KR101546391B1 - The method and system for monitoring cheating - Google Patents

Abstract

A test misconduct monitoring method and system are disclosed. A method for monitoring a cheating behavior of a candidate during a predetermined test using a candidate terminal according to an exemplary embodiment of the present invention includes the steps of: (a) determining whether a predetermined cheating event is generated; And (b) generating an irregularity notification message and transmitting the irregularity notification message to the administrator terminal when it is determined that the irregularity event is generated. The present invention can provide a method for automatically detecting a cheating behavior caused by a candidate during a predetermined test.

Description

[0001] The present invention relates to a method and a system for monitoring cheating,

The present invention relates to a test irregularity monitoring method and system, and more particularly, to a technique capable of automatically detecting an irregularity caused by a candidate during a predetermined test, thereby calculating a more reliable test result.

In general, examinations at school and at work, as well as certain qualification tests, are conducted in the presence of supervisors overseeing the examination by presenting the questions on a paper test paper and writing the answers on paper.

In recent years, various tests have been conducted on some PCs through PCs due to the generalization of PCs and the development of computer networks. In recent years, the rapid development of high-speed wireless networks and the spread of tablet PCs have become common. In this trend, it is expected that various tests at schools, workplaces, and hospitals will be conducted by tablet PCs in the next few years.

For example, if you are taking a test at school, your teachers will give you a tablet PC instead of paper, and your students will take the test with a tablet PC. Then, when the test is completed, the teacher collects the tablet PC from the students, and the test results will be computed and stored.

As described above, when a test is performed by a tablet PC, waste of resources can be suppressed because a paper test paper is not needed, and a tablet PC does not occupy a lot of space unlike a general PC, so space efficiency can be improved There are advantages.

However, if the test is performed using the tablet PC, the tablet PC may have mobility and portability characteristics, which may result in a different type of test malfeasance, which may degrade the reliability of the test result have.

Korea Patent Publication No. 2009-0003536 (Jan. 12, 2009)

SUMMARY OF THE INVENTION Accordingly, the present invention has been made keeping in mind the above problems occurring in the prior art, and it is an object of the present invention to provide a method for automatically detecting a cheating behavior caused by a candidate during a predetermined test using a tablet PC or the like.

The present invention is also intended to provide a test malfunction monitoring system capable of improving the reliability of test results.

Other objects of the present invention will become more apparent through the following preferred embodiments.

According to an aspect of the present invention, there is provided a method of monitoring a cheating behavior of a candidate during a predetermined test using a candidate terminal, comprising the steps of: (a) determining whether a predetermined cheating event is generated; And (b) generating a fraud alert message and transmitting the fraud alert message to the administrator terminal if it is determined that the fraud event has been generated.

The step (a) may include capturing a current view image, which is a video image during a test of a candidate using a camera module provided at the candidate terminal, at a predetermined cycle; And comparing the photographed current view image and the previous view image to determine whether there is a difference between the current view and the previous view image. If there is a difference between the current view and the previous view image, It can be judged that a cheating event has occurred.

Here, the step (a) may include: sensing dynamic information of the candidate terminal using a sensor attached to the candidate terminal; And comparing the sensed dynamic information with a preset reference value to determine whether the sensed dynamic information is equal to or greater than the preset reference value. If the sensed dynamic information is equal to or greater than the preset reference value, May be determined to have occurred.

Here, the sensor mounted on the candidate terminal may include at least one of an acceleration sensor, a tilt sensor, and a geomagnetic sensor.

Here, the step (a) may include: obtaining voice information around the candidate terminal; Comparing the obtained voice information with previously stored reference voice information to determine whether or not voice information other than the reference voice information stored in advance is included in the obtained voice pitch information, If voice information other than the stored reference voice information is included, it can be determined that a cheating event has occurred.

Here, the candidate terminal may be a tablet PC or a smart phone.

According to another aspect of the present invention, there is provided a recording medium on which a combination of instructions for performing the above-described test illegal act monitoring method is tangibly embodied and a program readable by the digital information processing apparatus is recorded.

According to still another aspect of the present invention, there is provided a method of controlling an ad hoc network system, the method comprising: determining whether a predetermined irregularity event is generated during a predetermined test; Terminal; And an administrator terminal for outputting the received fraud alert message.

