KR101957405B1 - Method and Apparatus for Inputting Pattern to Prevent Shoulder Surfing - Google Patents

Abstract

In the present embodiments, a plurality of learning patterns are combined to generate a public pattern, and the behavior information of the user who inputs the pattern as well as the pattern input at the time of user authentication is also compared together. Thus, the user need not memorize separately the password A pattern input method and apparatus capable of authenticating a legitimate user while preventing a shoulder surfing attack.

Description

FIELD OF THE INVENTION [0001] The present invention relates to a method and apparatus for inputting a strong pattern to a shoulder surfing attack,

The technical field to which this embodiment pertains is a method and apparatus for inputting a lock pattern in a device.

The contents described in this section merely provide background information on the present embodiment and do not constitute the prior art.

Pattern lock is a graphical password lock mechanism, consisting of 3x3 points. It should consist of a minimum of 4 points of connection, each point should be used only once, and the point between two points must not be skipped. There are 389,112 types of patterns that can be used while observing these rules. The number of patterns that can be made of four points is 1,624, and the number of patterns that can be made of four points is 140,704. It is more intuitive than disabling security by inserting numbers so many users are using pattern locks.

The complexity of a pattern increases the degree of cryptography, but many users find it easier to password-code an easy pattern because it is difficult for users to remember and the drawing complexity. Simple patterns are vulnerable to speculative attacks. In particular, there is a problem of being vulnerable to a shoulder surfing attack in which a secret pattern is stolen or an input pattern is recorded using a recording device such as a camera.

One of the algorithms of the shoulder surfing attack program analyzes the movement of the user's finger and graphs the trace immediately. It detects the pattern of rotation, symmetry, and specific shape from the user's line of sight, estimates the distance between points and calculates the number of cases, and unlocks it with up to 5 inputs.

Since patterns are exposed primarily in public places, the secret pattern itself is not sufficient to prepare for security threats, and additional security measures are needed.

In the embodiments of the present invention, it is necessary to create a public pattern by combining a plurality of learning patterns, and to compare not only the pattern inputted at the time of user authentication but also the behavior information of a user who inputs a pattern, The main purpose of the invention is to authenticate a legitimate user while preventing a shoulder surfing attack even if the pattern is leaked.

Other and further objects, which are not to be described, may be further considered within the scope of the following detailed description and easily deduced from the effects thereof.

According to an aspect of the present invention, there is provided a pattern input method by a computing device that uses a lock pattern to authenticate a party user, the method comprising: extracting first behavior information from a learning pattern input on a screen of the computing device, Extracting second behavior information from a release pattern input on a screen of the computing device, and authenticating a user based on the learned pattern characteristics of each user.

According to another aspect of the present invention, there is provided a computer-readable storage medium storing a program for causing a computer to function as: a pattern learning unit for extracting first behavior information from a learning pattern input on a screen of a computing device using a lock pattern to authenticate a party user, And a pattern authentication unit for extracting second behavior information from the release pattern input on the screen of the device and authenticating the user based on the learned pattern characteristics of each user.

According to yet another aspect of this embodiment, there is provided a computer program for pattern input, recorded on a non-transitory computer readable medium comprising computer program instructions executable by a processor, Extracting first behavior information from a learning pattern input to a screen of the computing device, when executed by a processor, and learning a pattern feature for each user; And authenticating the user based on the learned pattern characteristics of the user.

As described above, according to the embodiments of the present invention, a plurality of learning patterns are combined to generate a public pattern, and the behavior information of the user who inputs the pattern as well as the pattern input at the time of user authentication are compared together, Likewise, there is no need for the user to memorize separately, and even if the pattern is leaked, the valid user can be authenticated while preventing the shoulder surfing attack.

Even if the effects are not expressly mentioned here, the effects described in the following specification which are expected by the technical characteristics of the present invention and their potential effects are handled as described in the specification of the present invention.

