introduction of an open OS, a smart phone combining a high function of a PC with a mobile phone has become popular, and various attempts have been made to utilize a high-function and high-performance smart phone.

In particular, with the development of micro-fabrication technology, advanced sensors become smaller and cheaper, and more sensors can be mounted on smart phones, and intelligent applications utilizing such sensors, such as augmented reality and 3D games, are being developed .

In addition, sensors mounted on smart phones will be able to play a key role in communicating emotions with human beings by evolving into an intelligent sensor that takes into consideration user's physical changes and emotional states in a device that senses the surrounding environment. As a result, intelligent applications utilizing sensors are expected to grow even more.

There are camera (image) sensor, acoustic sensor, proximity sensor, illuminance sensor, gravity sensor, GPS sensor, acceleration sensor, gyro sensor, and geomagnetic sensor.

Among them, a camera (image) sensor is a sensor that detects light and converts the intensity of the light into digital image data, which can be used for face recognition and the like. The acoustic sensor detects a physical sound by changing the air pressure The proximity sensor is not a detection system based on mechanical contact but a proximity sensor that detects the presence or absence of an object to be detected when the detection object comes close to the proximity sensor Detection sensor that can be used to automatically turn off the screen when the smartphone is brought close to the face or placed in a pocket for a normal call.

The illuminance sensor is a sensor for sensing the ambient brightness. Normally, the illuminance sensor is used to reduce the power consumption of the mobile terminal and to reduce the fatigue of the eyes. It is a sensor that detects the direction of gravity and detects movement of objects. It is used to automatically correct the direction of the screen by determining the display direction (horizontal and vertical) of the smartphone.

In addition, the GPS sensor is a sensor capable of collecting time and position information of an object through a satellite positioning system, and is utilized for various location-based services. The acceleration sensor detects changes in object speed per unit time, In recent years, three-axis acceleration sensors using MEMS technology have become popular, and even object movements such as tilt changes and shakes can be detected. A geomagnetic sensor is a sensor that detects the azimuth angle like a compass by grasping the flow of the earth's magnetic field, The gyro sensor detects the inertial force of an object as an electric signal and mainly detects the rotation angle. It can detect the height, the rotation, and the tilt directly, so that it can recognize more precise motion when connected with the 3-axis acceleration sensor. Do.

In order to recognize an operation using these various sensors, it is necessary to specify a clear recognition condition for the operation to be recognized. Here, the recognition condition may be defined by the kind and range of the recognized value.

However, in the conventional motion recognition, only a predetermined type of motion defined in advance can be recognized, and it is impossible for the user to specify and recognize an arbitrary motion.

Korean Patent Laid-Open No. 10-2010-0081552, published on July 19, 2010 (name: device and method for detecting motion of portable terminal)

Accordingly, the present invention provides a method and apparatus for recognizing a user-defined motion by automatically setting a recognition condition of a motion arbitrarily specified by a user, and more particularly, A method for defining a user action capable of automatically setting a condition, and a motion recognition device using the same.

The present invention, as a solution to the above-mentioned problems, includes the steps of collecting a sensing value of one or more sensors that changes according to a user's operation; Calculating motion information based on the collected sensing values; Comparing the continuously calculated motion information to extract at least one sampling point at which a change of at least one of the movement direction and the velocity has occurred beyond the reference value; And extracting an operation sequence and a recognition condition of the extracted sampling points and generating an operation definition table for the operation of the user.

Here, the recognition condition may include at least one of a rotation angle calculated at each sampling point, a rotation angle change amount from a previous sampling point to a current sampling point, and a moving time from a previous sampling point to a current sampling point.

The generating of the operation definition table may include obtaining an average value of recognition conditions of each sampling point extracted for each operation of the user repeated two or more times and generating the operation definition table with the average value.

In addition, the method of defining a user operation according to the present invention may further include generating a margin management table that defines a maximum minimum range for recognition conditions of each sampling point defined in the operation definition table, The step of generating a table may determine a standard deviation of recognition conditions calculated at one or more sampling points extracted for each operation of the user repeated two or more times and set a margin value for each sampling point.

According to another aspect of the present invention, there is provided a method of defining a user operation, wherein the extracting of the sampling point comprises extracting a section including a variation pattern, the variation time being longer than a reference value, , And one or more points where a motion change occurs in the extracted section may be additionally extracted as a sampling point.