Here, the candidate terminal captures a current view image, which is a video during a test of the candidate, using a camera module provided in the candidate terminal, at a predetermined cycle, compares the captured current view image with a previous view image, If there is a difference between the previous viewpoint images, it can be assumed that a cheating event has occurred.

Here, the candidate terminal senses the dynamic information of the candidate terminal using the sensor mounted on the candidate terminal, compares the sensed dynamic information with a preset reference value, and if the sensed dynamic information is equal to or greater than the preset reference value , It can be determined that a cheating event has occurred.

Here, if the obtained voice information includes voice information other than the previously stored reference voice information in the obtained pitch information, the voice information of the candidate terminal is acquired, It can be judged that the occurrence of the problem has occurred.

According to another aspect of the present invention, there is provided a method for controlling an ad hoc network system, the method comprising: determining whether a predetermined irregularity event is generated during a predetermined test; generating a irregularity notification message when the irregularity event is generated; Behavior monitoring server; And an administrator terminal for outputting the received fraud alert message.

The method may further include a candidate terminal for capturing a current view image, which is a video during a test of the candidate using the camera module provided, at a predetermined cycle, and transmitting the captured current view image to the cheating action monitoring server, The server compares the transmitted current view image with the previous view image, and can determine that a cheating event has occurred when there is a difference between the current view and the previous view image.

The mobile terminal further includes a candidate terminal for sensing dynamic information of the candidate terminal using the installed sensor and transmitting the sensed dynamic information to the cheating behavior monitoring server, It is possible to compare the preset reference value and determine that a cheating event has occurred if the transmitted dynamic information is equal to or greater than the preset reference value.

The terminal further includes a candidate terminal for acquiring voice information around the candidate terminal and transmitting the obtained voice information to the cheating behavior monitoring server, wherein the cheating behavior monitoring server comprises: Information, and if the transmitted pitch information includes voice information other than the previously stored reference voice information, it can be determined that a cheating event has occurred.

Here, the candidate terminal may be a tablet PC or a smart phone.

Here, the sensor mounted on the candidate terminal may include any one of an acceleration sensor, a tilt sensor, and a geomagnetic sensor.

SUMMARY OF THE INVENTION Accordingly, the present invention has been made keeping in mind the above problems occurring in the prior art, and it is an object of the present invention to provide a method for automatically detecting a cheating behavior caused by a candidate during a predetermined test using a tablet PC or the like.

In addition, the present invention can provide a test malfunction monitoring system that can improve the reliability of test results.

Brief Description of the Drawings Fig. 1 is a block diagram of a test illegal behavior monitoring system according to an embodiment of the present invention. Fig.
FIG. 2 is a flowchart illustrating a test illegal behavior monitoring method according to a first embodiment of the present invention; FIG.
FIG. 3 is a flowchart illustrating a test illegal behavior monitoring method according to a second embodiment of the present invention. FIG.
4 is a flowchart illustrating a test illegal behavior monitoring method according to a third embodiment of the present invention.
FIG. 5 is a flowchart illustrating a test illegal behavior monitoring method according to a fourth embodiment of the present invention; FIG.
FIG. 6 is a flowchart illustrating a test illegal behavior monitoring method according to a fifth embodiment of the present invention; FIG.
FIG. 7 is a flowchart illustrating a method of monitoring a test malfunction according to the sixth embodiment of the present invention. FIG.

BRIEF DESCRIPTION OF THE DRAWINGS The present invention is capable of various modifications and various embodiments, and specific embodiments are illustrated in the drawings and described in detail in the detailed description. It is to be understood, however, that the invention is not to be limited to the specific embodiments, but includes all modifications, equivalents, and alternatives falling within the spirit and scope of the invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, the present invention will be described in detail with reference to the accompanying drawings.

The terms first, second, etc. may be used to describe various components, but the components should not be limited by the terms. The terms are used only for the purpose of distinguishing one component from another.

The terminology used in this application is used only to describe a specific embodiment and is not intended to limit the invention. The singular expressions include plural expressions unless the context clearly dictates otherwise. In the present application, the terms "comprises" or "having" and the like are used to specify that there is a feature, a number, a step, an operation, an element, a component or a combination thereof described in the specification, But do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, or combinations thereof. Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

FIG. 1 is a block diagram of a test irregularity monitoring system according to an exemplary embodiment of the present invention. Referring to FIG.