1 is a block diagram illustrating a pattern input device according to an embodiment of the present invention.
2 is a diagram illustrating a learning pattern processed by a pattern input apparatus according to an embodiment of the present invention.
3 is a diagram illustrating behavior information processed by a pattern input device according to an exemplary embodiment of the present invention.
4 is a diagram illustrating location information processed by a pattern input device according to an embodiment of the present invention.
5 is a diagram illustrating an open pattern processed by a pattern input apparatus according to an embodiment of the present invention.
6 is a diagram illustrating a screen of a computing device according to an exemplary embodiment of the present invention.
7 is a flowchart illustrating an operation of the pattern input device according to an embodiment of the present invention in a learning mode and an authentication mode.
8 is a diagram illustrating a release pattern input with reference to a disclosure pattern output by the pattern input apparatus according to an embodiment of the present invention.
9 is a flowchart illustrating operation of the pattern input apparatus according to an embodiment of the present invention in the authentication mode.
10 is a diagram illustrating a screen of a computing device according to an exemplary embodiment of the present invention.
11 is a flowchart illustrating a pattern input method according to another embodiment of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. Will be described in detail with reference to exemplary drawings.

1 is a block diagram illustrating a pattern input device according to an embodiment of the present invention.

As shown in FIG. 1, the pattern input device 100 includes a pattern learning unit 110 and a pattern authentication unit 120. The pattern input device 100 may omit some of the various components illustrated in FIG. 1 or may further include other components. For example, the pattern input apparatus 100 may further include a public pattern generating unit or a public pattern displaying unit.

The pattern input device 100 uses a lock pattern to authenticate a party user. A lock pattern is a way of setting and releasing locks using graphic elements. The locking pattern is composed of 3x3 points, but not limited thereto, and MxN (M, N is a natural number) suitable for the design to be implemented can be used.

When the pattern input device 100 receives a pattern on the touch screen of the computing device, it compares the patterns and authenticates the user. The pattern input device 100 generates a public pattern by combining a plurality of learning patterns, and compares the behavior information of a user who inputs a pattern as well as the pattern input at the time of user authentication.

The pattern learning unit 110 extracts the first behavior information from the learning pattern input on the screen of the computing device using the lock pattern to authenticate the user of the specific party, and learn pattern characteristics for each user. The learning pattern includes a plurality of points included in the lock pattern and a path selectively connected between the plurality of points. The first action information includes at least one of (i) position information at which the touch event occurred, (ii) touch pressure information, (iii) touch area information, (iv) touch time information, (v) motion information of the computing device, And includes attitude information of the device.

The pattern authentication unit 120 extracts second behavior information from the release pattern input on the screen of the computing device, and authenticates the user based on the learned pattern characteristics of each user. The release pattern is a pattern entered by the user to release the lock screen. The second action information includes at least one of (i) position information at which the touch event occurred, (ii) touch pressure information, (iii) touch area information, (iv) touch time information, (v) motion information of the computing device, And includes attitude information of the device.

Hereinafter, data to be learned by the pattern input device in the learning mode will be described with reference to FIG. 2 to FIG.

3 is a diagram illustrating behavior information processed by a pattern input device, and FIG. 4 is a diagram illustrating position information processed by a pattern input device according to an embodiment of the present invention. FIG. .

Referring to FIG. 2, the learning pattern has a section having a predetermined angle or a section changing the progress direction. A button wrapped in a large border is defined as the starting point of the learning pattern. When the 3x3 points on the screen of the device correspond to the numbers 1 to 9 in order, the learning pattern 1 is shown in FIG. 2A and the learning pattern 1 is connected in the order of 1-2-3-5. 2 (b) is the learning pattern 2, and the learning pattern 2 is connected in the order of 5-7-8-9. 2 (c) shows the learning pattern 3, and the learning pattern 3 is connected in the order of 5-6-8-9. 2 (d) is the learning pattern 4, and the learning pattern 4 is connected in the order of 5-9-4. 2 (e) is the learning pattern 5, and the learning pattern 5 is connected in the order of 8-7-2. 2 (f) is the learning pattern 6, and the learning pattern 6 is connected in the order of 2-3-6-7. The learning patterns can include obtuse angles connected to acute angles, right angles, as well as 1-5-6 sequences.