In addition, the present invention provides, as another solution to the above-mentioned problem, a sensing value collection module for collecting sensing values of one or more sensors that are changed according to a user operation; A calculation module for calculating motion information of the motion from the collected sensing values; And sequentially calculates motion information, extracts at least one sampling point at which at least one of the movement direction and the velocity has changed more than the reference value, extracts the operation order and the recognition condition of the extracted sampling point, And a learning module for generating an action definition table for the action recognition device.

Here, the learning module may generate the operation definition table by extracting a sampling point for the operation by repeating the operation twice or more, calculating an average value of the recognition conditions extracted at each sampling point, A standard deviation of recognition conditions of each sampling point repeatedly extracted is further determined and a further margin management table is defined based on the standard deviation to define a maximum minimum range for recognition conditions of each sampling point defined in the operation definition table .

Further, the motion recognition apparatus according to the present invention may further include: a storage module for storing the operation definition table and the margin management table; And a recognition module that compares the motion information calculated by the calculation module with the recognition condition set by the operation definition table and the margin management table to recognize the user defined operation.

The present invention extracts a sensed value of one or more sensors generated in response to a user's motion continuously and compares the calculated sensed motion information with continuous motion information so that at least one of a direction and a velocity changes more than a reference value, By defining the order between the sampling points and extracting the sampling point, the recognition condition of the user-defined operation made up of one or more unit operations can be automatically set.

In addition, the present invention can improve the recognition rate for the user-defined motion by setting the reference value and the margin for the motion information of the extracted one or more sampling points corresponding to the motion of the user.

1 is a diagram illustrating a reference coordinate system and motion information for defining an operation of a user terminal.
2 is a block diagram illustrating a motion recognition apparatus having a user motion definition function according to the present invention.
3 is a flowchart illustrating a method of defining a user operation according to the present invention.
4 is a flowchart illustrating a sampling point extracting process in a user operation defining method according to the present invention.
5 is a diagram illustrating an example of a user-defined operation according to the present invention.
6 is a view showing an example of an operation definition table set according to a method of defining a user operation according to the present invention.
7 is a diagram illustrating an example of a margin management table set according to a method of defining a user operation according to the present invention.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the following description and the accompanying drawings, detailed description of well-known functions or constructions that may obscure the subject matter of the present invention will be omitted. It should be noted that the same constituent elements are denoted by the same reference numerals as possible throughout the drawings.

The terms and words used in the present specification and claims should not be construed to be limited to ordinary or dictionary meanings and the inventor is not limited to the concept of terminology for describing his or her invention in the best way. It should be interpreted as meaning and concept consistent with the technical idea of the present invention. Therefore, the embodiments described in the present specification and the configurations shown in the drawings are merely the most preferred embodiments of the present invention, and not all of the technical ideas of the present invention are described. Therefore, It is to be understood that equivalents and modifications are possible.

Also, terms including ordinal numbers such as first, second, etc. are used to describe various elements, and are used only for the purpose of distinguishing one element from another, Not used. For example, without departing from the scope of the present invention, the second component may be referred to as a first component, and similarly, the first component may also be referred to as a second component.

In addition, when referring to an element as being "connected" or "connected" to another element, it means that it can be connected or connected logically or physically. In other words, it is to be understood that although an element may be directly connected or connected to another element, there may be other elements in between, or indirectly connected or connected.

Also, the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The singular expressions include plural expressions unless the context clearly dictates otherwise. It is also to be understood that the terms such as " comprising "or" having ", as used herein, are intended to specify the presence of stated features, integers, It should be understood that the foregoing does not preclude the presence or addition of other features, numbers, steps, operations, elements, parts, or combinations thereof.

In addition, the method and apparatus for recognizing user actions according to the present invention can be applied to various fields such as user operation recognition, robot control, and the like. Hereinafter, the present invention is applied to a user terminal.

The motion recognition in the user terminal is used for controlling a specific function of the user terminal by sensing a predetermined specific motion (flipping, wiggling in a specific direction, drawing a specific pattern, user access) Can be represented by an azimuth angle, a pitch, and a roll through a three-dimensional rectangular coordinate system as shown in FIG.

1, when the horizontal direction of the user terminal is the X axis, the vertical direction is the Y axis, and the width direction is the Z axis, the azimuth angle is a direction in which the user terminal is oriented (east, west, (Or -180 ° to 180 °) with respect to the Z axis, and the pitch is the horizontal axis rotation angle, which is represented by -90 ° to 90 ° according to the form in which the user terminal is erected, The reference rotation angle is expressed as -180 ° to 180 ° according to the form in which the user terminal is divided.