1, test illegality monitoring system 100 includes at least one candidate terminal 10-1, 10-2, 10-3, ..., hereinafter collectively referred to as 10 and an administrator terminal 30 , And may further include a malicious activity monitoring server (20).

The candidate terminal 10 is connected to the administrator terminal 30 via the communication network 40. The communication network 40 may be a wireless communication network such as a short-range wireless communication network (e.g., WIFI, Bluetooth, etc.), a mobile communication network, or a wired communication network. Or the communication network 40 may be a wired line for some sections and a wireless communication network for some sections.

The candidate terminal 10 can be variously applied according to embodiments such as a PC, a tablet PC, and a smart phone. However, for clarity and concise description of the present invention, the candidate terminal 10 will be described as an example of a tablet PC. The candidate terminal 10 may be provided with an information obtaining apparatus or module for obtaining various information generated during a predetermined test. For example, the candidate terminal 10 may be equipped with a camera module capable of photographing the candidate's gazing state. Alternatively, the candidate terminal 10 may be provided with a sensor capable of sensing dynamic information of the candidate terminal 10 (for example, information that indicates whether or not the tablet PC of the candidate during testing is transmitted to another person) Can be. Alternatively, the candidate terminal 10 may be provided with a microphone capable of acquiring voice information around the candidate terminal 10. [

The candidate terminal 10 outputs a test item so that the candidate can perform a predetermined test, and performs a function of receiving the answer of the candidate. The test is not limited in its kind, such as psychological tests, personality tests, aptitude tests, and general tests. The test may be performed through a test agent (i.e., a test application) installed on the candidate terminal 10, or may be performed through a web connection (i.e., connection through a browser).

The candidate terminal 10 can determine whether a predetermined cheating event is generated during a predetermined test. At this time, if it is determined that a cheating event has occurred, the cheating behavior notification message may be generated and transmitted to the administrator terminal 30. According to another embodiment of the present invention, the candidate terminal 10 may obtain only information that can determine whether a predetermined irregularity event is generated. At this time, the acquired information is transmitted to the fraud monitoring server 20, and the fraud monitoring server 20 can determine whether a predetermined fraud event is generated using the received information. If the fraud monitoring server 20 determines that a fraudulent event has been generated, the fraud monitoring server 20 may generate a fraudulent notification message and transmit the fraudulent notification message to the administrator terminal 30. [ The details of the above-described embodiments will be described with reference to FIGS. 2 to 7. FIG.

The administrator terminal 30 outputs a fraud alert message so that the administrator can view the fraud alert message. The fraud alert message may be information such as a text form, a voice form, and an image form. In addition, the fraud alert message includes candidate information so that the administrator can know who the fraud has occurred. In addition, the cheating behavior notification message may include the identification information of the candidate terminal 10 so that the administrator can know which cheating behavior occurred in which candidate terminal 10. [ The administrator terminal 30 can be a PC, a tablet PC, a smart phone, a terminal dedicated to test management, and the like.

FIG. 2 is a flowchart illustrating a test malfunction monitoring method according to the first embodiment of the present invention.

As shown in FIG. 2, the candidate terminal 10 captures the current view image at a predetermined cycle using the camera module provided in the candidate terminal (S210). The current image is a test image of the candidate. That is, the camera module provided on the front side of the candidate terminal 10 captures an external image including a candidate's image. The candidate terminal 10 can take a current view image by applying a zoom in or zoom out function according to the distance between the camera module and the candidate. The period of taking the current view image can be variously set in consideration of the type and importance of the test, the age of the candidate, and the occupation.

In step S220, the candidate terminal 10 compares the photographed current view image with the previous view image. The candidate terminal 10 can process the current view image for more accurate comparison between the current viewpoint image and the previous viewpoint image. For example, the candidate terminal 10 can extract only the candidate's face from the current view image and compare the face with the previous view image. Alternatively, the candidate terminal 10 may extract only the pupil portion of the candidate from the current view image and compare the extracted portion with the previous view image. Alternatively, the candidate terminal 10 may extract only the background part of the candidate from the current video and compare it with the previous video. The previous viewpoint image may be an image corresponding to the processed current viewpoint image. For example, if the processed current image is the candidate's face, the previous view image may be a legitimate candidate's face image. Or if the processed current image is the candidate's pupil image, the previous view image may be a valid candidate's pupil image. Alternatively, if the processed current viewpoint image is the background of the candidate, the previous viewpoint image may be a legitimate candidate's background image.