The preferred attitude is different for each user when using the device. For example, a lying position may be preferred, a device may be used vertically, or the device may be used while moving. The user may artificially learn the attitude or motion information of the device while touching the screen.

Referring to FIG. 3, the action information includes a User_ID; Input_ID; Action; X coordinate, Y coordinate, Pressure, Area; Accelerometer_x, Accelerometer_y, Accelerometer_z; Orientation_azimuth, Orientation_pitch, Orientation_roll; Time It can contain 14 fields. The action information refers to data obtained by processing input data or input data collected in the data collection step. An extracted example is shown in Fig.

User_ID is identification information of a user, and Input_ID is identification information of each touch event to be generated.

Action is the type of touch event that occurs. DOWN is a state in which something is pressed on the screen, MOVE is a state in which something is being moved on the screen, and UP is a state in which something is off the screen. That is, the user's body is state information that is obtained by pressing the button on the screen of the device, pushing the screen, and the like.

X coordinate is the x coordinate when the touch event occurs, Y coordinate is the y coordinate when the touch event occurs, Pressure is the touch pressure when the touch event occurs, Touch area, and Time is the time when the touch event occurred.

The accelerometer is the data collected by the device's three-axis acceleration sensor, and the orientation is the data collected by the direction sensor of the device.

The acceleration sensor measures the acceleration for three axes x, y, and z. The x-axis is the acceleration acting on the side of the smartphone, the y-axis is the acceleration acting on the top and bottom surfaces, and the z-axis is the acceleration (m / s ² ) do.

The direction sensor measures the change in azimuth (x-axis), pitch (y-axis), and roll (z-axis) Azimuth ranges from 0 to 360 degrees, pitch ranges from -180 to 180 degrees, and roll ranges from 90 degrees to 90 degrees. Azimuth indicates the direction in which the head of the device is pointing when the device is placed horizontally. The data values along each direction start from the north and add 90 degrees clockwise. Pitch (slope) refers to the vertical slope of the instrument. It has a value of 0 when the head and the lower part of the apparatus are horizontal. The value decreases gradually as the height of the head increases. The value increases as the height of the head decreases. roll (horizontal rotation) means the horizontal slope of the device. This value has a value of 0 when the left and right parts of the device are horizontal when the screen of the device is pointing to the sky, and the value gradually increases when the left position of the device is higher and decreases gradually when the right position is higher.

Referring to FIG. 4, the pattern input device calculates a position relative to a reference point of the lock pattern. The pattern input device defines position information in which a touch event occurs in positions 402, 404, and 406 relative to the respective center points 401, 403, and 405 existing in nine buttons (circles) in the pattern UI. That is, if the reference point of one arbitrary button is B (403), the position of the touch point P (404) generated when the button is input is obtained. Based on the coordinates (x, y) of B, the position relative to P is calculated and used for authentication.

The pattern input device calculates the button input duration and the button-to-button travel time with respect to the time information. The button input duration is defined as a value obtained by subtracting the input start time from the input end time for one of the nine buttons in the pattern UI, and the movement time between the buttons is defined as the input time between any two buttons do.

Hereinafter, the operation of the pattern input device for displaying the pattern in the authentication mode will be described with reference to FIGS. 5 to 6. FIG.

FIG. 5 is a diagram illustrating a disclosure pattern processed by the pattern input apparatus, and FIG. 6 is a diagram illustrating a screen of a computing device.

The pattern authentication unit 120 displays a public pattern generated by combining the learning patterns, and determines the degree of similarity between the displayed public pattern and the inputted releasing pattern. The pattern authentication unit 120 may include a public pattern generating unit and a public pattern displaying unit.