Of course, in the motion recognition, the reference coordinate system and the method of expressing the motion can be changed, and the above definition is only an example.

The present invention is for recognizing a random motion specified by a user in accordance with a set recognition condition by extracting a feature value of an arbitrary motion designated by the user during the motion of the user terminal and setting a recognition condition, The motion recognition apparatus according to the present invention may be configured as shown in FIG.

2 is a block diagram showing an operation recognition apparatus according to the present invention. The operation recognition apparatus according to the present invention includes a sensing value collection module 100, a calculation module 200, a recognition module 300, , A learning module (400), and a storage module (500).

The sensing value collection module 100 is configured to collect sensing values output from the plurality of sensors 10. At this time, the sensing value collection module 100 may collect sensing values from one or more sensors of the plurality of sensors 10 at regular intervals, and the collected sensing values may have different units depending on the sensors. For example, the sensing value of the illuminance sensor indicates the amount of illumination (Lux), the sensing value of the proximity sensor indicates the distance to and / or proximity to a nearby object, and the sensing value of the 3-axis acceleration sensor is 3 Axis, the sensing value of the three-axis gyro sensor indicates the angular velocity in the direction of the three axes (X, Y, Z), and the sensing value of the geomagnetism sensor indicates the acceleration value in the direction of the axis Direction.

The calculation module 200 calculates one or more sensing values collected by the sensing value collection module 100 as motion information that can be recognized by the recognition module 300. For example, the calculation module 200 calculates rotation angles and / or angular velocities of the motion information described in FIG. 1, i.e., the azimuth angle, the pitch angle, the roll angle, etc., from the sensed values obtained through the rotation vector and rotation matrix calculation can do. Also, the calculation module 200 can calculate the roughness measurement value or the roughness variation as the sensing value of the roughness sensor, and calculate the proximity frequency and proximity distance from the sensing value of the proximity sensor.

The recognition module 300 is a configuration for recognizing a predefined motion using the motion information calculated from the calculation module 200. [ Particularly, the recognition module 300 compares the calculated motion information with the recognition condition of each operation defined through the operation definition table 501 and the margin management table 502 stored in the storage module 500, A defined action occurs and is recognized. Here, the predefined actions may include user defined actions defined by the user.

The recognition module 300 recognizes one or more unit operations classified based on any one of direction, speed, and time, and recognizes the predefined operation by combining the recognized unit operations. Here, the unit operation is a division of the previously defined operation by one or more of direction, time, and speed. For example, if the operation is to draw a star pattern, it can be classified into five unit operations.

The learning module 400 may be configured to set a recognition condition for an operation to be recognized by the recognition module 300. In particular, the learning module 400 may set a recognition condition for a user-defined operation that the user takes. More specifically, the learning module 400 compares the motion information continuously calculated in the calculation module 200 based on the one or more sensed values collected in the sensing value acquisition module 100 for a predetermined time, The operation definition table 501 and the margin management table 502 for the operation desired by the user are obtained by comparing the motion information for each extracted sampling point with the sampling point for classifying the unit operation and calculating the recognition condition and the margin .

The storage module 500 stores an operation definition table 501 and a margin management table 502 for one or more user defined operations generated by the learning module 400 and stores the operation definition table 501 and the margin management table 502, And provides the table 502 to the recognition module 300. The operation definition table 501 and the margin management table 502 consist of one or more sampling points for distinguishing one or more unit operations included in a specific operation and recognition conditions at each sampling point.

Here, the recognition condition may include at least one of a rotation angle calculated at each sampling point, a rotation angle variation from the previous sampling point to the current sampling point, and a time from the previous sampling point to the current sampling point.

The recognition module 300 refers to the operation definition table 501 and the margin management table 502 of the storage module 500 to recognize the user defined operation.

A method of defining a user operation by the above-described motion recognition apparatus will be described in detail with reference to the flowcharts of FIG. 3 and FIG.

The operation mode of the motion recognition apparatus according to the present invention can be largely divided into a learning mode and a recognition mode. Here, the learning mode is a mode for learning and defining a characteristic of an operation to be recognized, and the sensing value collection module 100, the calculation module 200, and the learning module 400 are activated. On the other hand, the recognition mode is a mode for recognizing a defined operation, and the sensing value collection module 100, the calculation module 200 and the recognition module 300 are activated.