The shooting time of the previous viewpoint image to be compared can be variously applied. For example, the previous view image may be an image taken before the start of the test. Alternatively, the previous viewpoint image may be a current viewpoint image of the current viewpoint image periodically photographed during the test.

In step S230, the candidate terminal 10 compares the current viewpoint image with the previous viewpoint image to determine whether there is a difference between the current viewpoint image and the previous viewpoint image. For example, the candidate terminal 10 can determine whether or not an object (e.g., a person's appearance) that was not present in the previous viewpoint image is included in the current viewpoint image. Alternatively, the candidate terminal 10 may determine whether there is a difference between the background of the current viewpoint image and the background of the previous viewpoint image. At this time, the difference may be the shape of the face, the color difference, the shape of the background, the color, the texture difference, and the like.

If there is no difference between the current viewpoint image and the previous viewpoint image as a result of the determination, the candidate terminal 10 performs step S210 when a predetermined period has elapsed.

If there is a difference between the current viewpoint image and the previous viewpoint image, the candidate terminal 10 generates a fraud alert message (S240). The fraud alert message includes candidate information and fraud detection information. The illegal act judgment information refers to image information that has been subjected to the illegal act judgment. For example, the cheating determination information may include comparison image information between the current view image and the previous view image. The administrator can again check whether a test illegality actually occurred by viewing the comparison image.

The candidate terminal 10 transmits the generated irregularity notification message to the administrator terminal 30 (S250). The administrator terminal 30 outputs an irregularity notification message so that the administrator can view the irregularity notification message (S260). The administrator terminal 30 can output an alarm so that the administrator can immediately recognize that the test irregularity has occurred.

3 is a flowchart illustrating a method for monitoring a test malfunction according to the second embodiment of the present invention.

As shown in FIG. 3, the candidate terminal 10 captures the current view image at a predetermined cycle using the camera module provided in the candidate terminal (S310). The current image is a test image of the candidate. That is, the camera module provided on the front side of the candidate terminal 10 captures an external image including a candidate's image. The photographed current view image is a data for judging whether a cheating event has occurred or not.

In step S320, the candidate terminal 10 transmits the photographed current view image to the fraud monitoring server 20. In the present embodiment, unlike the embodiment shown in FIG. 2, the subject of comparison between the current viewpoint image and the previous viewpoint image is the fraud monitoring server 20. According to the present embodiment, there is an advantage that the processing load imposed on the candidate terminal 10 can be reduced by allowing the fraud monitoring server 20 to perform a complicated process such as comparison of images.

In step S330, the fraud monitoring server 20 compares the received current image with the previous image. The cheating behavior monitoring server 20 can process the current view image for more accurate comparison between the current viewpoint image and the previous viewpoint image. The matters concerning the image processing at the present time have been described above and will be omitted. According to another embodiment, the transmitted current image may be an already processed image. According to the present embodiment, since the candidate terminal 10 performs the process of image processing, there is an advantage that the burden on the process of the cheating behavior monitoring server 20 can be reduced.

In step S340, the fraud monitoring server 20 compares the current viewpoint image with the previous viewpoint image to determine whether there is a difference between the current viewpoint image and the previous viewpoint image. That is, the fraud monitoring server 20 can determine whether an object (for example, a person other than the candidate) that was not present in the previous view image is included in the current view image. Alternatively, the fraud monitoring server 20 may determine whether there is a difference between the background of the current viewpoint image and the background of the previous viewpoint image.

If the difference between the current viewpoint image and the previous viewpoint image does not exist as a result of the determination, the cheating behavior monitoring server 20 transmits a no-cheong not generated message to the candidate terminal 10 (S350). At this time, the candidate terminal 10 performs step S310 again when a predetermined period has elapsed.