The public pattern generation unit generates a public pattern by connecting one or more other learning patterns from a starting point, an end point, or an intermediate point of the selected learning pattern among the plurality of learning patterns. The disclosure pattern may be a pattern having one starting point and one ending point.

Referring to FIG. 5, a public pattern generated from a plurality of learning patterns has a section that has more angles than the learning pattern or a section that changes the progress direction. A button with a large border is defined as the start point of the corresponding open pattern. 5 (a) is the disclosure pattern 1, and the public pattern 1 is the learning pattern 1 (1-2-3-5) and the learning pattern 2 ( 5-7-8-9) are combined. 5 (b) shows the open pattern 2, and the open pattern 2 includes the learned pattern 1 (1-2-3-5) and the learned pattern 3 (5-6-8-9). 5 (c) shows the disclosure pattern 3, and the disclosure pattern 3 includes the learning pattern 1 (1-2-3-5) and the learning pattern 4 (5-9-4). 5 (d) shows the disclosure pattern 4, and the disclosure pattern 4 is the combination of the learning pattern 5 (8-7-2) and the learning pattern 1 (2-3-5). FIG. 5E shows the disclosure pattern 5, and the disclosure pattern 5 is the combination of the learning pattern 5 (8-7-2) and the learning pattern 6 (2-3-6-7). 5 (f) shows the open pattern 6, the open pattern 6 includes the learning pattern 5 (8-7-2), the part (2-3-5) of the learning pattern 1, and the learning pattern 4 ) Are combined. 5 (g) shows the disclosure pattern 7, and the disclosure pattern 7 is a combination of a part (2-3-5) of the learning pattern 1 and the learning pattern 4 (5-9-4). The disclosure patterns 1 to 7 are merely examples, but the present invention is not limited thereto and may be generated by combining a learning pattern or a partial region of the learning pattern according to an implemented design.

Referring to FIG. 6, the public pattern display unit displays the public pattern generated by the public pattern generating unit on the screen of the computing device. And may be displayed in the pattern input window 620 or in a separate screen area 610 from the pattern input window 620. [

Hereinafter, the operation of the pattern input device in the learning mode and the authentication mode will be described with reference to FIGS. 7 to 10. FIG. FIG. 7 is a flowchart illustrating an operation of the pattern input device in the learning mode and the authentication mode, FIG. 8 is a diagram illustrating a release pattern input by referring to a disclosure pattern output by the pattern input device, Figure 5 is a flow chart illustrating the operation of the device in the authentication mode.

In step S710, the pattern input device outputs the pattern in the authentication mode. The learning pattern is output in the learning mode, and the public pattern is output in the authentication mode.

The pattern is input in step S720, and the data is extracted in step S730. In step S740, the data is preprocessed. The collected data are vectorized for use in machine learning. It also removes unnecessary or redundant data for use as an authentication element in this process.

In step 750, feature elements are extracted from the preprocessed data. The pattern input device includes position data on a touch generated for inputting a pattern using the extracted data; Slide speed / Acceleration / Angle; Touch size, touch pressure; Button input duration (Duration), inter-button movement time (Interval); The direction of the device, and the acceleration applied to the device. Also, the pattern input device can take into account the statistical calculation values such as the average / minimum / maximum / standard deviation values of each extracted feature element.

Steps S720 to S750 may be performed in a learning mode, an authentication mode, or a registration mode, respectively, as a process of extracting behavior information (feature elements) from a pattern.

In step 760, it is determined whether the device corresponds to the learning mode or the authentication mode. The mode may be a registration mode for registering a secret pattern.

In step S770, the pattern learning unit 210 learns based on the first behavior information, i.e., the feature element, and generates a user classification model related to a pattern feature for each user. The pattern learning unit 210 mechanically learns the extracted authentication factors and generates a user classification model. The machine learning algorithm can be implemented by applying Boosted Decision Tree, Decision Forest, Random Forest, Decision Jungle, Naive Bayesian, Support Vector Machine, Locally Deep SVM, Logistic Regression and Neural Network.