3, in the case of the learning mode (S110), the motion recognition apparatus according to the present invention is configured to recognize the movement of the at least one sensor 10 based on the operation taken by the user through the sensing value collection module 100 The sensing values are collected (S120). For example, the sensing value acquisition module 100 may collect sensed values output from at least one of an acceleration sensor, a geomagnetic sensor, and a gyro sensor. Here, the collection of the one or more sensing values may be performed at regular intervals. That is, one or more sensed values varying according to the operation of the user consecutively for a predetermined time are collected at a predetermined period (for example, a sampling period).

In addition, the motion recognition apparatus according to the present invention may use motion information (e.g., pitch, roll, rotation angle and / or angular velocity) corresponding to the azimuth using the collected one or more sensed values . Since the sensing value collection module 100 collects and outputs sensing values that change according to an operation performed for a predetermined period of time at regular intervals, the calculation module 200 also detects movement information And outputs it.

At this time, the motion recognition apparatus according to the present invention compares motion information continuously calculated through the learning module 140, extracts a sampling point for classifying one or more unit operations, and determines an operation sequence of each sampling point (S140). The recognition condition at each sampling point can be stored together.

The sampling point extraction process will be described in more detail with reference to FIG.

First, the learning module 140 according to the present invention compares two consecutively calculated motion information (S210).

If one or more of the direction and the velocity is changed by more than a preset reference value, the changed point is extracted as a sampling point (S220). The direction may be the movement direction (+/-) of the x, y, and z axes, and the velocity may be a linear acceleration or a rotational angular velocity.

For example, when the user moves the terminal equipped with the motion recognition apparatus according to the present invention as shown in FIG. 5, the learning module 400 of the motion recognition apparatus according to the present invention, SP1, points SP2 and SP3 whose movement direction has been changed, and a point SP4 at which movement has ended can be extracted as sampling points.

5 can be defined as an operation in which the unit operation 1 of the interval of SP1 and SP2, the unit operation 2 of the interval of SP2-SP3 and the unit operation 3 of the interval of SP3-SP4 are sequentially performed, The sampling point SP1 is the starting point of the unit operation 1, SP2 is the unit operation 1 end point and the starting point of the unit operation 2, SP3 is the starting point of the unit operation 2 and the end point of the unit operation 3, It becomes an end point.

In addition, the learning module 400 of the motion recognition apparatus according to the present invention extracts one or more sampling points as described above, and if the time between the sampling points is long and there is a change, Can be extracted.

Specifically, the learning module 400 extracts at least one sampling point, and then extracts a section in which the time difference between each sampling point is larger than the reference value and the variation pattern exists (S230).

Then, in the extracted section, the intermediate point at which the motion change occurs can be further extracted as a sampling point (S240). For example, in the operation illustrated in FIG. 5, when the motion time for the unit operation 2 is longer than the reference value and moves in a zigzag pattern rather than a linear motion, the learning module 400 may determine the zigzag pattern Each point can be further extracted as a sampling point.

Steps S120 to S140 including the above-described sampling point extraction process are performed until the operation specified by the user is completed. Here, if no motion is detected or a specified time has elapsed, it can be determined that the operation is completed.

The learning module 400 of the motion recognition device according to the present invention counts the number of times of the operation learning at the time when the operation is completed, (S150). If it is not reached n times, the steps S120 through S140 are repeated again while taking the same action again by the user, and the same operation is repeated n times, and the sampling points and sampling points The recognition condition is extracted.

When the specified number of times is reached, the learning module 400 of the motion recognition apparatus can set the recognition condition of the sampling point to an average value of recognition conditions of each sampling point extracted for each n repeated operations (S160 ). The sampling points and the recognition conditions extracted from the above are set in the operation definition table 501 in order according to the operation order. Here, the recognition condition set in the operation definition table 501 may include at least one of a rotation angle calculated at each sampling point, a rotation angle variation from the previous sampling point to the current sampling point, and a time from the previous sampling point to the current sampling point . ≪ / RTI >

,

,

)이고, t는 이전 샘플링 포인트로부터 해당 샘플링 포인트까지 움직인 시간을 나타낸다. 참고로, 각 파라미터의 아래첨자 1,2,3,4는 샘플링 포인트를 나타낸다. 여기서, 최초 추출된 샘플링 포인트 SP1은 동작의 최초 시작점이므로, 그 변화량 (

)는 (0, 0, 0)이 되고, 그의 움직인 시간

도 0이 된다.For example, in the case of a user operation as shown in Fig. 5, an operation definition table can be constructed, as shown in Fig. 6, xa, ya, and za represent rotation angle values of the x-axis, y-axis, and z-axis calculated at each sampling point, and xd, yd, and zd represent rotational angle variation amounts from the previous sampling point to the corresponding sampling point

,

,

), And t represents the time from the previous sampling point to the corresponding sampling point. For reference, the subscripts 1,2,3,4 of each parameter represent sampling points. Here, since the sampling point SP1 extracted first is the initial starting point of the operation,

) Becomes (0, 0, 0) and its moving time

0 ".