If the difference between the current viewpoint image and the previous viewpoint image exists as a result of the determination, the fraud monitoring server 20 generates a fraud alert message (S360). The fraud alert message includes candidate information and fraud detection information. The illegal act judgment information refers to image information that has been subjected to the illegal act judgment.

The malicious activity monitoring server 20 transmits the generated malicious activity notification message to the administrator terminal 30 (S370). The administrator terminal 30 outputs an irregularity notification message so that the administrator can view the irregularity notification message (S380). The administrator terminal 30 can output an alarm so that the administrator can immediately recognize that the test irregularity has occurred.

4 is a flowchart illustrating a method for monitoring a test malfunction according to the third embodiment of the present invention.

The present embodiment can be applied to a case where the candidate terminal 10 is a mobile terminal such as a tablet PC or a smart phone. More specifically, the present embodiment has an effect that the test takers can detect test irregularities that may occur when the test tablet PC is replaced and replaced by the test.

4, the candidate terminal 10 senses dynamic information (i.e., motion information or movement information) of the candidate terminal 10 using a sensor mounted on the candidate terminal 10 (S410). The sensor mounted on the candidate terminal 10 may be an acceleration sensor, a tilt sensor, a geomagnetic sensor, or the like. The acceleration sensor processes the output signal to measure dynamic forces such as acceleration, vibration, and impact of the object. Acceleration sensors are inertia type, gyro type, and silicon semiconductor type depending on the detection method. The details of the structure and operation of the sensor are somewhat distant from the gist of the present invention and will not be described here.

In step S420, the candidate terminal 10 compares the sensed dynamic information with a predetermined reference value. In general, the candidate enters the test with the candidate terminal 10 fixed. Alternatively, when the candidate terminal 10 is a tablet PC, the candidate holds the candidate terminal 10 with one hand and goes to the test. In this case, since the candidate does not move the held tablet PC in a large range during the test, the predetermined reference value is set to a value corresponding to the general motion during the test of the candidate holding the tablet PC (for example, , Tilt, etc.).

In step S430, the candidate terminal 10 determines whether or not the sensed dynamic information is equal to or greater than a preset reference value. For example, the candidate terminal 10 determines whether the moving speed of the candidate terminal 10 is 10 m / s or more and whether the acceleration of the candidate terminal 10 is 20 m / s 2 or more.

If it is determined that the sensed dynamic information is less than the preset reference value, the candidate terminal 10 performs step S410 when a predetermined period has elapsed.

The candidate terminal 10 generates a cheating behavior notification message if the sensed dynamic information is equal to or greater than a preset reference value (S440). The fraud alert message may include candidate information, identification information of the candidate terminal 10, and the like.

Also, although not shown in FIG. 4, the candidate terminal 10 can photograph an external image by driving the camera module from the moment when the dynamic information is determined to be equal to or greater than a preset reference value. At this time, the photographed image may be a more accurate data for judging whether or not the test irregularity has occurred. That is, the candidate terminal 10 firstly determines whether a cheating event is generated using the dynamic information through a relatively simple process, and then compares the current view image captured secondarily with the previous view image, It may be possible to judge more accurately whether or not the occurrence of the abnormality occurs. As in the present embodiment, when the candidate terminal 10 photographs an external image, the fraud alert message may include the photographed external image information.

The candidate terminal 10 transmits the generated irregularity notification message to the administrator terminal 30 (S450). The administrator terminal 30 outputs an irregularity notification message so that the administrator can view the irregularity notification message (S460). The administrator terminal 30 can output an alarm so that the administrator can immediately recognize that the test irregularity has occurred.

5 is a flowchart illustrating a method of monitoring a test malfunction according to the fourth embodiment of the present invention.

This embodiment can be applied to the case where the candidate terminal 10 is a mobile terminal such as a tablet PC or a smart phone, as in the embodiment shown in FIG.

 5, the candidate terminal 10 senses dynamic information (i.e., motion information or movement information) of the candidate terminal 10 using a sensor mounted on the candidate terminal 10 (S510).

In step S520, the candidate terminal 10 transmits the sensed dynamic information to the irregularity monitoring server 20. In the present embodiment, unlike the embodiment shown in FIG. 4, the corruption-monitoring server 20 is a subject that compares the sensed dynamic information with preset reference values. According to the present embodiment, the cheating behavior monitoring server 20 performs the comparison between the sensed dynamic information and a preset reference value, thereby reducing the processing load on the candidate terminal 10. [

In step S530, the fraud monitoring server 20 compares the sensed dynamic information with a predetermined reference value.