In step S780, the pattern learning unit 210 repeats inputting for each pattern in the learning mode several times.

In step S790, the pattern authentication unit 220 extracts the behavior information (feature element) from the release pattern input by the user, and determines the similarity by referring to the user classification model related to the pattern characteristic for each user.

8 (a) shows the displayed open pattern, and FIGS. 8 (b) and 8 (c) show the release patterns inputted by the users into the pattern input window.

The user enters a pattern in consideration of his or her tendency or habits in his or her preferred or artificial device posture. Since the length of the finger, the area of the finger, the posture of holding the device, and the posture of using the device are different for each user, the traces of the release patterns inputted for the same open pattern are different. Location data for the touch as well as a trace of release patterns for each user; Slide speed / Acceleration / Angle; Touch size, touch pressure; Button input duration, time between button movements; The direction of the device, and the acceleration applied to the device are input differently.

Referring to FIG. 9, in step S910, the pattern input device determines the type of the input pattern. In step S920, if the input pattern is a public pattern, the pattern input device determines whether or not the input pattern is the same as the public pattern displayed on the screen. In step S930, the pattern input device refers to the user classification model related to the pattern characteristic for each user to determine the degree of similarity. If the similarity calculated through the user classification model is greater than or equal to the set value based on the action information extracted from the pattern inputted by the user, the user is authenticated as a legitimate user (S950).

If the similarity calculated through the user classification model based on the behavior information extracted from the public pattern in step S950 is smaller than the set value, it is determined that the user is not a legitimate user. In step S960, the open pattern outputted to the screen is changed to another open pattern, and the pattern is input again, or the secret pattern is input.

The pattern input device can release the lock using a secret pattern as required. A secret pattern that is not a displayed public pattern may be input, and the degree of similarity between the inputted secret pattern and a previously stored secret pattern may be determined. For example, a confidential pattern can be input when (i) the private space is not a public place, (ii) the points and connection relationships of the public pattern are identical but the similarity of the behavior information is inconsistent due to circumstances. In Fig. 10, a secret pattern inputted differently from the displayed public pattern is shown.

In step S970, if the input pattern is a secret pattern, the pattern input device determines whether it is the same as a previously stored secret pattern. In step S930, the pattern input device refers to the user classification model related to the pattern characteristic for each user to determine the degree of similarity. If the similarity calculated through the user classification model is greater than or equal to the set value based on the action information extracted from the pattern inputted by the user, the user is authenticated as a legitimate user (S950).

If the similarity calculated through the user classification model based on the behavior information extracted from the secret pattern in step S980 is smaller than the set value, it is determined that the user is not a legitimate user. In step S990, the pattern input device receives a release pattern in which the user views and inputs the release pattern output on the screen.

Although the components included in the pattern input device are shown separately in FIG. 1, a plurality of components may be combined with each other and implemented as at least one module. The components are connected to a communication path connecting a software module or a hardware module inside the device and operate organically with each other. These components communicate using one or more communication buses or signal lines.

The pattern input device may be implemented in logic circuitry by hardware, firmware, software, or a combination thereof, and may be implemented using a general purpose or special purpose computer. The device may be implemented using a hardwired device, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), or the like. Further, the device may be implemented as a System on Chip (SoC) including one or more processors and controllers.

The pattern input device may be mounted in a form of software, hardware, or a combination thereof, in a computing device having hardware elements. The computing device includes a communication device such as a communication modem for performing communication with various devices or wired / wireless communication networks, a memory for storing data for executing a program, a microprocessor for executing and calculating a program, Device. ≪ / RTI >

11 is a flowchart illustrating a pattern input method according to another embodiment of the present invention. The pattern input method can be performed by a computing device and operates in the same manner as the pattern input device.