Then, the learning module 400 of the motion recognition apparatus calculates a standard deviation between pieces of motion information of each sampling point extracted for each n repeated operations, and determines a maximum-minimum range, That is, the margin is set (S170). The margin value for the recognition condition of each sampling point is registered in the margin management table 502. [

For example, in the case of a user operation as shown in FIG. 5, a margin management table can be constructed as shown in FIG. The margin management table is a table for defining a maximum minimum value for each element defined in the operation definition table, and the standard deviation of the rotation angle, the variation amount, and the motion time calculated by repeating n times is set as the margin value.

In the motion recognition apparatus according to the present invention, the motion recognition is performed based on the motion definition table 61 and the margin management table 502. At this time, 502, "the recognition range of the recognition condition is set, and when the motion information satisfying the recognition allowable range is detected, it can be determined that the corresponding sampling point is recognized.

As described above, the user's operation, that is, the recognition condition for the user-defined operation, is set so that the user-defined operation can be efficiently recognized.

When the user operation definition is completed as described above, the operation recognition apparatus switches to the recognition mode and recognizes the user defined operation with reference to the operation definition table 501 and the margin management table 502 set as described above (S110).

For example, as shown in FIGS. 6 and 7, when the operation definition table 501 and the margin management table 502 are set, the recognition module 300 includes the sensing value collection module 100 and the calculation module 200 , Y and z satisfy the following expression (1), it is determined that the sampling point SP1 is recognized, and if the sampling points SP2, Sp3, and SP4 are sequentially recognized in the same process, It is determined that an operation has occurred as shown in FIG.

The method of defining a user action according to the present invention may be implemented in the form of software readable by various computer means and recorded in a computer-readable recording medium. Here, the recording medium may include program commands, data files, data structures, and the like, alone or in combination. Program instructions to be recorded on a recording medium may be those specially designed and constructed for the present invention or may be available to those skilled in the art of computer software. For example, the recording medium may be an optical recording medium such as a magnetic medium such as a hard disk, a floppy disk and a magnetic tape, a compact disk read only memory (CD-ROM), a digital video disk (DVD) Includes a hardware device that is specially configured to store and execute program instructions such as a magneto-optical medium such as a floppy disk and a ROM, a random access memory (RAM), a flash memory, do. Examples of program instructions may include machine language code such as those generated by a compiler, as well as high-level language code that may be executed by a computer using an interpreter or the like. Such a hardware device may be configured to operate as one or more software modules to perform the operations of the present invention, and vice versa.

Further, the functional operations and subject matter implementations described herein may be implemented in other types of digital electronic circuitry, or may be implemented in computer software, firmware, or hardware, including the structures disclosed herein and their structural equivalents, ≪ / RTI > Implementations of the subject matter described herein may be embodied in one or more computer program products, i. E. One for computer program instructions encoded on a program storage medium of the type for < RTI ID = 0.0 & And can be implemented as a module as described above. The computer-readable medium can be a machine-readable storage device, a machine-readable storage substrate, a memory device, a composition of matter that affects the machine readable propagation type signal, or a combination of one or more of the foregoing.

In addition, while the specification contains a number of specific implementation details, it should be understood that they are not to be construed as limitations on the scope of any invention or claim, but rather on the features that may be specific to a particular embodiment of a particular invention Should be understood as an explanation. Certain features described herein in the context of separate embodiments may be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented in multiple embodiments, either individually or in any suitable subcombination. Further, although the features may operate in a particular combination and may be initially described as so claimed, one or more features from the claimed combination may in some cases be excluded from the combination, Or a variant of a subcombination.

Likewise, although the operations are depicted in the drawings in a particular order, it should be understood that such operations must be performed in that particular order or sequential order shown to achieve the desired result, or that all illustrated operations should be performed. In certain cases, multitasking and parallel processing may be advantageous. Also, the separation of the various system components of the above-described embodiments should not be understood as requiring such separation in all embodiments, and the described program components and systems will generally be integrated together into a single software product or packaged into multiple software products It should be understood.