In step S540, the candidate terminal 10 determines whether or not the sensed dynamic information is equal to or greater than a preset reference value. For example, the candidate terminal 10 determines whether the moving speed of the candidate terminal 10 is 10 m / s or more and whether the acceleration of the candidate terminal 10 is 20 m / s 2 or more.

If the sensed dynamic information is less than a preset reference value, the cheating behavior monitoring server 20 transmits a cheating behavior non-occurrence message to the candidate terminal 10 (S550). At this time, the candidate terminal 10 performs step S510 again when a predetermined period has elapsed.

The malicious activity monitoring server 20 generates a malicious activity notification message when the sensed dynamic information is equal to or greater than a preset reference value (S560). The fraud alert message may include candidate information, identification information of the candidate terminal 10, and the like.

Although not shown in FIG. 5, when the dynamic information is determined to be equal to or greater than a preset reference value, the fraud monitoring server 20 can request the candidate terminal 10 to capture and transmit an external image from that moment. At this time, the photographed image may be a more accurate data for judging whether or not the test irregularity has occurred. That is, the cheating behavior monitoring server 20 first determines whether a cheating event is generated using the dynamic information through a relatively simple process, and then compares the current view image captured secondarily with the previous view image, It may be possible to more accurately determine whether or not an action event has occurred. As in the present embodiment, when the candidate terminal 10 photographs an external image, the fraud alert message may include the photographed external image information.

The malicious activity monitoring server 20 transmits the generated malicious activity notification message to the administrator terminal 30 (S570). The administrator terminal 30 outputs an irregularity notification message so that the administrator can view the irregularity notification message (S580). The administrator terminal 30 can output an alarm so that the administrator can immediately recognize that the test irregularity has occurred.

FIG. 6 is a flowchart illustrating a method of monitoring a test malfunction according to the fifth embodiment of the present invention.

As shown in FIG. 6, the candidate terminal 10 acquires voice information around the candidate terminal 10 using the microphone module provided in the candidate terminal (S610).

In step S620, the candidate terminal 10 compares the obtained voice information with previously stored reference voice information. The candidate terminal 10 can process the acquired voice information for more accurate comparison with the reference voice information. For example, the candidate terminal 10 can perform a process of removing a voice other than a voice (for example, a desk drag sound, etc.) among the obtained voice information by treating it as noise.

In step S630, the candidate terminal 10 determines whether the acquired voice information includes voice information other than the reference voice information stored in advance. The pre-stored reference voice information refers to voice information of a legitimate candidate, voice information of an administrator or supervisor.

The candidate terminal 10 performs step S610 if the voice information obtained as a result of the determination does not include voice information other than the reference voice information stored in advance, if a preset period has elapsed.

The candidate terminal 10 generates a cheating behavior notification message if voice information other than the reference voice information stored in advance is included in the acquired voice information (S640). The fraud alert message may include candidate information, identification information of the candidate terminal 10, and the like.

Although not shown in FIG. 6, the candidate terminal 10 can photograph an external image by driving the camera module from the moment when it is determined that voice information other than reference voice information previously stored in the obtained voice information is included. At this time, the photographed image may be a more accurate data for judging whether or not the test irregularity has occurred. That is, the candidate terminal 10 judges whether or not a cheating event is generated using the voice information obtained first, then compares the current view image captured secondarily with the previous view image, May be more accurately judged. As in the present embodiment, when the candidate terminal 10 photographs an external image, the fraud alert message may include the photographed external image information.

The candidate terminal 10 transmits the generated irregularity notification message to the administrator terminal 30 (S650). The administrator terminal 30 outputs an irregularity notification message so that the administrator can view the irregularity notification message (S660). The administrator terminal 30 can output an alarm so that the administrator can immediately recognize that the test irregularity has occurred.

FIG. 7 is a flowchart illustrating a method of monitoring a test malfunction according to the sixth embodiment of the present invention.

As shown in FIG. 7, the candidate terminal 10 acquires voice information around the candidate terminal 10 using the microphone module provided in the candidate terminal (S710).