In step S1110, the computing device extracts the first behavior information from the learning pattern input on the screen of the computing device, and learns pattern characteristics for each user. The learning pattern includes a plurality of points included in the lock pattern and a path selectively connected between the plurality of points, and includes a section having a predetermined angle or a section for changing the progress direction. The first action information includes at least one of (i) position information in which a touch event occurs, (ii) touch pressure information, (iii) touch area information, (iv) touch time information, (v) And includes attitude information of the computing device. The location information where the touch event occurred is a relative position calculated with respect to the reference point of the lock pattern.

In step S1110 of learning pattern features for each user, a user classification model is generated for pattern characteristics of each user by learning based on the first behavior information. In step S1110 of learning a pattern feature for each user, the extracted authentication elements are machine-learned and a user classification model is generated. The machine learning algorithm can be implemented by applying Boosted Decision Tree, Decision Forest, Random Forest, Decision Jungle, Naive Bayesian, Support Vector Machine, Locally Deep SVM, Logistic Regression and Neural Network.

In step S1120, the computing device extracts second behavior information from the release pattern input on the screen of the computing device, and authenticates the user based on the learned pattern characteristics of each user. (Ii) touch pressure information, (iii) touch area information, (iv) touch time information, (v) motion information of the computing device, and (vi) As shown in Fig.

The step of authenticating the user (S1120) displays a public pattern generated by combining the learning patterns, and determines the similarity between the displayed public pattern and the input release pattern. The open pattern is generated by concatenating at least one learning pattern from a start point, an end point, or an intermediate point of a selected learning pattern among a plurality of learning patterns, and is a pattern having one starting point and one ending point.

In the step of authenticating the user (S1120), the public pattern output on the screen may be changed to another public pattern and output. The step of authenticating the user (S1120) may receive a secret pattern that is not the displayed public pattern, and may determine the similarity between the input secret pattern and the previously stored secret pattern. There is a secret pattern, but this is simple to set up. For example, a secret pattern can be selectively used in a private place and a secret pattern in a public place.

According to the embodiments, there is no risk of loss / theft as in the case of owner-based authentication based on what the user has like OTP, such as knowledge-based authentication based on knowing like a password, Based authentication, there is no risk that the template can not be changed when the template is leaked.

11, it is described that each process is sequentially executed. However, those skilled in the art will appreciate that those skilled in the art can change and execute the procedure described in FIG. 11 without departing from the essential characteristics of the embodiments of the present invention Or may be variously modified and modified by executing one or more processes in parallel or by adding other processes.

The operations according to the present embodiments may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium. A computer-readable medium represents any medium that participates in providing instructions to a processor for execution. The computer readable medium may include program instructions, data files, data structures, or a combination thereof. For example, there may be a magnetic medium, an optical recording medium, a memory, and the like. The computer program may be distributed and distributed on a networked computer system so that computer readable code may be stored and executed in a distributed manner. Functional programs, codes, and code segments for implementing the present embodiment may be easily deduced by programmers of the technical field to which the present embodiment belongs.

The present embodiments are for explaining the technical idea of the present embodiment, and the scope of the technical idea of the present embodiment is not limited by these embodiments. The scope of protection of the present embodiment should be construed according to the following claims, and all technical ideas within the scope of equivalents thereof should be construed as being included in the scope of the present invention.

100: pattern input device
110: pattern learning unit
120: pattern authentication unit

Claims (16)