Certain embodiments of the subject matter described herein have been described. Other embodiments are within the scope of the following claims. For example, the operations recited in the claims may be performed in a different order and still achieve desirable results. By way of example, the process illustrated in the accompanying drawings does not necessarily require that particular illustrated or sequential order to obtain the desired results. In certain implementations, multitasking and parallel processing may be advantageous.

The description sets forth the best mode of the invention, and is provided to illustrate the invention and to enable those skilled in the art to make and use the invention. The written description is not intended to limit the invention to the specific terminology presented. Thus, while the present invention has been described in detail with reference to the above examples, those skilled in the art will be able to make adaptations, modifications, and variations on these examples without departing from the scope of the present invention.

Therefore, the scope of the present invention should not be limited by the described embodiments but should be defined by the claims.

The present invention extracts a sensed value of one or more sensors generated in response to a user's motion continuously and compares the calculated sensed motion information with continuous motion information so that at least one of a direction and a velocity changes more than a reference value, By defining the order between the sampling points and extracting the sampling point, the recognition condition of the user-defined operation made up of one or more unit operations can be automatically set.

In addition, the present invention can improve the recognition rate for the user-defined motion by setting the reference value and the margin for the motion information of the extracted one or more sampling points corresponding to the motion of the user.

10: Sensor
100: Sensing value acquisition module
200: Operation module
300: recognition module
400: Learning module
500: storage module

Claims (10)

Collecting a sensing value of one or more sensors that varies depending on a user's operation;
Recognizing a user defined operation corresponding to the sensed values based on a previously stored operation definition table;
Calculating motion information based on the collected sensing values while recognizing the user-defined motion, comparing the continuously calculated motion information, and calculating at least one sampling point at which at least one of the motion direction and the velocity has changed more than the reference value Extracting an operation sequence and a recognition condition of the extracted sampling point, and updating the pre-stored operation definition table for the user defined operation. 2. The method according to claim 1,
A rotation angle calculated at each sampling point, a rotation angle variation from the previous sampling point to the current sampling point, and a time from the previous sampling point to the current sampling point. 2. The method of claim 1, wherein updating the pre-stored operation definition table comprises:
Wherein the predefined operation definition table is obtained by obtaining a sampling point extracted in the user defined operation and an average value of recognition conditions of a sampling point defined in the predefined operation definition table, and updating the predefined operation definition table with the average value. The method according to claim 1,
The step of recognizing the user-
Acquiring a margin management table that defines a maximum minimum range for recognition conditions of each sampling point defined in the pre-stored operation definition table;
And recognizing the user-defined operation based on the pre-stored operation definition table and the pre-stored margin management table. 5. The method according to claim 4, further comprising: obtaining a standard deviation of a recognition condition calculated at one or more sampling points extracted while recognizing the user-defined motion and a recognition condition calculated at a sampling point defined in the previously stored operation table, And updating the margin management table by setting a margin margin value. The method of claim 1, wherein extracting the sampling point comprises:
Extracting one or more points that are longer than the reference value and include a variation pattern among the sections divided by the extracted one or more sampling points and extracting at least one point in which the motion variation occurs in the extracted section as a sampling point To define a user action. A sensing value collection module for collecting sensed values of one or more sensors that are changed according to a user operation;
A calculation module for calculating motion information of the motion from the collected sensing values;
A recognition module for collecting sensing values of one or more sensors that are changed according to an operation of a current user and recognizing a user-defined operation based on current sensing values sensed from an operation of the current user based on a previously stored operation definition table;
Extracting at least one sampling point at which at least one of the movement direction and the velocity has changed more than the reference value, extracting an operation order and a recognition condition of the extracted sampling point, And a learning module for generating and storing an operation definition table and updating the operation definition table based on the current sensing value obtained while recognizing the user defined operation by the recognition module, Device. 8. The system of claim 7, wherein the learning module
Extracting a sampling point for the operation of the current user and updating the operation definition table by obtaining an average value of recognition conditions defined by the recognition condition extracted from each sampling point and the operation definition table, Device. 8. The learning module of claim 7,
Determining a standard deviation of recognition conditions defined by the operation definition table and recognition conditions of each sampling point extracted from the sensed values collected in association with the operation of the current user, And generates a margin management table defining a maximum minimum range for recognition conditions of the extracted sampling points and recognition conditions of each sampling point defined in the operation definition table. 10. The method of claim 9,
And a storage module for storing the operation definition table and the margin management table,
The recognition module
Wherein the operation recognition unit recognizes the user operation using the updated operation definition table and the margin management table when recognizing the next user operation.

Images