In step S720, the candidate terminal 10 transmits the acquired voice information to the cheating behavior monitoring server 20. In the present embodiment, unlike the embodiment shown in FIG. 6, the corruption monitoring server 20 is a subject that compares the acquired voice information with the previously stored reference voice information. According to the present embodiment, it is possible to reduce the processing load on the candidate terminal 10 by allowing the cheating behavior monitoring server 20 to compare the obtained voice information with the preset reference voice information.

In step S730, the fraud monitoring server 20 compares the acquired voice information with the already stored voice information. The cheating behavior monitoring server 20 may process the obtained voice information for more accurate comparison of the obtained voice information and the previously stored reference voice information. For example, the cheating behavior monitoring server 20 can perform a process of removing a voice other than a voice (e.g., a desk drag sound, etc.) among the obtained voice information as noise.

In step S740, the fraud monitoring server 20 determines whether the acquired voice information includes voice information other than the reference voice information stored in advance. The reference voice information refers to voice information of a legitimate candidate, voice information of an administrator or supervisor, and the like.

If the voice information other than the reference voice information stored in advance is not included in the voice information obtained as a result of the determination, the cheating behavior monitoring server 20 transmits an undefined behavior occurrence message to the candidate terminal 10 (S750). At this time, the candidate terminal 10 performs step S710 again when a predetermined period has elapsed.

If the acquired voice information includes voice information other than the reference voice information stored in advance, the cheating behavior monitoring server 20 generates a cheating behavior notification message (S760). The fraud alert message includes candidate information, identification information of the candidate terminal 10, and the like.

Although not shown in FIG. 7, when the cheating action monitoring server 20 judges that the acquired voice information includes voice information other than the reference voice information stored in advance, the external device captures and transmits the external video from that moment The candidate terminal 10 can request the candidate terminal 10. At this time, the photographed image may be a more accurate data for judging whether or not the test irregularity has occurred. That is, the cheating behavior monitoring server 20 determines whether or not a cheating event is generated using the voice information that is primarily obtained, and then compares the current view image captured secondarily with the previous view image, It may be more accurate to judge whether or not it occurred. As in the present embodiment, when the candidate terminal 10 photographs an external image, the fraud alert message may include external image information to be photographed.

The malicious activity monitoring server 20 transmits the generated malicious activity notification message to the administrator terminal 30 (S770). The administrator terminal 30 outputs an irregularity notification message so that the administrator can view the irregularity notification message (S780). The administrator terminal 30 can output an alarm so that the administrator can immediately recognize that the test irregularity has occurred.

The method for monitoring the test malfunction according to the present invention described above can be implemented as a computer-readable code on a computer-readable recording medium. A computer-readable recording medium includes all kinds of recording apparatuses in which data that can be read by a computer system is stored. Examples of the computer-readable recording medium include a hard disk, a ROM, a RAM, a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like. . The computer readable recording medium may also be distributed over a networked computer system so that computer readable code can be stored and executed in a distributed manner.

It will be apparent to those skilled in the relevant art that various modifications, additions and substitutions are possible, without departing from the spirit and scope of the invention as defined by the appended claims. The appended claims are to be considered as falling within the scope of the following claims.

10: Candidate terminal
20: Cheating monitoring server
30:
40: Network

Claims (17)