1. A pattern input method by a computing device that uses a lock pattern to authenticate a party user,
Extracting first behavior information from a learning pattern input to a screen of the computing device from a plurality of previously stored learning patterns and learning a pattern feature for each user; And
Extracting second behavior information from a release pattern input on a screen of the computing device, and authenticating a user based on the learned pattern characteristics of each user,
The step of authenticating the user may include generating a public pattern by combining the plurality of learning patterns, displaying the generated public pattern, determining a degree of similarity between the displayed public pattern and the inputted releasing pattern,
Wherein the plurality of learning patterns include a plurality of points included in the lock pattern and a path selectively connected between the plurality of points and including a section having a predetermined angle or a section for changing the progress direction,
Wherein the open pattern is generated by concatenating at least one learning pattern from a starting point, an ending point, or an intermediate point of the selected learning pattern among the plurality of learning patterns, and generating the plurality of learning patterns by one pattern having one starting point and one ending point (I) has an angle larger than the pattern (i) or (ii) has a section for changing the traveling direction. The method according to claim 1,
The step of learning the pattern characteristic for each user includes:
And generating a user classification model related to the user-specific pattern feature by learning based on the first behavior information. delete The method according to claim 1,
Wherein the first behavior information and the second behavior information include at least one of:
(i) touch location information, (ii) touch pressure information, (iii) touch area information, (iv) touch time information, (v) motion information of the computing device, and (vi) Wherein the pattern information includes at least one of information on the pattern and information on the pattern. 5. The method of claim 4,
Wherein the location information of the touch event is a relative position calculated with respect to a reference point of the lock pattern. delete delete The method according to claim 1,
Wherein authenticating the user comprises:
And changing the open pattern output on the screen to another open pattern. The method according to claim 1,
Wherein authenticating the user comprises:
A secret pattern that is not the displayed public pattern, and determines similarity between the input secret pattern and a previously stored secret pattern. A pattern input device of a computing device that uses a lock pattern to authenticate a party user, comprising:
A pattern learning unit for extracting first behavior information from a learning pattern input on a screen of the computing device among a plurality of previously stored learning patterns and learning a pattern feature for each user; And
And a pattern authentication unit for extracting second behavior information from the release pattern input on the screen of the computing device and authenticating the user based on the learned pattern characteristics of each user,
Wherein the pattern authenticating unit generates a public pattern by combining the plurality of learning patterns, displays the generated public pattern, judges the similarity between the displayed public pattern and the inputted releasing pattern,
Wherein the plurality of learning patterns include a plurality of points included in the lock pattern and a path selectively connected between the plurality of points and including a section having a predetermined angle or a section for changing the progress direction,
Wherein the open pattern is generated by concatenating at least one learning pattern from a starting point, an ending point, or an intermediate point of the selected learning pattern among the plurality of learning patterns, and generating the plurality of learning patterns by one pattern having one starting point and one ending point (I) an angle greater than the pattern, and (ii) a section for changing the traveling direction. delete 11. The method of claim 10,
Wherein the first behavior information and the second behavior information include at least one of:
(i) touch location information, (ii) touch pressure information, (iii) touch area information, (iv) touch time information, (v) motion information of the computing device, and (vi) Wherein the pattern input device comprises: delete delete 11. The method of claim 10,
Wherein the pattern authenticating unit
Wherein the input device receives a secret pattern that is not the displayed public pattern, and determines the similarity between the input secret pattern and a previously stored secret pattern. A computer program stored in a non-transitory computer readable storage medium including computer program instructions executable by a processor, wherein the computer program instructions, when executed by a processor of a computing device,
Extracting first behavior information from a learning pattern input to a screen of the computing device from a plurality of previously stored learning patterns and learning a pattern feature for each user; And
Extracting second behavior information from a release pattern input on a screen of the computing device, and authenticating the user based on the learned pattern characteristics of each user,
The step of authenticating the user may include generating a public pattern by combining the plurality of learning patterns, displaying the generated public pattern, determining a degree of similarity between the displayed public pattern and the inputted releasing pattern,
Wherein the plurality of learning patterns include a plurality of points included in the lock pattern and a path selectively connected between the plurality of points and including a section having a predetermined angle or a section for changing a traveling direction,
Wherein the open pattern is generated by concatenating at least one learning pattern from a starting point, an ending point, or an intermediate point of the selected learning pattern among the plurality of learning patterns, and generating the plurality of learning patterns by one pattern having one starting point and one ending point Characterized in that it has an interval (i) greater than the pattern and (ii) a section that changes the direction of travel.

Images