A method for monitoring a cheating action of a candidate during a predetermined test using a candidate terminal corresponding to a tablet PC or a smart phone (the cheating action corresponds to an action of the candidate terminal transmitted to another person other than the candidate)
(a) sensing dynamic information of the candidate terminal using at least one of an acceleration sensor, a tilt sensor, and a geomagnetic sensor mounted on the candidate terminal, and using the microphone module mounted on the candidate terminal, ;
(b) comparing the sensed dynamic information with a predetermined reference value to determine whether the sensed dynamic information is equal to or greater than the preset reference value, comparing the obtained voice information with previously stored reference voice information, Determining whether the information includes voice information other than the reference voice information stored in advance;
(c) if the sensed dynamic information is equal to or greater than the preset reference value, or if the obtained pitch information includes voice information other than the previously stored reference voice information, determining that a first cheating event has occurred;
(d) driving a camera module provided in the candidate terminal from a point of time when the first irregularity event is generated;
(e) photographing the present-time image, which is a video during the test of the candidate by using the camera module, at a predetermined cycle, and zooming in or out according to the distance between the camera module and the candidate, Capturing the current view image including a background;
(f) comparing the photographed current view image with a previous view image to determine whether there is a difference between the current view and the previous view image, and if there is a difference between the current view and the previous view image, Determining that a car misconduct event has occurred, the difference being at least one of a form difference, a color difference, and a type difference of the background of the candidate face; And
(e) generating a fraud alert message and transmitting the fraud alert message to the administrator terminal if it is determined that the second malicious activity event has occurred. delete delete delete delete delete A recording medium in which a combination of instructions for carrying out the method of claim 1 is tangibly embodied and a program readable by a digital information processing apparatus is recorded. It is determined whether or not a candidate's cheating (corresponding to an action of the candidate terminal transmitted to another person other than the candidate) occurs during a predetermined test using the candidate terminal corresponding to the tablet PC or the smartphone, A candidate terminal generating a fraud alert message and transmitting the fraud alert message to the administrator terminal if it is determined that the fraudulent activity has occurred; And
And an administrator terminal for outputting the received fraud alert message,
The candidate terminal
Sensing dynamic information of the candidate terminal using at least one of an acceleration sensor, a tilt sensor, and a geomagnetic sensor mounted on the candidate terminal, acquiring voice information around the candidate terminal using a microphone module mounted on the candidate terminal , Comparing the sensed dynamic information with a preset reference value to determine whether the sensed dynamic information is equal to or greater than the preset reference value, comparing the obtained voice information with previously stored reference voice information, If the sensed dynamic information is equal to or larger than the preset reference value or if the obtained pitch information includes voice information other than the previously stored reference voice information , The first illegal act event has occurred And activating a camera module provided in the candidate terminal from a point of time at which the first irregularity event occurs, capturing a current view image, which is a video during a test of the candidate, at a predetermined cycle using the camera module, Zooming in or zooming out according to the distance between the module and the candidate, taking the current view image including the participant's face and background, comparing the captured current view image with the previous view image, Determining whether there is a difference between the current viewpoint and the previous viewpoint image, if a difference exists between the current viewpoint and the previous viewpoint image, determining that a second cheating event has occurred; Wherein the at least one of the at least one of the first, If it is determined, the cheating alert messages generated by negative test, characterized in that transmitting by the administrator terminal behavior monitoring system. delete delete delete It is determined whether or not a candidate's cheating (corresponding to an action of the candidate terminal transmitted to another person other than the candidate) occurs during a predetermined test using the candidate terminal corresponding to the tablet PC or the smartphone, A malicious activity monitoring server for generating an irregularity notification message and transmitting the generated irregularity notification message to the administrator terminal when it is determined that the irregularity has occurred;
The camera module is used to photograph a current view image, which is a video image during a test of a candidate, at a predetermined cycle, and senses dynamic information using at least one of the installed acceleration sensor, tilt sensor and geomagnetic sensor, A candidate terminal for acquiring voice information around the candidate terminal using the current viewpoint image, the sensed dynamic information, and the acquired voice information to the cheating behavior monitoring server; And
And an administrator terminal for outputting the received fraud alert message,
The malicious activity monitoring server
Comparing the sensed dynamic information with a preset reference value to determine whether the sensed dynamic information is equal to or greater than the predetermined reference value, comparing the obtained voice information with previously stored reference voice information, If the sensed dynamic information is equal to or larger than the preset reference value or if the obtained pitch information includes voice information other than the reference voice information stored in advance, A camera module provided in the candidate terminal is driven from a point of time when the first illegal act event is generated, and a camera module The viewpoint image is photographed at a preset cycle, Zoom in or zoom out according to the distance of the subject and photographs the current view image including the participant's face and background and compares the captured current view image with the previous view image, Determining whether there is a difference between the current time point and the previous point-in-time image, if a difference exists between the current point-in-time point and the previous point-in-time image, determining that a second irregularity event has occurred; A color difference, and a type difference of the background; and if it is determined that the second illegal act event is generated, a fraud alert message is generated and transmitted to the administrator terminal Cheating monitoring system.
delete delete delete delete delete

Images